merge from benchmark branch

benchmark/README.md

@@ -1,8 +0,0 @@
-
-# Revisiting Time Series Outlier Detection: Definitions and Benchmarks
-
-## Benchmark Directions
-* Step1: Follow the instructions in main page to intall the package
-* Step2: Go to the sub-directories (realworld\_data or synthetic) to see the detailed instruction for running the benchmarking pipelines.
-
-

benchmark/realworld_data/README.md

@@ -1,51 +0,0 @@
-# Revisiting Time Series Outlier Detection:Definitions and Benchmarks
-
-This branch is the source code of  experiment part of our paper. We provide everything needed when running the experiments: Dataset, Dataset Generator, Pipeline json, Python script, runner and the result (in "./result") we get from the experiments.
-
-## Resources
-* Paper: Under review
-
-
-## Datasets
-To get the dataset, please go to "data/script" to run all of the python scripts. They will download and preprocess the data automatically into "data/" folder.
-
-
-## Pipeline
-
-This Pipeline json files are organized by different settings of algorithms. 
-
-## Runner
-
-To run a pipeline, you can generate your own pipeline json file from script.
-
-```python
-sh build_pipelines.sh
-```
-
-Then run the pipeline with run\_pipeline.py (Below is the example for running IForest on GECCO dataset)
-```python
-python run_pipeline.py --pipeline_path pipelines/simple/pyod_iforest_0.01.json --data_path ./data/water_quality.csv
-```
-
-
-
-Or you can directly use the pipelines we have generated in /pipelines with bash script:
-
-```python
-sh run.sh
-```
-
-
-## Cite this Work:
-If you find this  work useful, you may cite this work:
-```
-@misc{lai2020tods,
-    title={TODS: An Automated Time Series Outlier Detection System},
-    author={Kwei-Harng Lai and Daochen Zha and Guanchu Wang and Junjie Xu and Yue Zhao and Devesh Kumar and Yile Chen and Purav Zumkhawaka and Minyang Wan and Diego Martinez and Xia Hu},
-    year={2020},
-    eprint={2009.09822},
-    archivePrefix={arXiv},
-    primaryClass={cs.DB}
-}
-```
-*Please refer master branch of TODS for details of running pipelines.

benchmark/realworld_data/build_pipelines.sh

@@ -1,26 +0,0 @@
-#!/bin/bash
-
-if [ ! -d "./pipelines/simple" ]; then
-	mkdir -p ./pipelines/simple
-fi
-if [ ! -d "./pipelines/subseq" ]; then
-	mkdir -p ./pipelines/subseq
-fi
-python pipeline_construction/pipeline_construction_simple.py 
-python pipeline_construction/pipeline_construction_subseq.py 
-
-data="swan_sf creditcard web_attack water_quality"
-for d in $data
-do 
-	if [ ! -d "./pipelines/AE/$d" ]; then
-		mkdir -p ./pipelines/AE/$d
-	fi
-	if [ ! -d "./pipelines/RNN_LSTM/$d" ]; then
-		mkdir -p ./pipelines/RNN_LSTM/$d
-	fi
-
-	python pipeline_construction/neural/build_AE_pipeline.py "./data/"$d".csv"
-	python pipeline_construction/neural/build_RNNLSTM_pipeline.py "./data/"$d".csv"
-done
-
-

benchmark/realworld_data/data/script/cicids.py

@@ -1,43 +0,0 @@
-import pandas as pd
-import numpy as np
-import os
-import requests
-
-
-def preprocess_web_attack():
-    def get_data():
-        link="http://205.174.165.80/CICDataset/CIC-IDS-2017/Dataset/MachineLearningCSV.zip"
-        r = requests.get(link)
-        with open('./raw_data/cicids.zip', 'wb') as f:
-                f.write(r.content)
-        os.system("unzip ./raw_data/cicids.zip -d ./raw_data")
-        os.system("mv ./raw_data/MachineLearningCSV/Thursday-WorkingHours-Morning-WebAttacks.pcap_ISCX.csv ./raw_data/cicids.csv")
-        os.system("rm -r MachineLearningCSV")
-        os.system("rm cicids.zip")
-
-    if get_data == True:
-        get_data()
-    #df = pd.read_csv("./raw_data/MachineLearningCSV/Thursday-WorkingHours-Morning-WebAttacks.pcap_ISCX.csv")
-    df = pd.read_csv("./raw_data/cicids.csv")
-
-    df.replace([float('inf'), 'Infinity',''], np.nan, inplace=True)
-    df = df.dropna()
-    #df = df.sample(frac=0.05, replace=False, random_state=1)
-    df[' Timestamp'] = pd.to_datetime(df[' Timestamp'], infer_datetime_format=True)
-    df = df.sort_values(by=[' Timestamp'])
-
-    # drop nan and str columns
-    drop_cols = list(df.columns)[0:5]
-    drop_cols = list(df.columns)[0:5]
-    drop_cols.append(list(df.columns)[6])
-    df = df.drop(columns=drop_cols)
-
-    # relabeing and put label in the first column
-    df[' Label'] = df[' Label'].map({'BENIGN':"0", "Web Attack Brute Force": "1","Web Attack Sql Injection": "1", "Web Attack XSS": "1"})
-    cols = df.columns.tolist()
-    cols = cols[-1:] + cols[:-1]
-    df = df[cols]
-    df.to_csv("../web_attack.csv", index=False, encoding='utf-8')
-
-if __name__ == "__main__":
-    preprocess_web_attack()

benchmark/realworld_data/data/script/creditcard.py

@@ -1,28 +0,0 @@
-import pandas as pd
-import os
-import requests
-
-def preprocess_creditcard():
-    def get_data():
-        link="https://www.openml.org/data/get_csv/1673544/phpKo8OWT"
-        r = requests.get(link)
-        with open('./raw_data/openml_creditcard.csv', 'wb') as f:
-                f.write(r.content)
-
-    get_data()
-    df = pd.read_csv("./raw_data/openml_creditcard.csv")
-    # drop nan and str columns
-    df = df.dropna()
-    #df = df.drop(columns=['Time'])
-    cols = df.columns.tolist()
-    cols = cols[-1:] + cols[:-1]
-    df = df[cols]
-    #df['Class'] = df['Class'].map({0:"nominal", 1: "anomaly"})
-    #df = df.sample(frac=0.025, replace=False, random_state=1)
-    df = df.sort_values(by=['Time'])
-    df = df.drop(columns=['Time'])
-    df['Class'] = df['Class'].str.replace(r'\'', '').astype(int)
-    df.to_csv("../creditcard.csv", index=False, encoding='utf-8')
-
-if __name__ == "__main__":
-    preprocess_creditcard()

benchmark/realworld_data/data/script/gecco.py

@@ -1,31 +0,0 @@
-import pandas as pd
-import os
-import requests
-
-def preprocess_gecco():
-    def get_data():
-        link="https://ndownloader.figshare.com/articles/12451142/versions/1"
-        r = requests.get(link)
-        with open('./raw_data/gecco.zip', 'wb') as f:
-                f.write(r.content)
-        os.system("unzip ./raw_data/gecco.zip -d ./raw_data")
-        os.system("rm ./raw_data/*.pdf ./raw_data/4_ResourcePackage_GECCO_Industrial_Challenge_2018.zip")
-
-    get_data()
-    df = pd.read_csv("./raw_data/1_gecco2018_water_quality.csv")
-    # drop nan and str columns
-    df = df.dropna()
-    df = df.drop(columns=['Time', df.columns[0]])
-    cols = df.columns.tolist()
-    cols = cols[-1:] + cols[:-1]
-    df = df[cols]
-    df['EVENT'] = df['EVENT'].map({False:"0", True: "1"})
-    df = df.rename(columns={"EVENT": "label"})
-    #df['Class'] = df['Class'].map({0:"nominal", 1: "anomaly"})
-    #df = df.sample(frac=0.025, replace=False, random_state=1)
-    #df = df.sort_values(by=['Time'])
-    #df = df.drop(columns=['Time'])
-    df.to_csv("../water_quality.csv", index=False, encoding='utf-8')
-
-if __name__ == "__main__":
-    preprocess_gecco()

benchmark/realworld_data/data/script/swan_sf.py

@@ -1,44 +0,0 @@
-import pandas as pd
-import os
-import requests
-
-def get_data():
-    link="https://bitbucket.org/gsudmlab/mvtsdata_toolkit/downloads/petdataset_01.zip"
-    r = requests.get(link)
-    with open('./swan_sf.zip', 'wb') as f:
-            f.write(r.content)
-    os.system("unzip swan_sf.zip")
-
-def read_labeled_data():
-    dir_path = "./petdataset_01"
-    files = os.listdir(dir_path)
-    inlier = []
-    label = {}
-    for f in files:
-        #if "csv" not in f and "NF" not in f:
-        if "csv" not in f:
-            continue
-        label = f.split("lab[")[1].split("]")[0]
-        #print(label)
-        f_path = os.path.join(dir_path, f)
-        df = pd.read_csv(f_path, header=0, sep='\t')
-        df['label'] = label
-        inlier.append(df)
-    df = pd.concat(inlier, axis=0, ignore_index=True)
-    df = df.sort_values(by=['Timestamp'])
-    drop_cols = [col for col in df.columns if "label" in col or "loc" in col or "Timestamp" in col][:-1]
-    df = df.drop(columns=drop_cols)
-    df.reset_index(drop=True, inplace=True)
-    df = df.fillna(method='ffill')
-    df = df.dropna(axis="columns")
-    df['label'].replace({"NF":0, "C":1, "B":1, "M":1, "X":1}, inplace=True)
-    df['IS_TMFI'].replace({True:1, False:0}, inplace=True)
-    cols = df.columns.tolist()
-    cols = cols[-1:] + cols[:-1]
-    df = df[cols]
-    df.to_csv("../swan_sf.csv", index=False)
-
-if __name__ == "__main__":
-    get_data()
-    read_labeled_data()
-    os.system("rm -rf swan_sf.zip petdataset_01")

benchmark/realworld_data/pipeline_construction/neural/build_AE_pipeline.py

@@ -1,78 +0,0 @@
-import sys
-import pandas as pd
-
-dataset = sys.argv[1]
-data_name = dataset.split("/")[-1].split(".")[0]
-df = pd.read_csv(dataset)
-feature_dim = len(df.columns) - 1 # take off label
-
-from d3m import index
-from d3m.metadata.base import ArgumentType
-from d3m.metadata.pipeline import Pipeline, PrimitiveStep
-
-for cont_rate in [0.01, 0.05, 0.1, 0.15, 0.2, 0.25]:
-    # Creating pipeline
-    pipeline_description = Pipeline()
-    pipeline_description.add_input(name='inputs')
-
-    # Step 0: dataset_to_dataframe
-    step_0 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.dataset_to_dataframe'))
-    step_0.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='inputs.0')
-    step_0.add_output('produce')
-    pipeline_description.add_step(step_0)
-
-    # Step 1: column_parser
-    step_1 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.column_parser'))
-    step_1.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
-    step_1.add_output('produce')
-    pipeline_description.add_step(step_1)
-
-    # Step 2: extract_columns_by_semantic_types(attributes)
-    step_2 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.extract_columns_by_semantic_types'))
-    step_2.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
-    step_2.add_output('produce')
-    step_2.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
-                                                              data=['https://metadata.datadrivendiscovery.org/types/Attribute'])
-    pipeline_description.add_step(step_2)
-
-    # Step 3: extract_columns_by_semantic_types(targets)
-    step_3 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.extract_columns_by_semantic_types'))
-    step_3.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
-    step_3.add_output('produce')
-    step_3.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
-                                                            data=['https://metadata.datadrivendiscovery.org/types/TrueTarget'])
-    pipeline_description.add_step(step_3)
-
-    attributes = 'steps.2.produce'
-    targets = 'steps.3.produce'
-
-    # Step 4: processing
-    step_4 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler'))
-    step_4.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference=attributes)
-    step_4.add_output('produce')
-    pipeline_description.add_step(step_4)
-
-    # Step 5: algorithm`
-    step_5 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.detection_algorithm.pyod_ae'))
-    step_5.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.4.produce')
-    step_5.add_hyperparameter(name='hidden_neurons', argument_type=ArgumentType.VALUE, data=[feature_dim, 32, 16, 32, feature_dim])
-    step_5.add_hyperparameter(name='contamination', argument_type=ArgumentType.VALUE, data=cont_rate)
-    step_5.add_output('produce')
-    pipeline_description.add_step(step_5)
-
-    # Step 6: Predictions
-    step_6 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.construct_predictions'))
-    step_6.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.5.produce')
-    step_6.add_argument(name='reference', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
-    step_6.add_output('produce')
-    pipeline_description.add_step(step_6)
-
-    # Final Output
-    pipeline_description.add_output(name='output predictions', data_reference='steps.6.produce')
-
-    # Output to json
-    data = pipeline_description.to_json()
-    with open('./pipelines/AE/'+data_name+'/ae_pipeline_'+str(cont_rate)+'.json', 'w') as f:
-        f.write(data)
-        print(data)
-

benchmark/realworld_data/pipeline_construction/neural/build_RNNLSTM_pipeline.py

@@ -1,78 +0,0 @@
-import sys
-import pandas as pd
-
-dataset = sys.argv[1]
-data_name = dataset.split("/")[-1].split(".")[0]
-df = pd.read_csv(dataset)
-feature_dim = len(df.columns) - 1 # take off label
-
-from d3m import index
-from d3m.metadata.base import ArgumentType
-from d3m.metadata.pipeline import Pipeline, PrimitiveStep
-
-for cont_rate in [0.01, 0.05, 0.1, 0.15, 0.2, 0.25]:
-    # Creating pipeline
-    pipeline_description = Pipeline()
-    pipeline_description.add_input(name='inputs')
-
-    # Step 0: dataset_to_dataframe
-    step_0 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.dataset_to_dataframe'))
-    step_0.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='inputs.0')
-    step_0.add_output('produce')
-    pipeline_description.add_step(step_0)
-
-    # Step 1: column_parser
-    step_1 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.column_parser'))
-    step_1.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
-    step_1.add_output('produce')
-    pipeline_description.add_step(step_1)
-
-    # Step 2: extract_columns_by_semantic_types(attributes)
-    step_2 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.extract_columns_by_semantic_types'))
-    step_2.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
-    step_2.add_output('produce')
-    step_2.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
-                                                              data=['https://metadata.datadrivendiscovery.org/types/Attribute'])
-    pipeline_description.add_step(step_2)
-
-    # Step 3: extract_columns_by_semantic_types(targets)
-    step_3 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.extract_columns_by_semantic_types'))
-    step_3.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
-    step_3.add_output('produce')
-    step_3.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
-                                                            data=['https://metadata.datadrivendiscovery.org/types/TrueTarget'])
-    pipeline_description.add_step(step_3)
-
-    attributes = 'steps.2.produce'
-    targets = 'steps.3.produce'
-
-    # Step 4: processing
-    step_4 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler'))
-    step_4.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference=attributes)
-    step_4.add_output('produce')
-    pipeline_description.add_step(step_4)
-
-    # Step 5: algorithm`
-    step_5 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.detection_algorithm.LSTMODetector'))
-    step_5.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.4.produce')
-    step_5.add_hyperparameter(name='feature_dim', argument_type=ArgumentType.VALUE, data=feature_dim)
-    step_5.add_hyperparameter(name='contamination', argument_type=ArgumentType.VALUE, data=cont_rate)
-    step_5.add_output('produce')
-    pipeline_description.add_step(step_5)
-
-    # Step 6: Predictions
-    step_6 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.construct_predictions'))
-    step_6.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.5.produce')
-    step_6.add_argument(name='reference', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
-    step_6.add_output('produce')
-    pipeline_description.add_step(step_6)
-
-    # Final Output
-    pipeline_description.add_output(name='output predictions', data_reference='steps.6.produce')
-
-    # Output to json
-    data = pipeline_description.to_json()
-    with open('./pipelines/RNN_LSTM/'+data_name+'/rnnlstm_pipeline_'+str(cont_rate)+'.json', 'w') as f:
-        f.write(data)
-        print(data)
-

benchmark/realworld_data/pipeline_construction/pipeline_construction_simple.py

@@ -1,183 +0,0 @@
-import uuid
-import random
-
-from d3m.metadata.pipeline import Pipeline
-
-from axolotl.algorithms.base import PipelineSearchBase
-from axolotl.utils import  schemas as schemas_utils
-
-primitive_python_paths = { # pragma: no cover
-    'data_processing': [
-        #'d3m.primitives.tods.data_processing.time_interval_transform',
-        #'d3m.primitives.tods.data_processing.categorical_to_binary',
-        #'d3m.primitives.tods.data_processing.column_filter',
-        #'d3m.primitives.tods.data_processing.timestamp_validation',
-        #'d3m.primitives.tods.data_processing.duplication_validation',
-        #'d3m.primitives.tods.data_processing.continuity_validation',
-    ],
-    'timeseries_processing': [
-        #'d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler',
-        #'d3m.primitives.tods.timeseries_processing.subsequence_segmentation',
-        'd3m.primitives.tods.timeseries_processing.transformation.standard_scaler',
-        #'d3m.primitives.tods.timeseries_processing.transformation.power_transformer',
-        #'d3m.primitives.tods.timeseries_processing.transformation.quantile_transformer',
-        #'d3m.primitives.tods.timeseries_processing.transformation.moving_average_transform',
-        #'d3m.primitives.tods.timeseries_processing.transformation.simple_exponential_smoothing',
-        #'d3m.primitives.tods.timeseries_processing.transformation.holt_smoothing',
-        #'d3m.primitives.tods.timeseries_processing.transformation.holt_winters_exponential_smoothing',
-        #'d3m.primitives.tods.timeseries_processing.decomposition.time_series_seasonality_trend_decomposition',
-    ],
-    'feature_analysis': [
-        #'d3m.primitives.tods.feature_analysis.auto_correlation',
-        #'d3m.primitives.tods.feature_analysis.statistical_mean',
-        #'d3m.primitives.tods.feature_analysis.statistical_median',
-        #'d3m.primitives.tods.feature_analysis.statistical_g_mean',
-        #'d3m.primitives.tods.feature_analysis.statistical_abs_energy',
-        #'d3m.primitives.tods.feature_analysis.statistical_abs_sum',
-        #'d3m.primitives.tods.feature_analysis.statistical_h_mean',
-        #'d3m.primitives.tods.feature_analysis.statistical_maximum',
-        #'d3m.primitives.tods.feature_analysis.statistical_minimum',
-        #'d3m.primitives.tods.feature_analysis.statistical_mean_abs',
-        #'d3m.primitives.tods.feature_analysis.statistical_mean_abs_temporal_derivative',
-        #'d3m.primitives.tods.feature_analysis.statistical_mean_temporal_derivative',
-        #'d3m.primitives.tods.feature_analysis.statistical_median_abs_deviation',
-        #'d3m.primitives.tods.feature_analysis.statistical_kurtosis',
-        #'d3m.primitives.tods.feature_analysis.statistical_skew',
-        #'d3m.primitives.tods.feature_analysis.statistical_std',
-        #'d3m.primitives.tods.feature_analysis.statistical_var',
-        #'d3m.primitives.tods.feature_analysis.statistical_variation',
-        #'d3m.primitives.tods.feature_analysis.statistical_vec_sum',
-        #'d3m.primitives.tods.feature_analysis.statistical_willison_amplitude',
-        #'d3m.primitives.tods.feature_analysis.statistical_zero_crossing',
-        #'d3m.primitives.tods.feature_analysis.spectral_residual_transform',
-        #'d3m.primitives.tods.feature_analysis.fast_fourier_transform',
-        #'d3m.primitives.tods.feature_analysis.discrete_cosine_transform',
-        #'d3m.primitives.tods.feature_analysis.non_negative_matrix_factorization',
-        #'d3m.primitives.tods.feature_analysis.bk_filter',
-        #'d3m.primitives.tods.feature_analysis.hp_filter',
-        #'d3m.primitives.tods.feature_analysis.truncated_svd',
-        #'d3m.primitives.tods.feature_analysis.wavelet_transform',
-        #'d3m.primitives.tods.feature_analysis.trmf',
-    ],
-    'detection_algorithm': [
-        #'d3m.primitives.tods.detection_algorithm.pyod_ae',
-        #'d3m.primitives.tods.detection_algorithm.pyod_vae',
-        #'d3m.primitives.tods.detection_algorithm.pyod_cof',
-        #'d3m.primitives.tods.detection_algorithm.pyod_sod',
-        #'d3m.primitives.tods.detection_algorithm.pyod_abod',
-        #'d3m.primitives.tods.detection_algorithm.pyod_hbos',
-        'd3m.primitives.tods.detection_algorithm.pyod_iforest',
-        #'d3m.primitives.tods.detection_algorithm.pyod_lof',
-        #'d3m.primitives.tods.detection_algorithm.pyod_knn',
-        'd3m.primitives.tods.detection_algorithm.pyod_ocsvm',
-        #'d3m.primitives.tods.detection_algorithm.pyod_loda',
-        #'d3m.primitives.tods.detection_algorithm.pyod_cblof',
-        'd3m.primitives.tods.detection_algorithm.pyod_sogaal',
-        'd3m.primitives.tods.detection_algorithm.pyod_mogaal',
-        'd3m.primitives.tods.detection_algorithm.matrix_profile',
-        'd3m.primitives.tods.detection_algorithm.AutoRegODetector',
-        #'d3m.primitives.tods.detection_algorithm.LSTMODetector',
-        #'d3m.primitives.tods.detection_algorithm.AutoRegODetector',
-        #'d3m.primitives.tods.detection_algorithm.PCAODetector',
-        #'d3m.primitives.tods.detection_algorithm.KDiscordODetector',
-        #'d3m.primitives.tods.detection_algorithm.deeplog',
-        #'d3m.primitives.tods.detection_algorithm.telemanom',
-    ],
-    'contamination': [0.01, 0.05, 0.1, 0.15, 0.2, 0.25],
-}
-
-def _generate_pipeline(combinations):
-    from d3m import index
-    from d3m.metadata.base import ArgumentType
-    from d3m.metadata.pipeline import Pipeline, PrimitiveStep
-
-    piplines = []
-    for combination in combinations:
-        # Creating pipeline
-        pipeline_description = Pipeline()
-        pipeline_description.add_input(name='inputs')
-        
-        # The first three steps are fixed
-        # Step 0: dataset_to_dataframe
-        step_0 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.dataset_to_dataframe'))
-        step_0.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='inputs.0')
-        step_0.add_output('produce')
-        pipeline_description.add_step(step_0)
-
-        # Step 1: column_parser
-        step_1 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.column_parser'))
-        step_1.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
-        step_1.add_output('produce')
-        pipeline_description.add_step(step_1)
-
-        # Step 2: extract_columns_by_semantic_types(attributes)
-        step_2 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.extract_columns_by_semantic_types'))
-        step_2.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
-        step_2.add_output('produce')
-        step_2.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
-                                                                  data=['https://metadata.datadrivendiscovery.org/types/Attribute'])
-        pipeline_description.add_step(step_2)
-
-        # Step 3: extract_columns_by_semantic_types(targets)
-        step_3 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.extract_columns_by_semantic_types'))
-        step_3.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
-        step_3.add_output('produce')
-        step_3.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
-                                                                data=['https://metadata.datadrivendiscovery.org/types/TrueTarget'])
-        pipeline_description.add_step(step_3)
-
-        attributes = 'steps.2.produce'
-        targets = 'steps.3.produce'
-
-        tods_step_4 = PrimitiveStep(primitive=index.get_primitive(combination[0]))
-        tods_step_4.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference=attributes)
-        #tods_step_4.add_hyperparameter(name='window_size', argument_type=ArgumentType.VALUE, data=10)
-        #tods_step_4.add_hyperparameter(name='step', argument_type=ArgumentType.VALUE, data=1)
-        tods_step_4.add_output('produce')
-        pipeline_description.add_step(tods_step_4)
-
-        tods_step_5= PrimitiveStep(primitive=index.get_primitive(combination[1]))
-        tods_step_5.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.4.produce')
-        tods_step_5.add_output('produce')
-        tods_step_5.add_hyperparameter(name='contamination', argument_type=ArgumentType.VALUE, data=combination[2])
-        pipeline_description.add_step(tods_step_5)
-
-        # Finalize the pipeline
-        final_step = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.construct_predictions'))
-        final_step.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.5.produce')
-        final_step.add_argument(name='reference', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
-        final_step.add_output('produce')
-        pipeline_description.add_step(final_step)
-
-        pipeline_description.add_output(name='output predictions', data_reference='steps.6.produce')
-        data = pipeline_description.to_json()
-        #with open('../pipelines/'+str(combination[1].split(".")[-1])+'_'+str(combination[2])+".json", 'w') as f:
-        with open('./pipelines/simple/'+str(combination[1].split(".")[-1])+'_'+str(combination[2])+".json", 'w') as f:
-            f.write(data)
-        pipeline_description.id = str(uuid.uuid4())
-        pipeline_description.created = Pipeline().created
-        piplines.append(pipeline_description)
-    return piplines
-
-def _generate_pipelines(primitive_python_paths, cpu_count=40): # pragma: no cover
-    """
-    Args:
-        primitive_python_paths: a list of primitive Python paths for algorithms
-    
-    Returns:
-        the pipline description json
-    """
-    import itertools
-    import multiprocessing as mp
-
-    #components = ['data_processing', 'timeseries_processing', 'feature_analysis', 'detection_algorithm']
-    components = ['timeseries_processing', 'detection_algorithm', 'contamination']
-    combinations = itertools.product(*(primitive_python_paths[k] for k in components))
-
-
-    return _generate_pipeline(combinations)
-
-
-if __name__ == "__main__":
-    combinations = _generate_pipelines(primitive_python_paths)
-    print(combinations)

benchmark/realworld_data/pipeline_construction/pipeline_construction_subseq.py

@@ -1,183 +0,0 @@
-import uuid
-import random
-
-from d3m.metadata.pipeline import Pipeline
-
-from axolotl.algorithms.base import PipelineSearchBase
-from axolotl.utils import  schemas as schemas_utils
-
-primitive_python_paths = { # pragma: no cover
-    'data_processing': [
-        #'d3m.primitives.tods.data_processing.time_interval_transform',
-        #'d3m.primitives.tods.data_processing.categorical_to_binary',
-        #'d3m.primitives.tods.data_processing.column_filter',
-        #'d3m.primitives.tods.data_processing.timestamp_validation',
-        #'d3m.primitives.tods.data_processing.duplication_validation',
-        #'d3m.primitives.tods.data_processing.continuity_validation',
-    ],
-    'timeseries_processing': [
-        #'d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler',
-        'd3m.primitives.tods.timeseries_processing.subsequence_segmentation',
-        #'d3m.primitives.tods.timeseries_processing.transformation.standard_scaler',
-        #'d3m.primitives.tods.timeseries_processing.transformation.power_transformer',
-        #'d3m.primitives.tods.timeseries_processing.transformation.quantile_transformer',
-        #'d3m.primitives.tods.timeseries_processing.transformation.moving_average_transform',
-        #'d3m.primitives.tods.timeseries_processing.transformation.simple_exponential_smoothing',
-        #'d3m.primitives.tods.timeseries_processing.transformation.holt_smoothing',
-        #'d3m.primitives.tods.timeseries_processing.transformation.holt_winters_exponential_smoothing',
-        #'d3m.primitives.tods.timeseries_processing.decomposition.time_series_seasonality_trend_decomposition',
-    ],
-    'feature_analysis': [
-        #'d3m.primitives.tods.feature_analysis.auto_correlation',
-        #'d3m.primitives.tods.feature_analysis.statistical_mean',
-        #'d3m.primitives.tods.feature_analysis.statistical_median',
-        #'d3m.primitives.tods.feature_analysis.statistical_g_mean',
-        #'d3m.primitives.tods.feature_analysis.statistical_abs_energy',
-        #'d3m.primitives.tods.feature_analysis.statistical_abs_sum',
-        #'d3m.primitives.tods.feature_analysis.statistical_h_mean',
-        #'d3m.primitives.tods.feature_analysis.statistical_maximum',
-        #'d3m.primitives.tods.feature_analysis.statistical_minimum',
-        #'d3m.primitives.tods.feature_analysis.statistical_mean_abs',
-        #'d3m.primitives.tods.feature_analysis.statistical_mean_abs_temporal_derivative',
-        #'d3m.primitives.tods.feature_analysis.statistical_mean_temporal_derivative',
-        #'d3m.primitives.tods.feature_analysis.statistical_median_abs_deviation',
-        #'d3m.primitives.tods.feature_analysis.statistical_kurtosis',
-        #'d3m.primitives.tods.feature_analysis.statistical_skew',
-        #'d3m.primitives.tods.feature_analysis.statistical_std',
-        #'d3m.primitives.tods.feature_analysis.statistical_var',
-        #'d3m.primitives.tods.feature_analysis.statistical_variation',
-        #'d3m.primitives.tods.feature_analysis.statistical_vec_sum',
-        #'d3m.primitives.tods.feature_analysis.statistical_willison_amplitude',
-        #'d3m.primitives.tods.feature_analysis.statistical_zero_crossing',
-        #'d3m.primitives.tods.feature_analysis.spectral_residual_transform',
-        #'d3m.primitives.tods.feature_analysis.fast_fourier_transform',
-        #'d3m.primitives.tods.feature_analysis.discrete_cosine_transform',
-        #'d3m.primitives.tods.feature_analysis.non_negative_matrix_factorization',
-        #'d3m.primitives.tods.feature_analysis.bk_filter',
-        #'d3m.primitives.tods.feature_analysis.hp_filter',
-        #'d3m.primitives.tods.feature_analysis.truncated_svd',
-        #'d3m.primitives.tods.feature_analysis.wavelet_transform',
-        #'d3m.primitives.tods.feature_analysis.trmf',
-    ],
-    'detection_algorithm': [
-        #'d3m.primitives.tods.detection_algorithm.pyod_ae',
-        #'d3m.primitives.tods.detection_algorithm.pyod_vae',
-        #'d3m.primitives.tods.detection_algorithm.pyod_cof',
-        #'d3m.primitives.tods.detection_algorithm.pyod_sod',
-        #'d3m.primitives.tods.detection_algorithm.pyod_abod',
-        #'d3m.primitives.tods.detection_algorithm.pyod_hbos',
-        'd3m.primitives.tods.detection_algorithm.pyod_iforest',
-        #'d3m.primitives.tods.detection_algorithm.pyod_lof',
-        #'d3m.primitives.tods.detection_algorithm.pyod_knn',
-        'd3m.primitives.tods.detection_algorithm.pyod_ocsvm',
-        #'d3m.primitives.tods.detection_algorithm.pyod_loda',
-        #'d3m.primitives.tods.detection_algorithm.pyod_cblof',
-        'd3m.primitives.tods.detection_algorithm.pyod_sogaal',
-        #'d3m.primitives.tods.detection_algorithm.pyod_mogaal',
-        #'d3m.primitives.tods.detection_algorithm.matrix_profile',
-        #'d3m.primitives.tods.detection_algorithm.AutoRegODetector',
-        #'d3m.primitives.tods.detection_algorithm.LSTMODetector',
-        #'d3m.primitives.tods.detection_algorithm.AutoRegODetector',
-        #'d3m.primitives.tods.detection_algorithm.PCAODetector',
-        #'d3m.primitives.tods.detection_algorithm.KDiscordODetector',
-        #'d3m.primitives.tods.detection_algorithm.deeplog',
-        #'d3m.primitives.tods.detection_algorithm.telemanom',
-    ],
-    'contamination': [0.01, 0.05, 0.1, 0.15, 0.2, 0.25],
-}
-
-def _generate_pipeline(combinations):
-    from d3m import index
-    from d3m.metadata.base import ArgumentType
-    from d3m.metadata.pipeline import Pipeline, PrimitiveStep
-
-    piplines = []
-    for combination in combinations:
-        # Creating pipeline
-        pipeline_description = Pipeline()
-        pipeline_description.add_input(name='inputs')
-        
-        # The first three steps are fixed
-        # Step 0: dataset_to_dataframe
-        step_0 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.dataset_to_dataframe'))
-        step_0.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='inputs.0')
-        step_0.add_output('produce')
-        pipeline_description.add_step(step_0)
-
-        # Step 1: column_parser
-        step_1 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.column_parser'))
-        step_1.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
-        step_1.add_output('produce')
-        pipeline_description.add_step(step_1)
-
-        # Step 2: extract_columns_by_semantic_types(attributes)
-        step_2 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.extract_columns_by_semantic_types'))
-        step_2.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
-        step_2.add_output('produce')
-        step_2.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
-                                                                  data=['https://metadata.datadrivendiscovery.org/types/Attribute'])
-        pipeline_description.add_step(step_2)
-
-        # Step 3: extract_columns_by_semantic_types(targets)
-        step_3 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.extract_columns_by_semantic_types'))
-        step_3.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
-        step_3.add_output('produce')
-        step_3.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
-                                                                data=['https://metadata.datadrivendiscovery.org/types/TrueTarget'])
-        pipeline_description.add_step(step_3)
-
-        attributes = 'steps.2.produce'
-        targets = 'steps.3.produce'
-
-        tods_step_4 = PrimitiveStep(primitive=index.get_primitive(combination[0]))
-        tods_step_4.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference=attributes)
-        tods_step_4.add_hyperparameter(name='window_size', argument_type=ArgumentType.VALUE, data=10)
-        tods_step_4.add_hyperparameter(name='step', argument_type=ArgumentType.VALUE, data=1)
-        tods_step_4.add_output('produce')
-        pipeline_description.add_step(tods_step_4)
-
-        tods_step_5= PrimitiveStep(primitive=index.get_primitive(combination[1]))
-        tods_step_5.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.4.produce')
-        tods_step_5.add_output('produce')
-        tods_step_5.add_hyperparameter(name='contamination', argument_type=ArgumentType.VALUE, data=combination[2])
-        pipeline_description.add_step(tods_step_5)
-
-        # Finalize the pipeline
-        final_step = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.construct_predictions'))
-        final_step.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.5.produce')
-        final_step.add_argument(name='reference', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
-        final_step.add_output('produce')
-        pipeline_description.add_step(final_step)
-
-        pipeline_description.add_output(name='output predictions', data_reference='steps.6.produce')
-        data = pipeline_description.to_json()
-        #with open('../pipelines/'+str(combination[1].split(".")[-1])+'_'+str(combination[2])+".json", 'w') as f:
-        with open('./pipelines/subseq/'+str(combination[1].split(".")[-1])+'_subseq_'+str(combination[2])+".json", 'w') as f:
-            f.write(data)
-        pipeline_description.id = str(uuid.uuid4())
-        pipeline_description.created = Pipeline().created
-        piplines.append(pipeline_description)
-    return piplines
-
-def _generate_pipelines(primitive_python_paths, cpu_count=40): # pragma: no cover
-    """
-    Args:
-        primitive_python_paths: a list of primitive Python paths for algorithms
-    
-    Returns:
-        the pipline description json
-    """
-    import itertools
-    import multiprocessing as mp
-
-    #components = ['data_processing', 'timeseries_processing', 'feature_analysis', 'detection_algorithm']
-    components = ['timeseries_processing', 'detection_algorithm', 'contamination']
-    combinations = itertools.product(*(primitive_python_paths[k] for k in components))
-
-
-    return _generate_pipeline(combinations)
-
-
-if __name__ == "__main__":
-    combinations = _generate_pipelines(primitive_python_paths)
-    print(combinations)

benchmark/realworld_data/pipelines/AE/creditcard/ae_pipeline_0.01.json

@@ -1 +0,0 @@
-{"id": "9913179f-f470-49fa-b373-a53603341cf7", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:36:06.644888Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [29, 32, 16, 32, 29]}, "contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "d42e26f9c3f72aaaf3935c651f6a54ef95dad4e3185d48eaed8001593aed3f43"}

benchmark/realworld_data/pipelines/AE/creditcard/ae_pipeline_0.05.json

@@ -1 +0,0 @@
-{"id": "29622c5d-efe7-4686-8879-62cf363fb250", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:36:17.614201Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [29, 32, 16, 32, 29]}, "contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "a533ce0e6328b36d0b543acfad94d10917eb1b4e16a49e33df05d808ae50894d"}

benchmark/realworld_data/pipelines/AE/creditcard/ae_pipeline_0.1.json

@@ -1 +0,0 @@
-{"id": "ccc31853-42c3-4d22-8d55-094d4dde69a0", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:36:17.660637Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [29, 32, 16, 32, 29]}, "contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "8c4e213f490f36966a8d529e7d3f9a9140d90d88c1635bac0519193e26659b98"}

benchmark/realworld_data/pipelines/AE/creditcard/ae_pipeline_0.15.json

@@ -1 +0,0 @@
-{"id": "b456f5aa-df45-4ebd-a21d-c4dd19df2eb9", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:36:17.716744Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [29, 32, 16, 32, 29]}, "contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "3e717015e7667bcdddf95145758017044a5e6138c58777305fd1f7c9288ae5f1"}

benchmark/realworld_data/pipelines/AE/creditcard/ae_pipeline_0.2.json

@@ -1 +0,0 @@
-{"id": "47a631e4-dbcc-4b44-8a8c-983280d130c9", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:36:17.772373Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [29, 32, 16, 32, 29]}, "contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "b98a156873f04bd6ba8c89add50556972e335e8eccb07b7000dea4883843245d"}

benchmark/realworld_data/pipelines/AE/creditcard/ae_pipeline_0.25.json

@@ -1 +0,0 @@
-{"id": "7a043a7d-9c68-45f6-9b20-200fc9b52459", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:36:17.813380Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [29, 32, 16, 32, 29]}, "contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "42d14dc85ec507a2e1ed3e4540a575630f5d39a8946f9f86161790cfb5d2ecf3"}

benchmark/realworld_data/pipelines/AE/swan_sf/ae_pipeline_0.01.json

@@ -1 +0,0 @@
-{"id": "e7f6b407-6b01-4bca-b0ae-f365ec2b2350", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:37:01.378163Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [38, 32, 16, 32, 38]}, "contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "46cabc7f516e1ac3cfc63dbe05b84eed539a7c4ba00cf74286f258d5cdcc3e0f"}

benchmark/realworld_data/pipelines/AE/swan_sf/ae_pipeline_0.05.json

@@ -1 +0,0 @@
-{"id": "fbc9610d-28e0-4bb0-a62f-b98222ee0edd", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:37:10.133959Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [38, 32, 16, 32, 38]}, "contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "814af5da286bbb0ddf5f26cbd79a0d032432da5b0c0ad2f7a82b48ba2d6ddaad"}

benchmark/realworld_data/pipelines/AE/swan_sf/ae_pipeline_0.1.json

@@ -1 +0,0 @@
-{"id": "a39415d9-0098-47cf-98f8-a944e73a0f55", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:37:10.181552Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [38, 32, 16, 32, 38]}, "contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "17a8f61df2664a7e7f227709596756071805fc24b54f6adfeead4641fa461906"}

benchmark/realworld_data/pipelines/AE/swan_sf/ae_pipeline_0.15.json

@@ -1 +0,0 @@
-{"id": "13e20baa-df34-4778-aa64-d89cbe3a6ab9", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:37:10.237728Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [38, 32, 16, 32, 38]}, "contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "98a3b704045b864bd1e6c97d0d5d3090c0f920b590b8f648d287d62c042f912b"}

benchmark/realworld_data/pipelines/AE/swan_sf/ae_pipeline_0.2.json

@@ -1 +0,0 @@
-{"id": "cdf82244-a396-42dc-aa8a-06970dc32494", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:37:10.293028Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [38, 32, 16, 32, 38]}, "contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "ac81b1ab0a762e924eaf6a03e4d7f3db82141cfbefbdc59988511241459b48c8"}

benchmark/realworld_data/pipelines/AE/swan_sf/ae_pipeline_0.25.json

@@ -1 +0,0 @@
-{"id": "f8ee79bd-a189-4f59-9680-cda0b7e4d89d", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:37:10.341788Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [38, 32, 16, 32, 38]}, "contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "4cbf0290fcbb491829dcf5bfafcb4e98f4886cffdc42a6526be8f757ca5a36b0"}

benchmark/realworld_data/pipelines/AE/water_quality/ae_pipeline_0.01.json

@@ -1 +0,0 @@
-{"id": "6ccf92d2-ac57-44f1-a889-2291e31607ee", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:37:36.450385Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [9, 32, 16, 32, 9]}, "contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "bbe626db087f8550b8a133a01fd27c6d3154cb20595eb2c1ef49b3a61c464a87"}

benchmark/realworld_data/pipelines/AE/water_quality/ae_pipeline_0.05.json

@@ -1 +0,0 @@
-{"id": "e939f78b-665d-4c66-a088-7ff33965643b", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:37:46.280476Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [9, 32, 16, 32, 9]}, "contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "3a9905fcc4c534d8ebf5f0253a61f214fbedb9cae49b8aa7dbd529e2eff54496"}

benchmark/realworld_data/pipelines/AE/water_quality/ae_pipeline_0.1.json

@@ -1 +0,0 @@
-{"id": "24fa39eb-1b88-42f1-a45d-c5ef7a640449", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:37:46.310859Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [9, 32, 16, 32, 9]}, "contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "ae04e147f6d0b72bd5da1411bc2f323f88b975eb7e1167a3d3efb2c5c5eb5263"}

benchmark/realworld_data/pipelines/AE/water_quality/ae_pipeline_0.15.json

@@ -1 +0,0 @@
-{"id": "5985d4d9-76c6-49f0-80a0-5bfd1852d20f", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:37:46.340968Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [9, 32, 16, 32, 9]}, "contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "64a3f5a702e2dabf7bf9552bcbb8ff2be142a0243b5491ac39a7cbfae1b3b462"}

benchmark/realworld_data/pipelines/AE/water_quality/ae_pipeline_0.2.json

@@ -1 +0,0 @@
-{"id": "a2f6e5c8-4831-4de9-9117-62fd7bc3d883", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:37:46.371140Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [9, 32, 16, 32, 9]}, "contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "98861848741466ecbd3c9450c250539694cb035148e3e6178ce1848a000390ec"}

benchmark/realworld_data/pipelines/AE/water_quality/ae_pipeline_0.25.json

@@ -1 +0,0 @@
-{"id": "ef7cee79-8137-4cc2-bcec-8359c044b74a", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T20:37:46.401464Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [9, 32, 16, 32, 9]}, "contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "0285644a57b8ccd23a060d83158f928537204b1dda27832e8d3e404592649aee"}

benchmark/realworld_data/pipelines/AE/web_attack/ae_pipeline_0.01.json

@@ -1 +0,0 @@
-{"id": "e2bc2e02-967f-4f2a-b2c7-2a4984541b59", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:31:25.543375Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [78, 32, 16, 32, 78]}, "contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "34135d5e6d0e842cb86f6b2ccc3a88356eb93d2c0f157829b1588ae36d6f4966"}

benchmark/realworld_data/pipelines/AE/web_attack/ae_pipeline_0.05.json

@@ -1 +0,0 @@
-{"id": "195dff47-5be5-4df3-8d88-566ace7695cb", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:31:32.717445Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [78, 32, 16, 32, 78]}, "contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "91239b31ba3ba33709c59ef8a7132027816582ef9a9615a156af90cfd57e43da"}

benchmark/realworld_data/pipelines/AE/web_attack/ae_pipeline_0.1.json

@@ -1 +0,0 @@
-{"id": "730c7937-f9ee-487e-ab62-8b3bf3299b2d", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:31:32.747648Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [78, 32, 16, 32, 78]}, "contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "d70f552865c943925631dd8e3bef91cc3f884103a221c6f95b2bee86a0c41318"}

benchmark/realworld_data/pipelines/AE/web_attack/ae_pipeline_0.15.json

@@ -1 +0,0 @@
-{"id": "39850584-667f-4025-86cc-9ecc5f59a881", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:31:32.778001Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [78, 32, 16, 32, 78]}, "contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "512f5a902e20609286578858f0bd61bb2781d4c913cb1d3dbde5efb6516a633b"}

benchmark/realworld_data/pipelines/AE/web_attack/ae_pipeline_0.2.json

@@ -1 +0,0 @@
-{"id": "f905be50-5ab1-4cd9-8bd9-21eb5799c9c0", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:31:32.808238Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [78, 32, 16, 32, 78]}, "contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "01c5e12f3dccc4706d2dbfbd1663788a13d4d7e37e363f6a572d8a8cd976b8b9"}

benchmark/realworld_data/pipelines/AE/web_attack/ae_pipeline_0.25.json

@@ -1 +0,0 @@
-{"id": "dbb88640-6650-4576-9632-3aaa8d7666a3", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:31:32.838352Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"hidden_neurons": {"type": "VALUE", "data": [78, 32, 16, 32, 78]}, "contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "2a23496391a86686039b341205d1b8a63039fead92a63ab1c1723e96081b8b0a"}

benchmark/realworld_data/pipelines/RNN_LSTM/creditcard/rnnlstm_pipeline_0.01.json

@@ -1 +0,0 @@
-{"id": "b848b3d1-a4fb-40c2-93ef-e592f23baca2", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:17:18.363961Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 29}, "contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "67507c9d2c955521699554e87f399037eaa8fe516a87a57e37e976857d9b85c1"}

benchmark/realworld_data/pipelines/RNN_LSTM/creditcard/rnnlstm_pipeline_0.05.json

@@ -1 +0,0 @@
-{"id": "771d0340-766d-4de0-9281-5e60f189aa2b", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:17:26.016782Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 29}, "contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "fa34e91e2698a6a3065f64ed2086b54bce1a18b0f76be72be691ec6a7f024449"}

benchmark/realworld_data/pipelines/RNN_LSTM/creditcard/rnnlstm_pipeline_0.1.json

@@ -1 +0,0 @@
-{"id": "38c95ff4-5c91-4644-80b2-7becfdbaf2ff", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:17:26.072847Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 29}, "contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "26947a57dc3248b37c41045821f07e2c1f2bb415fdd8ccd4ddc1adad687457e0"}

benchmark/realworld_data/pipelines/RNN_LSTM/creditcard/rnnlstm_pipeline_0.15.json

@@ -1 +0,0 @@
-{"id": "6dec6ad4-d422-4e3c-9a9a-1a00bde903df", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:17:26.101527Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 29}, "contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "0d2892f9a61872821acf6bdc8c48c304b64592ada574e9ffae61f65df101449e"}

benchmark/realworld_data/pipelines/RNN_LSTM/creditcard/rnnlstm_pipeline_0.2.json

@@ -1 +0,0 @@
-{"id": "b35ebf53-a193-4a47-a848-87c129f89688", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:17:26.130522Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 29}, "contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "bdc164db32e30f4f02c7de724482f19df2e52102a56151488f1d05f870df55af"}

benchmark/realworld_data/pipelines/RNN_LSTM/creditcard/rnnlstm_pipeline_0.25.json

@@ -1 +0,0 @@
-{"id": "ca2ba4dc-af06-4f0a-b297-e9db955c4cf4", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:17:26.159218Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 29}, "contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "ad3b498ef1fa61185a345ba40bb4eee441c28117d63de92d6c8ed078de23c744"}

benchmark/realworld_data/pipelines/RNN_LSTM/swan_sf/rnnlstm_pipeline_0.01.json

@@ -1 +0,0 @@
-{"id": "e4bf3257-8c7a-45f6-aac5-3d38d711892a", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:16:58.923155Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 38}, "contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "b2ff8cf56c27266612554d4b5d5b722800f4b786fe3f9b8ffd427fa471018974"}

benchmark/realworld_data/pipelines/RNN_LSTM/swan_sf/rnnlstm_pipeline_0.05.json

@@ -1 +0,0 @@
-{"id": "6f9fac38-870a-4945-b29b-26baf8be3925", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:17:06.326585Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 38}, "contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "975d9c0c45d77b6cd8d7fca8b116f5dabf6bcab4e30578ab7c21733bc37217b8"}

benchmark/realworld_data/pipelines/RNN_LSTM/swan_sf/rnnlstm_pipeline_0.1.json

@@ -1 +0,0 @@
-{"id": "5b327fe3-6131-45f5-a994-caade0adb1a4", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:17:06.356028Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 38}, "contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "d8368afb3203af6b3b19c2c2fc9a715226cb5f6db25f2ba981d8a818c83fae90"}

benchmark/realworld_data/pipelines/RNN_LSTM/swan_sf/rnnlstm_pipeline_0.15.json

@@ -1 +0,0 @@
-{"id": "1ac5aa2d-ae2d-4022-ad78-306a4d44e91b", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:17:06.384942Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 38}, "contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "8e60793e5ec5fe683c7f6fd21dbf368335c720293f1ba252a7e7dadc0712eee6"}

benchmark/realworld_data/pipelines/RNN_LSTM/swan_sf/rnnlstm_pipeline_0.2.json

@@ -1 +0,0 @@
-{"id": "cbf5fc28-23f8-4ccf-9abe-c12d6b754bf8", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:17:06.414674Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 38}, "contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "e3b1448e31c75d97668c705d44d09513d09f450dbf31e770380c739cb808e107"}

benchmark/realworld_data/pipelines/RNN_LSTM/swan_sf/rnnlstm_pipeline_0.25.json

@@ -1 +0,0 @@
-{"id": "79bb4b8c-b889-4882-a4ac-cb4b757dd9c2", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:17:06.443703Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 38}, "contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "e6c97eac15fa1e618da93bd6bd4016b68555c718ef6a1498fb3084216c3aa9b1"}

benchmark/realworld_data/pipelines/RNN_LSTM/water_quality/rnnlstm_pipeline_0.01.json

@@ -1 +0,0 @@
-{"id": "97bdd96b-236e-42d4-b2f8-46065f1fd32d", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:16:23.710425Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 9}, "contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "80000cb1cb0f681517bdc24b9b1e945c4c88a50e4205ac030af4b3354e63fba6"}

benchmark/realworld_data/pipelines/RNN_LSTM/water_quality/rnnlstm_pipeline_0.05.json

@@ -1 +0,0 @@
-{"id": "2c0c1812-df85-40cb-8d48-b78d89a86b07", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:16:31.096839Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 9}, "contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "15de0dd9e8b5896a23bc1a3c3f30a00e9fb45c72e3d76a2a16c4b73ea6e0e3db"}

benchmark/realworld_data/pipelines/RNN_LSTM/water_quality/rnnlstm_pipeline_0.1.json

@@ -1 +0,0 @@
-{"id": "10b11875-7d3d-426a-b009-19538759113a", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:16:31.126330Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 9}, "contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "6c1c4f4472a2c4b6a894dd71fafea272b8c9edf4a842df3f865af831211bebba"}

benchmark/realworld_data/pipelines/RNN_LSTM/water_quality/rnnlstm_pipeline_0.15.json

@@ -1 +0,0 @@
-{"id": "749e888e-c27e-4524-ba05-7dbb068861d5", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:16:31.155216Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 9}, "contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "77a6051c6024a437a6ca42f28618339f77cb207bcb59ca5da45a8e28707621f3"}

benchmark/realworld_data/pipelines/RNN_LSTM/water_quality/rnnlstm_pipeline_0.2.json

@@ -1 +0,0 @@
-{"id": "3bdadab1-ebb8-476a-88af-c5c22b9282fe", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:16:31.184833Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 9}, "contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "4b9673e0d513454d1ee4ea728285494d1fac61291b80751f17c4882f7ad413ba"}

benchmark/realworld_data/pipelines/RNN_LSTM/water_quality/rnnlstm_pipeline_0.25.json

@@ -1 +0,0 @@
-{"id": "bacc8da3-a2e3-43bf-b236-4fda3c638486", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:16:31.213721Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 9}, "contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "e84cab64ca429b870b45125ef921182c6c60d55fe14ca8c1f12a9239fb203f93"}

benchmark/realworld_data/pipelines/RNN_LSTM/web_attack/rnnlstm_pipeline_0.01.json

@@ -1 +0,0 @@
-{"id": "b03d73ae-cb97-4dec-a9d4-0f7e11f381d3", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:16:41.431992Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 78}, "contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "58bc79cb210ae253e3305879d5da85f65a2bc7613866a23cb1abf712db1df691"}

benchmark/realworld_data/pipelines/RNN_LSTM/web_attack/rnnlstm_pipeline_0.05.json

@@ -1 +0,0 @@
-{"id": "d49e8692-58a3-41e0-a2f1-100e5e40979f", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:16:48.747049Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 78}, "contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "0b8306736a8a4002109536a8f428a0f165354bdb70544fa6e0337a68c44dd293"}

benchmark/realworld_data/pipelines/RNN_LSTM/web_attack/rnnlstm_pipeline_0.1.json

@@ -1 +0,0 @@
-{"id": "54db901f-7803-4838-bddb-87a70f9713d5", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:16:48.776649Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 78}, "contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "ad3ffa015d5bc523ee7c4eb90e7d812c67c534d7be925ee517ead826b7c5af8b"}

benchmark/realworld_data/pipelines/RNN_LSTM/web_attack/rnnlstm_pipeline_0.15.json

@@ -1 +0,0 @@
-{"id": "26a5e2ed-262f-4e94-b924-7a1793be0f1b", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:16:48.806573Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 78}, "contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "84ea479d6c789a576e4225703cf87a78eec23019145cb56c2c1e33b44b6ab683"}

benchmark/realworld_data/pipelines/RNN_LSTM/web_attack/rnnlstm_pipeline_0.2.json

@@ -1 +0,0 @@
-{"id": "899a2ebc-7c38-416e-b662-5f49ca8217eb", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:16:48.835756Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 78}, "contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "3f2488598d9287ecad18fa8c0eaad418825c559b0bbb0db1950c2a81bac6d47c"}

benchmark/realworld_data/pipelines/RNN_LSTM/web_attack/rnnlstm_pipeline_0.25.json

@@ -1 +0,0 @@
-{"id": "76760467-d1f7-48b8-86f6-5fccd23d7236", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T18:16:48.865676Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "642de2e7-5590-3cab-9266-2a53c326c461", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler", "name": "Axis_wise_scale"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b2371630-e502-3161-b72b-1e4dc4d07ca2", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.LSTMODetector", "name": "LSTMODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"feature_dim": {"type": "VALUE", "data": 78}, "contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "12b2631cc669191bcdc9a62613ee7ca0ec47aba1cb777333aaa797004233ef8c"}

benchmark/realworld_data/pipelines/simple/AutoRegODetector_0.01.json

@@ -1 +0,0 @@
-{"id": "ec1a0abb-5588-4eae-b0b0-b8ab3f04c6dd", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.787932Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "cefdf682-da99-3822-a54c-b48dfdd86640", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.AutoRegODetector", "name": "AutoRegODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "209c54ae56be6d2663a2f7bc888dacc3925ca63e6808409009c70efe40a60787"}

benchmark/realworld_data/pipelines/simple/AutoRegODetector_0.05.json

@@ -1 +0,0 @@
-{"id": "fa105dc1-ad4d-4477-a58c-cf9a4bf0870f", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.889662Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "cefdf682-da99-3822-a54c-b48dfdd86640", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.AutoRegODetector", "name": "AutoRegODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "fb9b8b4e0dc4d6ffb8cb2a24353e1c7947031408a2db839de4487de9ba5b360e"}

benchmark/realworld_data/pipelines/simple/AutoRegODetector_0.1.json

@@ -1 +0,0 @@
-{"id": "c520ebc8-12a6-4994-b8d7-fe6fd1adce99", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.937302Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "cefdf682-da99-3822-a54c-b48dfdd86640", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.AutoRegODetector", "name": "AutoRegODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "cbd26a8e4b02b6ec6babf2d17a72ddaf526e458fdcb150fe200401842593d741"}

benchmark/realworld_data/pipelines/simple/AutoRegODetector_0.15.json

@@ -1 +0,0 @@
-{"id": "ef700cfa-2f6e-4b94-aff4-0302a8799b63", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.994344Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "cefdf682-da99-3822-a54c-b48dfdd86640", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.AutoRegODetector", "name": "AutoRegODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "addd8807005cb64f0af87cf1e6fcf604a02f2141ba9fd7d25ea832520213e560"}

benchmark/realworld_data/pipelines/simple/AutoRegODetector_0.2.json

@@ -1 +0,0 @@
-{"id": "7cad8213-702e-494f-b80d-b50df8bd9979", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:37.050591Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "cefdf682-da99-3822-a54c-b48dfdd86640", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.AutoRegODetector", "name": "AutoRegODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "00143747738bf44d31903b50ed0491732bf4fd5cfb442c8ce7cf9dfeecbf885f"}

benchmark/realworld_data/pipelines/simple/AutoRegODetector_0.25.json

@@ -1 +0,0 @@
-{"id": "f169c606-a094-4a29-9bdc-3909e082391b", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:37.097163Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "cefdf682-da99-3822-a54c-b48dfdd86640", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.AutoRegODetector", "name": "AutoRegODetector"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "17264de9f3941c83dc28894e42378e65503c194dc8ee32296c25e89512374a1d"}

benchmark/realworld_data/pipelines/simple/matrix_profile_0.01.json

@@ -1 +0,0 @@
-{"id": "3c50426a-87d0-4148-a89f-8990d927456a", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.425267Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "692155a3-9448-303b-8015-3eab35e3a842", "version": "0.0.2", "python_path": "d3m.primitives.tods.detection_algorithm.matrix_profile", "name": "Matrix Profile"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "a88ac33ed85e19472df6bb3da5244e0f0096e8f87f9b418226107c57e5115048"}

benchmark/realworld_data/pipelines/simple/matrix_profile_0.05.json

@@ -1 +0,0 @@
-{"id": "d0cdd9a2-91b5-4bae-8b9e-9f29f4a804d3", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.510829Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "692155a3-9448-303b-8015-3eab35e3a842", "version": "0.0.2", "python_path": "d3m.primitives.tods.detection_algorithm.matrix_profile", "name": "Matrix Profile"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "356729cf6580c97830c9461e98ce62c1948cc4a454dae06b05d8ff780bd8d57f"}

benchmark/realworld_data/pipelines/simple/matrix_profile_0.1.json

@@ -1 +0,0 @@
-{"id": "7905c669-e797-4e53-9398-e6768af0035d", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.576958Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "692155a3-9448-303b-8015-3eab35e3a842", "version": "0.0.2", "python_path": "d3m.primitives.tods.detection_algorithm.matrix_profile", "name": "Matrix Profile"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "5c09a38b1bdde07b49ff294da66428a63a62147d7adfcde2b6886ab320261ebd"}

benchmark/realworld_data/pipelines/simple/matrix_profile_0.15.json

@@ -1 +0,0 @@
-{"id": "47614018-27b9-48de-8435-fbe15a00a199", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.627604Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "692155a3-9448-303b-8015-3eab35e3a842", "version": "0.0.2", "python_path": "d3m.primitives.tods.detection_algorithm.matrix_profile", "name": "Matrix Profile"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "3e9e101bbd7c012234f09d962be454ae4e789abfa12b2ee4035d88aea4118e82"}

benchmark/realworld_data/pipelines/simple/matrix_profile_0.2.json

@@ -1 +0,0 @@
-{"id": "e66b58dc-7935-4dd0-9497-d99bdb80b1bd", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.677373Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "692155a3-9448-303b-8015-3eab35e3a842", "version": "0.0.2", "python_path": "d3m.primitives.tods.detection_algorithm.matrix_profile", "name": "Matrix Profile"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "0c0cdef9ca0074c2209563a43dd8e59cde11e733547892ca7f753deb66349914"}

benchmark/realworld_data/pipelines/simple/matrix_profile_0.25.json

@@ -1 +0,0 @@
-{"id": "cf61ba36-36d8-44b3-b0bd-ba67a51461a8", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.737464Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "692155a3-9448-303b-8015-3eab35e3a842", "version": "0.0.2", "python_path": "d3m.primitives.tods.detection_algorithm.matrix_profile", "name": "Matrix Profile"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "1f05c57fcb61521892bcebafbef8edff7e913605d56e233550ac4dd4ae31ea80"}

benchmark/realworld_data/pipelines/simple/pyod_iforest_0.01.json

@@ -1 +0,0 @@
-{"id": "4679ddb0-6b1d-4dac-9f97-9274af0f97db", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:12.460340Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "bf355270-ba87-314e-be63-f38a28dd6f2f", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_iforest", "name": "TODS.anomaly_detection_primitives.IsolationForest"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "080931dda12d093dff194632d3e998f3829fce92d854dfc3e8bec7e2873263a8"}

benchmark/realworld_data/pipelines/simple/pyod_iforest_0.05.json

@@ -1 +0,0 @@
-{"id": "6d049287-b8c3-4acb-b271-0b8c38e29d4c", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:34.785909Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "bf355270-ba87-314e-be63-f38a28dd6f2f", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_iforest", "name": "TODS.anomaly_detection_primitives.IsolationForest"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "ac6a8993d56a27bdfbe38ce0762aa838c27fd8368022a1a426a3f0ea8fb8d65a"}

benchmark/realworld_data/pipelines/simple/pyod_iforest_0.1.json

@@ -1 +0,0 @@
-{"id": "c417f9f1-4c81-4e5a-9ae1-d904d312ff43", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:34.844739Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "bf355270-ba87-314e-be63-f38a28dd6f2f", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_iforest", "name": "TODS.anomaly_detection_primitives.IsolationForest"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "1edb08a65c2105287ebcbf1467f185b33f9312ac80049281ed97b05267926265"}

benchmark/realworld_data/pipelines/simple/pyod_iforest_0.15.json

@@ -1 +0,0 @@
-{"id": "11efbad0-0a14-49d5-a7ae-7358e910d13c", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:34.909161Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "bf355270-ba87-314e-be63-f38a28dd6f2f", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_iforest", "name": "TODS.anomaly_detection_primitives.IsolationForest"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "b72b007049d65d31fcbf4587211943a2445b39c13795e28399e2a7941c82c398"}

benchmark/realworld_data/pipelines/simple/pyod_iforest_0.2.json

@@ -1 +0,0 @@
-{"id": "096978d8-5a7d-4e9b-85af-3e11cd701b25", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:34.974797Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "bf355270-ba87-314e-be63-f38a28dd6f2f", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_iforest", "name": "TODS.anomaly_detection_primitives.IsolationForest"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "689899773473d387553404bd62d407d459e533b9993f46544ef01757d5eb16eb"}

benchmark/realworld_data/pipelines/simple/pyod_iforest_0.25.json

@@ -1 +0,0 @@
-{"id": "16f97ac8-d977-4d19-b07c-1833ed80a3dd", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.035223Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "bf355270-ba87-314e-be63-f38a28dd6f2f", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_iforest", "name": "TODS.anomaly_detection_primitives.IsolationForest"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "cd120ec662672ff1cae745bc3be47f3ea413fcb808bf4a2d3793ee4ecffee1e3"}

benchmark/realworld_data/pipelines/simple/pyod_mogaal_0.01.json

@@ -1 +0,0 @@
-{"id": "9bd9c014-1896-4347-a33f-97b4d62b04c4", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.855035Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "906b96ea-f260-4ede-8f55-c26d1367eb32", "version": "0.1.0", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_mogaal", "name": "Mo_Gaal Anomaly Detection", "digest": "409d3791e3dd9a82e6a3ef4e8512e8904820e32bf88904c2aba4498c1cee130e"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "212db1d8dc1f41e2fe6860f1b0954442a085ddc9700a0042d726a2e69d297528"}

benchmark/realworld_data/pipelines/simple/pyod_mogaal_0.05.json

@@ -1 +0,0 @@
-{"id": "bbafa488-3a6b-4c9c-9c93-ccf684b874bc", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.035827Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "906b96ea-f260-4ede-8f55-c26d1367eb32", "version": "0.1.0", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_mogaal", "name": "Mo_Gaal Anomaly Detection", "digest": "409d3791e3dd9a82e6a3ef4e8512e8904820e32bf88904c2aba4498c1cee130e"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "57d874dac45a2c9bb34fb36b81508842fdd4b2edaadec291e985cc8f0853fd55"}

benchmark/realworld_data/pipelines/simple/pyod_mogaal_0.1.json

@@ -1 +0,0 @@
-{"id": "55a47d4a-9984-475d-b194-a4a61224f9b2", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.193259Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "906b96ea-f260-4ede-8f55-c26d1367eb32", "version": "0.1.0", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_mogaal", "name": "Mo_Gaal Anomaly Detection", "digest": "409d3791e3dd9a82e6a3ef4e8512e8904820e32bf88904c2aba4498c1cee130e"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "78daadb8295853693cb19b001256926de67ebd2b9898d16e9fd2c5a56b514540"}

benchmark/realworld_data/pipelines/simple/pyod_mogaal_0.15.json

@@ -1 +0,0 @@
-{"id": "248bc860-629c-4669-b60d-86c3cb2be984", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.241820Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "906b96ea-f260-4ede-8f55-c26d1367eb32", "version": "0.1.0", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_mogaal", "name": "Mo_Gaal Anomaly Detection", "digest": "409d3791e3dd9a82e6a3ef4e8512e8904820e32bf88904c2aba4498c1cee130e"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "ec015a8fb21b7ff9562dd16ff417ba5d09ee7fbb0079948779a33ed3558e017e"}

benchmark/realworld_data/pipelines/simple/pyod_mogaal_0.2.json

@@ -1 +0,0 @@
-{"id": "4ab2c78f-9d95-4c07-aaad-4f554097a06a", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.307310Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "906b96ea-f260-4ede-8f55-c26d1367eb32", "version": "0.1.0", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_mogaal", "name": "Mo_Gaal Anomaly Detection", "digest": "409d3791e3dd9a82e6a3ef4e8512e8904820e32bf88904c2aba4498c1cee130e"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "be0ba83fbc3683d900502a4d75282e892e8a53ac5495df1b580937da1424163f"}

benchmark/realworld_data/pipelines/simple/pyod_mogaal_0.25.json

@@ -1 +0,0 @@
-{"id": "9037070b-4072-4a8a-9546-6430cadc8bea", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:36.363090Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "906b96ea-f260-4ede-8f55-c26d1367eb32", "version": "0.1.0", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_mogaal", "name": "Mo_Gaal Anomaly Detection", "digest": "409d3791e3dd9a82e6a3ef4e8512e8904820e32bf88904c2aba4498c1cee130e"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "b2c5014aa3e6a35c402ccf61d5b440cdb82840eb9391b14807fd0f158e051972"}

benchmark/realworld_data/pipelines/simple/pyod_ocsvm_0.01.json

@@ -1 +0,0 @@
-{"id": "53fa3a30-1223-4d65-b46d-1e2b97283fd3", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.081820Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b454adf7-5820-3e6f-8383-619f13fb1cb6", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ocsvm", "name": "TODS.anomaly_detection_primitives.OCSVMPrimitive"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "dd50d58c91ad664045780112581318347f46b2b3a9dadaef570a70d6212d7c39"}

benchmark/realworld_data/pipelines/simple/pyod_ocsvm_0.05.json

@@ -1 +0,0 @@
-{"id": "fbd01736-be2b-4d99-b843-fa908b29a8ad", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.189771Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b454adf7-5820-3e6f-8383-619f13fb1cb6", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ocsvm", "name": "TODS.anomaly_detection_primitives.OCSVMPrimitive"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "a66b48b7e6f75c59eb2e0a412254babc763e45f95b2450545cd36fce751226d3"}

benchmark/realworld_data/pipelines/simple/pyod_ocsvm_0.1.json

@@ -1 +0,0 @@
-{"id": "18dde902-5264-4ebf-a244-f3776c9003d9", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.233069Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b454adf7-5820-3e6f-8383-619f13fb1cb6", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ocsvm", "name": "TODS.anomaly_detection_primitives.OCSVMPrimitive"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "5ecec8384b8700ae16d0ccf58d1ffce68ad51d6aec353b3450764a2b549f2e1f"}

benchmark/realworld_data/pipelines/simple/pyod_ocsvm_0.15.json

@@ -1 +0,0 @@
-{"id": "15f7c8e0-0064-4480-bf4d-bac1d97be546", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.279733Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b454adf7-5820-3e6f-8383-619f13fb1cb6", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ocsvm", "name": "TODS.anomaly_detection_primitives.OCSVMPrimitive"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "b7559467a1976c78b725f842ed0d194476e59ba1144e95204642e9ac95b1620d"}

benchmark/realworld_data/pipelines/simple/pyod_ocsvm_0.2.json

@@ -1 +0,0 @@
-{"id": "df99211e-3875-4a48-85be-4b6359a8b1a7", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.338747Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b454adf7-5820-3e6f-8383-619f13fb1cb6", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ocsvm", "name": "TODS.anomaly_detection_primitives.OCSVMPrimitive"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "27ff1fe598abf7f1f65cb13569517b0a739d9f0c2ae9b11c60c5d78c8d6e6a8a"}

benchmark/realworld_data/pipelines/simple/pyod_ocsvm_0.25.json

@@ -1 +0,0 @@
-{"id": "e717d027-1a34-4414-b919-bc56570926f0", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.390800Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "b454adf7-5820-3e6f-8383-619f13fb1cb6", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ocsvm", "name": "TODS.anomaly_detection_primitives.OCSVMPrimitive"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "79b26eb8a515a47b63296c2cc8a2e0ee35bc8feb25dd1c6e3de7002475c6ed16"}

benchmark/realworld_data/pipelines/simple/pyod_sogaal_0.01.json

@@ -1 +0,0 @@
-{"id": "171cdb2d-3667-4080-bedf-acbdc4de383d", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.439484Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "ca7993c9-e663-39a6-9569-751d5463ae3e", "version": "0.1.0", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_sogaal", "name": "So_Gaal Anomaly Detection"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "73141f7e4d967353bb237125ce915ffef5a7efcb04bd08243041cf85edda0a61"}

benchmark/realworld_data/pipelines/simple/pyod_sogaal_0.05.json

@@ -1 +0,0 @@
-{"id": "873aa9e9-b6d6-4454-98b9-0206cd96b0a3", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.529022Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "ca7993c9-e663-39a6-9569-751d5463ae3e", "version": "0.1.0", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_sogaal", "name": "So_Gaal Anomaly Detection"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "69422f695ecb2079b77833ba867117840065db12373fc2e61410a40653f460bf"}

benchmark/realworld_data/pipelines/simple/pyod_sogaal_0.1.json

@@ -1 +0,0 @@
-{"id": "4b83f870-d280-41f8-b6b4-7f774f88df9e", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.587452Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "ca7993c9-e663-39a6-9569-751d5463ae3e", "version": "0.1.0", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_sogaal", "name": "So_Gaal Anomaly Detection"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "ec064f2d5ebeb19b0cdaec5fc3c927f7f66c37f62be37f31460156600718cd22"}

benchmark/realworld_data/pipelines/simple/pyod_sogaal_0.15.json

@@ -1 +0,0 @@
-{"id": "f0b93a81-a015-4462-866b-df7f08eb1bdb", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.649388Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "ca7993c9-e663-39a6-9569-751d5463ae3e", "version": "0.1.0", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_sogaal", "name": "So_Gaal Anomaly Detection"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "e93cc35196699d0873f623585e7d719450614b76a7889ed19603be9ed4dd0e63"}

benchmark/realworld_data/pipelines/simple/pyod_sogaal_0.2.json

@@ -1 +0,0 @@
-{"id": "fdf1afb1-5fc9-45b0-9723-b08279741d72", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.707048Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "ca7993c9-e663-39a6-9569-751d5463ae3e", "version": "0.1.0", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_sogaal", "name": "So_Gaal Anomaly Detection"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.2}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "46c3770aafb88b9d9773cd28a0c1e320935b6533ca272deec0cbf4c3d228873f"}

benchmark/realworld_data/pipelines/simple/pyod_sogaal_0.25.json

@@ -1 +0,0 @@
-{"id": "8215e5c1-4965-474d-8b68-9867a1adbdc8", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:30:35.780959Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "3b54b820-d4c4-3a1f-813c-14c2d591e284", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.transformation.standard_scaler", "name": "Standard_scaler"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "ca7993c9-e663-39a6-9569-751d5463ae3e", "version": "0.1.0", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_sogaal", "name": "So_Gaal Anomaly Detection"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.25}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "86f2655fa5c990f4c7d71187419cea987ad81268351036e5e6bc828fff99bbb4"}

benchmark/realworld_data/pipelines/subseq/pyod_ae_subseq_0.01.json

@@ -1 +0,0 @@
-{"id": "0c48960f-2875-48b8-ab79-4082f5d82207", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:52:33.165465Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "7e875a62-b99c-340a-bbc8-ac63789fb2b4", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.subsequence_segmentation", "name": "Subsequence Segmentation Primitive"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"window_size": {"type": "VALUE", "data": 10}, "step": {"type": "VALUE", "data": 1}}}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.01}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "a94c29173edcc2dbeed1012dd91ec8cf0a1de09e82c88d72f1d6b6e067d87e79"}

benchmark/realworld_data/pipelines/subseq/pyod_ae_subseq_0.05.json

@@ -1 +0,0 @@
-{"id": "ef33487f-faf3-468b-b9b5-db46091e506c", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:52:39.377335Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "7e875a62-b99c-340a-bbc8-ac63789fb2b4", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.subsequence_segmentation", "name": "Subsequence Segmentation Primitive"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"window_size": {"type": "VALUE", "data": 10}, "step": {"type": "VALUE", "data": 1}}}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.05}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "9f4b04e9fdbc4c87c2d623f939c7a3551ae192d253fed6e01781543cb55b7d45"}

benchmark/realworld_data/pipelines/subseq/pyod_ae_subseq_0.1.json

@@ -1 +0,0 @@
-{"id": "d8161d93-5696-4c02-ade9-7ba380c67b92", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:52:39.407849Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "7e875a62-b99c-340a-bbc8-ac63789fb2b4", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.subsequence_segmentation", "name": "Subsequence Segmentation Primitive"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"window_size": {"type": "VALUE", "data": 10}, "step": {"type": "VALUE", "data": 1}}}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.1}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "cf206319cf6f77d3474d246cc7b7d3c9ea3d0995e9f0dd7b421051d1a86d716b"}

benchmark/realworld_data/pipelines/subseq/pyod_ae_subseq_0.15.json

@@ -1 +0,0 @@
-{"id": "74a23bff-43a7-40aa-b63f-a42f4a6bb93c", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T17:52:39.438190Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "c78138d9-9377-31dc-aee8-83d9df049c60", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.dataset_to_dataframe", "name": "Extract a DataFrame from a Dataset"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "81235c29-aeb9-3828-911a-1b25319b6998", "version": "0.6.0", "python_path": "d3m.primitives.tods.data_processing.column_parser", "name": "Parses strings into their types"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Attribute"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "a996cd89-ddf0-367f-8e7f-8c013cbc2891", "version": "0.4.0", "python_path": "d3m.primitives.tods.data_processing.extract_columns_by_semantic_types", "name": "Extracts columns by semantic type"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/TrueTarget"]}}}, {"type": "PRIMITIVE", "primitive": {"id": "7e875a62-b99c-340a-bbc8-ac63789fb2b4", "version": "0.0.1", "python_path": "d3m.primitives.tods.timeseries_processing.subsequence_segmentation", "name": "Subsequence Segmentation Primitive"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"window_size": {"type": "VALUE", "data": 10}, "step": {"type": "VALUE", "data": 1}}}, {"type": "PRIMITIVE", "primitive": {"id": "67e7fcdf-d645-3417-9aa4-85cd369487d9", "version": "0.0.1", "python_path": "d3m.primitives.tods.detection_algorithm.pyod_ae", "name": "TODS.anomaly_detection_primitives.AutoEncoder"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"contamination": {"type": "VALUE", "data": 0.15}}}, {"type": "PRIMITIVE", "primitive": {"id": "2530840a-07d4-3874-b7d8-9eb5e4ae2bf3", "version": "0.3.0", "python_path": "d3m.primitives.tods.data_processing.construct_predictions", "name": "Construct pipeline predictions output"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "c2baa51ca5e1a771d4b22ee007c1e8a2176600944c03e9987d5234a48068be7c"}