Revise main page readme

README.md

@@ -1,8 +1,10 @@
 
-# TODS: Automated Time-series Outlier Detection System
+# Revisiting Time Series Outlier Detection: Definitions and Benchmarks
 <img width="500" src="./docs/img/tods_logo.png" alt="Logo" />
 
-[![Build Status](https://travis-ci.org/datamllab/tods.svg?branch=master)](https://travis-ci.org/datamllab/tods)
+## For getting benchmark code, data and result, please follow the instruction below to intall the package and go to the "benchmark/" folder for pipelines, code, data, and benchmark results.
+
+[![Build Status](https://travis-ci.org/datamllab/tods.svg?branch=dev)](https://travis-ci.org/datamllab/tods)
 
 TODS is a full-stack automated machine learning system for outlier detection on multivariate time-series data. TODS provides exhaustive modules for building machine learning-based outlier detection systems, including: data processing, time series processing, feature analysis (extraction), detection algorithms, and reinforcement module. The functionalities provided via these modules include data preprocessing for general purposes, time series data smoothing/transformation, extracting features from time/frequency domains, various detection algorithms, and involving human expertise to calibrate the system. Three common outlier detection scenarios on time-series data can be performed: point-wise detection (time points as outliers), pattern-wise detection (subsequences as outliers), and system-wise detection (sets of time series as outliers), and a wide-range of corresponding algorithms are provided in TODS. This package is developed by [DATA Lab @ Texas A&M University](https://people.engr.tamu.edu/xiahu/index.html).
 

examples/axolotl_interface/example_pipelines/autoencoder_pipeline.json

@@ -1 +1 @@
-{"id": "924e9a77-da5f-4bcc-b9a0-ed65bbaf87fa", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-03-11T23:41:13.884494Z", "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": "f07ce875-bbc7-36c5-9cc1-ba4bfb7cf48e", "version": "0.1.0", "python_path": "d3m.primitives.tods.feature_analysis.statistical_maximum", "name": "Time Series Decompostional"}, "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"}]}, {"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": "bb1cb5328299d8d65cabc152092da553db267494fb12e6320c66110b2c48a265"}
+{"id": "d7188290-c316-4925-bf27-eabe0cb2099d", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2021-06-01T16:53:41.644557Z", "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": "f07ce875-bbc7-36c5-9cc1-ba4bfb7cf48e", "version": "0.1.0", "python_path": "d3m.primitives.tods.feature_analysis.statistical_maximum", "name": "Time Series Decompostional"}, "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": [32, 16, 8, 16, 32]}}}, {"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": "85174ebdb5d2f9fd708eed4f0807cac6d902d8b57ef9048341ef5d66f3b99f65"}

examples/axolotl_interface/example_pipelines/script/build_AutoEncoder_pipeline.py

@@ -51,6 +51,7 @@ 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=[32,16,8,16,32])
 step_5.add_output('produce')
 pipeline_description.add_step(step_5)