add run_pipeline example

Former-commit-id: 288393715a [formerly fd66dd92f8] [formerly f969a91e29 [formerly 328bc7f429]] [formerly 055971c1ba [formerly 2dc54dce68] [formerly 614269ccfe [formerly f37d0044dd]]] [formerly c524aa15ac [formerly 0c85249c00] [formerly c883bf8cf1 [formerly 045a32725a]] [formerly fca41f37d2 [formerly fbe1445b3f] [formerly ee00fd612b [formerly 8cb4e5a423]]]] [formerly 827b81298b [formerly fea21bff95] [formerly 46870a25ff [formerly 5f0a227ae9]] [formerly 51f667d8e7 [formerly c93cb06e20] [formerly 86c1b5c69b [formerly 1dd4ebf49e]]] [formerly f6e35b7fcd [formerly 037dd8a337] [formerly 69ce24d9a9 [formerly 1fcf5b8fd4]] [formerly 35e9100330 [formerly 28cb84ba65] [formerly 901542acd1 [formerly a9e8a39377]]]]] [formerly 8ece4325ab [formerly ba66105df3] [formerly 86d52f8e52 [formerly 540386c495]] [formerly 8ea7d87d77 [formerly 5399029369] [formerly f862e7add9 [formerly e946cfd883]]] [formerly 986ef588e1 [formerly 98f1111c6d] [formerly ed53a50f20 [formerly a0c848e95e]] [formerly 6da3707228 [formerly 8dcd999b94] [formerly dfb80dd48b [formerly d93676b105]]]] [formerly b3a8e4729f [formerly 7a16fe0543] [formerly 0fd9ccb912 [formerly 90cf76ed5f]] [formerly 98ccdd8f18 [formerly 9d09d642ee] [formerly 4091dda241 [formerly 507f2b27c4]]] [formerly f628b52f38 [formerly a85c59dc5d] [formerly f55864ca0c [formerly 816768d4b6]] [formerly 4b611c8ca9 [formerly 63aefd8cee] [formerly 1e48dbf314 [formerly 1c4b9c0a1c]]]]]]
Former-commit-id: 4214ab428b [formerly ec8c656b5c] [formerly d05bf6ca41 [formerly c12b38a108]] [formerly 426ffc8ab1 [formerly 8dfab4a38b] [formerly d3a97e3fa1 [formerly f2e7e2cb51]]] [formerly 060461b7be [formerly 5a001ba0f4] [formerly 385181b3c7 [formerly 90e9cdf946]] [formerly 2572c6d9b8 [formerly 3eb5ace3e3] [formerly 0d0bfb4fcb [formerly 42eb4bd144]]]] [formerly d872261dcc [formerly 2c92cf236b] [formerly 9f47a08afa [formerly e123cd95e1]] [formerly 8fcc9c9dd1 [formerly c6e0419dbc] [formerly 95c5650729 [formerly 1d3dc1a7e4]]] [formerly 0210e142de [formerly c33cb25185] [formerly 6f1280668e [formerly 2686c34dcd]] [formerly 28401889eb [formerly 2f7569552a] [formerly 1e48dbf314]]]]
Former-commit-id: 149e5f1a0b [formerly 9fd497b6ae] [formerly 13e0388bfe [formerly 21155c5857]] [formerly 194f3976cd [formerly dd7d329721] [formerly 741a66597f [formerly f4244702e8]]] [formerly 57ad7550ad [formerly dc2076235d] [formerly 2cd5644f99 [formerly 900eaa1a53]] [formerly 6608ad174b [formerly dfbf60f2b5] [formerly edbfe1bff6 [formerly 734463e4b7]]]]
Former-commit-id: 7fefbdfa7b [formerly 0f7c45a1be] [formerly c3b6bdf21e [formerly b818b775d2]] [formerly 4d04227c13 [formerly 4439eefeaa] [formerly d919921c2c [formerly c7f3529053]]]
Former-commit-id: ae31ceb1a0 [formerly aed7c1c488] [formerly 0a0eb413b8 [formerly d87ee60333]]
Former-commit-id: 36dee1f46e [formerly 2db524c908]
Former-commit-id: 46ed14eae2

examples/run_certain_pipeline.py

@@ -1,30 +0,0 @@
-
-import os
-
-results_dir = './'
-pipeline_run_yml_dir = './'
-
-pipeline_yml_name = './pipeline.yml' # './pipeline_yml/pipeline_10.yml'
-pipline_yml_index = pipeline_yml_name[11:-4]
-
-python_command = 'python3 -m d3m runtime fit-produce -p ' + pipeline_yml_name \
-                     + ' -r ./datasets/anomaly/yahoo_sub_5/TRAIN/problem_TRAIN/problemDoc.json' \
-                     + ' -i ./datasets/anomaly/yahoo_sub_5/TRAIN/dataset_TRAIN/datasetDoc.json' \
-                     + ' -t ./datasets/anomaly/yahoo_sub_5/TEST/dataset_TEST/datasetDoc.json -o ' \
-                     + results_dir + 'result.csv' \
-                     + ' -O ' \
-                     + pipeline_run_yml_dir + 'pipeline_run' + '.yml'
-
-print(python_command)
-os.system(python_command)
-# 'python3 -m d3m runtime fit-produce -p pipeline.yml
-# -r ../datasets/anomaly/kpi/TRAIN/problem_TRAIN/problemDoc.json
-# -i ../datasets/anomaly/kpi/TRAIN/dataset_TRAIN/datasetDoc.json
-# -t ../datasets/anomaly/kpi/TEST/dataset_TEST/datasetDoc.json
-# -o results.csv -O pipeline_run.yml'
-
-# python3 -m d3m runtime fit-produce -p pipeline.yml
-# -r ../datasets/anomaly/yahoo_sub_5/TRAIN/problem_TRAIN/problemDoc.json
-# -i ../datasets/anomaly/yahoo_sub_5/TRAIN/dataset_TRAIN/datasetDoc.json
-# -t ../datasets/anomaly/yahoo_sub_5/TEST/dataset_TEST/datasetDoc.json
-# -o result.csv -O pipeline_run.yml

examples/run_pipeline.py

@@ -0,0 +1,42 @@
+import pandas as pd
+import sys
+import argparse
+
+from searcher import schemas as schemas_utils
+from searcher.utils import generate_dataset_problem, evaluate_pipeline
+from axolotl.utils import pipeline as pipeline_utils
+import os
+
+this_path = os.path.dirname(os.path.abspath(__file__))
+#table_path = 'datasets/NAB/realTweets/labeled_Twitter_volume_IBM.csv' # The path of the dataset
+
+parser = argparse.ArgumentParser(description='Arguments for running predefined pipelin.')
+parser.add_argument('--table_path', type=str, default=os.path.join(this_path, '../datasets/yahoo_sub_5.csv'),
+                    help='Input the path of the input data table')
+parser.add_argument('--target_index', type=int, default=6,
+                    help='Index of the ground truth (for evaluation)')
+parser.add_argument('--metric',type=str, default='F1_MACRO',
+                    help='Evaluation Metric (F1, F1_MACRO)')
+parser.add_argument('--pipeline_path', default=os.path.join(this_path, '../tods/searcher/resources/default_pipeline.json'),
+                    help='Input the path of the pre-built pipeline description')
+
+args = parser.parse_args()
+
+table_path = args.table_path 
+target_index = args.target_index # what column is the target
+pipeline_path = args.pipeline_path
+metric = args.metric # F1 on both label 0 and 1
+
+time_limit = 30 # How many seconds you wanna search
+
+# Read data and generate dataset and problem
+df = pd.read_csv(table_path)
+dataset, problem_description = generate_dataset_problem(df, target_index=target_index, metric=metric)
+
+# Load the default pipeline
+pipeline = pipeline_utils.load_pipeline(pipeline_path)
+
+# Run the pipeline
+pipeline_result = evaluate_pipeline(problem_description, dataset, pipeline)
+print(pipeline_result)
+