add ensemble method to pipeline

Former-commit-id: 14cd2d7e2e [formerly 90fc6cfc5d] [formerly 6020a6b10f [formerly 29650194e4]] [formerly 1018ccdba4 [formerly 9918a67704] [formerly 4be62ee58e [formerly 41c44bcbc5]]] [formerly cf44ee98c0 [formerly e15a1b02da] [formerly 437698c169 [formerly 800cb276e3]] [formerly d999aa7192 [formerly 8ef23f4060] [formerly b4ae742b67 [formerly 5a73e6b100]]]] [formerly 40cb29bd16 [formerly fa4437b35c] [formerly 5805704b0c [formerly 25f7212c8f]] [formerly f5f2bef94f [formerly ab6675ff00] [formerly 3138e6ce1d [formerly 1ca84903a4]]] [formerly 4c9f3cf1d8 [formerly 88b5a07731] [formerly 3dbc2ec7b4 [formerly 299f376495]] [formerly bf0de2fed6 [formerly 9d34078213] [formerly 1246727e78 [formerly efa9f835b3]]]]] [formerly e371d3b5f5 [formerly 03670cae95] [formerly 3100fee57d [formerly 628219288a]] [formerly cd4b4fc0cb [formerly aaf4d9ae4e] [formerly 35fa33e696 [formerly 94582b19a9]]] [formerly 08f30cef34 [formerly 0317ee39f4] [formerly dcb5e225a7 [formerly c9d556cdcc]] [formerly 4c66fa2f44 [formerly f00839c917] [formerly 173d6553fe [formerly aa878ba32b]]]] [formerly 34ad5da184 [formerly c16238ad0f] [formerly 016565859c [formerly 2e17bffa66]] [formerly ac5dd34fe0 [formerly f35341ea9e] [formerly 63605c0cd2 [formerly 30768a97b4]]] [formerly 87ed311964 [formerly 0784466b8e] [formerly 7ef627c974 [formerly 4cc3f1229b]] [formerly 89ad58f769 [formerly c24354e066] [formerly 45e6e005e4 [formerly c2b44af7be]]]]]]
Former-commit-id: 6382bb839c [formerly cbb1e65926] [formerly b55ea3224b [formerly 1f9edfbd8e]] [formerly a578391dab [formerly 3f2d879789] [formerly ec8a57ce8f [formerly ed56ff08dc]]] [formerly 9bb025aa90 [formerly cc195f7b2a] [formerly f6a6743bc9 [formerly e6ed426d6b]] [formerly 285ad0b770 [formerly 3ce7edbc41] [formerly 1665a8d080 [formerly c990c3aa5a]]]] [formerly 20deda7f57 [formerly b8ec00710a] [formerly c7478488a6 [formerly 0e20ae05a2]] [formerly f8c3b5a8f2 [formerly a92fd944b8] [formerly ce86051611 [formerly 2b162b34d1]]] [formerly 53a8738060 [formerly 9fbd3fbed1] [formerly de32295f7c [formerly b72c882218]] [formerly 5d0ba3380a [formerly 8619d8109d] [formerly 45e6e005e4]]]]
Former-commit-id: b437ddaf20 [formerly a862b83e29] [formerly 2e5ecc53a8 [formerly 084ee9bf75]] [formerly ac0b50ab7d [formerly 9e965e26e0] [formerly 0455e27faa [formerly 96bb665c58]]] [formerly bfa26e9b0c [formerly a37c9a732e] [formerly e41d8ec8f6 [formerly c2501feab8]] [formerly 5464f49cd5 [formerly bb92ff4b9f] [formerly 3ba646f146 [formerly 425993cd18]]]]
Former-commit-id: 99a7cb6d6f [formerly 70230e04a8] [formerly 4c6a1e4309 [formerly 2689b8c34a]] [formerly 6bbe3e7407 [formerly 3c460c27d5] [formerly 53cf0c8ae5 [formerly 208c049ddd]]]
Former-commit-id: df6bd5ba7d [formerly be1022002b] [formerly 933790f0c5 [formerly dce7ea1261]]
Former-commit-id: db7210c37c [formerly 849759f3fc]
Former-commit-id: 2d96f01d17

examples/run_pipeline_ensemble.py

@@ -0,0 +1,48 @@
+import sys
+import argparse
+import os
+import pandas as pd
+
+from tods import generate_dataset, load_pipeline, evaluate_pipeline
+
+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('--table_path', type=str, default=os.path.join(this_path, '../datasets/anomaly/yahoo_system_sub_5/yahoo_system_sub_5_dataset/tables/learningData.csv'),
+                    help='Input the path of the input data table')
+
+parser.add_argument('--target_index', type=int, default=4,
+                    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/resources/default_pipeline.json'),
+#                    help='Input the path of the pre-built pipeline description')
+
+#Using the pipeline that was build and saved in example_pipeline
+parser.add_argument('--pipeline_path', default=os.path.join(this_path, './example_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
+
+# Read data and generate dataset
+df = pd.read_csv(table_path)
+dataset = generate_dataset(df, target_index)
+
+# Load the default pipeline
+pipeline = load_pipeline(pipeline_path)
+
+# Run the pipeline
+pipeline_result = evaluate_pipeline(dataset, pipeline, metric)
+print(pipeline_result)
+