SubsequenceClustering

Former-commit-id: ee3611c724 [formerly 1a66b1fd98] [formerly 7549fa5735 [formerly 80d2551807]] [formerly 9e4bc95f56 [formerly 291eb5bef0] [formerly f57c077ff3 [formerly 0051dbb84f]]] [formerly 42fcb2cec9 [formerly e9dbe8d9db] [formerly 6fa8617040 [formerly 97d8d309b2]] [formerly 4266e2af31 [formerly c77b2d5d20] [formerly 066165bcd5 [formerly 747cc9fb76]]]] [formerly 22b33ec903 [formerly a6ee617b4e] [formerly 42ee68458c [formerly a270a328c4]] [formerly a20a24a912 [formerly eb6668f3e1] [formerly 73f58dcea1 [formerly a4986c2690]]] [formerly fdb7d3c362 [formerly 0caf857529] [formerly d78f5b83c1 [formerly fd846aca19]] [formerly 595c771ea5 [formerly f5059178e8] [formerly 71bcdc8b03 [formerly 79364e58d5]]]]] [formerly 510e42081f [formerly e29a31dee1] [formerly ea8fea9bac [formerly e8e652e94a]] [formerly 099b7dbd10 [formerly e3f0a2436d] [formerly fc84902c7a [formerly 91ac0999e1]]] [formerly 73b34afd1f [formerly 53b5cb2b55] [formerly f823b5493f [formerly 2f2ffca3b5]] [formerly 2907ac7bb4 [formerly a515eef51e] [formerly f37002f7a9 [formerly 04a1c807da]]]] [formerly f48ab38cce [formerly c85244ae6e] [formerly 9087e84eea [formerly 9a2e6010c4]] [formerly d1b68d4326 [formerly 7ece3cffa1] [formerly fd27d58138 [formerly e5515d345b]]] [formerly 91c0de7661 [formerly 977b48b25c] [formerly 425356ba45 [formerly d82eaf9917]] [formerly 1b999fef3e [formerly 5e15fa2b17] [formerly 26b3d90ceb [formerly dca9f001ee]]]]]]
Former-commit-id: f8927bf6a1 [formerly 8a525287ce] [formerly 3be53aa5bc [formerly 6e6e9e8c22]] [formerly c87eec6caa [formerly 20490edfed] [formerly 101d1aacd4 [formerly e5c56b729c]]] [formerly 97e1248b3b [formerly d9ba8a1e71] [formerly 17e43f5284 [formerly 75be7c1a91]] [formerly 599cbd23c9 [formerly 4b709f27e2] [formerly d9b15ad851 [formerly da26d60415]]]] [formerly f44ee4fce6 [formerly 043753f079] [formerly af37ea1009 [formerly c2febea229]] [formerly 8c92ae9fc1 [formerly c4421952f6] [formerly d16cada0f0 [formerly b37c678b42]]] [formerly 0c63978b86 [formerly bf4e9680ca] [formerly d5b7c3157a [formerly c74311404a]] [formerly 38e2f391dc [formerly d88068a087] [formerly 26b3d90ceb]]]]
Former-commit-id: 87d2070c76 [formerly 662894cefe] [formerly 7f36146b9f [formerly 634e0d7de7]] [formerly 1ece75b7a2 [formerly 0b07bdc162] [formerly eaa32e82bf [formerly 99f57db7d2]]] [formerly bd04f7ddb7 [formerly 231a2046d1] [formerly f8e786941d [formerly 020a6a1726]] [formerly 2d6e8c3424 [formerly ec29d48876] [formerly aa30c4dd4c [formerly ac1006b9dd]]]]
Former-commit-id: e7eb9cbd01 [formerly f6c92c0ed4] [formerly fcadeeab80 [formerly 9b1a45d812]] [formerly 2971555319 [formerly 78c4d59730] [formerly 8942412377 [formerly eaa8682ab0]]]
Former-commit-id: 0360241df9 [formerly 51698fd464] [formerly c3c98d1be6 [formerly 58044df1d6]]
Former-commit-id: f74757ede3 [formerly f45f2bc2b8]
Former-commit-id: e2b4b6eeb8

primitive_tests/build_SubsequenceClustering_pipline.py

@@ -0,0 +1,80 @@
+from d3m import index
+from d3m.metadata.base import ArgumentType
+from d3m.metadata.pipeline import Pipeline, PrimitiveStep
+from d3m.metadata import hyperparams
+import copy
+
+# -> dataset_to_dataframe -> column_parser -> extract_columns_by_semantic_types(attributes) -> imputer -> random_forest
+#                                             extract_columns_by_semantic_types(targets)    ->            ^
+
+# Creating pipeline
+pipeline_description = Pipeline()
+pipeline_description.add_input(name='inputs')
+
+# Step 0: dataset_to_dataframe
+primitive_0 = index.get_primitive('d3m.primitives.tods.data_processing.dataset_to_dataframe')
+step_0 = PrimitiveStep(primitive=primitive_0)
+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
+primitive_1 = index.get_primitive('d3m.primitives.data_transformation.column_parser.Common')
+step_1 = PrimitiveStep(primitive=primitive_1)
+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.data_transformation.extract_columns_by_semantic_types.Common'))
+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.data_transformation.extract_columns_by_semantic_types.Common'))
+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: test primitive
+primitive_4 = index.get_primitive('d3m.primitives.tods.timeseries_processing.subsequence_clustering')
+step_4 = PrimitiveStep(primitive=primitive_4)
+
+step_4.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.2.produce')
+step_4.add_output('produce')
+pipeline_description.add_step(step_4)
+
+# Step 5: test primitive
+primitive_5 = index.get_primitive('d3m.primitives.tods.detection_algorithm.pyod_loda')
+step_5 = PrimitiveStep(primitive=primitive_5)
+step_5.add_hyperparameter(name='contamination', argument_type=ArgumentType.VALUE, data=0.1)
+step_5.add_hyperparameter(name='return_result', argument_type=ArgumentType.VALUE, data='new')
+step_5.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.4.produce')
+step_5.add_output('produce')
+pipeline_description.add_step(step_5)
+
+# Step 6: Predictions
+step_6 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.construct_predictions.Common'))
+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('example_pipeline.json', 'w') as f:
+    f.write(data)
+    print(data)
+