Commit 24d13c09 authored by Sujen's avatar Sujen

Merge branch 'pca_prim_base' into 'master'

Pca prim base

See merge request datadrivendiscovery/primitives!324
parents b714b350 e0b2e3ed
{"id": "0ab17bc0-e0c4-4b40-91ed-d313f7c96b59", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2019-06-25T15:33:50.226453Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.5.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "4b42ce1e-9b98-4a25-b68e-fad13311eb65", "version": "0.3.0", "python_path": "d3m.primitives.data_transformation.dataset_to_dataframe.Common", "name": "Extract a DataFrame from a Dataset", "digest": "4e971e251e548f1188c280c60f4e2f9a460865f21bcfd341114270bdafa4c4dc"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "04573880-d64f-4791-8932-52b7c3877639", "version": "3.0.2", "python_path": "d3m.primitives.feature_selection.pca_features.Pcafeatures", "name": "PCA Features", "digest": "57e6afa4ebf8bbea8da4d282e0f35a0d03b860e094c6bb3d4ad197dee2b3deb7"}, "arguments": {"outputs": {"type": "CONTAINER", "data": "steps.0.produce"}, "inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"threshold": {"type": "VALUE", "data": 0.0}}}, {"type": "PRIMITIVE", "primitive": {"id": "d510cb7a-1782-4f51-b44c-58f0236e47c7", "version": "0.5.0", "python_path": "d3m.primitives.data_transformation.column_parser.DataFrameCommon", "name": "Parses strings into their types", "digest": "b14b7bcd1a54ee658a7093658eb4b6c9a1b029698f981fec7ad26408a0b5cf64"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d016df89-de62-3c53-87ed-c06bb6a23cde", "version": "2019.6.7", "python_path": "d3m.primitives.data_cleaning.imputer.SKlearn", "name": "sklearn.impute.SimpleImputer", "digest": "1933705a04d8da0c4a34f4d4fc2ec4c9d826abaea53bc073b654588daaa5988d"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"return_result": {"type": "VALUE", "data": "replace"}, "use_semantic_types": {"type": "VALUE", "data": true}}}, {"type": "PRIMITIVE", "primitive": {"id": "fe0841b7-6e70-4bc3-a56c-0670a95ebc6a", "version": "0.1.0", "python_path": "d3m.primitives.classification.xgboost_gbtree.DataFrameCommon", "name": "XGBoost GBTree classifier", "digest": "a79f1fbf541dae2a6b716b1f87fc8858eb35f29eda13836daf129f3487fe6c37"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.3.produce"}, "outputs": {"type": "CONTAINER", "data": "steps.3.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"add_index_columns": {"type": "VALUE", "data": true}}}, {"type": "PRIMITIVE", "primitive": {"id": "8d38b340-f83f-4877-baaa-162f8e551736", "version": "0.3.0", "python_path": "d3m.primitives.data_transformation.construct_predictions.DataFrameCommon", "name": "Construct pipeline predictions output", "digest": "0c744dd6ea7eafb9c143f70b40452c6238bc6cab06a070d50868822f904388d3"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}, "reference": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "c9795af8fb3a99a4b27ad87649a4a57fb6c42eed6fd1121487f7ba7068a80126"}
\ No newline at end of file
{"id": "14829782-123f-4fe6-a902-4e2fd0a9fd21", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2019-05-21T19:34:28.094485Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.5.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "4b42ce1e-9b98-4a25-b68e-fad13311eb65", "version": "0.3.0", "python_path": "d3m.primitives.data_transformation.dataset_to_dataframe.Common", "name": "Extract a DataFrame from a Dataset", "digest": "ffca08229bc82d27e2d57c976783516fc6798752a37916b2b09a78eb759b6727"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "04573880-d64f-4791-8932-52b7c3877639", "version": "3.0.2", "python_path": "d3m.primitives.feature_selection.pca_features.Pcafeatures", "name": "PCA Features", "digest": "bb6d6eafb7a066bd64cf440eda072d94392e3752332b287673de2687b3b44d65"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d510cb7a-1782-4f51-b44c-58f0236e47c7", "version": "0.5.0", "python_path": "d3m.primitives.data_transformation.column_parser.DataFrameCommon", "name": "Parses strings into their types", "digest": "052d44e9ecd16349f06695a93834d149b548dd028396da6489ed515904fac840"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d016df89-de62-3c53-87ed-c06bb6a23cde", "version": "2019.4.4", "python_path": "d3m.primitives.data_cleaning.imputer.SKlearn", "name": "sklearn.impute.SimpleImputer", "digest": "8c36c71cc0018d0566008dd256748672a4d686bf00174f2c17ae063238be7b29"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"return_result": {"type": "VALUE", "data": "replace"}, "use_semantic_types": {"type": "VALUE", "data": true}}}, {"type": "PRIMITIVE", "primitive": {"id": "1dd82833-5692-39cb-84fb-2455683075f3", "version": "2019.4.4", "python_path": "d3m.primitives.classification.random_forest.SKlearn", "name": "sklearn.ensemble.forest.RandomForestClassifier", "digest": "b1c373d38eeffe7ca7e2fe12b7cae22b2518b9bef3cbf4c7b9167af3a972bee3"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.3.produce"}, "outputs": {"type": "CONTAINER", "data": "steps.3.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"add_index_columns": {"type": "VALUE", "data": true}, "use_semantic_types": {"type": "VALUE", "data": true}}}, {"type": "PRIMITIVE", "primitive": {"id": "8d38b340-f83f-4877-baaa-162f8e551736", "version": "0.3.0", "python_path": "d3m.primitives.data_transformation.construct_predictions.DataFrameCommon", "name": "Construct pipeline predictions output", "digest": "d8bac1a445d0108629b175c2d9386092251c562525785de182b49e5511a4b09a"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}, "reference": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "68c6be0db1b0200986efba56fbac20d8153412bebce01e0c10a6c6117b058388"}
\ No newline at end of file
{
"problem": "185_baseball_problem",
"full_inputs": [
"185_baseball_dataset"
],
"train_inputs": [
"185_baseball_dataset_TRAIN"
],
"test_inputs": [
"185_baseball_dataset_TEST"
],
"score_inputs": [
"185_baseball_dataset_SCORE"
]
}
{"id": "4a02e033-4a9b-41b7-b64a-70d9da00a414", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2019-06-25T15:33:31.003030Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.5.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "4b42ce1e-9b98-4a25-b68e-fad13311eb65", "version": "0.3.0", "python_path": "d3m.primitives.data_transformation.dataset_to_dataframe.Common", "name": "Extract a DataFrame from a Dataset", "digest": "4e971e251e548f1188c280c60f4e2f9a460865f21bcfd341114270bdafa4c4dc"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "04573880-d64f-4791-8932-52b7c3877639", "version": "3.0.2", "python_path": "d3m.primitives.feature_selection.pca_features.Pcafeatures", "name": "PCA Features", "digest": "57e6afa4ebf8bbea8da4d282e0f35a0d03b860e094c6bb3d4ad197dee2b3deb7"}, "arguments": {"outputs": {"type": "CONTAINER", "data": "steps.0.produce"}, "inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"threshold": {"type": "VALUE", "data": 0.0}}}, {"type": "PRIMITIVE", "primitive": {"id": "d510cb7a-1782-4f51-b44c-58f0236e47c7", "version": "0.5.0", "python_path": "d3m.primitives.data_transformation.column_parser.DataFrameCommon", "name": "Parses strings into their types", "digest": "b14b7bcd1a54ee658a7093658eb4b6c9a1b029698f981fec7ad26408a0b5cf64"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d016df89-de62-3c53-87ed-c06bb6a23cde", "version": "2019.6.7", "python_path": "d3m.primitives.data_cleaning.imputer.SKlearn", "name": "sklearn.impute.SimpleImputer", "digest": "1933705a04d8da0c4a34f4d4fc2ec4c9d826abaea53bc073b654588daaa5988d"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"return_result": {"type": "VALUE", "data": "replace"}, "use_semantic_types": {"type": "VALUE", "data": true}}}, {"type": "PRIMITIVE", "primitive": {"id": "fe0841b7-6e70-4bc3-a56c-0670a95ebc6a", "version": "0.1.0", "python_path": "d3m.primitives.classification.xgboost_gbtree.DataFrameCommon", "name": "XGBoost GBTree classifier", "digest": "a79f1fbf541dae2a6b716b1f87fc8858eb35f29eda13836daf129f3487fe6c37"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.3.produce"}, "outputs": {"type": "CONTAINER", "data": "steps.3.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"add_index_columns": {"type": "VALUE", "data": true}}}, {"type": "PRIMITIVE", "primitive": {"id": "8d38b340-f83f-4877-baaa-162f8e551736", "version": "0.3.0", "python_path": "d3m.primitives.data_transformation.construct_predictions.DataFrameCommon", "name": "Construct pipeline predictions output", "digest": "0c744dd6ea7eafb9c143f70b40452c6238bc6cab06a070d50868822f904388d3"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}, "reference": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "d4a1276b91204d707a6607fa6cc5d97bc439554fa08a0535f3fcef526b538dd0"}
\ No newline at end of file
{"id": "4b0395de-9cc3-4c64-b5d1-78dc2bac904a", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2019-06-14T19:40:08.695855Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.5.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "4b42ce1e-9b98-4a25-b68e-fad13311eb65", "version": "0.3.0", "python_path": "d3m.primitives.data_transformation.dataset_to_dataframe.Common", "name": "Extract a DataFrame from a Dataset", "digest": "0d46a2c5bc374e305682dc4f1c322518c07638153a8365034a513ea46960802b"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "04573880-d64f-4791-8932-52b7c3877639", "version": "3.0.2", "python_path": "d3m.primitives.feature_selection.pca_features.Pcafeatures", "name": "PCA Features", "digest": "803f20bea77432bc0b3c2a65788ff58865252104bb6883bd2e6447c9806958c2"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d510cb7a-1782-4f51-b44c-58f0236e47c7", "version": "0.5.0", "python_path": "d3m.primitives.data_transformation.column_parser.DataFrameCommon", "name": "Parses strings into their types", "digest": "312cacc014497dd674e34765f6eb54430e594c591e760da0383c87844753d2ce"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d016df89-de62-3c53-87ed-c06bb6a23cde", "version": "2019.4.4", "python_path": "d3m.primitives.data_cleaning.imputer.SKlearn", "name": "sklearn.impute.SimpleImputer", "digest": "9878fdeb255c5b4fb2beaf053e68b2913e3d7b1c26e40c530c1cb4fe562fde26"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"return_result": {"type": "VALUE", "data": "replace"}, "use_semantic_types": {"type": "VALUE", "data": true}}}, {"type": "PRIMITIVE", "primitive": {"id": "1dd82833-5692-39cb-84fb-2455683075f3", "version": "2019.4.4", "python_path": "d3m.primitives.classification.random_forest.SKlearn", "name": "sklearn.ensemble.forest.RandomForestClassifier", "digest": "1e95597335ea675f941f08c916e586a414c0405a2ea0e3da0a0e3b1ee47ba761"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.3.produce"}, "outputs": {"type": "CONTAINER", "data": "steps.3.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"add_index_columns": {"type": "VALUE", "data": true}, "use_semantic_types": {"type": "VALUE", "data": true}}}, {"type": "PRIMITIVE", "primitive": {"id": "8d38b340-f83f-4877-baaa-162f8e551736", "version": "0.3.0", "python_path": "d3m.primitives.data_transformation.construct_predictions.DataFrameCommon", "name": "Construct pipeline predictions output", "digest": "cfb2d595652c4ae0d24e67d4cb8e4916c9f3c2753eaccc2935263d054b3682fa"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}, "reference": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "02807fea853282db9b6f8c91f7806e3c16ae094c39b6a35a6a241c35a71c88ff"}
\ No newline at end of file
{"id": "5115ea5e-40d6-4b14-879d-9e1c4ea507e8", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2019-06-25T16:27:45.596364Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.5.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "4b42ce1e-9b98-4a25-b68e-fad13311eb65", "version": "0.3.0", "python_path": "d3m.primitives.data_transformation.dataset_to_dataframe.Common", "name": "Extract a DataFrame from a Dataset", "digest": "4e971e251e548f1188c280c60f4e2f9a460865f21bcfd341114270bdafa4c4dc"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "04573880-d64f-4791-8932-52b7c3877639", "version": "3.0.2", "python_path": "d3m.primitives.feature_selection.pca_features.Pcafeatures", "name": "PCA Features", "digest": "57e6afa4ebf8bbea8da4d282e0f35a0d03b860e094c6bb3d4ad197dee2b3deb7"}, "arguments": {"outputs": {"type": "CONTAINER", "data": "steps.0.produce"}, "inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"threshold": {"type": "VALUE", "data": 0.0}}}, {"type": "PRIMITIVE", "primitive": {"id": "d510cb7a-1782-4f51-b44c-58f0236e47c7", "version": "0.5.0", "python_path": "d3m.primitives.data_transformation.column_parser.DataFrameCommon", "name": "Parses strings into their types", "digest": "b14b7bcd1a54ee658a7093658eb4b6c9a1b029698f981fec7ad26408a0b5cf64"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d016df89-de62-3c53-87ed-c06bb6a23cde", "version": "2019.6.7", "python_path": "d3m.primitives.data_cleaning.imputer.SKlearn", "name": "sklearn.impute.SimpleImputer", "digest": "1933705a04d8da0c4a34f4d4fc2ec4c9d826abaea53bc073b654588daaa5988d"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"return_result": {"type": "VALUE", "data": "replace"}, "use_semantic_types": {"type": "VALUE", "data": true}}}, {"type": "PRIMITIVE", "primitive": {"id": "fe0841b7-6e70-4bc3-a56c-0670a95ebc6a", "version": "0.1.0", "python_path": "d3m.primitives.classification.xgboost_gbtree.DataFrameCommon", "name": "XGBoost GBTree classifier", "digest": "a79f1fbf541dae2a6b716b1f87fc8858eb35f29eda13836daf129f3487fe6c37"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.3.produce"}, "outputs": {"type": "CONTAINER", "data": "steps.3.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"add_index_columns": {"type": "VALUE", "data": true}}}, {"type": "PRIMITIVE", "primitive": {"id": "8d38b340-f83f-4877-baaa-162f8e551736", "version": "0.3.0", "python_path": "d3m.primitives.data_transformation.construct_predictions.DataFrameCommon", "name": "Construct pipeline predictions output", "digest": "0c744dd6ea7eafb9c143f70b40452c6238bc6cab06a070d50868822f904388d3"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}, "reference": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "f07a9c9e8cb2f07a722f3a5e85ba50fa4f9ccabbabe2884c0e7a951f14cb1a1c"}
\ No newline at end of file
{"problem": "185_baseball_problem","full_inputs": ["185_baseball_dataset"],"train_inputs": ["185_baseball_dataset_TRAIN"],"test_inputs": ["185_baseball_dataset_TEST"],"score_inputs": ["185_baseball_dataset_SCORE"]}
\ No newline at end of file
{"id": "6b368880-850d-4db9-b6d0-a582de99f2b8", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2019-06-14T19:39:44.087747Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.5.produce", "name": "output predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "4b42ce1e-9b98-4a25-b68e-fad13311eb65", "version": "0.3.0", "python_path": "d3m.primitives.data_transformation.dataset_to_dataframe.Common", "name": "Extract a DataFrame from a Dataset", "digest": "0d46a2c5bc374e305682dc4f1c322518c07638153a8365034a513ea46960802b"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "04573880-d64f-4791-8932-52b7c3877639", "version": "3.0.2", "python_path": "d3m.primitives.feature_selection.pca_features.Pcafeatures", "name": "PCA Features", "digest": "803f20bea77432bc0b3c2a65788ff58865252104bb6883bd2e6447c9806958c2"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d510cb7a-1782-4f51-b44c-58f0236e47c7", "version": "0.5.0", "python_path": "d3m.primitives.data_transformation.column_parser.DataFrameCommon", "name": "Parses strings into their types", "digest": "312cacc014497dd674e34765f6eb54430e594c591e760da0383c87844753d2ce"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d016df89-de62-3c53-87ed-c06bb6a23cde", "version": "2019.4.4", "python_path": "d3m.primitives.data_cleaning.imputer.SKlearn", "name": "sklearn.impute.SimpleImputer", "digest": "9878fdeb255c5b4fb2beaf053e68b2913e3d7b1c26e40c530c1cb4fe562fde26"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"return_result": {"type": "VALUE", "data": "replace"}, "use_semantic_types": {"type": "VALUE", "data": true}}}, {"type": "PRIMITIVE", "primitive": {"id": "1dd82833-5692-39cb-84fb-2455683075f3", "version": "2019.4.4", "python_path": "d3m.primitives.classification.random_forest.SKlearn", "name": "sklearn.ensemble.forest.RandomForestClassifier", "digest": "1e95597335ea675f941f08c916e586a414c0405a2ea0e3da0a0e3b1ee47ba761"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.3.produce"}, "outputs": {"type": "CONTAINER", "data": "steps.3.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"add_index_columns": {"type": "VALUE", "data": true}, "use_semantic_types": {"type": "VALUE", "data": true}}}, {"type": "PRIMITIVE", "primitive": {"id": "8d38b340-f83f-4877-baaa-162f8e551736", "version": "0.3.0", "python_path": "d3m.primitives.data_transformation.construct_predictions.DataFrameCommon", "name": "Construct pipeline predictions output", "digest": "cfb2d595652c4ae0d24e67d4cb8e4916c9f3c2753eaccc2935263d054b3682fa"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}, "reference": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "012c7bfa586d27ef7b3a457970101ad1cf08746436487c2d2fa597aed90e6d43"}
\ No newline at end of file
......@@ -15,7 +15,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/NewKnowledge/[email protected]4b31ed6098236ef7392768c45e4fa2f238124d3c#egg=PcafeaturesD3MWrapper"
"package_uri": "git+https://github.com/NewKnowledge/[email protected]ff15ca192c5386e2a003cca59f440df285b02f73#egg=PcafeaturesD3MWrapper"
}
],
"python_path": "d3m.primitives.feature_selection.pca_features.Pcafeatures",
......@@ -29,12 +29,11 @@
"class_type_arguments": {
"Inputs": "d3m.container.pandas.DataFrame",
"Outputs": "d3m.container.pandas.DataFrame",
"Hyperparams": "PcafeaturesD3MWrapper.wrapper.Hyperparams",
"Params": "NoneType"
"Params": "PcafeaturesD3MWrapper.wrapper.Params",
"Hyperparams": "PcafeaturesD3MWrapper.wrapper.Hyperparams"
},
"interfaces_version": "2019.6.7",
"interfaces": [
"transformer.TransformerPrimitiveBase",
"base.PrimitiveBase"
],
"hyperparams": {
......@@ -89,8 +88,12 @@
"type": "d3m.container.pandas.DataFrame",
"kind": "PIPELINE"
},
"outputs": {
"type": "d3m.container.pandas.DataFrame",
"kind": "PIPELINE"
},
"params": {
"type": "NoneType",
"type": "PcafeaturesD3MWrapper.wrapper.Params",
"kind": "RUNTIME"
}
},
......@@ -127,24 +130,25 @@
"iterations"
],
"returns": "d3m.primitive_interfaces.base.CallResult[NoneType]",
"description": "A noop.\n\nParameters\n----------\ntimeout : float\n A maximum time this primitive should be fitting during this method call, in seconds.\niterations : int\n How many of internal iterations should the primitive do.\n\nReturns\n-------\nCallResult[None]\n A ``CallResult`` with ``None`` value."
"description": "fits pcafeatures feature selection algorithm on the training set. applies same feature selection to test set\nfor consistency with downstream classifiers\n\nParameters\n----------\ntimeout : float\n A maximum time this primitive should be fitting during this method call, in seconds.\niterations : int\n How many of internal iterations should the primitive do.\n\nReturns\n-------\nCallResult[None]\n A ``CallResult`` with ``None`` value."
},
"fit_multi_produce": {
"kind": "OTHER",
"arguments": [
"produce_methods",
"inputs",
"outputs",
"timeout",
"iterations"
],
"returns": "d3m.primitive_interfaces.base.MultiCallResult",
"description": "A method calling ``fit`` and after that multiple produce methods at once.\n\nParameters\n----------\nproduce_methods : Sequence[str]\n A list of names of produce methods to call.\ninputs : Inputs\n The inputs given to all produce methods.\ntimeout : float\n A maximum time this primitive should take to both fit the primitive and produce outputs\n for all produce methods listed in ``produce_methods`` argument, in seconds.\niterations : int\n How many of internal iterations should the primitive do for both fitting and producing\n outputs of all produce methods.\n\nReturns\n-------\nMultiCallResult\n A dict of values for each produce method wrapped inside ``MultiCallResult``."
"description": "A method calling ``fit`` and after that multiple produce methods at once.\n\nThis method allows primitive author to implement an optimized version of both fitting\nand producing a primitive on same data.\n\nIf any additional method arguments are added to primitive's ``set_training_data`` method\nor produce method(s), or removed from them, they have to be added to or removed from this\nmethod as well. This method should accept an union of all arguments accepted by primitive's\n``set_training_data`` method and produce method(s) and then use them accordingly when\ncomputing results.\n\nThe default implementation of this method just calls first ``set_training_data`` method,\n``fit`` method, and all produce methods listed in ``produce_methods`` in order and is\npotentially inefficient.\n\nParameters\n----------\nproduce_methods : Sequence[str]\n A list of names of produce methods to call.\ninputs : Inputs\n The inputs given to ``set_training_data`` and all produce methods.\noutputs : Outputs\n The outputs given to ``set_training_data``.\ntimeout : float\n A maximum time this primitive should take to both fit the primitive and produce outputs\n for all produce methods listed in ``produce_methods`` argument, in seconds.\niterations : int\n How many of internal iterations should the primitive do for both fitting and producing\n outputs of all produce methods.\n\nReturns\n-------\nMultiCallResult\n A dict of values for each produce method wrapped inside ``MultiCallResult``."
},
"get_params": {
"kind": "OTHER",
"arguments": [],
"returns": "NoneType",
"description": "A noop.\n\nReturns\n-------\nParams\n An instance of parameters."
"returns": "PcafeaturesD3MWrapper.wrapper.Params",
"description": "Returns parameters of this primitive.\n\nParameters are all parameters of the primitive which can potentially change during a life-time of\na primitive. Parameters which cannot are passed through constructor.\n\nParameters should include all data which is necessary to create a new instance of this primitive\nbehaving exactly the same as this instance, when the new instance is created by passing the same\nparameters to the class constructor and calling ``set_params``.\n\nNo other arguments to the method are allowed (except for private arguments).\n\nReturns\n-------\nParams\n An instance of parameters."
},
"multi_produce": {
"kind": "OTHER",
......@@ -187,13 +191,16 @@
"params"
],
"returns": "NoneType",
"description": "A noop.\n\nParameters\n----------\nparams : Params\n An instance of parameters."
"description": "Sets parameters of this primitive.\n\nParameters are all parameters of the primitive which can potentially change during a life-time of\na primitive. Parameters which cannot are passed through constructor.\n\nNo other arguments to the method are allowed (except for private arguments).\n\nParameters\n----------\nparams : Params\n An instance of parameters."
},
"set_training_data": {
"kind": "OTHER",
"arguments": [],
"arguments": [
"inputs",
"outputs"
],
"returns": "NoneType",
"description": "A noop.\n\nParameters\n----------"
"description": "Sets primitive's training data\n\nParameters\n----------\ninputs = D3M dataframe"
}
},
"class_attributes": {
......@@ -206,9 +213,10 @@
"docker_containers": "typing.Dict[str, d3m.primitive_interfaces.base.DockerContainer]",
"volumes": "typing.Dict[str, str]",
"temporary_directory": "typing.Union[NoneType, str]"
}
},
"params": {}
},
"structural_type": "PcafeaturesD3MWrapper.wrapper.pcafeatures",
"description": "Perform principal component analysis on all numeric data in the dataset\nand then use each original features contribution to the first principal\ncomponent as a proxy for the 'score' of that feature. Returns a dataframe\ncontaining an ordered list of all original features as well as their\ncontribution to the first principal component.\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "0922d56aa3b37da0fe5b5e1b4db57e2f2e205d87710479f5236d982a8530ba7b"
"description": "Perform principal component analysis on all numeric data in the dataset\nand then use each original features contribution to the first principal\ncomponent as a proxy for the 'score' of that feature. Returns a dataframe\nthat only contains features whose score is above a threshold (HP)\n\nAttributes\n----------\nmetadata : PrimitiveMetadata\n Primitive's metadata. Available as a class attribute.\nlogger : Logger\n Primitive's logger. Available as a class attribute.\nhyperparams : Hyperparams\n Hyperparams passed to the constructor.\nrandom_seed : int\n Random seed passed to the constructor.\ndocker_containers : Dict[str, DockerContainer]\n A dict mapping Docker image keys from primitive's metadata to (named) tuples containing\n container's address under which the container is accessible by the primitive, and a\n dict mapping exposed ports to ports on that address.\nvolumes : Dict[str, str]\n A dict mapping volume keys from primitive's metadata to file and directory paths\n where downloaded and extracted files are available to the primitive.\ntemporary_directory : str\n An absolute path to a temporary directory a primitive can use to store any files\n for the duration of the current pipeline run phase. Directory is automatically\n cleaned up after the current pipeline run phase finishes.",
"digest": "30be9386ba49ccedd630e83fdbeed2fb22261b225b6e54abfd7ded434ed67d3f"
}
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment