Commit 45b69681 authored by Sujen's avatar Sujen

Merge branch 'master' into 'master'

add pipelines

See merge request !172
parents 3833d0d2 784569da
{
"created": "2019-06-05T19:40:54.744072Z",
"digest": "99b87aa6dda2615a5a95759852760734d32fc776a6607aa26460a7b7d669c0ca",
"id": "7eab6c73-9011-4369-8fca-587e5fbae537",
"inputs": [
{
"name": "inputs"
}
],
"outputs": [
{
"data": "steps.9.produce",
"name": "output"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"steps": [
{
"arguments": {
"inputs": {
"data": "inputs.0",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "748b3f6c9d26a4323a34a6da464c5de3dcab0d784a127819106acef1466e9550",
"id": "4b42ce1e-9b98-4a25-b68e-fad13311eb65",
"name": "Extract a DataFrame from a Dataset",
"python_path": "d3m.primitives.data_transformation.dataset_to_dataframe.Common",
"version": "0.3.0"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.0.produce",
"type": "CONTAINER"
}
},
"hyperparams": {
"semantic_types": {
"data": [
"https://metadata.datadrivendiscovery.org/types/Attribute"
],
"type": "VALUE"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "e1ef694b5642f037531be4f9a9c29aef62466b8e61dd8e174ccd673977761abb",
"id": "4503a4c6-42f7-45a1-a1d4-ed69699cf5e1",
"name": "Extracts columns by semantic type",
"python_path": "d3m.primitives.data_transformation.extract_columns_by_semantic_types.DataFrameCommon",
"version": "0.2.0"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.0.produce",
"type": "CONTAINER"
}
},
"hyperparams": {
"semantic_types": {
"data": [
"https://metadata.datadrivendiscovery.org/types/SuggestedTarget"
],
"type": "VALUE"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "e1ef694b5642f037531be4f9a9c29aef62466b8e61dd8e174ccd673977761abb",
"id": "4503a4c6-42f7-45a1-a1d4-ed69699cf5e1",
"name": "Extracts columns by semantic type",
"python_path": "d3m.primitives.data_transformation.extract_columns_by_semantic_types.DataFrameCommon",
"version": "0.2.0"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.2.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "943071cbebe517da54fcdf98edfc0464f2534c57de34cb40b1d3c0eb95faf268",
"id": "26fc8fd3-f6b2-4c65-8afb-edb54ed2a3e4",
"name": "Label encoder with an unseen category",
"python_path": "d3m.primitives.data_preprocessing.label_encoder.DataFrameCommon",
"version": "0.2.0"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.1.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "6deed8e4798fd219f4745c4459ba67036ed25dbb1d3a2459b24416cd4460951e",
"id": "d510cb7a-1782-4f51-b44c-58f0236e47c7",
"name": "Parses strings into their types",
"python_path": "d3m.primitives.data_transformation.column_parser.DataFrameCommon",
"version": "0.5.0"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.4.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "68d62990d02c086c91690a4d59517c471330ab772c808302eee91ce8d6646a3e",
"id": "e6ee30fa-af68-4bfe-9234-5ca7e7ac8e93",
"name": "Matrix Completion via Sparse Factorization",
"python_path": "d3m.primitives.cornell.high_rank_imputer",
"version": "v0.1.1"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.5.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "53890564fea5360b0ee8170af04a5590e293b640909838cae5d9e3416c1b31ec",
"id": "d639947e-ece0-3a39-a666-e974acf4521d",
"name": "sklearn.preprocessing.data.StandardScaler",
"python_path": "d3m.primitives.data_preprocessing.standard_scaler.SKlearn",
"version": "2019.4.4"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.6.produce",
"type": "CONTAINER"
},
"outputs": {
"data": "steps.3.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "ac92df6bc8251c73a600f664e21cb151fdf94a2b3016a14a937562ba897c839c",
"id": "0ae7d42d-f765-3348-a28c-57d94880aa6a",
"name": "sklearn.svm.classes.SVC",
"python_path": "d3m.primitives.classification.svc.SKlearn",
"version": "2019.4.4"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.7.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "a8aea6867f6a569a3cbadcf27a0fe86cee519a8bd60e39625786ddc606d0a1e2",
"id": "39ae30f7-39ed-40af-8679-5cf108499605",
"name": "Label decoder for UnseenLabelEncoderPrimitive",
"python_path": "d3m.primitives.data_preprocessing.label_decoder.DataFrameCommon",
"version": "0.1.0"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.8.produce",
"type": "CONTAINER"
},
"reference": {
"data": "steps.0.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "bc09b1d3e656bbf5ed10a6b13382e8a52ffd18552f5803f28b25b79fbf25ca52",
"id": "8d38b340-f83f-4877-baaa-162f8e551736",
"name": "Construct pipeline predictions output",
"python_path": "d3m.primitives.data_transformation.construct_predictions.DataFrameCommon",
"version": "0.3.0"
},
"type": "PRIMITIVE"
}
]
}
\ No newline at end of file
{
"problem": "38_sick_problem",
"full_inputs": [
"38_sick_dataset"
],
"train_inputs": [
"38_sick_dataset_TRAIN"
],
"test_inputs": [
"38_sick_dataset_TEST"
],
"score_inputs": [
"38_sick_dataset_SCORE"
]
}
......@@ -18,7 +18,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/cyangcornell/d3m-primitives.git@24cc94f6dc9f02bf00e40278dfc382647bd6ea37#egg=pyglrm-d3m"
"package_uri": "git+https://github.com/cyangcornell/d3m-primitives.git@f9e90b2b83bfea08b47d298223e9bbef7884312a#egg=pyglrm-d3m"
}
],
"python_path": "d3m.primitives.cornell.high_rank_imputer",
......@@ -224,5 +224,5 @@
},
"structural_type": "high_rank_imputer.HighRankImputer",
"description": "This primitive imputes a dataset in which data points are drawn from multiple subspaces, which in pratice means the data have mutiple groups/classes. In such cases, the data matrices are often of high-rank. In such cases, Sparse Factorization based Matrix Completion (SFMC) can outperform classical low-rank matrix completion methods.\nThe optimization is solved via accelerated proximal alternating minimization (APALM).The NaNs in the input matrix will be regarded as missing entries. The algorithm will recover the missing entries and return the recovered matrix as output.\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": "92118f4fdb23b25c635e3b6170322c75b0d0e776e306a5a5dcb742e41385ee26"
"digest": "68d62990d02c086c91690a4d59517c471330ab772c808302eee91ce8d6646a3e"
}
{
"created": "2019-06-05T05:47:07.014522Z",
"digest": "550a79ef0c40de4675427a379fe6e6fd8dd694241b7207cb022e458ec0844921",
"id": "22fb45eb-47c8-458d-8894-ad1c33c2a201",
"inputs": [
{
"name": "inputs"
}
],
"outputs": [
{
"data": "steps.10.produce",
"name": "output"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"steps": [
{
"arguments": {
"inputs": {
"data": "inputs.0",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "748b3f6c9d26a4323a34a6da464c5de3dcab0d784a127819106acef1466e9550",
"id": "4b42ce1e-9b98-4a25-b68e-fad13311eb65",
"name": "Extract a DataFrame from a Dataset",
"python_path": "d3m.primitives.data_transformation.dataset_to_dataframe.Common",
"version": "0.3.0"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.0.produce",
"type": "CONTAINER"
}
},
"hyperparams": {
"semantic_types": {
"data": [
"https://metadata.datadrivendiscovery.org/types/Attribute"
],
"type": "VALUE"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "e1ef694b5642f037531be4f9a9c29aef62466b8e61dd8e174ccd673977761abb",
"id": "4503a4c6-42f7-45a1-a1d4-ed69699cf5e1",
"name": "Extracts columns by semantic type",
"python_path": "d3m.primitives.data_transformation.extract_columns_by_semantic_types.DataFrameCommon",
"version": "0.2.0"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.0.produce",
"type": "CONTAINER"
}
},
"hyperparams": {
"semantic_types": {
"data": [
"https://metadata.datadrivendiscovery.org/types/SuggestedTarget"
],
"type": "VALUE"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "e1ef694b5642f037531be4f9a9c29aef62466b8e61dd8e174ccd673977761abb",
"id": "4503a4c6-42f7-45a1-a1d4-ed69699cf5e1",
"name": "Extracts columns by semantic type",
"python_path": "d3m.primitives.data_transformation.extract_columns_by_semantic_types.DataFrameCommon",
"version": "0.2.0"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.2.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "943071cbebe517da54fcdf98edfc0464f2534c57de34cb40b1d3c0eb95faf268",
"id": "26fc8fd3-f6b2-4c65-8afb-edb54ed2a3e4",
"name": "Label encoder with an unseen category",
"python_path": "d3m.primitives.data_preprocessing.label_encoder.DataFrameCommon",
"version": "0.2.0"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.1.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "6deed8e4798fd219f4745c4459ba67036ed25dbb1d3a2459b24416cd4460951e",
"id": "d510cb7a-1782-4f51-b44c-58f0236e47c7",
"name": "Parses strings into their types",
"python_path": "d3m.primitives.data_transformation.column_parser.DataFrameCommon",
"version": "0.5.0"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.4.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "8c36c71cc0018d0566008dd256748672a4d686bf00174f2c17ae063238be7b29",
"id": "d016df89-de62-3c53-87ed-c06bb6a23cde",
"name": "sklearn.impute.SimpleImputer",
"python_path": "d3m.primitives.data_cleaning.imputer.SKlearn",
"version": "2019.4.4"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.5.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "53890564fea5360b0ee8170af04a5590e293b640909838cae5d9e3416c1b31ec",
"id": "d639947e-ece0-3a39-a666-e974acf4521d",
"name": "sklearn.preprocessing.data.StandardScaler",
"python_path": "d3m.primitives.data_preprocessing.standard_scaler.SKlearn",
"version": "2019.4.4"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.6.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "94bf88bdf39ffd3e4d564d5dbc73b0c77b9fe4b408e88efb818127015e817d03",
"id": "7c357e6e-7124-4f2a-8371-8021c8c95cc9",
"name": "Huber PCA",
"python_path": "d3m.primitives.cornell.pyglrm_d3m.huber_pca",
"version": "v0.1.1"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.7.produce",
"type": "CONTAINER"
},
"outputs": {
"data": "steps.3.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "ac92df6bc8251c73a600f664e21cb151fdf94a2b3016a14a937562ba897c839c",
"id": "0ae7d42d-f765-3348-a28c-57d94880aa6a",
"name": "sklearn.svm.classes.SVC",
"python_path": "d3m.primitives.classification.svc.SKlearn",
"version": "2019.4.4"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.8.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "a8aea6867f6a569a3cbadcf27a0fe86cee519a8bd60e39625786ddc606d0a1e2",
"id": "39ae30f7-39ed-40af-8679-5cf108499605",
"name": "Label decoder for UnseenLabelEncoderPrimitive",
"python_path": "d3m.primitives.data_preprocessing.label_decoder.DataFrameCommon",
"version": "0.1.0"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.9.produce",
"type": "CONTAINER"
},
"reference": {
"data": "steps.0.produce",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "bc09b1d3e656bbf5ed10a6b13382e8a52ffd18552f5803f28b25b79fbf25ca52",
"id": "8d38b340-f83f-4877-baaa-162f8e551736",
"name": "Construct pipeline predictions output",
"python_path": "d3m.primitives.data_transformation.construct_predictions.DataFrameCommon",
"version": "0.3.0"
},
"type": "PRIMITIVE"
}
]
}
\ No newline at end of file
{
"problem": "38_sick_problem",
"full_inputs": [
"38_sick_dataset"
],
"train_inputs": [
"38_sick_dataset_TRAIN"
],
"test_inputs": [
"38_sick_dataset_TEST"
],
"score_inputs": [
"38_sick_dataset_SCORE"
]
}
{
"created": "2019-06-05T05:44:52.362809Z",
"digest": "331159512fa6f6dd11972531e21b0832f21665c56af980fbac0c7890a33aece7",
"id": "5140dbd1-c23c-41fa-b8fb-9544a1e0fe9e",
"inputs": [
{
"name": "inputs"
}
],
"outputs": [
{
"data": "steps.9.produce",
"name": "output"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"steps": [
{
"arguments": {
"inputs": {
"data": "inputs.0",
"type": "CONTAINER"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "748b3f6c9d26a4323a34a6da464c5de3dcab0d784a127819106acef1466e9550",
"id": "4b42ce1e-9b98-4a25-b68e-fad13311eb65",
"name": "Extract a DataFrame from a Dataset",
"python_path": "d3m.primitives.data_transformation.dataset_to_dataframe.Common",
"version": "0.3.0"
},
"type": "PRIMITIVE"
},
{
"arguments": {
"inputs": {
"data": "steps.0.produce",
"type": "CONTAINER"
}
},
"hyperparams": {
"semantic_types": {
"data": [
"https://metadata.datadrivendiscovery.org/types/Attribute"
],
"type": "VALUE"
}
},
"outputs": [
{
"id": "produce"
}
],
"primitive": {
"digest": "e1ef694b5642f037531be4f9a9c29aef62466b8e61dd8e174ccd673977761abb",
"id": "4503a4c6-42f7-45a1-a1d4-ed69699cf5e1",
"name": "Extracts columns by semantic type",