Commit b7b788bc authored by Chris Bethune's avatar Chris Bethune

updates audio classification pipeline

parent be910f85
{
"id": "aca60fa2-f27e-4c12-9b7c-bfcab2653480",
"id": "6e15da3c-c2ba-4e1f-b432-2f29adef9fc9",
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"created": "2019-06-18T02:10:41.150940Z",
"created": "2019-06-17T20:58:25.419769Z",
"inputs": [
{
"name": "inputs"
......@@ -21,7 +21,7 @@
"version": "0.2.0",
"python_path": "d3m.primitives.data_transformation.denormalize.Common",
"name": "Denormalize datasets",
"digest": "45df3c6aeff29448c28a010465a94f69ad027087944fe820585533523b58af00"
"digest": "afca078f05899b9f329e1b8cc0973848e39e83a7521d2cade81c1fbad5cf8139"
},
"arguments": {
"inputs": {
......@@ -42,7 +42,7 @@
"version": "0.3.0",
"python_path": "d3m.primitives.data_transformation.dataset_to_dataframe.Common",
"name": "Extract a DataFrame from a Dataset",
"digest": "43e118209c48c0d132134dde9115ede5678f348348520eafeefe28e81177b4ed"
"digest": "e557fc176af67913ed241dbe793cf986439157cfe9c4a12f1aafcba3c07b8b6f"
},
"arguments": {
"inputs": {
......@@ -63,7 +63,7 @@
"version": "0.5.0",
"python_path": "d3m.primitives.data_transformation.column_parser.DataFrameCommon",
"name": "Parses strings into their types",
"digest": "3feb9bcf7350e1975b9709d1565a27859d2cf354b095b29f174b158462224f24"
"digest": "7e16e2b1e559690e221de471826d7d1cd36698bc5140dc00f3c7a6c6b711c3b2"
},
"arguments": {
"inputs": {
......@@ -92,10 +92,10 @@
"type": "PRIMITIVE",
"primitive": {
"id": "4503a4c6-42f7-45a1-a1d4-ed69699cf5e1",
"version": "0.3.0",
"version": "0.2.0",
"python_path": "d3m.primitives.data_transformation.extract_columns_by_semantic_types.DataFrameCommon",
"name": "Extracts columns by semantic type",
"digest": "8c9de5cd06f74ea3f80fa9f1e1f775a1d3eddff1621512e6ab72aaab8724b88d"
"digest": "d4fa27a3e215b89d2231d344ec0202e1b8e41ad322deb79c68fd6ca673eae3f7"
},
"arguments": {
"inputs": {
......@@ -121,10 +121,10 @@
"type": "PRIMITIVE",
"primitive": {
"id": "4503a4c6-42f7-45a1-a1d4-ed69699cf5e1",
"version": "0.3.0",
"version": "0.2.0",
"python_path": "d3m.primitives.data_transformation.extract_columns_by_semantic_types.DataFrameCommon",
"name": "Extracts columns by semantic type",
"digest": "8c9de5cd06f74ea3f80fa9f1e1f775a1d3eddff1621512e6ab72aaab8724b88d"
"digest": "d4fa27a3e215b89d2231d344ec0202e1b8e41ad322deb79c68fd6ca673eae3f7"
},
"arguments": {
"inputs": {
......@@ -154,7 +154,7 @@
"version": "0.1.0",
"python_path": "d3m.primitives.classification.bert_classifier.DistilBertPairClassification",
"name": "BERT pair classification",
"digest": "46b736b1ec12dd4c187b9fe9675bc1bb3cf93cccd65a62f474d03646d404f016"
"digest": "a6ba6fa9c70e1741aeeb97c111c19a7ddd5a4fba286c6d45301f236cae741296"
},
"arguments": {
"inputs": {
......@@ -175,14 +175,6 @@
"metric": {
"type": "VALUE",
"data": "f1"
},
"doc_col_0": {
"type": "VALUE",
"data": 1
},
"doc_col_1": {
"type": "VALUE",
"data": 3
}
}
},
......@@ -193,7 +185,7 @@
"version": "0.3.0",
"python_path": "d3m.primitives.data_transformation.construct_predictions.DataFrameCommon",
"name": "Construct pipeline predictions output",
"digest": "dfbf9e3112dd7ab851fc85588741b66900ac25bd03f2e602327046f676036e28"
"digest": "077921b0d6cee9bbda9494bc60c8b48f8287db8d0bff674056a7c9e5cc92ebb9"
},
"arguments": {
"inputs": {
......@@ -212,5 +204,5 @@
]
}
],
"digest": "679a7d7de5a24766c48b68a7c821b0aa5c8f4731f6ea082c79d2ce45ecaf350c"
"digest": "48971db1b4bf582c46db8581dbac9215d49bcb66ab17bd39bfaf4eae2c4e8ad3"
}
......@@ -14,7 +14,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/uncharted-distil/[email protected]07420bc86fab469b0b1ac83b25dcc4499c69a125#egg=distil-primitives"
"package_uri": "git+https://github.com/uncharted-distil/[email protected]21b0a71a8585ce7b894ce241296d51c763f2078d#egg=distil-primitives"
},
{
"type": "FILE",
......@@ -236,5 +236,5 @@
},
"structural_type": "distil.primitives.bert_classification.BertPairClassificationPrimitive",
"description": "Uses a pre-trained pytorch BERT model to predict a label of 0 or 1 for a pair of documents, given training samples\nof document pairs labelled 0/1. Takes a datrame of documents and a dataframe of labels as inputs, and returns\na dataframe containing the predictions as a result.\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": "46b736b1ec12dd4c187b9fe9675bc1bb3cf93cccd65a62f474d03646d404f016"
"digest": "8d898b1ed2ee98f2fbba680c358653367637165b481a146cfc39f6cc15503332"
}
{
"id": "c42c529c-d66a-47ed-aec9-e5065f7e31fa",
"id": "b4756439-718b-4635-9e4b-5af3fc21fe57",
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"created": "2019-06-18T02:10:40.810392Z",
"created": "2019-06-17T20:58:25.084860Z",
"inputs": [
{
"name": "inputs"
......@@ -21,7 +21,7 @@
"version": "0.3.0",
"python_path": "d3m.primitives.data_transformation.dataset_to_dataframe.Common",
"name": "Extract a DataFrame from a Dataset",
"digest": "43e118209c48c0d132134dde9115ede5678f348348520eafeefe28e81177b4ed"
"digest": "e557fc176af67913ed241dbe793cf986439157cfe9c4a12f1aafcba3c07b8b6f"
},
"arguments": {
"inputs": {
......@@ -42,7 +42,7 @@
"version": "0.5.0",
"python_path": "d3m.primitives.data_transformation.column_parser.DataFrameCommon",
"name": "Parses strings into their types",
"digest": "3feb9bcf7350e1975b9709d1565a27859d2cf354b095b29f174b158462224f24"
"digest": "7e16e2b1e559690e221de471826d7d1cd36698bc5140dc00f3c7a6c6b711c3b2"
},
"arguments": {
"inputs": {
......@@ -71,10 +71,10 @@
"type": "PRIMITIVE",
"primitive": {
"id": "4503a4c6-42f7-45a1-a1d4-ed69699cf5e1",
"version": "0.3.0",
"version": "0.2.0",
"python_path": "d3m.primitives.data_transformation.extract_columns_by_semantic_types.DataFrameCommon",
"name": "Extracts columns by semantic type",
"digest": "8c9de5cd06f74ea3f80fa9f1e1f775a1d3eddff1621512e6ab72aaab8724b88d"
"digest": "d4fa27a3e215b89d2231d344ec0202e1b8e41ad322deb79c68fd6ca673eae3f7"
},
"arguments": {
"inputs": {
......@@ -103,7 +103,7 @@
"version": "0.1.0",
"python_path": "d3m.primitives.data_transformation.data_cleaning.DistilEnrichDates",
"name": "Enrich dates",
"digest": "842069a031374b658218b94a1fd69e4210078d047632bd65f49d0ca22a6e0ebd"
"digest": "a93c484ea573cbf3d947dac36f7d06c17939f074382d31b5b3fe414474b97ef9"
},
"arguments": {
"inputs": {
......@@ -124,7 +124,7 @@
"version": "0.1.0",
"python_path": "d3m.primitives.data_transformation.data_cleaning.DistilReplaceSingletons",
"name": "Replace singeltons",
"digest": "d2603e7d8ed314c1b8e0618b4e452ba74aab36d08a3c7a29cb85f4d61e64ba5b"
"digest": "8c3007040c0f79a12cf5457d513e0ba12ae5b80e676aeff9eda9c2e4773be9aa"
},
"arguments": {
"inputs": {
......@@ -145,7 +145,7 @@
"version": "0.1.0",
"python_path": "d3m.primitives.data_transformation.imputer.DistilCategoricalImputer",
"name": "Categorical imputer",
"digest": "91fba60912c7f3921d4c2c6d0af07b66f984a8799030a01530b7287d6fff0b61"
"digest": "91c1f7d98729af1fb3bcaadfd1b52f04df778768a41ee5a61b04cf806854f903"
},
"arguments": {
"inputs": {
......@@ -166,7 +166,7 @@
"version": "0.1.0",
"python_path": "d3m.primitives.data_transformation.one_hot_encoder.DistilOneHotEncoder",
"name": "One-hot encoder",
"digest": "88db43082bfb05c5132444df367d9cf7f0395b1fbbbb74772aafdc26a12332f1"
"digest": "93ace8ca63b2a5114c33a8b3487f494eec537bc7d3a03831e843c1289c3fe106"
},
"arguments": {
"inputs": {
......@@ -193,7 +193,7 @@
"version": "0.1.0",
"python_path": "d3m.primitives.data_transformation.encoder.DistilBinaryEncoder",
"name": "Binary encoder",
"digest": "d27135815d7a43d1e9a61c68271baa385dca5f9512e1ec369fe36c6b64a5f4ad"
"digest": "91e0fbfe17a28011e90bb8b109afdd29f0f11ffde100a26d611112a4068af348"
},
"arguments": {
"inputs": {
......@@ -290,7 +290,7 @@
"version": "0.1.0",
"python_path": "d3m.primitives.clustering.k_means.DistilKMeans",
"name": "K means",
"digest": "ac89d6644cb0ab314c69c05ad6e47e32ebdcd26dd14e6ba9e0cbdc630240a0a4"
"digest": "cf888a6922b343e15a261a69272ba26afcec28cf18a68b449ab079beedd91b5b"
},
"arguments": {
"inputs": {
......@@ -321,7 +321,7 @@
"version": "0.3.0",
"python_path": "d3m.primitives.data_transformation.construct_predictions.DataFrameCommon",
"name": "Construct pipeline predictions output",
"digest": "dfbf9e3112dd7ab851fc85588741b66900ac25bd03f2e602327046f676036e28"
"digest": "077921b0d6cee9bbda9494bc60c8b48f8287db8d0bff674056a7c9e5cc92ebb9"
},
"arguments": {
"inputs": {
......@@ -340,5 +340,5 @@
]
}
],
"digest": "cb54e71c542ad89b09cc65b92a08d4fd825a524d640904918dc20a4572228e77"
"digest": "f71db328d7746d296fda39a1c5e2161f3cc7175ee1408ea05789be3c38fb2355"
}
......@@ -14,7 +14,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/uncharted-distil/[email protected]07420bc86fab469b0b1ac83b25dcc4499c69a125#egg=distil-primitives"
"package_uri": "git+https://github.com/uncharted-distil/[email protected]21b0a71a8585ce7b894ce241296d51c763f2078d#egg=distil-primitives"
}
],
"algorithm_types": [
......@@ -212,5 +212,5 @@
},
"structural_type": "distil.primitives.k_means.KMeansPrimitive",
"description": "A wrapper for scikit learn k-means that takes in a dataframe as input and returns a dataframe of (d3mIndex, cluster numbers) tuples as its\noutput. It will ignore columns with a string structural type.\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": "ac89d6644cb0ab314c69c05ad6e47e32ebdcd26dd14e6ba9e0cbdc630240a0a4"
"digest": "459a6a49457ea6ac3090b119b011ed647a0dfcd2ac161ea9032b7bb11be77b6a"
}
{
"id": "5166fea2-6e3d-4a00-b7c2-6a1a88c4bdb8",
"id": "125bdd51-31bd-45ec-a34b-debfc5ec5efc",
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"created": "2019-06-18T01:53:14.879779Z",
"created": "2019-06-20T18:24:32.231085Z",
"inputs": [
{
"name": "inputs"
......@@ -9,7 +9,7 @@
],
"outputs": [
{
"data": "steps.3.produce",
"data": "steps.5.produce",
"name": "output"
}
],
......@@ -21,7 +21,7 @@
"version": "0.1.0",
"python_path": "d3m.primitives.data_preprocessing.audio_loader.DistilAudioDatasetLoader",
"name": "Load audio collection from dataset into a single dataframe",
"digest": "65e0b0cf4d70b4ac74db4c3930a5f031b7aa0da635442cac2c245158c2f32de2"
"digest": "a73c2f0f7684d34312db771c7ecb08fd1b71b72043f5f79166cde9ae26d391d0"
},
"arguments": {
"inputs": {
......@@ -33,14 +33,73 @@
{
"id": "produce"
},
{
"id": "produce_target"
},
{
"id": "produce_collection"
}
]
},
{
"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": "3feb9bcf7350e1975b9709d1565a27859d2cf354b095b29f174b158462224f24"
},
"arguments": {
"inputs": {
"type": "CONTAINER",
"data": "steps.0.produce"
}
},
"outputs": [
{
"id": "produce"
}
],
"hyperparams": {
"parse_semantic_types": {
"type": "VALUE",
"data": [
"http://schema.org/Boolean",
"http://schema.org/Integer",
"http://schema.org/Float",
"https://metadata.datadrivendiscovery.org/types/FloatVector"
]
}
}
},
{
"type": "PRIMITIVE",
"primitive": {
"id": "4503a4c6-42f7-45a1-a1d4-ed69699cf5e1",
"version": "0.3.0",
"python_path": "d3m.primitives.data_transformation.extract_columns_by_semantic_types.DataFrameCommon",
"name": "Extracts columns by semantic type",
"digest": "8c9de5cd06f74ea3f80fa9f1e1f775a1d3eddff1621512e6ab72aaab8724b88d"
},
"arguments": {
"inputs": {
"type": "CONTAINER",
"data": "steps.1.produce"
}
},
"outputs": [
{
"id": "produce"
}
],
"hyperparams": {
"semantic_types": {
"type": "VALUE",
"data": [
"https://metadata.datadrivendiscovery.org/types/Target",
"https://metadata.datadrivendiscovery.org/types/TrueTarget"
]
}
}
},
{
"type": "PRIMITIVE",
"primitive": {
......@@ -48,7 +107,7 @@
"version": "0.1.0",
"python_path": "d3m.primitives.feature_extraction.audio_transfer.DistilAudioTransfer",
"name": "Audio Transfer",
"digest": "869148edf66de09d934c73af3320a8fbd3e310a8003324d1141e4a12b46deed3"
"digest": "c5cffc8c204bc808c667cddcc265dffcedb1d1893d80e1f7b693956d930b2f39"
},
"arguments": {
"inputs": {
......@@ -69,16 +128,16 @@
"version": "0.1.0",
"python_path": "d3m.primitives.learner.random_forest.DistilEnsembleForest",
"name": "EnsembleForest",
"digest": "5f1ba725c9ac1794477f3fdd5bd237ee4e39cb20dc278cc71543c2d02e36ab19"
"digest": "320510ba2afcacb5fa05be10c6b1ae40e2e11a60b37b75ac3d27b1143fbfe3cb"
},
"arguments": {
"inputs": {
"type": "CONTAINER",
"data": "steps.1.produce"
"data": "steps.3.produce"
},
"outputs": {
"type": "CONTAINER",
"data": "steps.0.produce_target"
"data": "steps.2.produce"
}
},
"outputs": [
......@@ -105,28 +164,19 @@
"arguments": {
"inputs": {
"type": "CONTAINER",
"data": "steps.2.produce"
"data": "steps.4.produce"
},
"reference": {
"type": "CONTAINER",
"data": "steps.0.produce_target"
"data": "steps.1.produce"
}
},
"outputs": [
{
"id": "produce"
}
],
"hyperparams": {
"use_columns": {
"type": "VALUE",
"data": [
0,
1
]
}
}
]
}
],
"digest": "a540771361eb93f8112a63a11ed522eac8421ec47360c44f48e59d66c3c43d9e"
"digest": "347e12f00ee716dc2e3d246a0e12a51fbd735c6efadec545717c4cdcc9f5175a"
}
......@@ -14,7 +14,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/uncharted-distil/[email protected]07420bc86fab469b0b1ac83b25dcc4499c69a125#egg=distil-primitives"
"package_uri": "git+https://github.com/uncharted-distil/[email protected]21b0a71a8585ce7b894ce241296d51c763f2078d#egg=distil-primitives"
}
],
"algorithm_types": [
......@@ -36,15 +36,6 @@
"base.PrimitiveBase"
],
"hyperparams": {
"collection_type": {
"type": "d3m.metadata.hyperparams.Hyperparameter",
"default": "timeseries",
"structural_type": "str",
"semantic_types": [
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
"description": "the type of collection to load"
},
"sample": {
"type": "d3m.metadata.hyperparams.Hyperparameter",
"default": 1.0,
......@@ -202,17 +193,6 @@
"singleton": false,
"inputs_across_samples": []
},
"produce_target": {
"kind": "PRODUCE",
"arguments": [
"inputs",
"timeout",
"iterations"
],
"returns": "d3m.primitive_interfaces.base.CallResult[d3m.container.pandas.DataFrame]",
"singleton": false,
"inputs_across_samples": []
},
"set_params": {
"kind": "OTHER",
"arguments": [
......@@ -242,5 +222,5 @@
},
"structural_type": "distil.primitives.audio_loader.AudioDatasetLoaderPrimitive",
"description": "A primitive which reads columns referencing audio files.\n\nEach column which has ``https://metadata.datadrivendiscovery.org/types/FileName`` semantic type\nand a valid media type (``audio/aiff``, ``audio/flac``, ``audio/ogg``, ``audio/wav``, ``audio/mpeg``)\nhas every filename read into an audio represented as a numpy array. By default the resulting column\nwith read arrays is appended to existing columns.\n\nThe shape of numpy arrays is S x C. S is the number of samples, C is the number of\nchannels in an audio (e.g., C = 1 for mono, C = 2 for stereo). dtype is float32.\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": "65e0b0cf4d70b4ac74db4c3930a5f031b7aa0da635442cac2c245158c2f32de2"
"digest": "a73c2f0f7684d34312db771c7ecb08fd1b71b72043f5f79166cde9ae26d391d0"
}
{
"id": "363fda97-7102-4f20-aea6-c6f915502213",
"id": "d2389635-dcf4-407a-b91b-27ea92aa687e",
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"created": "2019-06-18T01:08:09.991784Z",
"created": "2019-06-17T20:58:02.486398Z",
"inputs": [
{
"name": "inputs"
......@@ -21,7 +21,7 @@
"version": "0.1.0",
"python_path": "d3m.primitives.data_transformation.load_single_graph.DistilSingleGraphLoader",
"name": "Load single graph and dataframe into a parseable object",
"digest": "ef36b3e960456d993ddbbb274788b892c130742d61088ae67ac06b53fc16b387"
"digest": "9893cb98b9eef3357dbd2caa82197afecab77d9acf135712c74b4ce4d57976b3"
},
"arguments": {
"inputs": {
......@@ -45,7 +45,7 @@
"version": "0.1.0",
"python_path": "d3m.primitives.data_transformation.community_detection.DistilCommunityDetection",
"name": "CommunityDetection",
"digest": "771b5ff59106b7b835b2e6403dc3aa6869ebf76f347e816c42ce4c26ce1033f8"
"digest": "5b6dee41c2d70ec17ab6a7c1d476176cd29c7cb0d977507ecbc7980da55b6ee8"
},
"arguments": {
"inputs": {
......@@ -70,5 +70,5 @@
}
}
],
"digest": "70531a8bf97707f75825f28ccfa008daf49bfb70b3d9a78088d09c59801e3e62"
"digest": "9276ccffebfd8548119fb09c6f744afba72b83a6609d744bb2deecb831cdb77b"
}
......@@ -14,7 +14,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/uncharted-distil/[email protected]07420bc86fab469b0b1ac83b25dcc4499c69a125#egg=distil-primitives"
"package_uri": "git+https://github.com/uncharted-distil/[email protected]21b0a71a8585ce7b894ce241296d51c763f2078d#egg=distil-primitives"
}
],
"algorithm_types": [
......@@ -190,5 +190,5 @@
},
"structural_type": "distil.primitives.community_detection.DistilCommunityDetectionPrimitive",
"description": "A primitive that wraps a null model handling of community detection.\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": "771b5ff59106b7b835b2e6403dc3aa6869ebf76f347e816c42ce4c26ce1033f8"
"digest": "e4aa14b39fedae1a416bdd3f61afee135af38eed26cb8fa2cd4017962c7a1b7b"
}
{
"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"
]
}
{
"problem": "1491_one_hundred_plants_margin_clust_problem",
"full_inputs": [
"1491_one_hundred_plants_margin_clust_dataset"
],
"train_inputs": [
"1491_one_hundred_plants_margin_clust_dataset_TRAIN"
],
"test_inputs": [
"1491_one_hundred_plants_margin_clust_dataset_TEST"
],
"score_inputs": [
"1491_one_hundred_plants_margin_clust_dataset_SCORE"
]
}
......@@ -14,7 +14,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/uncharted-distil/[email protected]07420bc86fab469b0b1ac83b25dcc4499c69a125#egg=distil-primitives"
"package_uri": "git+https://github.com/uncharted-distil/[email protected]21b0a71a8585ce7b894ce241296d51c763f2078d#egg=distil-primitives"
}
],
"algorithm_types": [
......@@ -210,5 +210,5 @@
},
"structural_type": "distil.primitives.enrich_dates.EnrichDatesPrimitive",
"description": "Enriches dates by converting to seconds from a base time and computing Z scores. The results\nare appended to the existing dataset, and the original column is left in place for additional\ndownstream processing.\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": "842069a031374b658218b94a1fd69e4210078d047632bd65f49d0ca22a6e0ebd"
"digest": "04746e52b5a2aded12d7c5dbbf06c0222f90d43cbc7abc24a8e45cc73f92a236"
}
......@@ -14,7 +14,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/uncharted-distil/[email protected]07420bc86fab469b0b1ac83b25dcc4499c69a125#egg=distil-primitives"
"package_uri": "git+https://github.com/uncharted-distil/[email protected]21b0a71a8585ce7b894ce241296d51c763f2078d#egg=distil-primitives"
}
],
"algorithm_types": [
......@@ -222,5 +222,5 @@
},
"structural_type": "distil.primitives.ragged_dataset_loader.RaggedDatasetLoaderPrimitive",
"description": "A primitive that loads multiple data into a single dataframe.\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": "75a376733f3592af99ee7b3cfdaa38ec0629928255da70e73a18feee78ff1804"
"digest": "a0c0e755fbd70d71d7934454165a3a665e8498a73206928fdab29c6aa27f9544"
}
{
"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"
]
}