Commit 5ce0b53d authored by Mitar's avatar Mitar
Browse files

Merge branch 'sn/winter_eval_pipeline_testing_4' into 'master'

Fixing Docker image versions

See merge request !154
parents ced7aa4f d8a77fd1
Pipeline #111795930 passed with stages
in 85 minutes and 34 seconds
{"id": "3c9d4cc0-27f6-45d7-8d09-8f26ef4249ed", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2020-01-14T20:42:52.222359Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.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": "a1a0109be87a6ae578fd20e9d46c70c806059076c041b80b6314e7e41cf62d82"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "e193afa1-b45e-4d29-918f-5bb1fa3b88a7", "version": "0.2.0", "python_path": "d3m.primitives.schema_discovery.profiler.Common", "name": "Determine missing semantic types for columns automatically", "digest": "a3d51cbc0bf18168114c1c8f12c497d691dbe30b71667f355f30c13a9a08ba32"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "fc6bf33a-f3e0-3496-aa47-9a40289661bc", "version": "3.0.2", "python_path": "d3m.primitives.data_cleaning.data_cleaning.Datacleaning", "name": "Data cleaning", "digest": "86f391bddc57bcab2d5af1728f442e7469298425a6678dc004312ed4a470f4d8"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d510cb7a-1782-4f51-b44c-58f0236e47c7", "version": "0.6.0", "python_path": "d3m.primitives.data_transformation.column_parser.Common", "name": "Parses strings into their types", "digest": "b020e14e3d4f1e4266aa8a0680d83afcf2862300549c6f6c903742d7d171f879"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d016df89-de62-3c53-87ed-c06bb6a23cde", "version": "2019.11.13", "python_path": "d3m.primitives.data_cleaning.imputer.SKlearn", "name": "sklearn.impute.SimpleImputer", "digest": "e698baa218e91ff6e2beca3e8134a000812c8bce2764c460b2ad296a5d7a6318"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.3.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.Common", "name": "XGBoost GBTree classifier", "digest": "2046db9d29ad9dff3a4191b92477e17b7c28a57c39f5ef692c9c67aa4cea5732"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}, "outputs": {"type": "CONTAINER", "data": "steps.4.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.Common", "name": "Construct pipeline predictions output", "digest": "674a644333a3a481769591341591461b06de566fef7439010284739194e18af8"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "0c9bdafe0a6247db9a5ae05a86d5ccbc75c7551ad3cbbca151df3f4efe630182"}
\ No newline at end of file
{"id": "dcb9199d-05a8-400f-baf3-63cba2aaf753", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2020-01-21T19:21:23.046164Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.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": "a1a0109be87a6ae578fd20e9d46c70c806059076c041b80b6314e7e41cf62d82"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "e193afa1-b45e-4d29-918f-5bb1fa3b88a7", "version": "0.2.0", "python_path": "d3m.primitives.schema_discovery.profiler.Common", "name": "Determine missing semantic types for columns automatically", "digest": "a3d51cbc0bf18168114c1c8f12c497d691dbe30b71667f355f30c13a9a08ba32"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "fc6bf33a-f3e0-3496-aa47-9a40289661bc", "version": "3.0.2", "python_path": "d3m.primitives.data_cleaning.data_cleaning.Datacleaning", "name": "Data cleaning", "digest": "bb2a9e13bafdb9c5f6693d01e1c533731b27ec08962433ee161e214496354d1d"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d510cb7a-1782-4f51-b44c-58f0236e47c7", "version": "0.6.0", "python_path": "d3m.primitives.data_transformation.column_parser.Common", "name": "Parses strings into their types", "digest": "b020e14e3d4f1e4266aa8a0680d83afcf2862300549c6f6c903742d7d171f879"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d016df89-de62-3c53-87ed-c06bb6a23cde", "version": "2019.11.13", "python_path": "d3m.primitives.data_cleaning.imputer.SKlearn", "name": "sklearn.impute.SimpleImputer", "digest": "e698baa218e91ff6e2beca3e8134a000812c8bce2764c460b2ad296a5d7a6318"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.3.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.Common", "name": "XGBoost GBTree classifier", "digest": "2046db9d29ad9dff3a4191b92477e17b7c28a57c39f5ef692c9c67aa4cea5732"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}, "outputs": {"type": "CONTAINER", "data": "steps.4.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.Common", "name": "Construct pipeline predictions output", "digest": "674a644333a3a481769591341591461b06de566fef7439010284739194e18af8"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "a64f44051523aa570ab4b28e940ffc011e1caf3062684acfdaee08593048698e"}
\ No newline at end of file
{"id": "cc4aef67-d876-4222-a186-c3ae4799c799", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2020-01-16T20:41:04.798440Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.2.produce", "name": "output_predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "f31f8c1f-d1c5-43e5-a4b2-2ae4a761ef2e", "version": "0.2.0", "python_path": "d3m.primitives.data_transformation.denormalize.Common", "name": "Denormalize datasets", "digest": "f5e329a61d031c5ca89f962b79c2aaea5273761408bde6311eb2f0e580e0313e"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"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": "a1a0109be87a6ae578fd20e9d46c70c806059076c041b80b6314e7e41cf62d82"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"dataframe_resource": {"type": "VALUE", "data": "learningData"}}}, {"type": "PRIMITIVE", "primitive": {"id": "46612a42-6120-3559-9db9-3aa9a76eb94f", "version": "1.2.0", "python_path": "d3m.primitives.data_cleaning.text_summarization.Duke", "name": "duke", "digest": "bc839f0d49953b0cb477b9a1d716e8eaf1485bdec50b3e856015a9d2bca16c8b"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "ef43ddb19e13a5df999509969d7367baed78595adaacf49ae4ad086d8b7e9c10"}
\ No newline at end of file
{"id": "2d7579e8-f001-4745-9a55-dd6af2607ff4", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2020-01-21T19:52:23.935805Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.2.produce", "name": "output_predictions"}], "steps": [{"type": "PRIMITIVE", "primitive": {"id": "f31f8c1f-d1c5-43e5-a4b2-2ae4a761ef2e", "version": "0.2.0", "python_path": "d3m.primitives.data_transformation.denormalize.Common", "name": "Denormalize datasets", "digest": "f5e329a61d031c5ca89f962b79c2aaea5273761408bde6311eb2f0e580e0313e"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"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": "a1a0109be87a6ae578fd20e9d46c70c806059076c041b80b6314e7e41cf62d82"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"dataframe_resource": {"type": "VALUE", "data": "learningData"}}}, {"type": "PRIMITIVE", "primitive": {"id": "46612a42-6120-3559-9db9-3aa9a76eb94f", "version": "1.2.0", "python_path": "d3m.primitives.data_cleaning.text_summarization.Duke", "name": "duke", "digest": "bc839f0d49953b0cb477b9a1d716e8eaf1485bdec50b3e856015a9d2bca16c8b"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "0606e428239e6ead2d656650e73098d8040cb2bab5053ce52fb37a29cace0233"}
\ No newline at end of file
{"id": "ef936c2c-8581-4ff4-9d40-67df20e43873", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2020-01-21T19:59:11.341299Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.7.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": "a1a0109be87a6ae578fd20e9d46c70c806059076c041b80b6314e7e41cf62d82"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "e193afa1-b45e-4d29-918f-5bb1fa3b88a7", "version": "0.2.0", "python_path": "d3m.primitives.schema_discovery.profiler.Common", "name": "Determine missing semantic types for columns automatically", "digest": "a3d51cbc0bf18168114c1c8f12c497d691dbe30b71667f355f30c13a9a08ba32"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d510cb7a-1782-4f51-b44c-58f0236e47c7", "version": "0.6.0", "python_path": "d3m.primitives.data_transformation.column_parser.Common", "name": "Parses strings into their types", "digest": "b020e14e3d4f1e4266aa8a0680d83afcf2862300549c6f6c903742d7d171f879"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d016df89-de62-3c53-87ed-c06bb6a23cde", "version": "2019.11.13", "python_path": "d3m.primitives.data_cleaning.imputer.SKlearn", "name": "sklearn.impute.SimpleImputer", "digest": "e698baa218e91ff6e2beca3e8134a000812c8bce2764c460b2ad296a5d7a6318"}, "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": "04573880-d64f-4791-8932-52b7c3877639", "version": "3.1.2", "python_path": "d3m.primitives.feature_selection.pca_features.Pcafeatures", "name": "PCA Features", "digest": "89a396517f47e84d6e8ccb9209763a2f923d0b9e86cb6e532d29954ac39db340"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.3.produce"}, "outputs": {"type": "CONTAINER", "data": "steps.3.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "4503a4c6-42f7-45a1-a1d4-ed69699cf5e1", "version": "0.3.0", "python_path": "d3m.primitives.data_transformation.extract_columns_by_semantic_types.Common", "name": "Extracts columns by semantic type", "digest": "505df38f9be4964ff19683ab3e185f19333fb35c26121c12a1c55bddd9d38f72"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.2.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"semantic_types": {"type": "VALUE", "data": ["https://metadata.datadrivendiscovery.org/types/Target"]}, "add_index_columns": {"type": "VALUE", "data": true}}}, {"type": "PRIMITIVE", "primitive": {"id": "fe0841b7-6e70-4bc3-a56c-0670a95ebc6a", "version": "0.1.0", "python_path": "d3m.primitives.classification.xgboost_gbtree.Common", "name": "XGBoost GBTree classifier", "digest": "2046db9d29ad9dff3a4191b92477e17b7c28a57c39f5ef692c9c67aa4cea5732"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}, "outputs": {"type": "CONTAINER", "data": "steps.5.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.Common", "name": "Construct pipeline predictions output", "digest": "674a644333a3a481769591341591461b06de566fef7439010284739194e18af8"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.6.produce"}, "reference": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "6310bb9062c4634488f2b2004bcc7d86da9ea342b55426dc991de18b548a6997"}
\ No newline at end of file
{
"id": "04573880-d64f-4791-8932-52b7c3877639",
"version": "3.1.2",
"name": "PCA Features",
"keywords": [
"Rank and score numeric features based on principal component analysis"
],
"source": {
"name": "Distil",
"contact": "mailto:numa@yonder.co",
"uris": [
"https://github.com/NewKnowledge/pcafeatures-d3m-wrapper"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/NewKnowledge/pcafeatures-d3m-wrapper.git@054651558f02dda3b15a206d9f6a19f856b1f06c#egg=PcafeaturesD3MWrapper"
}
],
"python_path": "d3m.primitives.feature_selection.pca_features.Pcafeatures",
"algorithm_types": [
"PRINCIPAL_COMPONENT_ANALYSIS"
],
"primitive_family": "FEATURE_SELECTION",
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
"original_python_path": "PcafeaturesD3MWrapper.wrapper.pcafeatures",
"primitive_code": {
"class_type_arguments": {
"Inputs": "d3m.container.pandas.DataFrame",
"Outputs": "d3m.container.pandas.DataFrame",
"Params": "PcafeaturesD3MWrapper.wrapper.Params",
"Hyperparams": "PcafeaturesD3MWrapper.wrapper.Hyperparams"
},
"interfaces_version": "2020.1.9",
"interfaces": [
"base.PrimitiveBase"
],
"hyperparams": {
"threshold": {
"type": "d3m.metadata.hyperparams.Uniform",
"default": 0.0,
"structural_type": "float",
"semantic_types": [
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
"description": "pca score threshold for feature selection",
"lower": 0.0,
"upper": 1.0,
"lower_inclusive": true,
"upper_inclusive": false
},
"only_numeric_cols": {
"type": "d3m.metadata.hyperparams.UniformBool",
"default": true,
"structural_type": "bool",
"semantic_types": [
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
"description": "consider only numeric columns for feature selection"
}
},
"arguments": {
"hyperparams": {
"type": "PcafeaturesD3MWrapper.wrapper.Hyperparams",
"kind": "RUNTIME"
},
"random_seed": {
"type": "int",
"kind": "RUNTIME",
"default": 0
},
"timeout": {
"type": "typing.Union[NoneType, float]",
"kind": "RUNTIME",
"default": null
},
"iterations": {
"type": "typing.Union[NoneType, int]",
"kind": "RUNTIME",
"default": null
},
"produce_methods": {
"type": "typing.Sequence[str]",
"kind": "RUNTIME"
},
"inputs": {
"type": "d3m.container.pandas.DataFrame",
"kind": "PIPELINE"
},
"outputs": {
"type": "d3m.container.pandas.DataFrame",
"kind": "PIPELINE"
},
"params": {
"type": "PcafeaturesD3MWrapper.wrapper.Params",
"kind": "RUNTIME"
}
},
"class_methods": {},
"instance_methods": {
"__init__": {
"kind": "OTHER",
"arguments": [
"hyperparams",
"random_seed"
],
"returns": "NoneType"
},
"fit": {
"kind": "OTHER",
"arguments": [
"timeout",
"iterations"
],
"returns": "d3m.primitive_interfaces.base.CallResult[NoneType]",
"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\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": "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",
"arguments": [
"produce_methods",
"inputs",
"timeout",
"iterations"
],
"returns": "d3m.primitive_interfaces.base.MultiCallResult",
"description": "A method calling multiple produce methods at once.\n\nWhen a primitive has multiple produce methods it is common that they might compute the\nsame internal results for same inputs but return different representations of those results.\nIf caller is interested in multiple of those representations, calling multiple produce\nmethods might lead to recomputing same internal results multiple times. To address this,\nthis method allows primitive author to implement an optimized version which computes\ninternal results only once for multiple calls of produce methods, but return those different\nrepresentations.\n\nIf any additional method arguments are added to primitive's produce method(s), they have\nto be added to this method as well. This method should accept an union of all arguments\naccepted by primitive's produce method(s) and then use them accordingly when computing\nresults.\n\nThe default implementation of this method just calls all produce methods listed in\n``produce_methods`` in order and is potentially inefficient.\n\nIf primitive should have been fitted before calling this method, but it has not been,\nprimitive should raise a ``PrimitiveNotFittedError`` exception.\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 produce outputs for all produce methods\n listed in ``produce_methods`` argument, in seconds.\niterations : int\n How many of internal iterations should the primitive do.\n\nReturns\n-------\nMultiCallResult\n A dict of values for each produce method wrapped inside ``MultiCallResult``."
},
"produce": {
"kind": "PRODUCE",
"arguments": [
"inputs",
"timeout",
"iterations"
],
"returns": "d3m.primitive_interfaces.base.CallResult[d3m.container.pandas.DataFrame]",
"singleton": false,
"inputs_across_samples": [],
"description": "Produce primitive's best choice of the output for each of the inputs.\n\nThe output value should be wrapped inside ``CallResult`` object before returning.\n\nIn many cases producing an output is a quick operation in comparison with ``fit``, but not\nall cases are like that. For example, a primitive can start a potentially long optimization\nprocess to compute outputs. ``timeout`` and ``iterations`` can serve as a way for a caller\nto guide the length of this process.\n\nIdeally, a primitive should adapt its call to try to produce the best outputs possible\ninside the time allocated. If this is not possible and the primitive reaches the timeout\nbefore producing outputs, it should raise a ``TimeoutError`` exception to signal that the\ncall was unsuccessful in the given time. The state of the primitive after the exception\nshould be as the method call has never happened and primitive should continue to operate\nnormally. The purpose of ``timeout`` is to give opportunity to a primitive to cleanly\nmanage its state instead of interrupting execution from outside. Maintaining stable internal\nstate should have precedence over respecting the ``timeout`` (caller can terminate the\nmisbehaving primitive from outside anyway). If a longer ``timeout`` would produce\ndifferent outputs, then ``CallResult``'s ``has_finished`` should be set to ``False``.\n\nSome primitives have internal iterations (for example, optimization iterations).\nFor those, caller can provide how many of primitive's internal iterations\nshould a primitive do before returning outputs. Primitives should make iterations as\nsmall as reasonable. If ``iterations`` is ``None``, then there is no limit on\nhow many iterations the primitive should do and primitive should choose the best amount\nof iterations on its own (potentially controlled through hyper-parameters).\nIf ``iterations`` is a number, a primitive has to do those number of iterations,\nif possible. ``timeout`` should still be respected and potentially less iterations\ncan be done because of that. Primitives with internal iterations should make\n``CallResult`` contain correct values.\n\nFor primitives which do not have internal iterations, any value of ``iterations``\nmeans that they should run fully, respecting only ``timeout``.\n\nIf primitive should have been fitted before calling this method, but it has not been,\nprimitive should raise a ``PrimitiveNotFittedError`` exception.\n\nParameters\n----------\ninputs : Input pandas frame\n\nReturns\n-------\nOutputs : pandas frame with list of original features in first column, ordered\n by their contribution to the first principal component, and scores in\n the second column."
},
"produce_metafeatures": {
"kind": "PRODUCE",
"arguments": [
"inputs",
"timeout",
"iterations"
],
"returns": "d3m.primitive_interfaces.base.CallResult[d3m.container.pandas.DataFrame]",
"singleton": false,
"inputs_across_samples": [],
"description": "Parameters\n-------\ninputs : Input pandas frame\n\nReturns\n-------\nOutputs : pandas frame with list of original features in first column, ordered\n by their contribution to the first principal component, and scores in\n the second column."
},
"set_params": {
"kind": "OTHER",
"arguments": [
"params"
],
"returns": "NoneType",
"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": [
"inputs",
"outputs"
],
"returns": "NoneType",
"description": "Sets primitive's training data\n\nParameters\n----------\ninputs = D3M dataframe"
}
},
"class_attributes": {
"logger": "logging.Logger",
"metadata": "d3m.metadata.base.PrimitiveMetadata"
},
"instance_attributes": {
"hyperparams": "d3m.metadata.hyperparams.Hyperparams",
"random_seed": "int",
"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\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": "89a396517f47e84d6e8ccb9209763a2f923d0b9e86cb6e532d29954ac39db340"
}
{"id": "8df01917-db82-44fb-985a-a55ac2492039", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "created": "2020-01-21T20:11:04.983365Z", "inputs": [{"name": "inputs"}], "outputs": [{"data": "steps.6.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": "a1a0109be87a6ae578fd20e9d46c70c806059076c041b80b6314e7e41cf62d82"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "inputs.0"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "e193afa1-b45e-4d29-918f-5bb1fa3b88a7", "version": "0.2.0", "python_path": "d3m.primitives.schema_discovery.profiler.Common", "name": "Determine missing semantic types for columns automatically", "digest": "a3d51cbc0bf18168114c1c8f12c497d691dbe30b71667f355f30c13a9a08ba32"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d510cb7a-1782-4f51-b44c-58f0236e47c7", "version": "0.6.0", "python_path": "d3m.primitives.data_transformation.column_parser.Common", "name": "Parses strings into their types", "digest": "b020e14e3d4f1e4266aa8a0680d83afcf2862300549c6f6c903742d7d171f879"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.1.produce"}}, "outputs": [{"id": "produce"}]}, {"type": "PRIMITIVE", "primitive": {"id": "d016df89-de62-3c53-87ed-c06bb6a23cde", "version": "2019.11.13", "python_path": "d3m.primitives.data_cleaning.imputer.SKlearn", "name": "sklearn.impute.SimpleImputer", "digest": "e698baa218e91ff6e2beca3e8134a000812c8bce2764c460b2ad296a5d7a6318"}, "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": "ef6f3887-b253-4bfd-8b35-ada449efad0c", "version": "3.1.2", "python_path": "d3m.primitives.feature_selection.rffeatures.Rffeatures", "name": "RF Features", "digest": "924700316c674fa9afa487672f489e9e6728d9171fb0494b43d394c3b903921c"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.3.produce"}, "outputs": {"type": "CONTAINER", "data": "steps.3.produce"}}, "outputs": [{"id": "produce"}], "hyperparams": {"only_numeric_cols": {"type": "VALUE", "data": true}, "proportion_of_features": {"type": "VALUE", "data": 1.0}}}, {"type": "PRIMITIVE", "primitive": {"id": "1dd82833-5692-39cb-84fb-2455683075f3", "version": "2019.11.13", "python_path": "d3m.primitives.classification.random_forest.SKlearn", "name": "sklearn.ensemble.forest.RandomForestClassifier", "digest": "d58b25ffaffe1b289162293148c1e48cc5080b9e4848260e8462c585273619e8"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.4.produce"}, "outputs": {"type": "CONTAINER", "data": "steps.4.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.Common", "name": "Construct pipeline predictions output", "digest": "674a644333a3a481769591341591461b06de566fef7439010284739194e18af8"}, "arguments": {"inputs": {"type": "CONTAINER", "data": "steps.5.produce"}, "reference": {"type": "CONTAINER", "data": "steps.0.produce"}}, "outputs": [{"id": "produce"}]}], "digest": "e9097a719ff77cb2261ce99c6ba2de24a17898721eb95a029a5a7c41932cd6a8"}
\ No newline at end of file
{
"id": "ef6f3887-b253-4bfd-8b35-ada449efad0c",
"version": "3.1.2",
"name": "RF Features",
"keywords": [
"Rank and score numeric features based on Random Forest and Recursive Feature Elimination"
],
"source": {
"name": "Distil",
"contact": "mailto:numa@yonder.co",
"uris": [
"https://github.com/NewKnowledge/rffeatures-d3m-wrapper"
]
},
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/NewKnowledge/rffeatures-d3m-wrapper.git@0ccd4313f07a72255660cb088fc2dcb4071a60b6#egg=RffeaturesD3MWrapper"
}
],
"python_path": "d3m.primitives.feature_selection.rffeatures.Rffeatures",
"algorithm_types": [
"RANDOM_FOREST"
],
"primitive_family": "FEATURE_SELECTION",
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
"original_python_path": "RffeaturesD3MWrapper.wrapper.rffeatures",
"primitive_code": {
"class_type_arguments": {
"Inputs": "d3m.container.pandas.DataFrame",
"Outputs": "d3m.container.pandas.DataFrame",
"Params": "RffeaturesD3MWrapper.wrapper.Params",
"Hyperparams": "RffeaturesD3MWrapper.wrapper.Hyperparams"
},
"interfaces_version": "2020.1.9",
"interfaces": [
"base.PrimitiveBase"
],
"hyperparams": {
"proportion_of_features": {
"type": "d3m.metadata.hyperparams.Uniform",
"default": 1.0,
"structural_type": "float",
"semantic_types": [
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
"description": "proportion of top features from input dataset to keep",
"lower": 0.0,
"upper": 1.0,
"lower_inclusive": true,
"upper_inclusive": true
},
"only_numeric_cols": {
"type": "d3m.metadata.hyperparams.UniformBool",
"default": false,
"structural_type": "bool",
"semantic_types": [
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
"description": "consider only numeric columns for feature selection"
}
},
"arguments": {
"hyperparams": {
"type": "RffeaturesD3MWrapper.wrapper.Hyperparams",
"kind": "RUNTIME"
},
"random_seed": {
"type": "int",
"kind": "RUNTIME",
"default": 0
},
"timeout": {
"type": "typing.Union[NoneType, float]",
"kind": "RUNTIME",
"default": null
},
"iterations": {
"type": "typing.Union[NoneType, int]",
"kind": "RUNTIME",
"default": null
},
"produce_methods": {
"type": "typing.Sequence[str]",
"kind": "RUNTIME"
},
"inputs": {
"type": "d3m.container.pandas.DataFrame",
"kind": "PIPELINE"
},
"outputs": {
"type": "d3m.container.pandas.DataFrame",
"kind": "PIPELINE"
},
"params": {
"type": "RffeaturesD3MWrapper.wrapper.Params",
"kind": "RUNTIME"
}
},
"class_methods": {},
"instance_methods": {
"__init__": {
"kind": "OTHER",
"arguments": [
"hyperparams",
"random_seed"
],
"returns": "NoneType"
},
"fit": {
"kind": "OTHER",
"arguments": [
"timeout",
"iterations"
],
"returns": "d3m.primitive_interfaces.base.CallResult[NoneType]",
"description": "fits rffeatures 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\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": "RffeaturesD3MWrapper.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",
"arguments": [
"produce_methods",
"inputs",
"timeout",
"iterations"
],
"returns": "d3m.primitive_interfaces.base.MultiCallResult",
"description": "A method calling multiple produce methods at once.\n\nWhen a primitive has multiple produce methods it is common that they might compute the\nsame internal results for same inputs but return different representations of those results.\nIf caller is interested in multiple of those representations, calling multiple produce\nmethods might lead to recomputing same internal results multiple times. To address this,\nthis method allows primitive author to implement an optimized version which computes\ninternal results only once for multiple calls of produce methods, but return those different\nrepresentations.\n\nIf any additional method arguments are added to primitive's produce method(s), they have\nto be added to this method as well. This method should accept an union of all arguments\naccepted by primitive's produce method(s) and then use them accordingly when computing\nresults.\n\nThe default implementation of this method just calls all produce methods listed in\n``produce_methods`` in order and is potentially inefficient.\n\nIf primitive should have been fitted before calling this method, but it has not been,\nprimitive should raise a ``PrimitiveNotFittedError`` exception.\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 produce outputs for all produce methods\n listed in ``produce_methods`` argument, in seconds.\niterations : int\n How many of internal iterations should the primitive do.\n\nReturns\n-------\nMultiCallResult\n A dict of values for each produce method wrapped inside ``MultiCallResult``."
},
"produce": {
"kind": "PRODUCE",
"arguments": [
"inputs",
"timeout",
"iterations"
],
"returns": "d3m.primitive_interfaces.base.CallResult[d3m.container.pandas.DataFrame]",
"singleton": false,
"inputs_across_samples": [],
"description": "Perform supervised recursive feature elimination using random forests to generate an ordered\nlist of features\n\nParameters\n----------\ninputs : Input pandas frame, NOTE: Target column MUST be the last column\n\nReturns\n-------\nOutputs : pandas frame with ordered list of original features in first column"
},
"produce_metafeatures": {
"kind": "PRODUCE",
"arguments": [
"inputs",
"timeout",
"iterations"
],
"returns": "d3m.primitive_interfaces.base.CallResult[d3m.container.pandas.DataFrame]",
"singleton": false,
"inputs_across_samples": [],
"description": "Perform supervised recursive feature elimination using random forests to generate an ordered\nlist of features \nParameters\n----------\ninputs : Input pandas frame, NOTE: Target column MUST be the last column\n\nReturns\n-------\nOutputs : pandas frame with ordered list of original features in first column"
},
"set_params": {
"kind": "OTHER",
"arguments": [
"params"
],
"returns": "NoneType",