Commit 2e2b43ab authored by Jarod Wang's avatar Jarod Wang Committed by Mitar
parent 5cc431d0
{ {
"id": "157f962c-3f42-423e-b479-d985474162d9", "id": "2b8d0f1e-be76-400e-926b-2efbfd12a135",
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"created": "2019-04-12T17:03:46.558669Z", "created": "2019-05-21T18:34:55.728249Z",
"context": "EVALUATION",
"inputs": [ "inputs": [
{ {
"name": "dataset inputs" "name": "dataset inputs"
...@@ -80,14 +79,6 @@ ...@@ -80,14 +79,6 @@
"data": [ "data": [
"https://metadata.datadrivendiscovery.org/types/Attribute" "https://metadata.datadrivendiscovery.org/types/Attribute"
] ]
},
"exclude_columns": {
"type": "VALUE",
"data": [
1,
17,
18
]
} }
} }
}, },
...@@ -109,7 +100,17 @@ ...@@ -109,7 +100,17 @@
{ {
"id": "produce" "id": "produce"
} }
] ],
"hyperparams": {
"use_semantic_types": {
"type": "VALUE",
"data": true
},
"return_result": {
"type": "VALUE",
"data": "replace"
}
}
}, },
{ {
"type": "PRIMITIVE", "type": "PRIMITIVE",
...@@ -134,7 +135,7 @@ ...@@ -134,7 +135,7 @@
"semantic_types": { "semantic_types": {
"type": "VALUE", "type": "VALUE",
"data": [ "data": [
"https://metadata.datadrivendiscovery.org/types/SuggestedTarget" "https://metadata.datadrivendiscovery.org/types/TrueTarget"
] ]
} }
} }
...@@ -143,7 +144,7 @@ ...@@ -143,7 +144,7 @@
"type": "PRIMITIVE", "type": "PRIMITIVE",
"primitive": { "primitive": {
"id": "e770fae6-da6d-45f8-86bf-38a121a4e65a", "id": "e770fae6-da6d-45f8-86bf-38a121a4e65a",
"version": "3.0.0", "version": "3.0.1",
"python_path": "d3m.primitives.classification.cover_tree.Fastlvm", "python_path": "d3m.primitives.classification.cover_tree.Fastlvm",
"name": "Nearest Neighbor Classification with Cover Trees" "name": "Nearest Neighbor Classification with Cover Trees"
}, },
...@@ -193,6 +194,5 @@ ...@@ -193,6 +194,5 @@
} }
] ]
} }
], ]
"pipeline_rank": "1" }
} \ No newline at end of file
{ {
"id": "e770fae6-da6d-45f8-86bf-38a121a4e65a", "id": "e770fae6-da6d-45f8-86bf-38a121a4e65a",
"version": "3.0.0", "version": "3.0.1",
"name": "Nearest Neighbor Classification with Cover Trees", "name": "Nearest Neighbor Classification with Cover Trees",
"description": "Classifier implementing the k-nearest neighbors vote using Cover Trees.\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.", "description": "Classifier implementing the k-nearest neighbors vote using Cover Trees.\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.",
"python_path": "d3m.primitives.classification.cover_tree.Fastlvm", "python_path": "d3m.primitives.classification.cover_tree.Fastlvm",
...@@ -24,7 +24,7 @@ ...@@ -24,7 +24,7 @@
"installation": [ "installation": [
{ {
"type": "PIP", "type": "PIP",
"package_uri": "git+https://github.com/autonlab/fastlvm.git@c77b1413155f4db3b4dea2f99870d155e58322a0#egg=fastlvm" "package_uri": "git+https://github.com/autonlab/fastlvm.git@f3229d5190a6eb5f0b3d20bb3e45f20f49feea92#egg=fastlvm"
} }
], ],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
...@@ -216,5 +216,5 @@ ...@@ -216,5 +216,5 @@
} }
}, },
"structural_type": "fastlvm.covertree_classifier.CoverTreeClassifier", "structural_type": "fastlvm.covertree_classifier.CoverTreeClassifier",
"digest": "cc351533f7f6b7a5546633ef960c991a3c33ab7dd0d2c2b0e1c0cedb4076cc6e" "digest": "3346d6c52e2ad646d95acd68e85b0b08aa9000ce24c27ff34bad65adca95be3c"
} }
{ {
"id": "0fea2402-abac-4a26-bb56-98d021a0b753", "id": "216053cd-f72d-445a-bef7-b317bc766fde",
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"created": "2019-04-29T17:02:28.819341Z", "created": "2019-05-21T18:51:09.394944Z",
"context": "EVALUATION",
"inputs": [ "inputs": [
{ {
"name": "dataset inputs" "name": "dataset inputs"
...@@ -53,7 +52,16 @@ ...@@ -53,7 +52,16 @@
{ {
"id": "produce" "id": "produce"
} }
] ],
"hyperparams": {
"parse_semantic_types": {
"type": "VALUE",
"data": [
"http://schema.org/Integer",
"http://schema.org/Float"
]
}
}
}, },
{ {
"type": "PRIMITIVE", "type": "PRIMITIVE",
...@@ -78,15 +86,8 @@ ...@@ -78,15 +86,8 @@
"semantic_types": { "semantic_types": {
"type": "VALUE", "type": "VALUE",
"data": [ "data": [
"https://metadata.datadrivendiscovery.org/types/Attribute" "http://schema.org/Integer",
] "http://schema.org/Float"
},
"exclude_columns": {
"type": "VALUE",
"data": [
1,
17,
18
] ]
} }
} }
...@@ -143,7 +144,7 @@ ...@@ -143,7 +144,7 @@
"type": "PRIMITIVE", "type": "PRIMITIVE",
"primitive": { "primitive": {
"id": "84f39131-6618-4d90-9590-b79d41dfb093", "id": "84f39131-6618-4d90-9590-b79d41dfb093",
"version": "2.2.0", "version": "2.2.1",
"python_path": "d3m.primitives.classification.search.Find_projections", "python_path": "d3m.primitives.classification.search.Find_projections",
"name": "find projections" "name": "find projections"
}, },
...@@ -187,6 +188,5 @@ ...@@ -187,6 +188,5 @@
} }
] ]
} }
], ]
"pipeline_rank": "1"
} }
\ No newline at end of file
{ {
"id": "84f39131-6618-4d90-9590-b79d41dfb093", "id": "84f39131-6618-4d90-9590-b79d41dfb093",
"version": "2.2.0", "version": "2.2.1",
"name": "find projections", "name": "find projections",
"description": "Class to search for 2-d projection boxes in raw feature space for discrete(categorical) output (for\nclassification problems) . For discrete output, the algorithm tries to find 2-d projection boxes which can\nseparate out any class of data from the rest with high purity.\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.", "description": "Class to search for 2-d projection boxes in raw feature space for discrete(categorical) output (for\nclassification problems) . For discrete output, the algorithm tries to find 2-d projection boxes which can\nseparate out any class of data from the rest with high purity.\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.",
"python_path": "d3m.primitives.classification.search.Find_projections", "python_path": "d3m.primitives.classification.search.Find_projections",
...@@ -31,7 +31,7 @@ ...@@ -31,7 +31,7 @@
}, },
{ {
"type": "PIP", "type": "PIP",
"package_uri": "git+https://github.com/autonlab/find_projections.git@c544c40b49d76a0d99c5c5499dd9e5c156610f72#egg=find_projections" "package_uri": "git+https://github.com/autonlab/find_projections.git@09faa5f89789a0b8ec6b4af7e2e0c979d2fd25b9#egg=find_projections"
} }
], ],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
...@@ -271,5 +271,5 @@ ...@@ -271,5 +271,5 @@
} }
}, },
"structural_type": "find_projections.search_projections.Search", "structural_type": "find_projections.search_projections.Search",
"digest": "2773fa418f16aae21b7a8ef87bf51805ed8c5afad5d9fae9262308ae56cec77d" "digest": "261a1a1c5faf7aafeca93b4e6c3c0d10a56405f02f284f496f11cb2e76ee6e7d"
} }
{ {
"id": "ebcde203-46ef-403c-9f99-9e91234a2026", "id": "e674d53a-8a8a-40dd-b988-7b1f3ffc7cde",
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"created": "2019-04-29T18:55:29.543049Z", "created": "2019-05-21T18:52:13.216586Z",
"context": "EVALUATION",
"inputs": [ "inputs": [
{ {
"name": "dataset inputs" "name": "dataset inputs"
...@@ -53,7 +52,16 @@ ...@@ -53,7 +52,16 @@
{ {
"id": "produce" "id": "produce"
} }
] ],
"hyperparams": {
"parse_semantic_types": {
"type": "VALUE",
"data": [
"http://schema.org/Integer",
"http://schema.org/Float"
]
}
}
}, },
{ {
"type": "PRIMITIVE", "type": "PRIMITIVE",
...@@ -78,15 +86,8 @@ ...@@ -78,15 +86,8 @@
"semantic_types": { "semantic_types": {
"type": "VALUE", "type": "VALUE",
"data": [ "data": [
"https://metadata.datadrivendiscovery.org/types/Attribute" "http://schema.org/Integer",
] "http://schema.org/Float"
},
"exclude_columns": {
"type": "VALUE",
"data": [
1,
17,
18
] ]
} }
} }
...@@ -143,7 +144,7 @@ ...@@ -143,7 +144,7 @@
"type": "PRIMITIVE", "type": "PRIMITIVE",
"primitive": { "primitive": {
"id": "448590e7-8cf6-4bfd-abc4-db2980d8114e", "id": "448590e7-8cf6-4bfd-abc4-db2980d8114e",
"version": "2.2.0", "version": "2.2.1",
"python_path": "d3m.primitives.classification.search_hybrid.Find_projections", "python_path": "d3m.primitives.classification.search_hybrid.Find_projections",
"name": "find projections" "name": "find projections"
}, },
...@@ -187,6 +188,5 @@ ...@@ -187,6 +188,5 @@
} }
] ]
} }
], ]
"pipeline_rank": "1"
} }
\ No newline at end of file
{ {
"id": "448590e7-8cf6-4bfd-abc4-db2980d8114e", "id": "448590e7-8cf6-4bfd-abc4-db2980d8114e",
"version": "2.2.0", "version": "2.2.1",
"name": "find projections", "name": "find projections",
"description": "Class to search for 2-d projection boxes in raw feature space for discrete(categorical) output (for\nclassification problems) . For discrete output, the algorithm tries to find 2-d projection boxes which can\nseparate out any class of data from the rest with high purity.\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.", "description": "Class to search for 2-d projection boxes in raw feature space for discrete(categorical) output (for\nclassification problems) . For discrete output, the algorithm tries to find 2-d projection boxes which can\nseparate out any class of data from the rest with high purity.\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.",
"python_path": "d3m.primitives.classification.search_hybrid.Find_projections", "python_path": "d3m.primitives.classification.search_hybrid.Find_projections",
...@@ -31,7 +31,7 @@ ...@@ -31,7 +31,7 @@
}, },
{ {
"type": "PIP", "type": "PIP",
"package_uri": "git+https://github.com/autonlab/find_projections.git@c544c40b49d76a0d99c5c5499dd9e5c156610f72#egg=find_projections" "package_uri": "git+https://github.com/autonlab/find_projections.git@09faa5f89789a0b8ec6b4af7e2e0c979d2fd25b9#egg=find_projections"
} }
], ],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
...@@ -285,5 +285,5 @@ ...@@ -285,5 +285,5 @@
} }
}, },
"structural_type": "find_projections.search_projections_hybrid.SearchHybrid", "structural_type": "find_projections.search_projections_hybrid.SearchHybrid",
"digest": "aaa898aa9e6d2fe28abda7f55508e1f0bdcc076889594c0869d9b6e0f3332bad" "digest": "70411b701ff36f1b65823a29319720cda82b39cd39b830ccb8936102ecd827bc"
} }
{ {
"id": "f6f8017d-080f-4b88-8dfb-a6b578f96bea", "id": "02e413d7-f5d0-4d5e-90cd-64fb513c9101",
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"created": "2019-04-12T18:22:22.773009Z", "created": "2019-05-21T18:42:36.780590Z",
"context": "EVALUATION",
"inputs": [ "inputs": [
{ {
"name": "dataset inputs" "name": "dataset inputs"
...@@ -80,12 +79,6 @@ ...@@ -80,12 +79,6 @@
"data": [ "data": [
"https://metadata.datadrivendiscovery.org/types/Attribute" "https://metadata.datadrivendiscovery.org/types/Attribute"
] ]
},
"exclude_columns": {
"type": "VALUE",
"data": [
65
]
} }
} }
}, },
...@@ -107,13 +100,23 @@ ...@@ -107,13 +100,23 @@
{ {
"id": "produce" "id": "produce"
} }
] ],
"hyperparams": {
"use_semantic_types": {
"type": "VALUE",
"data": true
},
"return_result": {
"type": "VALUE",
"data": "replace"
}
}
}, },
{ {
"type": "PRIMITIVE", "type": "PRIMITIVE",
"primitive": { "primitive": {
"id": "49af9397-d9a2-450f-93eb-c3b631ba6646", "id": "49af9397-d9a2-450f-93eb-c3b631ba6646",
"version": "3.0.0", "version": "3.0.1",
"python_path": "d3m.primitives.clustering.gmm.Fastlvm", "python_path": "d3m.primitives.clustering.gmm.Fastlvm",
"name": "Gaussian Mixture Models" "name": "Gaussian Mixture Models"
}, },
...@@ -163,6 +166,5 @@ ...@@ -163,6 +166,5 @@
} }
] ]
} }
], ]
"pipeline_rank": "1" }
} \ No newline at end of file
{ {
"id": "49af9397-d9a2-450f-93eb-c3b631ba6646", "id": "49af9397-d9a2-450f-93eb-c3b631ba6646",
"version": "3.0.0", "version": "3.0.1",
"name": "Gaussian Mixture Models", "name": "Gaussian Mixture Models",
"description": "This class provides functionality for unsupervised inference on Gaussian mixture model, which is a probabilistic\nmodel that assumes all the data points are generated from a mixture of a finite number of Gaussian distributions\nwith unknown parameters. It can be viewed as a generalization of the K-Means clustering to incorporate\ninformation about the covariance structure of the data. Standard packages, like those in scikit learn run on a\nsingle machine and often only on one thread. Whereas our underlying C++ implementation can be distributed to run\non multiple machines. To enable the distribution through python interface is work in progress. In this class,\nwe implement inference on (Bayesian) Gaussian mixture models using Canopy algorithm. The API is similar to\nsklearn.mixture.GaussianMixture. The class is pickle-able.\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.", "description": "This class provides functionality for unsupervised inference on Gaussian mixture model, which is a probabilistic\nmodel that assumes all the data points are generated from a mixture of a finite number of Gaussian distributions\nwith unknown parameters. It can be viewed as a generalization of the K-Means clustering to incorporate\ninformation about the covariance structure of the data. Standard packages, like those in scikit learn run on a\nsingle machine and often only on one thread. Whereas our underlying C++ implementation can be distributed to run\non multiple machines. To enable the distribution through python interface is work in progress. In this class,\nwe implement inference on (Bayesian) Gaussian mixture models using Canopy algorithm. The API is similar to\nsklearn.mixture.GaussianMixture. The class is pickle-able.\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.",
"python_path": "d3m.primitives.clustering.gmm.Fastlvm", "python_path": "d3m.primitives.clustering.gmm.Fastlvm",
...@@ -23,7 +23,7 @@ ...@@ -23,7 +23,7 @@
"installation": [ "installation": [
{ {
"type": "PIP", "type": "PIP",
"package_uri": "git+https://github.com/autonlab/fastlvm.git@c77b1413155f4db3b4dea2f99870d155e58322a0#egg=fastlvm" "package_uri": "git+https://github.com/autonlab/fastlvm.git@f3229d5190a6eb5f0b3d20bb3e45f20f49feea92#egg=fastlvm"
} }
], ],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
...@@ -240,5 +240,5 @@ ...@@ -240,5 +240,5 @@
} }
}, },
"structural_type": "fastlvm.gmm.GMM", "structural_type": "fastlvm.gmm.GMM",
"digest": "56c87c821d1e239b2dbc0b82b9c922dfc38336f02bcdc0de3253eedaed7ab44d" "digest": "1c18b0887841096424a199a9adf13dc95f5c3c34500114bb16cb2cc58f3aabdd"
} }
{ {
"id": "f3ac5b88-decf-4dd1-bee7-aedb4c1950a6", "id": "971902a2-71a5-43e8-a594-1f30e91b6ffb",
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"created": "2019-04-12T18:33:08.202953Z", "created": "2019-05-21T18:45:10.617865Z",
"context": "EVALUATION",
"inputs": [ "inputs": [
{ {
"name": "dataset inputs" "name": "dataset inputs"
...@@ -80,12 +79,6 @@ ...@@ -80,12 +79,6 @@
"data": [ "data": [
"https://metadata.datadrivendiscovery.org/types/Attribute" "https://metadata.datadrivendiscovery.org/types/Attribute"
] ]
},
"exclude_columns": {
"type": "VALUE",
"data": [
65
]
} }
} }
}, },
...@@ -107,13 +100,23 @@ ...@@ -107,13 +100,23 @@
{ {
"id": "produce" "id": "produce"
} }
] ],
"hyperparams": {
"use_semantic_types": {
"type": "VALUE",
"data": true
},
"return_result": {
"type": "VALUE",
"data": "replace"
}
}
}, },
{ {
"type": "PRIMITIVE", "type": "PRIMITIVE",
"primitive": { "primitive": {
"id": "66c3bb07-63f7-409e-9f0f-5b07fbf7cd8e", "id": "66c3bb07-63f7-409e-9f0f-5b07fbf7cd8e",
"version": "3.0.0", "version": "3.0.1",
"python_path": "d3m.primitives.clustering.k_means.Fastlvm", "python_path": "d3m.primitives.clustering.k_means.Fastlvm",
"name": "K-means Clustering" "name": "K-means Clustering"
}, },
...@@ -159,6 +162,5 @@ ...@@ -159,6 +162,5 @@
} }
] ]
} }
], ]
"pipeline_rank": "1" }
} \ No newline at end of file
{ {
"id": "66c3bb07-63f7-409e-9f0f-5b07fbf7cd8e", "id": "66c3bb07-63f7-409e-9f0f-5b07fbf7cd8e",
"version": "3.0.0", "version": "3.0.1",
"name": "K-means Clustering", "name": "K-means Clustering",
"description": "This class provides functionality for unsupervised clustering, which according to Wikipedia is 'the task of\ngrouping a set of objects in such a way that objects in the same group (called a cluster) are more similar to\neach other than to those in other groups'. It is a main task of exploratory data mining, and a common technique\nfor statistical data analysis. The similarity measure can be, in general, any metric measure: standard Euclidean\ndistance is the most common choice and the one currently implemented. In future, adding other metrics should not\nbe too difficult. Standard packages, like those in scikit learn run on a single machine and often only on one\nthread. Whereas our underlying C++ implementation can be distributed to run on multiple machines. To enable the\ndistribution through python interface is work in progress. In this class, we implement a K-Means clustering using\nLlyod's algorithm and speed-up using Cover Trees. The API is similar to sklearn.cluster.KMeans. The class is\npickle-able.\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.", "description": "This class provides functionality for unsupervised clustering, which according to Wikipedia is 'the task of\ngrouping a set of objects in such a way that objects in the same group (called a cluster) are more similar to\neach other than to those in other groups'. It is a main task of exploratory data mining, and a common technique\nfor statistical data analysis. The similarity measure can be, in general, any metric measure: standard Euclidean\ndistance is the most common choice and the one currently implemented. In future, adding other metrics should not\nbe too difficult. Standard packages, like those in scikit learn run on a single machine and often only on one\nthread. Whereas our underlying C++ implementation can be distributed to run on multiple machines. To enable the\ndistribution through python interface is work in progress. In this class, we implement a K-Means clustering using\nLlyod's algorithm and speed-up using Cover Trees. The API is similar to sklearn.cluster.KMeans. The class is\npickle-able.\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.",
"python_path": "d3m.primitives.clustering.k_means.Fastlvm", "python_path": "d3m.primitives.clustering.k_means.Fastlvm",
...@@ -23,7 +23,7 @@ ...@@ -23,7 +23,7 @@
"installation": [ "installation": [
{ {
"type": "PIP", "type": "PIP",
"package_uri": "git+https://github.com/autonlab/fastlvm.git@c77b1413155f4db3b4dea2f99870d155e58322a0#egg=fastlvm" "package_uri": "git+https://github.com/autonlab/fastlvm.git@f3229d5190a6eb5f0b3d20bb3e45f20f49feea92#egg=fastlvm"
} }
], ],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
...@@ -240,5 +240,5 @@ ...@@ -240,5 +240,5 @@
} }
}, },
"structural_type": "fastlvm.kmeans.KMeans", "structural_type": "fastlvm.kmeans.KMeans",
"digest": "7ece7c8e3ebd8696eb17139485697c52149eef39730dba176a7aee221e721a4a" "digest": "8a0784246835d7258eb3622f548662c5c61d8221f432d25d01f68dd1437e469f"
} }
{ {
"id": "71eaa234-f8b6-4fce-a849-64a7404b0723", "id": "51e27d46-fd25-4c47-a6cf-1d3885a7b7df",
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json", "schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"created": "2019-04-30T20:49:47.330195Z", "created": "2019-05-21T18:39:14.563729Z",
"context": "EVALUATION",
"inputs": [ "inputs": [
{ {
"name": "dataset inputs" "name": "dataset inputs"
...@@ -87,7 +86,7 @@ ...@@ -87,7 +86,7 @@
"type": "PRIMITIVE", "type": "PRIMITIVE",
"primitive": { "primitive": {
"id": "a3d490a4-ef39-4de1-be02-4c43726b3b24", "id": "a3d490a4-ef39-4de1-be02-4c43726b3b24",
"version": "3.0.0", "version": "3.0.1",
"python_path": "d3m.primitives.natural_language_processing.glda.Fastlvm", "python_path": "d3m.primitives.natural_language_processing.glda.Fastlvm",
"name": "Gaussian Latent Dirichlet Allocation Topic Modelling"