Commit 91ed2649 authored by Sujen's avatar Sujen

Disable failing primitives

parent 470ac942
......@@ -20,7 +20,7 @@
},
{
"type": "PIP",
"package_uri": "git+https://github.com/NewKnowledge/TimeSeries-D3M-Wrappers.git@e5355acdc8f1b497bf72c25120a03f47fd48ff42#egg=TimeSeriesD3MWrappers"
"package_uri": "git+https://github.com/NewKnowledge/TimeSeries-D3M-Wrappers.git@b7754221711e18a64d23477e5508acc5e421aae3#egg=TimeSeriesD3MWrappers"
}
],
"python_path": "d3m.primitives.clustering.hdbscan.Hdbscan",
......@@ -242,5 +242,5 @@
},
"structural_type": "TimeSeriesD3MWrappers.Hdbscan.Hdbscan",
"description": "Produce primitive's best guess for the cluster number of each series using Hierarchical Density-Based\nClustering or Density-Based Clustering.\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": "8717c01d00f929384879113d87c88a38212bba0fc9828d1cf3de1e50718378f0"
"digest": "ed909476fae52b8982b40b4a8b279272fce0af5fd557465a7c6d55ea4e1456f0"
}
......@@ -21,7 +21,7 @@
},
{
"type": "PIP",
"package_uri": "git+https://github.com/NewKnowledge/TimeSeries-D3M-Wrappers.git@e5355acdc8f1b497bf72c25120a03f47fd48ff42#egg=TimeSeriesD3MWrappers"
"package_uri": "git+https://github.com/NewKnowledge/TimeSeries-D3M-Wrappers.git@b7754221711e18a64d23477e5508acc5e421aae3#egg=TimeSeriesD3MWrappers"
}
],
"python_path": "d3m.primitives.clustering.k_means.Sloth",
......@@ -225,5 +225,5 @@
},
"structural_type": "TimeSeriesD3MWrappers.Storc.Storc",
"description": "Produce primitive's best guess for the cluster number of each series.\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": "d12bc3e491b082b5f50f8de5ec62672be9141cfc01c21f7c75eedb67c4bee784"
"digest": "90ddd22a63c24c82e7b21d0ecce2974fa5af4a37413f4971e6eaafe73146befb"
}
......@@ -20,7 +20,7 @@
},
{
"type": "PIP",
"package_uri": "git+https://github.com/NewKnowledge/TimeSeries-D3M-Wrappers.git@e5355acdc8f1b497bf72c25120a03f47fd48ff42#egg=TimeSeriesD3MWrappers"
"package_uri": "git+https://github.com/NewKnowledge/TimeSeries-D3M-Wrappers.git@b7754221711e18a64d23477e5508acc5e421aae3#egg=TimeSeriesD3MWrappers"
}
],
"python_path": "d3m.primitives.time_series_classification.k_neighbors.Kanine",
......@@ -211,5 +211,5 @@
},
"structural_type": "TimeSeriesD3MWrappers.Kanine.Kanine",
"description": "Produce primitive's classifications for new time series data. The input is a numpy ndarray of\nsize (number_of_time_series, time_series_length) containing new time series.\nThe output is a numpy ndarray containing a predicted class for each of the input time series.\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": "c9a5c50be81181f5e54593a3f240296341d50a3e54f0e328a4ffb4324988419b"
"digest": "2f12df11dd31f482c3c7434187af483c7307a46b508e0466166ec5fef2450a7b"
}
......@@ -21,7 +21,7 @@
},
{
"type": "PIP",
"package_uri": "git+https://github.com/NewKnowledge/TimeSeries-D3M-Wrappers.git@e5355acdc8f1b497bf72c25120a03f47fd48ff42#egg=TimeSeriesD3MWrappers"
"package_uri": "git+https://github.com/NewKnowledge/TimeSeries-D3M-Wrappers.git@b7754221711e18a64d23477e5508acc5e421aae3#egg=TimeSeriesD3MWrappers"
}
],
"python_path": "d3m.primitives.time_series_classification.shapelet_learning.Shallot",
......@@ -264,5 +264,5 @@
},
"structural_type": "TimeSeriesD3MWrappers.Shallot.Shallot",
"description": "Produce primitive's classifications for new time series data The input is a numpy ndarray of\nsize (number_of_time_series, time_series_length, dimension) containing new time series.\nThe output is a numpy ndarray containing a predicted class for each of the input time series.\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": "76e69522530c33c1d16b771d35e72b963695c431ab3f90417ab3e84e351255a4"
"digest": "126990bec4e240f11bd81e703c8bbd30b00d556feb3abd4434322036756b1a07"
}
......@@ -20,7 +20,7 @@
},
{
"type": "PIP",
"package_uri": "git+https://github.com/NewKnowledge/TimeSeries-D3M-Wrappers.git@e5355acdc8f1b497bf72c25120a03f47fd48ff42#egg=TimeSeriesD3MWrappers"
"package_uri": "git+https://github.com/NewKnowledge/TimeSeries-D3M-Wrappers.git@b7754221711e18a64d23477e5508acc5e421aae3#egg=TimeSeriesD3MWrappers"
}
],
"python_path": "d3m.primitives.time_series_forecasting.arima.Parrot",
......@@ -233,5 +233,5 @@
},
"structural_type": "TimeSeriesD3MWrappers.Parrot.Parrot",
"description": "Produce the primitive's prediction for future time series data. The output\nis a list of length 'n_periods' that contains a prediction for each of 'n_periods'\nfuture time periods. 'n_periods' is a hyperparameter that must be set before making the prediction.\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": "14f5afe8bcee2b9f8297e5b9db472afca52bdb38cecd103dfa5abc3ca2bd6776"
"digest": "a38044e7524ba6f66923efae1f80ceeb7b0179b1ecf90bb0d20c59d0f933d2b8"
}
......@@ -20,7 +20,7 @@
},
{
"type": "PIP",
"package_uri": "git+https://github.com/NewKnowledge/TimeSeries-D3M-Wrappers.git@e5355acdc8f1b497bf72c25120a03f47fd48ff42#egg=TimeSeriesD3MWrappers"
"package_uri": "git+https://github.com/NewKnowledge/TimeSeries-D3M-Wrappers.git@b7754221711e18a64d23477e5508acc5e421aae3#egg=TimeSeriesD3MWrappers"
}
],
"python_path": "d3m.primitives.time_series_forecasting.vector_autoregression.VAR",
......@@ -316,5 +316,5 @@
},
"structural_type": "TimeSeriesD3MWrappers.VAR.VAR",
"description": "Produce primitive's prediction for future time series data. The output is a data frame containing the d3m index and a\nforecast for each of the 'n_periods' future time periods, modified if desired by the 'interval' HP. The default is a\nfuture forecast for each of the selected input variables. This can be modified to just one output variable with\nthe associated 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": "ed62e7e2e49fe0bb0e3885efa275ddd73145d7373d37630d2a0d8b5747e9406f"
"digest": "f14c9e2804affdb14d8a71cb21dfb26e6eba8c0da22faf05094bacc1056dd889"
}
......@@ -23,7 +23,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@cae151551eb33219338b725cd5543bca4e5dbceb#egg=dsbox-primitives"
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@be7fde1416f3de3644ffba84efda207e4cfc4373#egg=dsbox-primitives"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
......@@ -215,5 +215,5 @@
}
},
"structural_type": "dsbox.datapreprocessing.cleaner.wikifier.Wikifier",
"digest": "ea4a704a34cbe1155909ebebc9a8d4d25c568374bdbe1fddd5fcefe9a25b8428"
"digest": "cdb0d66d7ac1edbebad40e39d7da3269a6ef7f38c3a55131660b793ccbe3997a"
}
{
"problem":"196_autoMpg_problem",
"full_inputs":[
"196_autoMpg_dataset"
],
"train_inputs":[
"196_autoMpg_dataset_TRAIN"
],
"test_inputs":[
"196_autoMpg_dataset_TEST"
],
"score_inputs":[
"196_autoMpg_dataset_SCORE"
]
}
\ No newline at end of file
{
"problem":"38_sick_problem",
"full_inputs":[
"38_sick_dataset"
],
"train_inputs":[
"38_sick_dataset_TRAIN"
],
"test_inputs":[
"38_sick_dataset_TEST"
],
"score_inputs":[
"38_sick_dataset_SCORE"
]
}
\ No newline at end of file
......@@ -2,7 +2,6 @@
"id": "dsbox-cleaning-featurizer",
"version": "1.5.0",
"name": "DSBox Cleaning Featurizer",
"description": "A base class for primitives which have to be fitted before they can start\nproducing (useful) outputs from inputs, but they are fitted only on input data.\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.data_cleaning.cleaning_featurizer.DSBOX",
"primitive_family": "DATA_CLEANING",
"algorithm_types": [
......@@ -25,7 +24,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@cae151551eb33219338b725cd5543bca4e5dbceb#egg=dsbox-primitives"
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@be7fde1416f3de3644ffba84efda207e4cfc4373#egg=dsbox-primitives"
}
],
"location_uris": [],
......@@ -298,5 +297,6 @@
}
},
"structural_type": "dsbox.datapreprocessing.cleaner.cleaning_featurizer.CleaningFeaturizer",
"digest": "2524e6ded9f5d5a74d42ec1d920c60fbbd098cb2884bf2f908db3a35979392bf"
"description": "A cleaning featurizer for imperfect data. Capabilities of this featurizer include:\n\n+ Split a column with compound string values (e.g. \"118,32\") to multiple columns.\n+ Split a date column into year, month, day, day-of-week.\n+ Split American phone number column into area code, prefix, and number.\n+ Split alphanumeric columns into multiple columns.\n\nThis primitive requires d3m.primitives.schema_discovery.profiler.DSBOX profiler.\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": "e803fecc4763199d228e7922b28f3c714732f7a29752219d6af80dccba9ac322"
}
......@@ -2,7 +2,6 @@
"id": "dsbox-fold-columns",
"version": "1.5.0",
"name": "DSBox Fold Columns",
"description": "A base class for primitives which have to be fitted before they can start\nproducing (useful) outputs from inputs, but they are fitted only on input data.\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.data_cleaning.column_fold.DSBOX",
"primitive_family": "DATA_CLEANING",
"algorithm_types": [
......@@ -21,7 +20,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@cae151551eb33219338b725cd5543bca4e5dbceb#egg=dsbox-primitives"
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@be7fde1416f3de3644ffba84efda207e4cfc4373#egg=dsbox-primitives"
}
],
"location_uris": [],
......@@ -176,5 +175,6 @@
}
},
"structural_type": "dsbox.datapreprocessing.cleaner.column_fold.FoldColumns",
"digest": "c283410ab5da518f2cff644f32cd4f6c6779891116021569cde4e3a351ea3379"
"description": "A column folding primitive for imperfect data. Fold multiple columns into one column based on common column name prefix.\nFor example, columns with names 'month-jan', 'month-feb', 'month-mar' and so on are folded into one column named 'month'.\"\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": "d048db8b1ee12039574b5ffa314a479fdce648af9e05b6dde47b72d62bc1057c"
}
{
"problem":"38_sick_problem",
"full_inputs":[
"38_sick_dataset"
],
"train_inputs":[
"38_sick_dataset_TRAIN"
],
"test_inputs":[
"38_sick_dataset_TEST"
],
"score_inputs":[
"38_sick_dataset_SCORE"
]
}
\ No newline at end of file
{
"problem":"196_autoMpg_problem",
"full_inputs":[
"196_autoMpg_dataset"
],
"train_inputs":[
"196_autoMpg_dataset_TRAIN"
],
"test_inputs":[
"196_autoMpg_dataset_TEST"
],
"score_inputs":[
"196_autoMpg_dataset_SCORE"
]
}
\ No newline at end of file
......@@ -2,7 +2,7 @@
"id": "18f0bb42-6350-3753-8f2d-d1c3da70f279",
"version": "1.5.0",
"name": "ISI DSBox Data Encoder",
"description": "An one-hot encoder, which\n1. n_limit: max number of distinct values to one-hot encode,\n remaining values with fewer occurence are put in [colname]_other_ column.\n\n2. feed in data by set_training_data, then apply fit() function to tune the encoder.\n\n3. produce(): input data would be encoded and return.\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": "A robust one-hot encoder. Missing values are encoded as an additional column. Use hyperparamter n_limit to limit the\nmaximum number of column generated. If n_limit>0, then only the top n_limit most frequent values are encoded into\ncolumns. the rest of the values are encoded into a single column.\"\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.data_preprocessing.encoder.DSBOX",
"primitive_family": "DATA_PREPROCESSING",
"algorithm_types": [
......@@ -22,7 +22,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@cae151551eb33219338b725cd5543bca4e5dbceb#egg=dsbox-primitives"
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@be7fde1416f3de3644ffba84efda207e4cfc4373#egg=dsbox-primitives"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
......@@ -49,7 +49,7 @@
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
"description": "Limits the maximum number of columns generated from a single categorical column",
"lower": 5,
"lower": 0,
"upper": 100,
"lower_inclusive": true,
"upper_inclusive": false
......@@ -258,5 +258,5 @@
}
},
"structural_type": "dsbox.datapreprocessing.cleaner.encoder.Encoder",
"digest": "c4a4be66bb5fe3aec2d3526dbce5675f9c37fec9f9839a6bb60e41411b6a16c2"
"digest": "15a5e918863c0113f8b842d6f42581b498a9a6590b7ca5d6bc5659655d5048f2"
}
......@@ -22,7 +22,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@cae151551eb33219338b725cd5543bca4e5dbceb#egg=dsbox-primitives"
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@be7fde1416f3de3644ffba84efda207e4cfc4373#egg=dsbox-primitives"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
......@@ -188,5 +188,5 @@
}
},
"structural_type": "dsbox.datapostprocessing.ensemble_voting.EnsembleVoting",
"digest": "325b41979e137d7cd8b1e0848e376f966f962437a436338faf9da3051c5f2a29"
"digest": "e049b97fd05a40195a0adca89bd233a35f5429ef40c7818b2b770cce6bb9d0f6"
}
......@@ -2,7 +2,7 @@
"id": "ebebb1fa-a20c-38b9-9f22-bc92bc548c19",
"version": "1.5.0",
"name": "DSBox Greedy Imputer",
"description": "Impute the missing value by greedy search of the combinations of standalone simple imputation method.\n\nParameters:\n----------\nverbose: bool\n Control the verbosity\n\nAttributes:\n----------\nimputation_strategies: list of string,\n each is a standalone simple imputation method\n\nbest_imputation: dict. key: column name; value: trained imputation method (parameters)\n which is one of the imputation_strategies\n\nmodel: a sklearn machine learning class\n The machine learning model that will be used to evaluate the imputation strategies\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": "Use greedy search to impute missing values by finding the best simple imputation method for each column.\nThe simple imputation methods include mean, min, max, and zero.\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.data_preprocessing.greedy_imputation.DSBOX",
"primitive_family": "DATA_PREPROCESSING",
"algorithm_types": [
......@@ -23,7 +23,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@cae151551eb33219338b725cd5543bca4e5dbceb#egg=dsbox-primitives"
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@be7fde1416f3de3644ffba84efda207e4cfc4373#egg=dsbox-primitives"
}
],
"location_uris": [],
......@@ -263,5 +263,5 @@
}
},
"structural_type": "dsbox.datapreprocessing.cleaner.greedy.GreedyImputation",
"digest": "cfd06b18d086d2876489dfbb5eb445c8384a2ae2b68809915bc1e6f9e8b845f9"
"digest": "e730ae35c8ef13930dc87c197376ccb8d9b9a597442019fb7b1c55aa3b2db2d2"
}
......@@ -22,7 +22,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@cae151551eb33219338b725cd5543bca4e5dbceb#egg=dsbox-primitives"
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@be7fde1416f3de3644ffba84efda207e4cfc4373#egg=dsbox-primitives"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
......@@ -220,5 +220,5 @@
}
},
"structural_type": "dsbox.datapostprocessing.horizontal_concat.HorizontalConcat",
"digest": "b1c21f90adf0597000bfaf14db7c0a0c5cdf80b2adf98bdaf615c60c9d876796"
"digest": "cc0d994737e72e6e7b996435f165a7a81a56a08887acc7273c5ec8821cee2c35"
}
......@@ -2,7 +2,7 @@
"id": "f70b2324-1102-35f7-aaf6-7cd8e860acc4",
"version": "1.5.0",
"name": "DSBox Iterative Regression Imputer",
"description": "Impute the missing value by iteratively regress using other attributes.\n It will fit and fill the missing value in the training set, and store the learned models.\n In the `produce` phase, it will use the learned models to iteratively regress on the\n testing data again, and return the imputed testing data.\n\nParameters:\n----------\nverbose: bool\n Control the verbosity\n\nAttributes:\n----------\nbest_imputation: dict. key: column name; value: trained imputation method (parameters)\n could be sklearn regression model, or \"mean\" (which means the regression failed)\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": "Impute the missing value by iteratively regress using other attributes. It will fit and fill the missing value in\nthe training set, and store the learned models. In the `produce` phase, it will use the learned models to\niteratively regress on the testing data again, and return the imputed testing data.\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.data_preprocessing.iterative_regression_imputation.DSBOX",
"primitive_family": "DATA_PREPROCESSING",
"algorithm_types": [
......@@ -22,7 +22,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@cae151551eb33219338b725cd5543bca4e5dbceb#egg=dsbox-primitives"
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@be7fde1416f3de3644ffba84efda207e4cfc4373#egg=dsbox-primitives"
}
],
"location_uris": [],
......@@ -260,5 +260,5 @@
}
},
"structural_type": "dsbox.datapreprocessing.cleaner.iterative_regression.IterativeRegressionImputation",
"digest": "ea9efe5e9c0e77a9ef0792ad01bfc9e4c4f902d83d8d7f6a8611f7d668ac285f"
"digest": "97958068e8d862cc95fa18d463975b97b4e2816712be139db5a7c93ae4782fa7"
}
{
"problem":"38_sick_problem",
"full_inputs":[
"38_sick_dataset"
],
"train_inputs":[
"38_sick_dataset_TRAIN"
],
"test_inputs":[
"38_sick_dataset_TEST"
],
"score_inputs":[
"38_sick_dataset_SCORE"
]
}
\ No newline at end of file
{
"problem":"196_autoMpg_problem",
"full_inputs":[
"196_autoMpg_dataset"
],
"train_inputs":[
"196_autoMpg_dataset_TRAIN"
],
"test_inputs":[
"196_autoMpg_dataset_TEST"
],
"score_inputs":[
"196_autoMpg_dataset_SCORE"
]
}
\ No newline at end of file
......@@ -23,7 +23,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@cae151551eb33219338b725cd5543bca4e5dbceb#egg=dsbox-primitives"
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@be7fde1416f3de3644ffba84efda207e4cfc4373#egg=dsbox-primitives"
}
],
"location_uris": [],
......@@ -259,5 +259,5 @@
}
},
"structural_type": "dsbox.datapreprocessing.cleaner.mean.MeanImputation",
"digest": "3ba62e287acca259a5c36f6b4149496938dd4d99e7914f9c0ea6038242d5a767"
"digest": "7652ac2e71988a06a904dd5f424ce4176e5a789563b47d9993839256746b90d8"
}
......@@ -22,7 +22,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@cae151551eb33219338b725cd5543bca4e5dbceb#egg=dsbox-primitives"
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@be7fde1416f3de3644ffba84efda207e4cfc4373#egg=dsbox-primitives"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
......@@ -239,5 +239,5 @@
}
},
"structural_type": "dsbox.datapreprocessing.cleaner.splitter.Splitter",
"digest": "dea95c25f5a7d95fffecc09c0c64012414703380c549b2dea94bb423c0f829d9"
"digest": "2e98ab02ff12f285e4ccda1ad2b688e76f427ff60e5a3c6d264c0dcfc99f1daf"
}
......@@ -22,7 +22,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@cae151551eb33219338b725cd5543bca4e5dbceb#egg=dsbox-primitives"
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@be7fde1416f3de3644ffba84efda207e4cfc4373#egg=dsbox-primitives"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
......@@ -258,5 +258,5 @@
}
},
"structural_type": "dsbox.datapreprocessing.cleaner.unary_encoder.UnaryEncoder",
"digest": "21feb349f7a57669a4622b8bb0247a2ad1eadbe1e9f1656cac46f92edbdbd114"
"digest": "13d6fd22b0f774c4524ce64c0d5bd11d66771253eae05e45ba12413f7474b51e"
}
......@@ -21,7 +21,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@cae151551eb33219338b725cd5543bca4e5dbceb#egg=dsbox-primitives"
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@be7fde1416f3de3644ffba84efda207e4cfc4373#egg=dsbox-primitives"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
......@@ -198,5 +198,5 @@
}
},
"structural_type": "dsbox.datapostprocessing.unfold.Unfold",
"digest": "a8e09be1a83c5d1d3099b372d0e24ec74cf2d58ca974d42321b65f6acacc5166"
"digest": "883928e8a0c5ded8f7d1292bca7a1072f44d6b717755d0e12553370625273bf8"
}
......@@ -22,7 +22,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@cae151551eb33219338b725cd5543bca4e5dbceb#egg=dsbox-primitives"
"package_uri": "git+https://github.com/usc-isi-i2/dsbox-primitives@be7fde1416f3de3644ffba84efda207e4cfc4373#egg=dsbox-primitives"
}
],
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/primitive.json",
......@@ -199,5 +199,5 @@
}
},
"structural_type": "dsbox.datapostprocessing.vertical_concat.VerticalConcat",
"digest": "ea0b4bf986018c75a8d0d83264db9f7c095e7a3ff0258a07a3d52b8a22d1246d"
"digest": "2c03d5303d05a7f7b6edfe13c6efb2903c7ba338ee4a45c51d91eacd5ce37d87"
}
{
"problem":"38_sick_problem",
"full_inputs":[
"38_sick_dataset"
],
"train_inputs":[
"38_sick_dataset_TRAIN"
],
"test_inputs":[
"38_sick_dataset_TEST"
],
"score_inputs":[
"38_sick_dataset_SCORE"
]
}
\ No newline at end of file
{
"problem":"196_autoMpg_problem",
"full_inputs":[
"196_autoMpg_dataset"
],
"train_inputs":[
"196_autoMpg_dataset_TRAIN"
],
"test_inputs":[
"196_autoMpg_dataset_TEST"
],
"score_inputs":[
"196_autoMpg_dataset_SCORE"
]
}
\ No newline at end of file
{
"problem":"38_sick_problem",
"full_inputs":[
"38_sick_dataset"
],
"train_inputs":[
"38_sick_dataset_TRAIN"
],
"test_inputs":[
"38_sick_dataset_TEST"
],
"score_inputs":[
"38_sick_dataset_SCORE"
]
}
\ No newline at end of file
{
"id":"9e8b9c35-b25f-4fdc-a1e5-59d55120fbba",
"schema":"https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"created":"2019-05-16T20:50:19.270783Z",
"inputs":[
{
"name":"input dataset"
}
],
"outputs":[
{
"data":"steps.6.produce",
"name":"predictions of input dataset"
}