Commit c2f4ba67 authored by Donghan Wang's avatar Donghan Wang

enhancement and add pipeline example

parent b2561e38
{
"id": "5f1a456f-a888-441d-8811-c959036b95e3",
"schema": "https://metadata.datadrivendiscovery.org/schemas/v0/pipeline.json",
"created": "2019-05-30T20:47:21.287174Z",
"inputs": [
{
"name": "dataset 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"
},
"arguments": {
"inputs": {
"type": "CONTAINER",
"data": "inputs.0"
}
},
"outputs": [
{
"id": "produce"
}
]
},
{
"type": "PRIMITIVE",
"primitive": {
"id": "d510cb7a-1782-4f51-b44c-58f0236e47c7",
"version": "0.5.0",
"python_path": "d3m.primitives.data_transformation.column_parser.DataFrameCommon",
"name": "Parses strings into their types"
},
"arguments": {
"inputs": {
"type": "CONTAINER",
"data": "steps.0.produce"
}
},
"outputs": [
{
"id": "produce"
}
]
},
{
"type": "PRIMITIVE",
"primitive": {
"id": "4503a4c6-42f7-45a1-a1d4-ed69699cf5e1",
"version": "0.2.0",
"python_path": "d3m.primitives.data_transformation.extract_columns_by_semantic_types.DataFrameCommon",
"name": "Extracts columns by semantic type"
},
"arguments": {
"inputs": {
"type": "CONTAINER",
"data": "steps.1.produce"
}
},
"outputs": [
{
"id": "produce"
}
],
"hyperparams": {
"semantic_types": {
"type": "VALUE",
"data": [
"https://metadata.datadrivendiscovery.org/types/Attribute"
]
}
}
},
{
"type": "PRIMITIVE",
"primitive": {
"id": "d016df89-de62-3c53-87ed-c06bb6a23cde",
"version": "2019.4.4",
"python_path": "d3m.primitives.data_cleaning.imputer.SKlearn",
"name": "sklearn.impute.SimpleImputer"
},
"arguments": {
"inputs": {
"type": "CONTAINER",
"data": "steps.2.produce"
}
},
"outputs": [
{
"id": "produce"
}
]
},
{
"type": "PRIMITIVE",
"primitive": {
"id": "4503a4c6-42f7-45a1-a1d4-ed69699cf5e1",
"version": "0.2.0",
"python_path": "d3m.primitives.data_transformation.extract_columns_by_semantic_types.DataFrameCommon",
"name": "Extracts columns by semantic type"
},
"arguments": {
"inputs": {
"type": "CONTAINER",
"data": "steps.1.produce"
}
},
"outputs": [
{
"id": "produce"
}
],
"hyperparams": {
"semantic_types": {
"type": "VALUE",
"data": [
"https://metadata.datadrivendiscovery.org/types/TrueTarget"
]
}
}
},
{
"type": "PRIMITIVE",
"primitive": {
"id": "6bb5824f-cf16-4615-8643-8c1758bd6751",
"version": "0.1.0",
"python_path": "d3m.primitives.semisupervised_classification.iterative_labeling.AutonBox",
"name": "Iterative labeling for semi-supervised learning"
},
"arguments": {
"inputs": {
"type": "CONTAINER",
"data": "steps.3.produce"
},
"outputs": {
"type": "CONTAINER",
"data": "steps.4.produce"
}
},
"outputs": [
{
"id": "produce"
}
]
},
{
"type": "PRIMITIVE",
"primitive": {
"id": "8d38b340-f83f-4877-baaa-162f8e551736",
"version": "0.3.0",
"python_path": "d3m.primitives.data_transformation.construct_predictions.DataFrameCommon",
"name": "Construct pipeline predictions output"
},
"arguments": {
"inputs": {
"type": "CONTAINER",
"data": "steps.5.produce"
},
"reference": {
"type": "CONTAINER",
"data": "steps.0.produce"
}
},
"outputs": [
{
"id": "produce"
}
]
}
]
}
\ No newline at end of file
{
"problem": "SEMI_1053_jm1_problem",
"full_inputs": [
"SEMI_1053_jm1_dataset"
],
"train_inputs": [
"SEMI_1053_jm1_dataset_TRAIN"
],
"test_inputs": [
"SEMI_1053_jm1_dataset_TEST"
],
"score_inputs": [
"SEMI_1053_jm1_dataset_SCORE"
]
}
\ No newline at end of file
......@@ -14,7 +14,7 @@
"installation": [
{
"type": "PIP",
"package_uri": "git+https://github.com/autonlab/[email protected]f2b26c01e465e7036667a9130a490562ce41d0f8#egg=autonbox"
"package_uri": "git+https://github.com/autonlab/[email protected]72bcbcce3efb1483f9081c9d20bb792e9812bbfc#egg=autonbox"
}
],
"algorithm_types": [
......@@ -36,6 +36,32 @@
"base.PrimitiveBase"
],
"hyperparams": {
"iters": {
"type": "d3m.metadata.hyperparams.UniformInt",
"default": 5,
"structural_type": "int",
"semantic_types": [
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
"description": "The number of iterations of labeling",
"lower": 1,
"upper": 100,
"lower_inclusive": true,
"upper_inclusive": false
},
"frac": {
"type": "d3m.metadata.hyperparams.Uniform",
"default": 0.2,
"structural_type": "float",
"semantic_types": [
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
"description": "The fraction of unlabeled item to label",
"lower": 0.01,
"upper": 1.0,
"lower_inclusive": true,
"upper_inclusive": false
},
"blackbox": {
"type": "d3m.metadata.hyperparams.Primitive",
"default": "sklearn_wrap.SKRandomForestClassifier.SKRandomForestClassifier",
......@@ -43,7 +69,7 @@
"semantic_types": [
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
"description": "Black box model for the classification.",
"description": "Black box model for the classification",
"primitive_families": [
"CLASSIFICATION"
],
......@@ -192,5 +218,5 @@
}
},
"structural_type": "autonbox.iterative_labeling.IterativeLabelingPrimitive",
"digest": "080ad44552bd00f25e8ca145a07c8a44ff83ca0861f0521c17de37c1979ae843"
"digest": "855fc8f63be5cc58c5e5b8f60d5f5da9c6c81db0e46146266d0f1897bb135304"
}
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment