Extracting features importance #71
Description
- MLBlocks version: '0.2.0'
- Python version: Python 3.6.3
- Operating System: MacOS High Sierra
Description
I have been trying to produce the features importance from a classifier (RandomForrest). The feature_importances function doesn't take arguments. So, the MLPipeline doesn't execute (TypeError: 'numpy.ndarray' object is not callable).
What I Did
I left the arguments empty in the primitive definition file in the produce part.
{
"name": "sklearn.ensemble.RandomForestClassifier1",
"documentation": "http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html",
"description": "Scikit-learn RandomForestClassifier.",
"classifiers": {
"type": "estimator",
"subtype": "classifier"
},
"modalities": [],
"primitive": "sklearn.ensemble.RandomForestClassifier",
"fit": {
"method": "fit",
"args": [
{
"name": "X",
"type": "DataFrame"
},
{
"name": "y",
"type": "Series"
}
]
},
"produce": {
"method": "feature_importances_",
"args": [],
"output": [
{
"name": "y",
"type": "Series"
}
]
},
"hyperparameters": {
"fixed": {
"n_jobs": {
"type": "int",
"default": -1
}
},
"tunable": {
"criterion": {
"type": "str",
"default": "entropy",
"values": ["entropy", "gini"]
},
"max_features": {
"type": "str",
"default": null,
"range": [null, "auto", "log2"]
},
"max_depth": {
"type": "int",
"default": 10,
"range": [1, 30]
},
"min_samples_split": {
"type": "float",
"default": 0.1,
"range": [0.0001, 0.5]
},
"min_samples_leaf": {
"type": "float",
"default": 0.1,
"range": [0.0001, 0.5]
},
"n_estimators": {
"type": "int",
"default": 30,
"values": [2, 500]
},
"class_weight": {
"type": "str",
"default": null,
"range": [null, "balanced"]
}
}
}
}