def test_fit_transform(self): X = _data() ct, ct_categorical_feature = make_lightgbm_column_transformer(X.dtypes, missing_value_aware = False) dfm, dfm_categorical_feature = make_lightgbm_dataframe_mapper(X.dtypes, missing_value_aware = False) self.assertEqual(ct.fit_transform(X).tolist(), dfm.fit_transform(X).tolist()) self.assertEqual([0, 1, 3], ct_categorical_feature) self.assertEqual([0, 1, 3], dfm_categorical_feature) ct, ct_categorical_feature = make_lightgbm_column_transformer(X.dtypes, missing_value_aware = True) dfm, dfm_categorical_feature = make_lightgbm_dataframe_mapper(X.dtypes, missing_value_aware = True) self.assertEqual(ct.fit_transform(X).tolist(), dfm.fit_transform(X).tolist()) self.assertEqual([0, 1, 3], ct_categorical_feature) self.assertEqual([0, 1, 3], dfm_categorical_feature)
def lightgbm_auto():
mapper, categorical_feature = make_lightgbm_dataframe_mapper(
auto_X.dtypes, missing_value_aware=False)
pipeline = PMMLPipeline([("mapper", mapper),
("regressor",
LGBMRegressor(n_estimators=31,
max_depth=5,
random_state=13))])
pipeline.fit(auto_X,
auto_y,
regressor__categorical_feature=categorical_feature)
pipeline.configure(compact=True)
sklearn2pmml(pipeline, "pmml/LightGBMAuto.pmml", with_repr=False)
def lightgbm_audit():
mapper, categorical_feature = make_lightgbm_dataframe_mapper(
audit_X.dtypes, missing_value_aware=False)
pipeline = PMMLPipeline([("mapper", mapper),
("classifier",
LGBMClassifier(n_estimators=71,
max_depth=7,
random_state=13))])
pipeline.fit(audit_X,
audit_y,
classifier__categorical_feature=categorical_feature)
pipeline.configure(compact=True)
sklearn2pmml(pipeline, "pmml/LightGBMAudit.pmml", with_repr=False)