def get_space_categorical_pipeline_complex():
space = HyperSpace()
with space.as_default():
input = HyperInput(name='input1')
p1 = categorical_pipeline_complex()(input)
p3 = DataFrameMapper(input_df=True, df_out=True)([p1]) # passthrough
est = LightGBMEstimator(task='binary', fit_kwargs={})(p3)
space.set_inputs(input)
return space
def get_space_num_cat_pipeline_multi_complex(dataframe_mapper_default=False,
lightgbm_fit_kwargs={},
xgb_fit_kwargs={}):
space = HyperSpace()
with space.as_default():
input = HyperInput(name='input1')
p1 = numeric_pipeline_complex()(input)
p2 = categorical_pipeline_complex()(input)
p3 = DataFrameMapper(default=dataframe_mapper_default,
input_df=True,
df_out=True,
df_out_dtype_transforms=[(column_object,
'category')])([p1, p2])
p4 = numeric_pipeline_complex(seq_no=1)(p3)
p5 = categorical_pipeline_complex(seq_no=1)(p3)
p6 = DataFrameMapper(default=dataframe_mapper_default,
input_df=True,
df_out=True,
df_out_dtype_transforms=[(column_object,
'category')])([p4, p5])
lightgbm_init_kwargs = {
'boosting_type': Choice(['gbdt', 'dart', 'goss']),
'num_leaves': Choice([11, 31, 101, 301, 501]),
'learning_rate': Real(0.001, 0.1, step=0.005),
'n_estimators': 100,
'max_depth': -1,
# subsample_for_bin = 200000, objective = None, class_weight = None,
# min_split_gain = 0., min_child_weight = 1e-3, min_child_samples = 20,
}
lightgbm_est = LightGBMEstimator(task='binary',
fit_kwargs=lightgbm_fit_kwargs,
**lightgbm_init_kwargs)
xgb_init_kwargs = {}
xgb_est = XGBoostEstimator(task='binary',
fit_kwargs=xgb_fit_kwargs,
**xgb_init_kwargs)
or_est = ModuleChoice([lightgbm_est, xgb_est])(p6)
space.set_inputs(input)
return space
def get_space_num_cat_pipeline(default=False):
space = HyperSpace()
with space.as_default():
input = HyperInput(name='input1')
p1 = numeric_pipeline_simple()(input)
p2 = categorical_pipeline_simple()(input)
p3 = DataFrameMapper(default=default, input_df=True,
df_out=True)([p1, p2]) # passthrough
est = LightGBMEstimator(task='binary', fit_kwargs={})(p3)
space.set_inputs(input)
return space