def test_XGBoost(self):
model=XGBClassifier()
sk_model=iris_dataset(model)
derived_col_names=['sepal_length','petal_length']
col_names=['sepal_length','petal_length']
target_name='species'
mining_imp_value=()
categoric_values=()
self.assertEqual(
len(xgb.get_segments_for_xgbc(sk_model,derived_col_names,col_names,target_name,mining_imp_value,categoric_values)),
4)
self.assertEqual(
xgb.get_segments_for_xgbc(sk_model,derived_col_names,col_names,target_name,mining_imp_value,categoric_values)[
3].get_id(),4)
self.assertEqual(
xgb.get_segments_for_xgbc(sk_model, derived_col_names, col_names, target_name, mining_imp_value,categoric_values)[
3].get_RegressionModel().get_RegressionTable()[0].get_intercept(), '0.0')
self.assertEqual(
xgb.mining_Field_For_First_Segment(col_names).__class__.__name__,
pml.MiningSchema().__class__.__name__)
self.assertEqual(
xgb.mining_Field_For_First_Segment(col_names).get_MiningField()[0].get_name(),
'sepal_length')
self.assertEqual(len(xgb.mining_Field_For_First_Segment(['a','b','d','e']).get_MiningField())
,4)
self.assertEqual(
type(xgb.generate_Segments_Equal_To_Estimators([],derived_col_names,col_names)),
type([]))
self.assertEqual(
xgb.add_segmentation(sk_model,[],[],pml.Output,1).__class__.__name__,
pml.Segment().__class__.__name__)
self.assertEqual(
xgb.add_segmentation(sk_model,[],[],pml.Output,1).get_MiningModel().__class__.__name__,
pml.MiningModel().__class__.__name__)
self.assertEqual(xgb.add_segmentation(sk_model, [], [], pml.Output, 1).get_id(),
2)
self.assertEqual(type(xgb.get_regrs_tabl(sk_model,col_names,'species',categoric_values)),type([]))
def get_segments_for_lgbc(model, derived_col_names, feature_names, target_name,
mining_imp_val, categoric_values, model_name):
"""
It returns all the segments of the LGB classifier.
Parameters
----------
model :
Contains LGB model object.
derived_col_names : List
Contains column names after preprocessing.
feature_names: List
Contains list of feature/column names.
target_name : String
Name of the Target column.
mining_imp_val : tuple
Contains the mining_attributes,mining_strategy, mining_impute_value
categoric_values : tuple
Contains Categorical attribute names and its values
model_name : string
Name of the model
Returns
-------
regrs_models :
Returns all the segments of the LGB model.
"""
segments = list()
if model.n_classes_ == 2:
main_key_value = []
lgb_dump = model.booster_.dump_model()
for i in range(len(lgb_dump['tree_info'])):
tree = lgb_dump['tree_info'][i]['tree_structure']
main_key_value.append(tree)
mining_schema_for_1st_segment = xgboostToPmml.mining_Field_For_First_Segment(
feature_names)
outputField = list()
outputField.append(
pml.OutputField(name="lgbValue",
optype=OPTYPE.CONTINUOUS,
dataType=DATATYPE.DOUBLE,
feature=RESULT_FEATURE.PREDICTED_VALUE,
isFinalResult="false"))
out = pml.Output(OutputField=outputField)
oField = list()
oField.append("lgbValue")
segments_equal_to_estimators = generate_Segments_Equal_To_Estimators(
main_key_value, derived_col_names, feature_names)
First_segment = xgboostToPmml.add_segmentation(
model, segments_equal_to_estimators, mining_schema_for_1st_segment,
out, 1)
reg_model = sklToPmml.get_regrs_models(model, oField, oField,
target_name, mining_imp_val,
categoric_values, model_name)[0]
reg_model.normalizationMethod = REGRESSION_NORMALIZATION_METHOD.LOGISTIC
last_segment = pml.Segment(True_=pml.True_(),
id=2,
RegressionModel=reg_model)
segments.append(First_segment)
segments.append(last_segment)
else:
main_key_value = []
lgb_dump = model.booster_.dump_model()
for i in range(len(lgb_dump['tree_info'])):
tree = lgb_dump['tree_info'][i]['tree_structure']
main_key_value.append(tree)
oField = list()
for index in range(0, model.n_classes_):
inner_segment = []
for in_seg in range(index, len(main_key_value), model.n_classes_):
inner_segment.append(main_key_value[in_seg])
mining_schema_for_1st_segment = xgboostToPmml.mining_Field_For_First_Segment(
feature_names)
outputField = list()
outputField.append(
pml.OutputField(name='lgbValue(' + str(index) + ')',
optype=OPTYPE.CONTINUOUS,
feature=RESULT_FEATURE.PREDICTED_VALUE,
dataType=DATATYPE.FLOAT,
isFinalResult="true"))
out = pml.Output(OutputField=outputField)
oField.append('lgbValue(' + str(index) + ')')
segments_equal_to_estimators = generate_Segments_Equal_To_Estimators(
inner_segment, derived_col_names, feature_names)
segments_equal_to_class = xgboostToPmml.add_segmentation(
model, segments_equal_to_estimators,
mining_schema_for_1st_segment, out, index)
segments.append(segments_equal_to_class)
reg_model = sklToPmml.get_regrs_models(model, oField, oField,
target_name, mining_imp_val,
categoric_values, model_name)[0]
reg_model.normalizationMethod = REGRESSION_NORMALIZATION_METHOD.SOFTMAX
last_segment = pml.Segment(True_=pml.True_(),
id=model.n_classes_ + 1,
RegressionModel=reg_model)
segments.append(last_segment)
return segments
def get_segments_for_lgbc(model, derived_col_names, feature_names, target_name,
mining_imp_val, categoric_values):
"""
It returns all the segments of the LGB classifier.
Parameters
----------
model :
Contains LGB model object.
derived_col_names : List
Contains column names after preprocessing.
feature_names: List
Contains list of feature/column names.
target_name : String
Name of the Target column.
mining_imp_val : tuple
Contains the mining_attributes,mining_strategy, mining_impute_value
categoric_values : tuple
Contains Categorical attribute names and its values
Returns
-------
regrs_models :
Returns all the segments of the LGB model.
"""
segments = list()
if model.n_classes_ == 2:
main_key_value = []
lgb_dump = model.booster_.dump_model()
for i in range(len(lgb_dump['tree_info'])):
tree = lgb_dump['tree_info'][i]['tree_structure']
list_of_nodes = []
main_key_value.append(
generate_structure_for_lgb(tree, list_of_nodes,
derived_col_names))
mining_schema_for_1st_segment = xgboostToPmml.mining_Field_For_First_Segment(
feature_names)
outputField = list()
outputField.append(
pml.OutputField(name="lgbValue",
optype="continuous",
dataType="float",
feature="predictedValue",
isFinalResult="true"))
out = pml.Output(OutputField=outputField)
oField = list()
oField.append('lgbValue')
segments_equal_to_estimators = xgboostToPmml.generate_Segments_Equal_To_Estimators(
main_key_value, derived_col_names, feature_names)
First_segment = xgboostToPmml.add_segmentation(
model, segments_equal_to_estimators, mining_schema_for_1st_segment,
out, 1)
last_segment = pml.Segment(True_=pml.True_(),
id=2,
RegressionModel=sklToPmml.get_regrs_models(
model, oField, oField, target_name,
mining_imp_val, categoric_values)[0])
segments.append(First_segment)
segments.append(last_segment)
else:
main_key_value = []
lgb_dump = model.booster_.dump_model()
for i in range(len(lgb_dump['tree_info'])):
tree = lgb_dump['tree_info'][i]['tree_structure']
list_of_nodes = []
main_key_value.append(
generate_structure_for_lgb(tree, list_of_nodes,
derived_col_names))
oField = list()
for index in range(0, model.n_classes_):
inner_segment = []
for in_seg in range(index, len(main_key_value), model.n_classes_):
inner_segment.append(main_key_value[in_seg])
mining_schema_for_1st_segment = xgboostToPmml.mining_Field_For_First_Segment(
feature_names)
outputField = list()
outputField.append(
pml.OutputField(name='lgbValue(' + str(index) + ')',
optype="continuous",
feature="predictedValue",
isFinalResult="true"))
out = pml.Output(OutputField=outputField)
oField.append('lgbValue(' + str(index) + ')')
segments_equal_to_estimators = xgboostToPmml.generate_Segments_Equal_To_Estimators(
inner_segment, derived_col_names, feature_names)
segments_equal_to_class = xgboostToPmml.add_segmentation(
model, segments_equal_to_estimators,
mining_schema_for_1st_segment, out, index)
segments.append(segments_equal_to_class)
last_segment = pml.Segment(True_=pml.True_(),
id=model.n_classes_ + 1,
RegressionModel=sklToPmml.get_regrs_models(
model, oField, oField, target_name,
mining_imp_val, categoric_values)[0])
segments.append(last_segment)
return segments