def add_segmentation(model,segments_equal_to_estimators,mining_schema_for_1st_segment,out,id):
"""
It returns the First Segments for a binary classifier and returns number of Segments equls to number of values
target class for multiclass classifier
Parameters
----------
model:
Contains Xgboost model object.
segments_equal_to_estimators: List
Contains List Segements equals to the number of the estimators of the model.
mining_schema_for_1st_segment:
Contains Mining Schema for the First Segment
out:
Contains the Output element
id: Integer
Index of the Segements
Returns:
-------
segments_equal_to_estimators:
Returns list of segments equal to number of estimator of the model
"""
segmentation = pml.Segmentation(multipleModelMethod="sum", Segment=segments_equal_to_estimators)
mining_model = pml.MiningModel(functionName='regression', modelName="MiningModel", MiningSchema=mining_schema_for_1st_segment,
Output=out, Segmentation=segmentation)
if model.n_classes_==2:
First_segment = pml.Segment(True_=pml.True_(), id=id, MiningModel=mining_model)
return First_segment
else:
segments_equal_to_class = pml.Segment(True_=pml.True_(), id=id + 1, MiningModel=mining_model)
return segments_equal_to_class
def generate_Segments_Equal_To_Estimators(val, derived_col_names, col_names):
"""
It returns number of Segments equal to the estimator of the model.
Parameters
----------
val: List
Contains a list of well structured node for binary classification/inner segments for multi-class classification
derived_col_names: List
Contains column names after preprocessing.
col_names: List
Contains list of feature/column names.
Returns:
-------
segments_equal_to_estimators:
Returns list of segments equal to number of estimator of the model
"""
segments_equal_to_estimators = []
for i in range(len(val)):
main_node = pml.Node(True_=pml.True_())
m_flds = []
mining_field_for_innner_segments = col_names
create_node(val[i], main_node, derived_col_names)
for name in mining_field_for_innner_segments:
m_flds.append(pml.MiningField(name=name))
segments_equal_to_estimators.append((pml.Segment(id=i + 1, True_=pml.True_(),
TreeModel=pml.TreeModel(functionName="regression",
modelName="DecisionTreeModel",
missingValueStrategy="none",
noTrueChildStrategy="returnLastPrediction",
splitCharacteristic="multiSplit",
Node=main_node,
MiningSchema=pml.MiningSchema(
MiningField=m_flds)))))
return segments_equal_to_estimators
def get_segments_for_xgbc(model, derived_col_names, feature_names, target_name, mining_imp_val,categoric_values):
"""
It returns all the segments of the Xgboost classifier.
Parameters
----------
model :
Contains Xgboost 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 xgboost model.
"""
segments = list()
if model.n_classes_ == 2:
get_nodes_in_json_format=[]
for i in range(model.n_estimators):
get_nodes_in_json_format.append(json.loads(model._Booster.get_dump(dump_format='json')[i]))
mining_schema_for_1st_segment = mining_Field_For_First_Segment(feature_names)
outputField = list()
outputField.append(pml.OutputField(name="xgbValue", optype="continuous", dataType="float",
feature="predictedValue", isFinalResult="true"))
out = pml.Output(OutputField=outputField)
oField=list()
oField.append('xgbValue')
segments_equal_to_estimators = generate_Segments_Equal_To_Estimators(get_nodes_in_json_format, derived_col_names,
feature_names)
First_segment = 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)[0]
reg_model.normalizationMethod='logit'
last_segment = pml.Segment(True_=pml.True_(), id=2,
RegressionModel=reg_model)
segments.append(First_segment)
segments.append(last_segment)
else:
get_nodes_in_json_format = []
for i in range(model.n_estimators * model.n_classes_):
get_nodes_in_json_format.append(json.loads(model._Booster.get_dump(dump_format='json')[i]))
oField = list()
for index in range(0, model.n_classes_):
inner_segment = []
for in_seg in range(index, len(get_nodes_in_json_format), model.n_classes_):
inner_segment.append(get_nodes_in_json_format[in_seg])
mining_schema_for_1st_segment = mining_Field_For_First_Segment(feature_names)
outputField = list()
outputField.append(pml.OutputField(name='xgbValue(' + str(index) + ')', optype="continuous",
feature="predictedValue", dataType="float", isFinalResult="true"))
out = pml.Output(OutputField=outputField)
oField.append('xgbValue(' + str(index) + ')')
segments_equal_to_estimators = generate_Segments_Equal_To_Estimators(inner_segment, derived_col_names,
feature_names)
segments_equal_to_class = 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