def _nyoka_pmml_model(
self, simple_pmml_ruleset_model: models.SimplePMMLRuleSetModel
) -> nyoka_pmml.PMML:
timestamp = datetime.datetime.now(
) if self._timestamp is None else self._timestamp
return nyoka_pmml.PMML(
version=nyoka_constants.PMML_SCHEMA.VERSION,
Header=nyoka_pmml.Header(
copyright=NyokaSerializer.COPYRIGHT_STRING,
description=nyoka_constants.HEADER_INFO.DEFAULT_DESCRIPTION,
Timestamp=nyoka_pmml.Timestamp(timestamp),
Application=nyoka_pmml.Application(
name=NyokaSerializer.APPLICATION_NAME,
version=version.version)),
DataDictionary=None
if simple_pmml_ruleset_model.dataDictionary is None else
self._nyoka_data_dictionary(
simple_pmml_ruleset_model.dataDictionary),
RuleSetModel=None
if simple_pmml_ruleset_model.ruleSetModel is None else [
self._nyoka_rule_set_model(
simple_pmml_ruleset_model.ruleSetModel)
])
def lgb_to_pmml(pipeline,
col_names,
target_name,
pmml_f_name='from_lgbm.pmml',
model_name=None,
description=None):
"""
Exports LGBM pipeline object into pmml
Parameters
----------
pipeline :
Contains an instance of Pipeline with preprocessing and final estimator
col_names : List
Contains list of feature/column names.
target_name : String
Name of the target column.
pmml_f_name : String
Name of the pmml file. (Default='from_lgbm.pmml')
model_name : string (optional)
Name of the model
description : string (optional)
Description of the model
Returns
-------
Exports the generated PMML object to `pmml_f_name`
"""
try:
model = pipeline.steps[-1][1]
except:
raise TypeError(
"Exporter expects pipeleine_instance and not an estimator_instance"
)
else:
if col_names.__class__.__name__ == "ndarray":
col_names = col_names.tolist()
ppln_sans_predictor = pipeline.steps[:-1]
trfm_dict_kwargs = dict()
derived_col_names = col_names
categoric_values = tuple()
mining_imp_val = tuple()
if ppln_sans_predictor:
pml_pp = pp.get_preprocess_val(ppln_sans_predictor, col_names,
model)
trfm_dict_kwargs['TransformationDictionary'] = pml_pp['trfm_dict']
derived_col_names = pml_pp['derived_col_names']
col_names = pml_pp['preprocessed_col_names']
categoric_values = pml_pp['categorical_feat_values']
mining_imp_val = pml_pp['mining_imp_values']
PMML_kwargs = get_PMML_kwargs(model, derived_col_names, col_names,
target_name, mining_imp_val,
categoric_values, model_name)
pmml = pml.PMML(version=PMML_SCHEMA.VERSION,
Header=sklToPmml.get_header(description),
DataDictionary=sklToPmml.get_data_dictionary(
model, col_names, target_name, categoric_values),
**trfm_dict_kwargs,
**PMML_kwargs)
pmml.export(outfile=open(pmml_f_name, "w"), level=0)
