Skip to content

Instantly share code, notes, and snippets.

@lakshay-arora
Created March 16, 2020 07:14
Show Gist options
  • Save lakshay-arora/890785e48f7871f07269ddbad1afef00 to your computer and use it in GitHub Desktop.
Save lakshay-arora/890785e48f7871f07269ddbad1afef00 to your computer and use it in GitHub Desktop.
def transform_data(_data,_validate,_test,_target,encoding) :
if 'BinaryEncoding' in encoding['type'].keys():
ce_OHE = ce.BinaryEncoder(cols=encoding['type']['BinaryEncoding'])
ce_OHE.fit(_data)
_data = ce_OHE.transform(_data)
_test = ce_OHE.transform(_test)
_validate = ce_OHE.transform(_validate)
if 'TargetEncoding' in encoding['type'].keys():
# encoding of target is required
ce_LE = LabelEncoder()
ce_LE.fit(_data[_target].astype(str))
y = ce_LE.transform(_data[_target].astype(str))
ce_TE = ce.TargetEncoder(cols=encoding['type']['TargetEncoding'])
ce_TE.fit(_data,y)
_data = ce_TE.transform(_data)
_test = ce_TE.transform(_test)
_validate = ce_TE.transform(_validate)
if 'OneHotEncoding' in encoding['type'].keys():
ce_OHE = ce.OneHotEncoder(cols=encoding['type']['OneHotEncoding'])
ce_OHE.fit(_data)
_data = ce_OHE.transform(_data)
_test = ce_OHE.transform(_test)
_validate = ce_OHE.transform(_validate)
return _data, _validate , _test
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment