fdd7

fdd7.py

def transform_columns(transformer,columns_to_transform,X_train = X_train,X_valid = X_valid,):
    cols_train =  pd.DataFrame(transformer.fit_transform(X_train[columns_to_transform]))
    cols_valid = pd.DataFrame(transformer.transform(X_valid[columns_to_transform]))
    cols_train.index = X_train.index
    cols_valid.index = X_valid.index
    return cols_train, cols_valid

columns_to_transform_list = [ordered_columns, unordered_columns, numeric_columns]
ordinal_encoder = OrdinalEncoder()
onehot_encoder = OneHotEncoder(handle_unknown='ignore', sparse=False)
standard_scaler = StandardScaler()
transformers = [ordinal_encoder, onehot_encoder, standard_scaler]
encoded_train = []
encoded_validation = []

for columns_to_transform, transformer in zip(columns_to_transform_list, transformers):
    print(columns_to_transform)
    cols_train, cols_valid = transform_columns(transformer, columns_to_transform)
    #print(cols_train)
    encoded_train.append(cols_train)
    encoded_validation.append(cols_valid)
encoded_X_train = pd.concat(encoded_train, axis = 1)
encoded_X_valid = pd.concat(encoded_validation, axis = 1)

########################################################################################
########################################################################################
['year', 'model']
['transmission', 'fuel_type']
Index(['km_traveled', 'tax', 'engineSize', 'km_per_liters'], dtype='object')
########################################################################################
########################################################################################