custom_estimator.py

# import the BaseEstimator
from sklearn.base import BaseEstimator

# define the class OutletTypeEncoder
# This will be our custom transformer that will create 3 new binary columns
# custom transformer must have methods fit and transform
class OutletTypeEncoder(BaseEstimator):

    def __init__(self):
        pass

    def fit(self, documents, y=None):
        return self

    def transform(self, x_dataset):
        x_dataset['outlet_grocery_store'] = (x_dataset['Outlet_Type'] == 'Grocery Store')*1
        x_dataset['outlet_supermarket_3'] = (x_dataset['Outlet_Type'] == 'Supermarket Type3')*1
        x_dataset['outlet_identifier_OUT027'] = (x_dataset['Outlet_Identifier'] == 'OUT027')*1
        
        return x_dataset