custom_transformer.py

import numpy as np
from sklearn.base import BaseEstimator, TransformerMixin

class StoreAgeAdder(BaseEstimator, TransformerMixin):
    def __init__(self, current_year=2025):
        self.current_year = current_year

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

    def transform(self, X):
        X = X.copy()
        X['store_age'] = self.current_year - X['Store_Establishment_Year']
        return X.drop(columns='Store_Establishment_Year')

class OutlierCapper(BaseEstimator, TransformerMixin):
    def __init__(self, factor=1.5):
        self.factor = factor
        self.bounds = {}

    def fit(self, X, y=None):
        for col in X.columns:
            Q1 = X[col].quantile(0.25)
            Q3 = X[col].quantile(0.75)
            IQR = Q3 - Q1
            lower = Q1 - self.factor * IQR
            upper = Q3 + self.factor * IQR
            self.bounds[col] = (lower, upper)
        return self

    def transform(self, X):
        X = X.copy()
        for col in X.columns:
            lower, upper = self.bounds[col]
            X[col] = np.clip(X[col], lower, upper)
        return X