Custom Transformers

ct1.py

import pandas as pd
import numpy as np
from sklearn.base import BaseEstimator,TransformerMixin
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import FunctionTransformer
from sklearn.datasets import load_iris
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.linear_model import LogisticRegression

#Data Import
data = pd.DataFrame(load_iris()['data'],columns=load_iris()['feature_names'])

ct2.py

#TransformerMixin enables fit_transform without declaring the method
class OutlierRemover(BaseEstimator,TransformerMixin):
    def __init__(self,factor=1.5):
        self.factor = factor
        
    def outlier_removal(self,X,y=None):
        X = pd.Series(X).copy()
        q1 = X.quantile(0.25)
        q3 = X.quantile(0.75)
        iqr = q3 - q1
        lower_bound = q1 - (self.factor * iqr)
        upper_bound = q3 + (self.factor * iqr)
        X.loc[((X < lower_bound) | (X > upper_bound))] = np.nan 
        return pd.Series(X)
    
    def fit(self,X,y=None):
        return self
    
    def transform(self,X,y=None):
        return X.apply(self.outlier_removal)

#creating outlier_remover object of OutlierRemover class
outlier_remover = OutlierRemover()