custom_transformer_1.py

import numpy as np
import pandas as pd
from sklearn.datasets import make_blobs
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LogisticRegression


class CustomImputer(BaseEstimator, TransformerMixin):
    """Impute missing data for numerical features."""

    def __init__(self, variables=None):
        if not isinstance(variables, list):
            self.variables = [variables]
        else:
            self.variables = variables

    def fit(self, X, y = None) :
        self.imputer_dict_ = {}
        for feature in self.variables:
            self.imputer_dict_[feature] = X[feature].mean()
        return self

    def transform(self, X):
        X = X.copy()
        for feature in self.variables:
            X[feature].fillna(self.imputer_dict_[feature], inplace=True)
        return X

# generate some data
X, y = make_blobs(n_samples=10, centers=3, n_features=4,
                  random_state=0)


df = pd.DataFrame(X, columns = ['X1', 'X2', 'X3', 'X4'])
df['X1'].iloc[2:8] = np.nan # add missing values

missing_columns = df.columns[df.isnull().any()].values[0]
    
preprocessor = Pipeline(steps=[
    ('imputer', CustomImputer(missing_columns)),
    ('scaler', StandardScaler())])


lr = Pipeline(steps=[('preprocessor', preprocessor),
                    ('classifier', LogisticRegression())])

lr.fit(df, y)