Training a Linear Regression model in Pipeline.

regressionPipeline.py

# Train the model
import numpy as np
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.linear_model import LinearRegression


# Define preprocessing for numeric columns (scale them)
numeric_features = [6,7,8,9]
numeric_transformer = Pipeline(steps=[
    ('scaler', StandardScaler())])

# Define preprocessing for categorical features (encode them)
categorical_features = [0,1,2,3,4,5]
categorical_transformer = Pipeline(steps=[
    ('onehot', OneHotEncoder(handle_unknown='ignore'))])

# Combine preprocessing steps
preprocessor = ColumnTransformer(
    transformers=[
        ('num', numeric_transformer, numeric_features),
        ('cat', categorical_transformer, categorical_features)])

# Create preprocessing and training pipeline
pipeline = Pipeline(steps=[('preprocessor', preprocessor),
                           ('regressor', LinearRegression())])


# fit the pipeline to train a linear regression model on the training set
model = pipeline.fit(X_train, (y_train))
print (model)

# Output :
# Pipeline(steps=[('preprocessor',
#                 ColumnTransformer(transformers=[('num',
#                                                  Pipeline(steps=[('scaler',
#                                                                   StandardScaler())]),
#                                                  [6, 7, 8, 9]),
#                                                 ('cat',
#                                                  Pipeline(steps=[('onehot',
#                                                                   OneHotEncoder(handle_unknown='ignore'))]),
#                                                  [0, 1, 2, 3, 4, 5])])),
#                ('regressor', LinearRegression())])