train.py

import joblib
from sklearn.datasets import fetch_openml
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import make_column_transformer
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
import numpy as np
import pandas as pd

# Read data
df = pd.read_csv("insurance.csv")

# Create the y, X variables by splitting of the target continuous variable 'charges'
# from the remaining features

print("Creating data subsets")

y = df['charges']
X = df.drop('charges', axis=1)

print("Data subsets created")

# Extract the names of the numerical and categorical columns
numeric_features = X.select_dtypes(include=['int64', 'float64']).columns.tolist()
categorical_features = X.select_dtypes(include=['object']).columns.tolist()
target = 'charges'

# Split the independent and dependent features into X and y variables with a test size of 20% and random state set to 42
Xtrain, Xtest, ytrain, ytest = train_test_split(
    X, y,
    test_size=0.2,
    random_state=42
)

print("Preprocessing Data")

preprocessor = make_column_transformer(
    (StandardScaler(), numeric_features),
    (OneHotEncoder(handle_unknown='ignore'), categorical_features)
)

model_linear_regression = LinearRegression(n_jobs=-1)

print("Estimating Model Pipeline")

model_pipeline = make_pipeline(
    preprocessor,
    model_linear_regression
)

model_pipeline.fit(Xtrain, ytrain)

print("Logging Metrics")
print(f"R-squared: {r2_score(ytest, model_pipeline.predict(Xtest))}")

print("Serializing Model")

saved_model_path = "model.joblib"

joblib.dump(model_pipeline, saved_model_path)