train.py

# Import libraries
import pandas as pd
import joblib 

from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import make_column_transformer
from sklearn.compose import ColumnTransformer
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

# Read the data
data_df = pd.read_csv("insurance.csv")
# Process the data
data_df = data_df.drop(columns=['index'])

X = data_df.drop(columns='charges')
y = data_df['charges']

categorical_features = X.select_dtypes(include=['object']).columns
numeric_features = X.select_dtypes(include=['number']).columns

print("Creating data subsets")

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

Xtrain, Xtest, ytrain, ytest = train_test_split(
    X, y,
    test_size=0.2,
    random_state=42
)
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)