train.py

import pandas as pd

import sklearn
import joblib 

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 
from math import sqrt

sklearn.set_config(display='diagram')

data = pd.read_csv('insurance.csv')
df = data.copy(deep=True)

df = df.drop(columns=['index'])
df.drop_duplicates(inplace=True)

target = 'charges'
numeric_features = ['age', 'bmi', 'children']
categorical_features = ['sex', 'smoker', 'region']

print('Creating data subsets')

X = df[numeric_features + categorical_features]
y = df[target]

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

Xtest = Xtest[['age', 'bmi', 'children', 'sex', 'smoker', 'region']]

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

model_linear_regression = LinearRegression(n_jobs=-1)

print('Estimating Best 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)