train.py

import joblib

import pandas as pd

from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import make_column_transformer

from sklearn.pipeline import make_pipeline, Pipeline

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score

data_df = pd.read_csv("insurance.csv")
#dataset = fetch_openml(name='insurance')
#data_df = dataset.data

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

print("Creating data subsets")

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

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

numerical_pipeline = Pipeline([
    ('imputer', SimpleImputer(strategy='median')), # No missing!
    ('scaler', StandardScaler())
])

categorical_pipeline = Pipeline([
    ('imputer', SimpleImputer(strategy='most_frequent')),
    ('onehot', OneHotEncoder(handle_unknown='ignore'))
])

preprocessor = make_column_transformer(
    (numerical_pipeline, numeric_features),
    (categorical_pipeline, categorical_features)
)

model_logistic_regression = LinearRegression(n_jobs=-1)

print("Estimating Model Pipeline")

model_pipeline = make_pipeline(
    preprocessor,  # Applying preprocessing steps
    model_logistic_regression  # Training logistic regression model
)

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)