train.py

import math
import pandas as pd
import numpy as np

from datasets import load_dataset
import sklearn
import joblib

from sklearn.datasets import fetch_openml

from sklearn.preprocessing import StandardScaler, OneHotEncoder, LabelEncoder
from sklearn.compose import make_column_transformer
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import train_test_split, RandomizedSearchCV
from sklearn.linear_model import LinearRegression

data_df = pd.read_csv('insurance.csv')

data_df = data_df.drop(columns=['index'])
categorical_features = ['sex', 'smoker', 'region']
numerical_features = ['age', 'bmi', 'children', ]
target = 'charges'

print("Creating data subsets")

X = data_df[numerical_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')), ('scaler', StandardScaler())])
categorical_pipeline = Pipeline([('imputer', SimpleImputer(strategy='most_frequent')),('onehot', OneHotEncoder(handle_unknown='ignore'))])

preprocessor = make_column_transformer((numerical_pipeline, numerical_features), (categorical_pipeline, categorical_features))
model_linear_regression = LinearRegression(n_jobs=-1)
model_pipeline = make_pipeline(preprocessor,  model_linear_regression )

print("Estimating Model Pipeline")
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)