scripts/pipeline.py

import pandas as pd
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
import joblib
import os

print("======================================")
print("STEP 1/2: Loading dataset")
print("======================================")

data = pd.DataFrame({
"Age":[25,45,33,52,23,40,60,48],
"Balance":[1000,5000,2300,8000,1200,4500,9000,3000],
"Exited":[0,1,0,1,0,1,1,0]
})

print("Dataset loaded")

print("======================================")
print("STEP 2/2: Training model")
print("======================================")

X=data[["Age","Balance"]]
y=data["Exited"]

X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2)

model=LogisticRegression()
model.fit(X_train,y_train)

os.makedirs("models",exist_ok=True)
joblib.dump(model,"models/pipeline.joblib")

print("Model saved to models/pipeline.joblib")
print("DONE")