import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
import pickle

# Load data
df = pd.read_csv('hiring_data_enriched.csv')

# Features and Target
X = df[['Job_Category', 'Years_Experience', 'Education_Level', 'Skill_Fit_Score']]
y = df['Final_Decision']

# Preprocessing
categorical_features = ['Job_Category', 'Education_Level']
numerical_features = ['Years_Experience', 'Skill_Fit_Score']

preprocessor = ColumnTransformer(
    transformers=[
        ('num', StandardScaler(), numerical_features),
        ('cat', OneHotEncoder(handle_unknown='ignore'), categorical_features)
    ])

# Model Pipeline
model = Pipeline(steps=[
    ('preprocessor', preprocessor),
    ('classifier', LogisticRegression(random_state=42))
])

# Train
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
model.fit(X_train, y_train)

# Save model and preprocessor
with open('hiring_model.pkl', 'wb') as f:
    pickle.dump(model, f)

print("Model trained and saved as hiring_model.pkl")