import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.cluster import KMeans
import joblib
import os

print("Training Risk Model...")

os.makedirs("models", exist_ok=True)

np.random.seed(42)
n_samples = 500

conf_population = np.random.uniform(0.4, 0.98, n_samples)
cam_population = np.random.uniform(0.05, 0.35, n_samples)
disease_population = np.random.randint(0, 2, n_samples)

training_vectors = np.column_stack([
    conf_population,
    cam_population,
    disease_population
]).astype(np.float32)

scaler = StandardScaler()
training_vectors = scaler.fit_transform(training_vectors).astype(np.float32)

kmeans = KMeans(n_clusters=3, random_state=42, n_init=10)
kmeans.fit(training_vectors)

joblib.dump(kmeans, "models/risk_model.pkl")
joblib.dump(scaler, "models/risk_scaler.pkl")

print("✅ Risk model saved successfully!")