# train_model.py
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
import joblib
from huggingface_hub import HfApi, HfFolder, Repository

# 1. Load dataset
df = pd.read_csv("water_quality_dataset.csv")

# Features & labels
X = df.drop(columns=["label"])
y = df["label"]

# 2. Split data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 3. Train model
model = RandomForestClassifier()
model.fit(X_train, y_train)

# 4. Save model
joblib.dump(model, "model.joblib")

print("✅ Model trained and saved as model.joblib")