import pandas as pd
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.metrics import accuracy_score
import joblib

# Load dataset
df = pd.read_csv('diabetes.csv')

# Handle missing values (replace zeros with NaN for specific columns)
columns_to_replace = ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI']
df[columns_to_replace] = df[columns_to_replace].replace(0, pd.NA)

# Fill missing values with the median
df.fillna(df.median(), inplace=True)

# Separate features and labels
X = df.drop('Outcome', axis=1)
y = df['Outcome']

# Train/test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create a pipeline with scaling and Random Forest
pipeline = Pipeline([
    ('scaler', StandardScaler()),
    ('classifier', RandomForestClassifier(random_state=42))
])

# Hyperparameter tuning
param_grid = {
    'classifier__n_estimators': [100, 200, 300],
    'classifier__max_depth': [5, 10, 15],
    'classifier__min_samples_split': [2, 5, 10],
    'classifier__min_samples_leaf': [1, 2, 4]
}

grid_search = GridSearchCV(pipeline, param_grid, cv=5, scoring='accuracy', n_jobs=-1)
grid_search.fit(X_train, y_train)

# Best model
best_model = grid_search.best_estimator_

# Evaluate
y_pred = best_model.predict(X_test)
acc = accuracy_score(y_test, y_pred)
print(f"Accuracy: {acc * 100:.2f}%")

# Save the model
joblib.dump(best_model, 'diabetes_model.pkl')
print("Model saved as diabetes_model.pkl")