script 2.py

# Prepare data for machine learning
from sklearn.preprocessing import LabelEncoder

# Create a copy for ML processing
ml_data = df.copy()

# Encode categorical variables
le_gender = LabelEncoder()
le_ses = LabelEncoder()
le_parent_ed = LabelEncoder()

ml_data['gender_encoded'] = le_gender.fit_transform(ml_data['gender'])
ml_data['ses_encoded'] = le_ses.fit_transform(ml_data['socioeconomic_status'])
ml_data['parent_education_encoded'] = le_parent_ed.fit_transform(ml_data['parent_education'])

# Select features for ML model
feature_columns = [
    'age', 'gender_encoded', 'ses_encoded', 'math_grade', 'english_grade', 
    'science_grade', 'previous_gpa', 'attendance_rate', 'days_absent',
    'disciplinary_actions', 'participation_score', 'homework_completion',
    'parent_education_encoded', 'family_support', 'extracurricular_activities',
    'teacher_relationship'
]

X = ml_data[feature_columns]
y = ml_data['dropout']

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

# Scale the features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Train multiple models
models = {
    'Random Forest': RandomForestClassifier(n_estimators=100, random_state=42),
    'Logistic Regression': LogisticRegression(random_state=42, max_iter=1000)
}

model_results = {}

for name, model in models.items():
    if name == 'Logistic Regression':
        model.fit(X_train_scaled, y_train)
        predictions = model.predict(X_test_scaled)
    else:
        model.fit(X_train, y_train)
        predictions = model.predict(X_test)
    
    accuracy = accuracy_score(y_test, predictions)
    model_results[name] = {
        'accuracy': accuracy,
        'predictions': predictions,
        'model': model
    }
    
    print(f"\n{name} Results:")
    print(f"Accuracy: {accuracy:.3f}")
    print("Classification Report:")
    print(classification_report(y_test, predictions))

# Select best model (Random Forest performed better)
best_model = models['Random Forest']
best_scaler = None  # Random Forest doesn't need scaling

# Save feature names for the web app
feature_names = feature_columns

print(f"\nFeature Importance (Random Forest):")
importances = best_model.feature_importances_
feature_importance = list(zip(feature_names, importances))
feature_importance.sort(key=lambda x: x[1], reverse=True)

for feature, importance in feature_importance:
    print(f"{feature}: {importance:.3f}")