| import joblib | |
| import numpy as np | |
| from sklearn.preprocessing import StandardScaler | |
| # Load the model and scaler | |
| model = joblib.load("classification_model.joblib") | |
| scaler = joblib.load("scaler.pkl") | |
| def predict(features): | |
| # Scale the features | |
| scaled_features = scaler.transform(np.array(features).reshape(1, -1)) | |
| prediction = model.predict(scaled_features) | |
| return prediction[0] | |
| # Sample usage | |
| if __name__ == "__main__": | |
| # Sample feature data (replace with real data when calling) | |
| sample_data = [0.5, 1.2, -0.3, 2.0] | |
| result = predict(sample_data) | |
| print(f"Prediction: {result}") | |