from sklearn.svm import SVR
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import make_pipeline
from master_function import data_preprocessing, mass_import
from master_function import plot_train_test_values, calculate_accuracy, model_bias
from sklearn.metrics import mean_squared_error
# Fitting the model
model = make_pipeline(StandardScaler(), SVR(kernel = 'rbf', C = 1, gamma = 0.04, epsilon = 0.01))
model.fit(x_train, y_train)
# Predicting in-sample
y_predicted_train = np.reshape(model.predict(x_train), (-1, 1))
# Predicting out-of-sample
y_predicted = np.reshape(model.predict(x_test), (-1, 1))
# plotting
plot_train_test_values(100, 50, y_train, y_test, y_predicted)
# Performance evaluation
print('---')
print('Accuracy Train = ', round(calculate_accuracy(y_predicted_train, y_train), 2), '%')
print('Accuracy Test = ', round(calculate_accuracy(y_predicted, y_test), 2), '%')
print('RMSE Train = ', round(np.sqrt(mean_squared_error(y_predicted_train, y_train)), 10))
print('RMSE Test = ', round(np.sqrt(mean_squared_error(y_predicted, y_test)), 10))
print('Correlation In-Sample Predicted/Train = ', round(np.corrcoef(np.reshape(y_predicted_train, (-1)), y_train)[0][1], 3))
print('Correlation Out-of-Sample Predicted/Test = ', round(np.corrcoef(np.reshape(y_predicted, (-1)), np.reshape(y_test, (-1)))[0][1], 3))
print('Model Bias = ', round(model_bias(y_predicted, y_test), 2), '%')
print('---')
# To get true bias by looking ath the difference between actual and forecast total
Actual_Total = np.sum(y_test)
Forecast_Total = np.sum(y_predicted)
# A simple bias check: are we over or under forecasting in total?
Total_Bias = (Forecast_Total - Actual_Total) / Actual_Total
print(f"Volume Bias: {Total_Bias:.2%}")
