Delete Random Forest Model

Random Forest Model

-# Feeding the data into the algorithm
-rf_model = RandomForestRegressor(n_estimators=100, max_depth=20)
-rf_model.fit(x_train, y_train)
-rf_pred = rf_model.predict(x_test)
-
-# Transform the prediction back to it's original state
-rf_pred = rf_pred.reshape(-1,1)
-rf_pred_test_set = np.concatenate([rf_pred, x_test], axis=1)
-rf_pred_test_set = scaler.inverse_transform(rf_pred_test_set)
-
-# calculating the predicted exports values from the difference values and append that to the predicted data frame
-result_list = []
-for index in range(0, len(rf_pred_test_set)):
-    result_list.append(rf_pred_test_set[index][0] + act_exports[index])
-rf_pred_series = pd.Series(result_list, name='rf_pred')
-predict_df = predict_df.merge(rf_pred_series, left_index=True, right_index=True)
-
-# Now that we have calculated the predicted data and now we can evaluate it with varius matrix to test it's accuracy
-rf_rmse = np.sqrt(mean_squared_error(predict_df['rf_pred'], monthly_exports['Quantity'][-12:]))
-rf_mae = mean_absolute_error(predict_df['rf_pred'], monthly_exports['Quantity'][-12:])
-rf_r2 = r2_score(predict_df['rf_pred'], monthly_exports['Quantity'][-12:])
-print('Random Forest RMSE: ', rf_rmse)
-print('Random Forest MAE: ', rf_mae)
-print('Random Forest R2 Score: ', rf_r2)
-
-# Visualising the data with the original values
-plt.figure(figsize=(15,7))
-plt.plot(monthly_exports['Date'], monthly_exports['Quantity'])
-plt.plot(predict_df['Date'], predict_df['rf_pred'])
-plt.title("Export Forecast using Random Forest")
-plt.xlabel("Date")
-plt.ylabel("Exports")
-plt.legend(["Original exports", "Predicted exports"])
-plt.show()
\ No newline at end of file