Model Evaluation

The model is evaluated based on various regression based metrics.

Contains classes and methods to obtain various regression based metrics to evaluate

class dlmfg.core.metrics_eval.MetricsEval[source]

MetricsEval Class

Evaluate metrics to evaluate model performance

metrics_eval_base(predicted_y, test_y, logs_path, run_id=0)[source]

Get predicted and actual value for all KCCs and return regression metrics namely: Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, R-Squared Value

Parameters
  • predicted_y – predicted values for the process parameters

  • predicted_y – actual values for the process parameters

  • logs_path (str (required)) – Logs path to save the evaluation metrics

Returns

dictionary of all metrics for each KCC

Return type

dict

Returns

dataframe of all metrics for each KCC

Return type

pandas.dataframe

metrics_eval_classification(y_pred, y_true, logs_path, run_id=0)[source]

Get predicted and actual value for all KCCs and return regression metrics namely: Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, R-Squared Value

Parameters
  • predicted_y – predicted values for the process parameters

  • predicted_y – actual values for the process parameters

  • logs_path (str (required)) – Logs path to save the evaluation metrics

Returns

dictionary of all metrics for each KCC

Return type

dict

Returns

dataframe of all metrics for each KCC

Return type

pandas.dataframe

metrics_eval_cop(predicted_y, test_y, logs_path, run_id=0)[source]

Get predicted and actual value for all KCCs and return regression metrics namely: Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, R-Squared Value

Parameters
  • predicted_y – predicted values for the process parameters

  • predicted_y – actual values for the process parameters

  • logs_path (str (required)) – Logs path to save the evaluation metrics

Returns

dictionary of all metrics for each KCC

Return type

dict

Returns

dataframe of all metrics for each KCC

Return type

pandas.dataframe