def get_training_testing_prediction_stats(self):
print_to_consol(
'Getting basic stats for training set and cross-validation')
training_stats, y_train_pred, y_train_pred_proba = training_cv_stats_multiclass(
self.model, self.X_train_scaled, self.y_train, self.cv)
logging.info(
f'Basic stats achieved for training set and 3-fold CV \n'
f'Accuracy for each individual fold of 3 CV folds: {training_stats["acc_cv"]} \n'
f'Accuracy across all 3 CV-folds: {training_stats["acc"]} \n'
f'Recall across all 3 CV-folds: {training_stats["recall"]} \n'
f'Precision across all 3 CV-folds: {training_stats["precision"]} \n'
f'F1 score across all 3 CV-folds: {training_stats["f1-score"]} \n'
f'Storing cross-validated y_train classes in y_train_pred \n'
f'Storing cross-validated y_train probabilities in y_train_pred_proba \n'
)
print_to_consol(
'Getting class predictions and probabilities for test set')
test_stats, self.y_pred, self.y_pred_proba = testing_predict_stats_multiclass(
self.model, self.X_test_scaled, self.y_test)
y_pred_out = os.path.join(self.directory,
"y_pred_before_calibration.csv")
np.savetxt(y_pred_out, self.y_pred, delimiter=",")
y_pred_proba_out = os.path.join(self.directory,
"y_pred_proba_before_calibration.csv")
np.savetxt(y_pred_proba_out, self.y_pred_proba, delimiter=",")
logging.info(
f'Writing y_pred and y_pred_proba before calibration to disk. \n')
confidence_train = self.model.decision_function(self.X_train_scaled)
confidence_test = self.model.decision_function(self.X_test_scaled)
logging.info(
f'Predicting on the test set. \n'
f'Storing classes in y_pred and probabilities in y_pred_proba \n'
f'Prediction confidence for train set: {confidence_train} \n'
f'Prediction confidence for test set: {confidence_test} \n')
print_to_consol(
'Calculate prediction stats for y_pred and y_pred_proba of test set'
)
logging.info(
f'Basic stats on the test set. \n'
f'Prediction accuracy on the test set: {test_stats["predict_acc"]} \n'
f'Class distributio in the test set: {test_stats["class_distribution"]} \n'
f'Matthews Correlation Coefficient: {test_stats["mcc"]} \n')
def get_training_testing_prediction_stats(self):
print_to_consol(
'Getting basic stats for training set and cross-validation')
training_stats, y_train_pred, y_train_pred_proba = training_cv_stats_multiclass(
self.model, self.X_train, self.y_train, self.cv)
logging.info(
f'Basic stats achieved for training set and 3-fold CV \n'
f'Accuracy for each individual fold of 3 CV folds: {training_stats["acc_cv"]} \n'
f'Accuracy across all 3 CV-folds: {training_stats["acc"]} \n'
f'Recall across all 3 CV-folds: {training_stats["recall"]} \n'
f'Precision across all 3 CV-folds: {training_stats["precision"]} \n'
f'F1 score across all 3 CV-folds: {training_stats["f1-score"]} \n'
f'Storing cross-validated y_train classes in y_train_pred \n'
f'Storing cross-validated y_train probabilities in y_train_pred_proba \n'
)
print_to_consol(
'Getting class predictions and probabilities for test set')
test_stats, self.y_pred, self.y_pred_proba = testing_predict_stats_multiclass(
self.model, self.X_test, self.y_test)
logging.info(
f'Predicting on the test set. \n'
f'Storing classes in y_pred and probabilities in y_pred_proba \n')
print_to_consol(
'Calculate prediction stats for y_pred and y_pred_proba of test set'
)
logging.info(
f'Basic stats on the test set. \n'
f'Prediction accuracy on the test set: {test_stats["predict_acc"]} \n'
f'Class distributio in the test set: {test_stats["class_distribution"]} \n'
f'Matthews Correlation Coefficient: {test_stats["mcc"]} \n')
def detailed_analysis(self):
print_to_consol(
'Making a confusion matrix for test set classification outcomes')
matrix_stats, report = confusion_matrix_and_stats_multiclass(
self.y_test, self.y_pred, 'before_cal', self.directory)
logging.info(f'Detailed analysis of confusion matrix for test set. \n'
f'True positives: {matrix_stats["TP"]} \n'
f'True negatives: {matrix_stats["TN"]} \n'
f'False positives: {matrix_stats["FP"]} \n'
f'False negatives: {matrix_stats["FN"]} \n'
f'Classification accuracy: {matrix_stats["acc"]} \n'
f'Classification error: {matrix_stats["err"]} \n'
f'Sensitivity: {matrix_stats["sensitivity"]} \n'
f'Specificity: {matrix_stats["specificity"]} \n'
f'False positive rate: {matrix_stats["FP-rate"]} \n'
f'False negative rate: {matrix_stats["FN-rate"]} \n'
f'Precision: {matrix_stats["precision"]} \n'
f'F1-score: {matrix_stats["F1-score"]} \n')
logging.info(
f'Classification report on test set before calibration. \n'
f'{report} \n')
print_to_consol('Make a radar plot for performance metrics')
radar_dict = {
'Classification accuracy': matrix_stats["acc"],
'Classification error': matrix_stats["err"],
'Sensitivity': matrix_stats["sensitivity"],
'Specificity': matrix_stats["specificity"],
'False positive rate': matrix_stats["FP-rate"],
'False negative rate': matrix_stats["FN-rate"],
'Precision': matrix_stats["precision"],
'F1-score': matrix_stats["F1-score"],
'ROC AUC': None
}
plot_radar_chart(radar_dict, self.directory)
print_to_consol(
'Calibrating classifier and writing to disk; getting new accuracy')
self.calibrated_clf, clf_acc = calibrate_classifier(
self.model, self.X_cal_scaled, self.y_cal)
date = datetime.strftime(datetime.now(), '%Y%m%d_%H%M')
joblib.dump(
self.calibrated_clf,
os.path.join(self.directory,
'best_calibrated_predictor_' + date + '.pkl'))
logging.info(
f'Calibrated the best classifier with X_cal and y_cal and new accuracy {clf_acc}\n'
f'Writing file to disk disk in {self.directory} \n')
print_to_consol(
'Getting 95% confidence interval for calibrated classifier')
alpha, upper, lower = get_confidence_interval(
self.X_train_scaled, self.y_train, self.X_test_scaled, self.y_test,
self.calibrated_clf, self.directory, self.bootiter, 'calibrated')
logging.info(f'{alpha}% confidence interval {upper}% and {lower}% \n'
f'for calibrated classifier. \n')
print_to_consol('Running prediction for calibrated classifier')
print_to_consol(
'Getting class predictions and probabilities for test set with calibrated classifier'
)
test_stats_cal, self.y_pred_cal, self.y_pred_proba_cal = testing_predict_stats_multiclass(
self.calibrated_clf, self.X_test_scaled, self.y_test)
y_pred_cal_out = os.path.join(self.directory,
"y_pred_after_calibration.csv")
np.savetxt(y_pred_cal_out, self.y_pred_cal, delimiter=",")
y_pred_proba_cal_out = os.path.join(
self.directory, "y_pred_proba_after_calibration.csv")
np.savetxt(y_pred_proba_cal_out, self.y_pred_proba_cal, delimiter=",")
logging.info(
f'Writing y_pred and y_pred_proba after calibration to disk. \n'
f'Predicting on the test set with calibrated classifier. \n'
f'Storing classes for calibrated classifier in y_pred and probabilities in y_pred_proba. \n'
)
print_to_consol(
'Calculate prediction stats for y_pred and y_pred_proba of test set with calibrated classifier'
)
logging.info(
f'Basic stats on the test set woth calibrated classifier. \n'
f'Prediction accuracy on the test set: {test_stats_cal["predict_acc"]} \n'
f'Class distributio in the test set: {test_stats_cal["class_distribution"]} \n'
f'Matthews Correlation Coefficient: {test_stats_cal["mcc"]} \n')
print_to_consol(
'Making a confusion matrix for test set classification outcomes with calibrated classifier'
)
matrix_stats_cal, report_cal = confusion_matrix_and_stats_multiclass(
self.y_test, self.y_pred_cal, 'after_cal', self.directory)
logging.info(
f'Detailed analysis of confusion matrix for test set with calibrated classifier. \n'
f'True positives: {matrix_stats_cal["TP"]} \n'
f'True negatives: {matrix_stats_cal["TN"]} \n'
f'False positives: {matrix_stats_cal["FP"]} \n'
f'False negatives: {matrix_stats_cal["FN"]} \n'
f'Classification accuracy: {matrix_stats_cal["acc"]} \n'
f'Classification error: {matrix_stats_cal["err"]} \n'
f'Sensitivity: {matrix_stats_cal["sensitivity"]} \n'
f'Specificity: {matrix_stats_cal["specificity"]} \n'
f'False positive rate: {matrix_stats_cal["FP-rate"]} \n'
f'False negative rate: {matrix_stats_cal["FN-rate"]} \n'
f'Precision: {matrix_stats_cal["precision"]} \n'
f'F1-score: {matrix_stats_cal["F1-score"]} \n')
logging.info(
f'Classification report on test set afetr callibration. \n'
f'{report_cal} \n')
print_to_consol(
'Make a radar plot for performance metrics with calibrated classifier'
)
radar_dict_cal = {
'Classification accuracy': matrix_stats_cal["acc"],
'Classification error': matrix_stats_cal["err"],
'Sensitivity': matrix_stats_cal["sensitivity"],
'Specificity': matrix_stats_cal["specificity"],
'False positive rate': matrix_stats_cal["FP-rate"],
'False negative rate': matrix_stats_cal["FN-rate"],
'Precision': matrix_stats_cal["precision"],
'F1-score': matrix_stats_cal["F1-score"],
'ROC AUC': None
}
plot_radar_chart(radar_dict_cal, self.directory)
end = datetime.now()
duration = end - self.start
logging.info(f'Training lasted for {duration} minutes \n')
logging.info(f'Training completed \n')
print_to_consol('Training completed')
