select_pvalue_significant_features_FP

This feature proprocessor object applies an ANOVA separately to each feature using data from the training set to find the p-value of all features. It then removes all features that have p-values greater than a specified threshold from the training and test sets.

Methods

fp = select_pvalue_significant_features_FP

Basic constructor

fp = set_pvalue_threshold(fp, X_data)

This method sets the threshold so that all features with ANOVA p-values less than this threshold will be used, and all features with p-values greater than this threshold will be excluded. This method must be called prior to using the object to normalize data.

fp = save_extra_preprocessing_info(save_extra_info)

If this method is passed a value of 1, the p-values for all features will be saved and returned along with the classifier results. It should be noted that setting this value to 1 will greatly increase the size of the results file.

The following methods are used by the cross-validator algorithm to apply feature preprocessing to the data:

[fp XTr_preprocesed] = set_properties_with_training_data(fp, XTr, YTr)

Calculates the p-values for each feature by applying an ANOVA to the training data, and returns potentially lower dimensional training data in XTr_normalized due to less selective feature being removed.

X_preprocessed = preprocess_test_data(fp, X_data)

Removes the features that were considered non-selective from the test data (X_data) (where the non-selective features were determined previously by running an ANOVA on the training data), and returns the modified data in X_preprocessed.

current_FP_info_to_save = get_current_info_to_save(fp)

Returns the p-values from ANOVAs applied to each feature in the structure current_preprocessing_information_to_save.the_p_values_org_order. These values will then be saved by the cross-validator.