A feature-preprocessor (FP) method to pre-process training and test data

This is a generic function that must be implemented by all FP objects. This object learns a set of parameters from the training data (i.e., the data generated from a datasource get_data() method). The preprocess_data() method then uses these parameters do processing on the training and test data before the data is sent to the classifier. This method should not be called directly but instead it is used internally by the cross-validator (CV) object.

preprocess_data(fp, training_set, test_set)

Arguments

fp	The FP object.
training_set	The training set data from one time bin. This is a data frame where the rows correspond to data from a given trial. There must be a column called train_labels that has the labels of what occurred on each trial. The rest of the columns correspond to the neural activity of a particular site on each trial (and typically have names like site_0001, site_0002, etc).
test_set	The test set data from all times. This is a data frame where the rows correspond to data from a given trial. There must be a column called time_ bin that contains a label indicating the time point that a row (test point) came from. The rest of the columns correspond to the neural activity of a particular site on each test trial (and typically have names like site_0001, site_0002, etc).

Value

A list is returned that contains two data frames called training_set and test_set which contain data in the same format as the training_set and test_set arguments passed to this function, however the data in these data frames has been processed by the FP object.

See also

fp_zscore(), fp_select_k_features()