Performs a series of simple checks on a dataset that may be important to perform ahead of data analysis. This function makes no changes to data, but reports potential course of action that can be taken using preprocess
checkData(x, name = NULL, str = FALSE, recommend = TRUE,
reportCases.thres = NULL, reportFeatures.thres = NULL)
Input dataset; will be converted to data.frame
String, optional: Name of dataset. (This is helpful when applying preprocess
on a list of items using by vectorization, e.g. using *ply commands, where the names of the list
elements will not be displayed correctly)
Logical: If TRUE, show output of str
Logical: If TRUE, print recommendations based on check. Default = TRUE
Float (0, 1]: Report, by number, all cases missing greater or equal to this fraction of features
Float (0, 1]: Report, by name, all features missing in greater or equal to this fraction of cases