CAT2DSET

Create categorical dataset

    A = CAT2DSET(DATA,LABELS)

Input
DATA	Cell array or integer array with categorical data
LABELS	Desired labels, default: unlabeled

Output
A	PRTools dataset

Description

This routine creates a dataset of categorical data, either given as  integers, or as a set of string arrays. If given, the dataset is labeled  by LABELS.

In case DATA is an array of integers, the unique values of the columns  are used as the 'names' of the categories of that features (stored as  doubles).

In case DATA is a cell array of size [1,K], it is assumed that every cell  contains a string array of M named categories, in which M is the number  of objects.

In case DATA is a cell array of size [M,1], it is assumed that every cell  contains a string array of K named categories, one for every feature.  Alternatively DATA can be a [M,K] cell array containing a single string  per cell.

Use CELL2DSET for conversion of mixed cell types into a dataset.  Use FEAT2LAB for conversion of a categorical feature into a class label.  A categorical dataset A can be combined with a dataset B representing a  set of numeric features for the same objects by [A B].

See also

datasets, prdataset, setfeatdom, getfeatdom, feat2lab, cell2dset, feattypes,