tf.keras.utils.to_ordinal

Converts a class vector (integers) to an ordinal regression matrix.

View aliases

Compat aliases for migration

See Migration guide for more details.

`tf.compat.v1.keras.utils.to_ordinal`

tf.keras.utils.to_ordinal(
    y, num_classes=None, dtype='float32'
)

This utility encodes class vector to ordinal regression/classification matrix where each sample is indicated by a row and rank of that sample is indicated by number of ones in that row.

Args
y	Array-like with class values to be converted into a matrix (integers from 0 to num_classes - 1).
num_classes	Total number of classes. If None, this would be inferred as max(y) + 1.
dtype	The data type expected by the input. Default: 'float32'.

Returns
An ordinal regression matrix representation of the input as a NumPy array. The class axis is placed last.

Example:

a = tf.keras.utils.to_ordinal([0, 1, 2, 3], num_classes=4)
print(a)
[[0. 0. 0.]
 [1. 0. 0.]
 [1. 1. 0.]
 [1. 1. 1.]]