sciquence.sequences.wingen

sciquence.sequences.wingen(X, window_size, step=1, raw=False)

Generate subsequences from a single sequence. Generator usage reduces memory consumption.

Parameters:

• X (ndarray (n_samples, n_features)) – Array of size
• window_size (int) – Size of sliding window
• step (int) – Size of sliding window step
• raw (bool) – If true, the last window will be yielded even if shorter than

Yields:

subsequence (ndarray (window_size, n_features)) – Subsequence from X sequence

Examples

>>> import sciquence.sequences as sq
>>> import numpy as np
>>> X = np.array([[1, 2, 3,],
>>>               [11, 12, 13],
>>>               [21, 22, 23],
>>>               [31, 32, 33]])
>>> print sq.wingen(X, 2, 1).next()
>>> [[ 1  2  3]
>>>  [11 12 13]]