def cutStrings(seqs, length):
print('Preparing Data...')
X = np.zeros([0, length * 2 + 3])
count = 0
bar = ProgressBar()
for seq in bar(seqs):
paddedSeq = np.pad(np.asarray(seq), (length, length),
'constant',
constant_values=23.)
if paddedSeq.size > length * 2:
cutSeq = vaw(paddedSeq, (length * 2 + 1, ))
label = np.ones([
cutSeq.shape[0],
]) * cutSeq[:, length]
cutSeq = np.delete(cutSeq, length, axis=1)
indLabel = np.ones([cutSeq.shape[0], 1]) * np.arange(
cutSeq.shape[0])[:, None]
cutSeq = np.concatenate(
(indLabel, indLabel[::-1, :], cutSeq, label[:, None]), 1)
X = np.concatenate((X, cutSeq), 0)
count += 1
else:
continue
print('Used {} proteins.'.format(count))
return X
def _get_patches(mspec, w, step):
h = mspec.shape[1]
data = vaw(mspec, (w,h), step=step)
data.shape = (len(data), w*h)
data = (data - np.mean(data, axis=1).reshape((len(data), 1))) / np.std(data, axis=1).reshape((len(data), 1))
lfill = [data[0,:].reshape(1, h*w)] * (w // (2 * step))
rfill = [data[-1,:].reshape(1, h*w)] * (w // (2* step) - 1 + len(mspec) % 2)
data = np.vstack(lfill + [data] + rfill )
finite = np.all(np.isfinite(data), axis=1)
data.shape = (len(data), w, h)
return data, finite
def avg_patch_vals(A, patch_size=(3, 3), pad_mode='edge'):
'''Get the average value of each patch of A.
Parameters
----------
A : array_like
Array to patch-ify.
patch_size : tuple, optional
Size of patches.
pad_mode : str, optional
Mode to pass to numpy.pad.
'''
patches = vaw(A, patch_size)
pad_width = [
int((A.shape[ii] - patches.shape[ii]) / 2) for ii in range(A.ndim)
]
patches = np.pad(patches, pad_width, pad_mode)
return np.mean(np.mean(patches, axis=-1), axis=-1)
