def cv_match_index_chunk(texts, pattern, chunk_size='m'):
"""
Performs the cv_match_index algorithm on chunks that are 'chunk_size' long.
If the length of the portion of the text that we're sampling is less than
the length of the pattern, we pad the end with 0s. Change this if 0s are in
the alphabet.
This is similar to fftmatch.fft_match_index_n_log_m, but it operates on
multiple texts at the same time.
Arguments
---------
texts : list of str
the genomic strings to search
pattern : str
the pattern that may be contained in multiple locations inside the text
chunk_size : type str or int
if 'm', it will use the standard algorithm for the n log m algorithm,
which breaks the string into 2m size chunks and performs the
fft match index algorithm on those chunks
if a positive integer, it will break up the string into size
2*chunk_size chunks
returns: a list containing the 0-based indices of matches of pattern in text
"""
if not (chunk_size == 'm' or
((type(chunk_size) == int) and chunk_size > 0)):
raise Exception('fft_match_index_n_log_m chunk_size must be str or \
positive integer')
n = max(map(len, texts))
m = len(pattern)
texts = texts_to_array(texts)
pattern = np.array([string_to_binary_array(pattern)])\
.astype(np.float32)
start = 0
if chunk_size == 'm':
chunk_size = m
indices = [np.array([])] * texts.shape[0]
while start < n - chunk_size:
index = cv_match(texts[:, start:start + chunk_size * 2], pattern)
for i in range(len(indices)):
if index[i].shape > 0:
indices[i] = np.append(indices[i], start + index[i])
start += chunk_size
out = [[]] * texts.shape[0]
for i in range(len(out)):
out[i] = np.unique(indices[i]).astype(int)
return np.array(out)
def cv_match_index_chunk(texts, pattern, chunk_size='m'):
"""
Performs the cv_match_index algorithm on chunks that are 'chunk_size' long.
If the length of the portion of the text that we're sampling is less than
the length of the pattern, we pad the end with 0s. Change this if 0s are in
the alphabet.
This is similar to fftmatch.fft_match_index_n_log_m, but it operates on
multiple texts at the same time.
Arguments
---------
texts : list of str
the genomic strings to search
pattern : str
the pattern that may be contained in multiple locations inside the text
chunk_size : type str or int
if 'm', it will use the standard algorithm for the n log m algorithm,
which breaks the string into 2m size chunks and performs the
fft match index algorithm on those chunks
if a positive integer, it will break up the string into size
2*chunk_size chunks
returns: a list containing the 0-based indices of matches of pattern in text
"""
if not (chunk_size == 'm' or ((type(chunk_size) == int) and chunk_size>0)):
raise Exception('fft_match_index_n_log_m chunk_size must be str or \
positive integer')
n = max(map(len, texts))
m = len(pattern)
texts = texts_to_array(texts)
pattern = np.array([string_to_binary_array(pattern)])\
.astype(np.float32)
start = 0
if chunk_size == 'm':
chunk_size = m
indices = [np.array([])] * texts.shape[0]
while start < n-chunk_size:
index = cv_match(texts[:,start:start+chunk_size*2], pattern)
for i in range(len(indices)):
if index[i].shape > 0:
indices[i] = np.append(indices[i], start+index[i])
start += chunk_size
out = [[]]*texts.shape[0]
for i in range(len(out)):
out[i] = np.unique(indices[i]).astype(int)
return np.array(out)
def cv_match_index(texts, pattern):
"""
This method uses Open CV's template matching algorithm to do substring
matching inside of len(texts) genome strings for the specified pattern
"""
texts = texts_to_array(texts)
pattern = np.array([string_to_binary_array(pattern)])\
.astype(np.float32)
return cv_match(texts, pattern)
def cv_match_index(texts, pattern):
"""
This method uses Open CV's template matching algorithm to do substring
matching inside of len(texts) genome strings for the specified pattern
"""
texts = texts_to_array(texts)
pattern = np.array([string_to_binary_array(pattern)])\
.astype(np.float32)
return cv_match(texts, pattern)
def cv_match_index_gpu(texts, pattern):
texts = texts_to_array(texts)
pattern = cv.fromarray(texts_to_array(pattern))
texts = cv.fromarray(texts)
def cv_match_index_gpu(texts, pattern):
texts = texts_to_array(texts)
pattern = cv.fromarray(texts_to_array(pattern))
texts = cv.fromarray(texts)