def faster_frequent_words(text, k):
frequent_patterns = set()
frequency_array = computing_frequencies(text, k)
max_count = max(frequency_array)
for pattern, count in frequency_array.iteritems():
if count == max_count:
frequent_patterns.add(pattern)
def faster_frequent_words(text, k):
frequent_patterns = set()
frequency_array = computing_frequencies(text, k)
max_count = max(frequency_array)
for pattern, count in frequency_array.iteritems():
if count == max_count:
frequent_patterns.add(pattern)
def faster_frequent_words(text, k):
frequent_patterns = []
frequency_array = cf.computing_frequencies(text,k)
max_count = max(frequency_array)
for i in range(0,4**k):
if frequency_array[i] == max_count:
pattern = cf.number_to_pattern(i,k)
if pattern not in frequent_patterns:
frequent_patterns.append(pattern)
return frequent_patterns
def clump_finding(genome, k, t, L):
frequent_patterns = []
clump = [0] * (4**k)
for i in range(0,len(genome)-L+1):
text = genome[i:i+L]
frequency_array = cf.computing_frequencies(text,k)
for index in range(0,4**k):
if frequency_array[index] >= t:
clump[index] = 1
for i in range(0,4**k):
if clump[i] == 1:
pattern = number_to_pattern(i, k)
frequent_patterns.append(pattern)
return frequent_patterns