sorry
this is the code :
B = 65521
T = {}
for datasetPath in directories:
    samples = [f for f in listdir(datasetPath)]
    for file in samples:
        filePath = datasetPath+"/"+file
        fileByteSequence = readFile(filePath)
        fileNgrams = byteSequenceToNgrams(fileByteSequence,N)
        hashFileNgramsIntoDictionary(fileNgrams,T)
K1 = 1000
import heapq
K1_most_common_Ngrams_Using_Hash_Grams = heapq.nlargest(K1, T)