sampling.py 文件源码

def read_files(directory, length, num):
    files = [join(directory, f)
             for f in listdir(directory) if isfile(join(directory, f))]

    # make sure there are enough text chunks to make num combinations
    # of them.
    txt = ""
    count = 0
    for f in files:
        print("reading %s..." % (f))
        txt += read(f)
        num_chunks = len(txt) / length
        count = count + 1
        if num < nCr(num_chunks, 2):
            break

    print("Read %s/%s files in '%s'" % (count, len(files), directory))

    chunks = [txt[x:x + length] for x in range(0, len(txt), length)]

    print("Calculating distance average of %s measurements of text " +
          "strings length %s...") % (num, length)

    return list(islice(combinations(chunks, 2), 0, num))