test.py 文件源码

def feature(terms):
    dataMatrix = np.genfromtxt(finaltest, delimiter='|', dtype=None, skip_header=True)
    n = dataMatrix.size
    l = len(terms)
    occurence = np.zeros((n, l), dtype=np.int)
    d = 0
    for row in dataMatrix:
        temp = row[0].lower().decode('UTF-8').split(' ')
        for i in range(l):
            if terms[i] in temp:
                occurence[d][i] += 1
        d += 1
    transformer = TfidfTransformer()
    tfdif = transformer.fit_transform(occurence)
    occurence = tfdif.toarray()
    np.savetxt('occurencetest.csv',occurence,delimiter=',')

    return occurence, dataMatrix