getFeature.py 文件源码

def getFeature():
    fileData = open("data")
    row = []
    col = []
    data = []
    evalRes = []
    rowIndex = -1
    fileList = fileData.readlines()
    random.shuffle(fileList)
    for line in fileList:
        line = line.rstrip('\n')
        dataList = re.split(' |:', line)

        if int(dataList[0]) >= 7:
            evalRes.append(1)
        else:
            if int(dataList[0]) <= 4:
                evalRes.append(-1)
            else:
                continue
        del dataList[0]

        rowIndex = rowIndex + 1
        row.extend([rowIndex] * int(len(dataList) / 2))
        col.extend(map(int, dataList[::2]))
        data.extend(map(int, dataList[1::2]))

    featureMatrix = csr_matrix((data, (row, col)))
    featureMNew = SelectKBest(chi2, k=20000).fit_transform(featureMatrix, evalRes)
    return featureMNew, evalRes