python数据集处理，加载成list

正确加载方法：

def loadDataSet(filename):
    numFeatures = len(open(filename).readline().split('\t')) - 1
    dataMat = []
    labelMat = []
    f = open(filename)
    for line in f.readlines():
        lineArr=[]
        curLine=line.strip().split('\t')
        for i in range(0,numFeatures):
            lineArr.append(float(curLine[i]))
        dataMat.append(lineArr)
        labelMat.append(float(curLine[-1]))
    return dataMat,labelMat

 

错误加载方法：

def loadDataSet(filename):
    f = open(filename)
    numFeatures = len(f.readline().split('\t')) - 1
    dataMat = []
    labelMat = []
    for line in f.readlines():
        lineArr=[]
        curLine=line.strip().split('\t')
        for i in range(0,numFeatures):
            lineArr.append(float(curLine[i]))
        dataMat.append(lineArr)
        labelMat.append(float(curLine[-1]))
    return dataMat,labelMat

 原因：获取numFeatures时使用了readline()函数，使得句柄f移动到第二行，下面代码中的readlines()函数只能读取剩下的行，相当于少读取了第一行。