//样本数据编号,色泽,根蒂,敲声,纹理,脐部,触感,密度,含糖率,好瓜 1,青绿,蜷缩,浊响,清晰,凹陷,硬滑,0.697,0.46,是 2,乌黑,蜷缩,沉闷,清晰,凹陷,硬滑,0.774,0.376,是 3,乌黑,蜷缩,浊响,清晰,凹陷,硬滑,0.634,0.264,是 4,青绿,蜷缩,沉闷,清晰,凹陷,硬滑,0.608,0.318,是 5,浅白,蜷缩,浊响,清晰,凹陷,硬滑,0.556,0.215,是 6,青绿,稍蜷,浊响,清晰,稍凹,软粘,0.403,0.237,是 7,乌黑,稍蜷,浊响,稍糊,稍凹,软粘,0.481,0.149,是 8,乌黑,稍蜷,浊响,清晰,稍凹,硬滑,0.437,0.211,是 9,乌黑,稍蜷,沉闷,稍糊,稍凹,硬滑,0.666,0.091,否 10,青绿,硬挺,清脆,清晰,平坦,软粘,0.243,0.267,否 11,浅白,硬挺,清脆,模糊,平坦,硬滑,0.245,0.057,否 12,浅白,蜷缩,浊响,模糊,平坦,软粘,0.343,0.099,否 13,青绿,稍蜷,浊响,稍糊,凹陷,硬滑,0.639,0.161,否 14,浅白,稍蜷,沉闷,稍糊,凹陷,硬滑,0.657,0.198,否 15,乌黑,稍蜷,浊响,清晰,稍凹,软粘,0.36,0.37,否 16,浅白,蜷缩,浊响,模糊,平坦,硬滑,0.593,0.042,否 17,青绿,蜷缩,沉闷,稍糊,稍凹,硬滑,0.719,0.103,否
#前期整理# -*- coding: utf-8 -*-from itertools import islicedef test(): values = { 'color': { '青绿': 1, '乌黑': 2, '浅白': 3 }, 'root': { '蜷缩': 1, '稍蜷': 2, '硬挺': 3 }, 'sound': { '浊响': 1, '沉闷': 2, '清脆': 3 }, 'strip': { '清晰': 1, '稍糊': 2, '模糊': 3 }, 'texture': { '凹陷': 1, '稍凹': 2, '平坦': 3 }, 'feel': { '硬滑': 1, '软粘': 2 }, u'label': { '是': 1, '否': -1 } } fileread = file('d://a/xigua.txt', 'r', -1) biaotou = fileread.readline().strip('\n').strip(" ").split(",") biaotouc = biaotou[1:7] + [biaotou[-1].strip('\n').strip(" ")] biaotouEn = ['color', 'root', 'sound', 'strip', 'texture', 'feel', 'label'] biaotouDict = {} for index in range(len(biaotouEn)): biaotouDict[biaotouc[index]] = biaotouEn[index] res = [] for eachLine in fileread.readlines(): eachLineArray = eachLine.split(',') reselem = [] for elemIndex in range(len(eachLineArray)): eachLineArrayElemIndexOp=eachLineArray[elemIndex].strip('\n').strip(" ") if (biaotouDict.has_key(biaotou[elemIndex])): reselem.append(values[biaotouDict[biaotou[elemIndex]]][eachLineArrayElemIndexOp]) else: reselem.append(float(eachLineArrayElemIndexOp)) res.append(reselem) print resif __name__ == '__main__': test()
