完整代码
from __future__ import print_function
from numpy import *
import operator
from os import listdir
from collections import Counter
def file2matrix(filename):
"""
Desc:
导入训练数据
:param filename:数据文件路径
:return: 数据矩阵 returnMat 和对应的类别 classLabelVector
"""
fr = open(filename)
numberOfLines = len(fr.readlines())
returnMat = zeros((numberOfLines, 3))
classLabelVector = []
fr = open(filename)
index = 0
for line in fr.readlines():
line = line.strip()
listFromLine = line.split('\t')
returnMat[index, :] = listFromLine[0:3]
classLabelVector.append(int(listFromLine[-1]))
index += 1
return returnMat, classLabelVector
def autoNorm(dataSet):
"""
归一化特征值,消除属性之间量级不同导致的影响
:param dataSet: 数据集
:return: 归一化后的数据集normDataSet,ranges 和 minVals即范围与最小值(没有用到)
归一化公式:
Y = (X-Xmin)/(Xmax-Xmin)
其中的 min 和 max 分别是数据集中的最小特征值和最大特征值。该函数可以自动将数字特征值转化为0到1的区间。
"""
minVals = dataSet.min(0)
maxVals = dataSet.max(0)
ranges = maxVals - minVals
normDataSet = zeros(shape(dataSet))
m = dataSet.shape[0]
normDataSet = dataSet - tile(minVals, (m, 1))
normDataSet = normDataSet / tile(ranges, (m, 1))
return normDataSet, ranges, minVals
def classify0(inX, dataSet, labels, k):
"""
inX: 用于分类的输入向量
dataSet: 输入的训练样本集
labels: 标签向量
k: 选择最近邻居的数目
注意:labels元素数目和dataSet行数相同;程序使用欧式距离公式.
预测数据所在分类可在输入下列命令
kNN.classify0([0,0], group, labels, 3)
"""
dataSetSize = dataSet.shape[0]
diffMat = tile(inX, (dataSetSize, 1)) - dataSet
sqDiffMat = diffMat ** 2
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances ** 0.5
sortedDistIndicies = distances.argsort()
classCount = {}
for i in range(k):
voteIlabel = labels[sortedDistIndicies[i]]
classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
return sortedClassCount[0][0]
def datingClassTest():
"""
对约会网站的测试方法
:return: 错误数
"""
hoRatio = 0.1
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m * hoRatio)
print('numTestVecs=', numTestVecs)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = classify0(normMat[i, :], normMat[numTestVecs:m, :], datingLabels[numTestVecs:m], 3)
print("the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i]))
if classifierResult != datingLabels[i]:
errorCount += 1.0
print("the total error rate is: %0.3f" % (errorCount / float(numTestVecs)))
print("the total number of errors is: %0.1f" % errorCount)
def classifyPerson():
resultList = ['not at all', 'in small doses', 'in large doses']
percentTats = float(input('percentage of time spent playing video games?'))
ffMiles = float(input('frequent filer miles earned per year?'))
iceCream = float(input("liters of ice cream consumed per year?"))
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = autoNorm(datingDataMat)
inArr = array([ffMiles, percentTats, iceCream])
classifierResult = classify0((inArr - minVals) / ranges, normMat, datingLabels, 3)
print("You will probably like this person: ", resultList[classifierResult - 1])
def img2vector(filename):
"""
将图像文本数据转换为向量
:param filename:数据文件路径
:return:数据矩阵 一维矩阵
该函数将图像转换为向量:该函数创建 1 * 1024 的NumPy数组,然后打开给定的文件,
循环读出文件的前32行,并将每行的头32个字符值存储在NumPy数组中,最后返回数组。
"""
returnVect = zeros((1, 1024))
fr = open(filename)
for i in range(32):
lineStr = fr.readline()
for j in range(32):
returnVect[0, 32 * i + j] = int(lineStr[j])
return returnVect
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir('trainingDigits')
m = len(trainingFileList)
trainingMat = zeros((m, 1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr)
testFileList = listdir('testDigits')
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2vector('testDigits\%s' % fileNameStr)
classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
print('the classifier came back with:%d,the real answer is:%d' % (classifierResult, classNumStr))
if classifierResult != classNumStr:
errorCount += 1.0
print('\n the total number of errors is:%d' % errorCount)
print('\n the total error rate is:%f' % (errorCount / float(mTest)))
if __name__ == '__main__':
classifyPerson()