机器学习实战——在约会网站上使用ｋ－近邻算法

from numpy import *
import operator
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from os import listdir
import matplotlib.pyplot as plt


def autoNorm(dataSet):
    minVals = dataSet.min(0)　　＃从一列中选取最小值
    maxVals = dataSet.max(0)　　＃从一列中选取最大值
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]　　　　＃第二维的长度
    normDataSet = dataSet - tile(minVals, (m, 1))
    normDataSet = normDataSet / tile(ranges, (m, 1))  # element wise divide
    return normDataSet, ranges, minVals


def classify0(inX, dataSet, labels, k):　　　＃ｋ－近邻算法具体实现
    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 file2matrix(filename):　　　＃数据处理
    fr = open(filename)
    numberOfLines = len(fr.readlines())  # get the number of lines in the file
    returnMat = zeros((numberOfLines, 3))  # prepare matrix to return
    classLabelVector = []  # prepare labels return
    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 datingClassTest():　　　　　　＃归一化数值
    hoRatio = 0.50      #hold out 10%
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)　　＃取第ｉ行
        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: %f" % (errorCount/float(numTestVecs)))
    print(errorCount)


datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = autoNorm(datingDataMat)
X_train, X_test, y_train, y_test = train_test_split(normMat,datingLabels,random_state=0)
clf = KNeighborsClassifier(n_neighbors=3)
clf.fit(X_train, y_train)
y_pred = clf.predict([datingDataMat[0]])
print(y_pred)
print(clf.score(X_test,y_test))