机器学习学习笔记（一）之K邻近算法（KNeighborsClassifier）

算法步骤：
1.计算输入数据与已知标签样本集的距离
2.将步骤1计算的距离值进行排序
3.选取排序的前K个取值（K邻近算法中K的由来）
4.计算这K个取值中不同标签出现的频率，将频率最大的标签作为本次预测的结果

这里选取距离计算公式为欧式距离，欧式距离也是最常见的距离计算公式：

数据集 datingTestSet2.txt

40920	8.326976	0.953952	3
14488	7.153469	1.673904	2
26052	1.441871	0.805124	1
75136	13.147394	0.428964	1
38344	1.669788	0.134296	1
72993	10.141740	1.032955	1
35948	6.830792	1.213192	3
42666	13.276369	0.543880	3
67497	8.631577	0.749278	1
35483	12.273169	1.508053	3
50242	3.723498	0.831917	1
63275	8.385879	1.669485	1
5569	4.875435	0.728658	2
51052	4.680098	0.625224	1
77372	15.299570	0.331351	1
43673	1.889461	0.191283	1
61364	7.516754	1.269164	1
69673	14.239195	0.261333	1
15669	0.000000	1.250185	2
28488	10.528555	1.304844	3
6487	3.540265	0.822483	2
37708	2.991551	0.833920	1
22620	5.297865	0.638306	2
28782	6.593803	0.187108	3
19739	2.816760	1.686209	2
36788	12.458258	0.649617	3

sklearn直接调库实现

from sklearn.preprocessing import MinMaxScaler
from sklearn.neighbors import KNeighborsClassifier
import numpy as np


def file2matrix(filename): #打开文件，获取数据和标签
    love_dictionary = {'largeDoses':3, 'smallDoses':2, 'didntLike':1}
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)            #get the number of lines in the file
    returnMat = np.zeros((numberOfLines, 3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return
    index = 0
    for line in arrayOLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index, :] = listFromLine[0:3]
        if(listFromLine[-1].isdigit()):
            classLabelVector.append(int(listFromLine[-1]))
        else:
            classLabelVector.append(love_dictionary.get(listFromLine[-1]))
        index += 1
    return returnMat, classLabelVector
if __name__ == '__main__':

    hoRatio = 0.50      #取数据的50%作为已知标签的样本集 50%作为未知标签数据
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
    scaler = MinMaxScaler()  # 归一化数据
    scaler = scaler.fit(datingDataMat)  # fit，在这里本质是生成min(x)和max(x)
    normMat = scaler.transform(datingDataMat)  # 通过接口导出结果
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    errorCount = 0.0

    model =KNeighborsClassifier(n_neighbors=3)
    model.fit(normMat[numTestVecs:m, :], datingLabels[numTestVecs:m])
    y=model.predict(normMat[0:numTestVecs, :])
    #计算准确率
    result = y - datingLabels[0:numTestVecs]
    error=0
    for i in range(len(result)):
        if result[i]!=0:
            error+=1
    print(f'准确率：{((1-error/len(result))*100)}%')

import numpy as np
from os import listdir
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = np.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):
    love_dictionary = {'largeDoses':3, 'smallDoses':2, 'didntLike':1}
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)            #get the number of lines in the file
    returnMat = np.zeros((numberOfLines, 3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return
    index = 0
    for line in arrayOLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index, :] = listFromLine[0:3]
        if(listFromLine[-1].isdigit()):
            classLabelVector.append(int(listFromLine[-1]))
        else:
            classLabelVector.append(love_dictionary.get(listFromLine[-1]))
        index += 1
    return returnMat, classLabelVector


def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = np.zeros(np.shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - np.tile(minVals, (m, 1))
    normDataSet = normDataSet/np.tile(ranges, (m, 1))   #element wise divide
    return normDataSet, ranges, minVals

def datingClassTest():
    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)
        print("返回的分类结果是: %d, 真实的分类标签是: %d" % (classifierResult, datingLabels[i]))
        if (classifierResult != datingLabels[i]): errorCount += 1.0
    print('准确率为{:.2f}%'.format((1-errorCount / float(numTestVecs))*100))
    print(errorCount)
if __name__ == '__main__':
    datingClassTest()