机器学习课上的KNN作业（python）

        主要代码：KNN.py

'''
优点：精度高、对异常值不敏感、无数据输入假定
缺点：计算复杂度高、空间复杂度高
适用数据范围：数值型和标称型
'''
from numpy import *
import operator  #运算符模块
def createDataSet():
    group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]])
    labels = ['A', 'A', 'B', 'B']
    return group, labels
def classify0(inX, dataSet, labels, k):
    '''

    :param inX: 输入要分类的向量
    :param dataSet: 已有的数据分类
    :param labels: 分类标签
    :param k: 选择就近的k个分类
    :return:
    '''
    dataSetSize = dataSet.shape[0]  #求行数
    diffmat = tile(inX, (dataSetSize, 1)) - dataSet  #复制成样本数据的个数，然后减去
    sqDiffmat = diffmat**2  #每个位置平方
    sqDistances = sqDiffmat.sum(axis = 1)  #行求和
    distances = sqDistances ** 0.5  #开根号
    sortedDistIndicise = distances.argsort()   #排序，返回的坐标值
    classCount = {}  #创建字典
    for i in range(k):
        voteIlabel = labels[sortedDistIndicise[i]] #获取标签
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1  #标签计数
    sortedClassCount = sorted(classCount.items(), key = operator.itemgetter(1),\
                              reverse = True)
    classCount.items()
    #将classCount字典分解为元组列表，operator.itemgetter(1)
    #按照第二个元素的次序对元组进行排序，reverse = True是逆序，即按照从大到小的顺序排列
    return sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    returnMat = zeros((numberOfLines, 3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()  #除去所有回车符
        listFromLine = line.split('\t')  #将整行数据分割成一个元素列表
        returnMat[index, :] = listFromLine[0 : 3]  #取前三个数据
        classLabelVector.append(int(listFromLine[-1]))  #取标签
        index += 1
    return returnMat, classLabelVector

def autoNorm(dataSet):
    '''

    标准化公式：newValue = (oldValue - min) / (max - min)
    '''
    minVals = dataSet.min(0)  #0表示每一列的最小值
    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


#测试准确率
def datingClassTest(filename):
    hoRatio = 0.10   #测试百分之十的数据
    datingDataMat, datingLabels = file2matrix(filename)  #读取数据
    normMat, ranges, minVals = autoNorm(datingDataMat)  #标准化
    m = normMat.shape[0]
    numTestVecs = int(m * hoRatio)
    errorCount = 0.0
    for i in range(numTestVecs):
        classfierResult = classify0(normMat[i, :], normMat[numTestVecs: m, :], \
                                    datingLabels[numTestVecs : m], 4)
        print('the classifier came back with: %d, the real answer is: %d'\
              %(classfierResult, datingLabels[i]))
        if(classfierResult != datingLabels[i]):
            errorCount += 1.0
    print('the total error rate is:%d' % (errorCount / float(numTestVecs)))

测试导入数据：利用KNN.createDataSet()测试导入数据，以及KNN.file2matrix()导入分类数据。

data.txt为任意的分类数据

import KNN
group, labels = KNN.createDataSet()
print(KNN.classify0([0,0], group, labels, 3))
dataingDataMat, datingLabels =  KNN.file2matrix('data.txt')
print(dataingDataMat, datingLabels)

        在分类前，可以对数据进行分析，例如画图分析

# 创建散点图
fig = plt.figure()
ax = fig.add_subplot(111)

# 设置标题
ax.set_title('Scatter plot')
# 设置x轴标签
ax.set_xlabel("X")
# 设置y轴标签
ax.set_ylabel("Y")
ax.scatter(dataingDataMat[:, 0], dataingDataMat[:, 2], 15.0*array(datingLabels), \
           15.0 * array(datingLabels))
plt.show()

 对每个数据标签

fig = plt.figure()
ax = fig.add_subplot(111)
datingLabels = array(datingLabels)
idx_1 = where(datingLabels == 1)[0][:]#去坐标
ax.scatter(dataingDataMat[idx_1,0], dataingDataMat[idx_1,2], c='r', label='1',s=20,marker='*')
idx_2 = where(datingLabels == 2)[0][:]
ax.scatter(dataingDataMat[idx_2,0], dataingDataMat[idx_2,2], c='b', label='2',s=10,marker='o')
idx_3 = where(datingLabels == 3)[0][:]
ax.scatter(dataingDataMat[idx_3,0], dataingDataMat[idx_3,2], c='g', label='3',s=30,marker='+')
# 设置图标
plt.legend(loc='upper right')
plt.show()

 最后对数据进行标准化，以及计算准确率

# 数据标准化
# normMat, ranges, minVals = KNN.autoNorm(dataingDataMat)



#计算正确率
#KNN.datingClassTest('data.txt')

        如果对于画图部分的代码有问题可以参考以下几个大佬的博客：

https://blog.csdn.net/qq_29581601/article/details/81285187

https://www.cnblogs.com/pengsky2016/p/8126623.html