(机器学习)-knn分类器的两个实例

1 KNN电影的分类K-Nearest Neighbor

根据打斗镜头和接吻镜头来给电影分出到底是动作片还是爱情片

存在一个样本数据集合，也称作训练样本集，并且样本集中每个数据都存在标签，即我们知道样本集中每一个数据与所属分类的对应关系。输入本有标签的新数据后，将新数据的每个特征与样本集中数据对应的特征进行比较，然后算法提取出样本集中特征最相似数据（最近邻）的分类标签。一般来说，我们只选择样本数据集中前k个最相似的数据，通常k是不大于20的整数

最后，选择k个最相似数据中出现次数最多的分类，作为新数据的分类

# -*- coding:utf-8 -*-
# @Time : 19-4-14 下午4:16
# @Author : flower
# @Filename : 7_knn1.py
# @software : PyCharm

import numpy as np
def createDataSet():
    group = np.array([[3,104],[2,100],[1,81],[101,10],[95,5],[98,2]])
    labels = ['Roman','Roman','Roman','Action','Action','Action']
    return group,labels

def classify(inX,dataSet,labels,k):
    """

    :param inX:要预测的电影数据 eg[18,90]
    :param dataSet: 我们要传入的已知数据集
    :param labels: 我们传入的标签 eg,labels
    :param k: KNN里的K,也就是要选几个近邻
    :return: 电影类型的排序
    """
    dataSetSize = dataSet.shape[0] # 取6:(6,2)(数据集一共6行 2列)
    # 重复inx，把他重复成((dataSetSize,1))矩阵(6,1)
    diffMat = np.tile(inX,(dataSetSize,1))-dataSet # [[18,90],[18,90].....] - [[3,104],[2,100],[1,81],[101,10],[95,5],[98,2]]
    sqDiffMat = diffMat **2  # 平方
    sqDistance = sqDiffMat.sum(axis=1)  # axis=1 行相加
    distances = sqDistance ** 0.5 # 开根号
    sortedDistIndicies = distances.argsort()  # 排序 ,输出index值 [1 2 0 4 3 5]
    classCount={}
    for i in range(k):
        voteLable = labels[sortedDistIndicies[i]]
        classCount[voteLable] = classCount.get(voteLable,0) +1
        # 为了避免0影响计算 所以加1
        # print(classCount)
        sortClassCount = sorted(classCount.items(),key=lambda d:float(d[1]),reverse=True)
        return sortClassCount


if __name__ == '__main__':
    group,label = createDataSet()
    result = classify([18,90],group,label,3)
    print(result)

输出:
[(‘Roman’, 1)]

2.约会app的改进

原数据:链接: https://pan.baidu.com/s/11L68F1Of386DcvKQzK9JKw 提取码: hwj6

#encoding:utf-8
"""
KNN实现，海伦的约会
"""
import numpy as np
import matplotlib.pyplot as plt

def file2matrix(filename):
    fr = open(filename)
    arrayOfLines = fr.readlines()
    # print(arrayOfLines)
    numerOfLines = len(arrayOfLines)
    returnMat = np.zeros((numerOfLines, 3))
    classLabelVetor = []
    index = 0
    for line in arrayOfLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index, :] = listFromLine[0:3]
        classLabelVetor.append(listFromLine[-1])
        index += 1
    return returnMat, classLabelVetor

def autoNorm(dataSet):
    maxVals = dataSet.max(0)
    m = dataSet.shape[0]
    normDataSet = dataSet/np.tile(maxVals, (m, 1))
    return normDataSet, maxVals

def classify(inX, dataSet, labels, k):
    """
    :param inX: 要预测的电影数据 e.g. [18, 90]
    :param dataSet: 我们要传入的已知数据集 e.g. group  相当于x
    :param labels:  我们要传入的标签 e.g. labels  相当于y
    :param k: KNN里的k， 也就是说我们要选几个近邻
    :return: 电影类型的排序
    """
    dataSetSize = dataSet.shape[0] # (6,2) 6
    # tile会重复inX, 把他重复成（datasetsize, 1）型的矩阵
    # print(inX)
    # (x1 - y1), (x2- y2)
    diffMat = np.tile(inX, (dataSetSize, 1)) - dataSet
    # 平方
    sqDiffMat = diffMat ** 2
    # 相加, axis=1 行相加
    sqDistance = sqDiffMat.sum(axis=1)
    # 开根号
    distances = sqDistance ** 0.5
    # print(distances)
    # 排序 输出的是序列号index，并不是值
    sortedDistIndicies = distances.argsort()
    # print(sortedDistIndicies)

    classCount = {}
    for i in range(k):
        voteLabel = labels[sortedDistIndicies[i]]
        classCount[voteLabel] = classCount.get(voteLabel, 0) + 1
        # print(classCount)
    sortedClassCount = sorted(classCount.items(), key=lambda d: float(d[1]), reverse=True)
    return sortedClassCount

def datingClassTest(Person):
    datingDataMat, datingLabels = file2matrix('./datingTestSet2.txt')
    print(datingDataMat, datingLabels)
    normDataSet, maxVals = autoNorm(datingDataMat)
    classiferResult = classify(Person/maxVals, normDataSet, datingLabels, 3)
    # print(classiferResult)
    if classiferResult[0][0] == '1':
        print("Didn`t Like")
    elif classiferResult[0][0] == '2':
        print("Smalll Does Like")
    else:
        print("Large Does Like")

if __name__ == '__main__':
    datingDataMat, datingLabels = file2matrix('./datingTestSet2.txt')
    #我们要把数据改成astype形式
    datingLabels = np.array(datingLabels)
    datingLabels = datingLabels.astype('float64')
    # print(datingLabels)

    # 创建画布
    fig = plt.figure()
    ax = fig.add_subplot(111)
    # print(datingDataMat)
    ax.scatter(datingDataMat[:, 0], datingDataMat[:, 2], 15.0*datingLabels, datingLabels)
    plt.show()

    normDataSet, maxVals = autoNorm(datingDataMat)
    print(normDataSet)

    datingClassTest([30000, 10 ,1.3])

输出:
Large Does Like