KNN(k近邻)

参考链接：http://blog.csdn.net/c406495762/article/details/75172850

 

import numpy as np
import operator


def creatDataset():
    group = np.array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
    labels = ['A','A','B','B']
    return group,labels


def knn(inx,dataset,labels,k):
    datasetsize  = dataset.shape[0]
    diffmat = np.tile(inx,(datasetsize,1))-dataset
    #print(diffmat)
    sqdiffmat = diffmat**2
    sqdistances = sqdiffmat.sum(1)
    distances = sqdistances**0.5
    sorteddistindices = distances.argsort()
    #print(sorteddistindices)
    classcount = {}
    for i in range(k):
        voteilabel = labels[sorteddistindices[i]]
        #print(voteilabel)
        classcount[voteilabel] = classcount.get(voteilabel, 0) + 1
        #print(classcount[voteilabel])
    #print(classcount)
    sortedClassCount = sorted(classcount.items(), key=operator.itemgetter(1), reverse=True)
    #print(sortedClassCount)
    return sortedClassCount[0][0]


if __name__ == '__main__':
    #创建数据集
    group, labels = creatDataset()
    #测试集
    test = [1.2,1.8]
    #kNN分类
    test_class = knn(test, group, labels, 3)
    #打印分类结果
    print(test_class)

 

 

根据三个特征判断对人的喜好

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
import matplotlib.lines as mlines
from pylab import *
import operator
#mpl.rcParams['font.sans-serif'] = ['SimHei'] #指定默认字体
#mpl.rcParams['axes.unicode_minus'] = False #解决保存图像是负号'-'显示为方块的问题

def file_matrix():
    """
    处理数据格式问题
    :return: 特征矩阵，标签矩阵
    """
    fr = open(r'C:\Users\TuZhiqiang\Desktop\MLIA\Ch02\datingTestSet.txt')
    array_of_lines = fr.readlines()
    number_of_lines = len(array_of_lines)
    return_matrix = np.zeros((number_of_lines,3))
    class_lable_vector = []
    index = 0
    for line in array_of_lines:
        line = line.strip()
        list_from_line = line.split('\t')
        return_matrix[index,:] = list_from_line[0:3]
        if list_from_line[-1] == 'didntLike':
            class_lable_vector.append(1)
        elif list_from_line[-1] == 'smallDoses':
            class_lable_vector.append(2)
        elif list_from_line[-1] == 'largeDoses':
            class_lable_vector.append(3)
        index +=1
    #print(class_lable_vector)
    return return_matrix,class_lable_vector



def showdatas(dating_data_matrix,dating_lables):
    """
    数据可视化
    :param dating_data_matrix: 特征矩阵
    :param dating_lables: 标签矩阵
    :return: 特征之间的关系图像
    """
    font = FontProperties(fname=r"C:\WINDOWS\Fonts\simsun.ttc", size=14)
    fig , axs = plt.subplots(nrows=2, ncols=2, sharex=False, sharey=False, figsize=(13, 8))  #画多图
    number_of_lables = len(dating_lables)
    labels_colors = []
    for i in dating_lables:
        if i == 1:
            labels_colors.append('black')
        if i == 2:
            labels_colors.append('orange')
        if i == 3:
            labels_colors.append('red')
    #print(labels_colors)

    # 每年获得的飞行常客里程数   与   玩视频游戏所消耗时间占比
    axs[0][0].scatter(x = dating_data_matrix[:,0], y=dating_data_matrix[:,1], color=labels_colors,s=15, alpha=0.5)
    axs0_title_text = axs[0][0].set_title(u'每年获得的飞行常客里程数与玩视频游戏所消耗时间占比',fontproperties=font)
    axs0_xlabel_text = axs[0][0].set_xlabel(u'每年获得的飞行常客里程数',fontproperties=font)
    axs0_ylabel_text = axs[0][0].set_ylabel(u'玩视频游戏所消耗时间占比',fontproperties=font)
    plt.setp(axs0_title_text, size=9, weight='bold', color='green')
    plt.setp(axs0_xlabel_text, size=7, weight='bold', color='black')
    plt.setp(axs0_ylabel_text, size=7, weight='bold', color='black')

    #每年获得的飞行常客里程数   与   每周消费冰激凌公升数
    axs[0][1].scatter(x = dating_data_matrix[:,0], y=dating_data_matrix[:,2], color=labels_colors,s=15, alpha=0.5)
    axs1_title_text = axs[0][1].set_title(u'每年获得的飞行常客里程数与每周消费冰激凌公升数',fontproperties=font)
    axs1_xlabel_text = axs[0][1].set_xlabel(u'每年获得的飞行常客里程数',fontproperties=font)
    axs1_ylabel_text = axs[0][1].set_ylabel(u'每周消费冰激凌公升数',fontproperties=font)
    plt.setp(axs1_title_text, size=9, weight='bold', color='green')
    plt.setp(axs1_xlabel_text, size=7, weight='bold', color='black')
    plt.setp(axs1_ylabel_text, size=7, weight='bold', color='black')


    #玩视频游戏所消耗时间占比    与   每周消费冰激凌公升数
    axs[1][0].scatter(x = dating_data_matrix[:,1], y=dating_data_matrix[:,2], color=labels_colors,s=15,alpha=0.5)
    axs2_title_text = axs[1][0].set_title(u'玩视频游戏所消耗时间占比与每周消费冰激凌公升数',fontproperties=font)
    axs2_xlabel_text = axs[1][0].set_xlabel(u'玩视频游戏所消耗时间占比',fontproperties=font)
    axs2_ylabel_text = axs[1][0].set_ylabel(u'每周消费冰激凌公升数',fontproperties=font)
    plt.setp(axs2_title_text, size=9, weight='bold', color='green')
    plt.setp(axs2_xlabel_text, size=7, weight='bold', color='black')
    plt.setp(axs2_ylabel_text, size=7, weight='bold', color='black')


    #设置图例
    didntLike = mlines.Line2D([], [], color='black', marker='.',markersize=6, label='didntLike')
    smallDoses = mlines.Line2D([], [], color='orange', marker='.',markersize=6, label='smallDoses')
    largeDoses = mlines.Line2D([], [], color='red', marker='.',markersize=6, label='largeDoses')


    #添加图例
    axs[0][0].legend(handles=[didntLike,smallDoses,largeDoses])
    axs[0][1].legend(handles=[didntLike,smallDoses,largeDoses])
    axs[1][0].legend(handles=[didntLike,smallDoses,largeDoses])

    plt.show()



def auto_norm(data_set):
    """
    #数据归一化
    :param data_set:
    :return:
    """
    min_vals = data_set.min(0)
    #print(min_vals)
    max_vals = data_set.max(0)
    #print(max_vals)
    ranges = max_vals - min_vals
    norm_data_set = np.zeros(np.shape(data_set))
    m = data_set.shape[0]
    norm_data_set = data_set - np.tile(min_vals,(m,1))
    norm_data_set = norm_data_set/np.tile(ranges,(m,1))
    return norm_data_set,ranges,min_vals


def classifier_calculator(inx,data_set,labels,k):
    data_set_size  = data_set.shape[0]
    diff_mat = np.tile(inx,(data_set_size,1))-data_set
    #print(diffmat)
    sq_diff_mat = diff_mat**2
    sq_distances = sq_diff_mat.sum(1)
    distances = sq_distances**0.5
    sorted_dist_indices = distances.argsort()
    #print(sorteddistindices)
    class_count = {}
    for i in range(k):
        vote_i_label = labels[sorted_dist_indices[i]]
        #print(voteilabel)
        class_count[vote_i_label] = class_count.get(vote_i_label, 0) + 1
        #print(classcount[voteilabel])
    #print(classcount)
    sorted_Class_Count = sorted(class_count.items(), key=operator.itemgetter(1), reverse=True)
    #print(sortedClassCount)
    return sorted_Class_Count[0][0]





# def dataing_class_test():
#     dating_data_matrix, dating_lables = file_matrix()
#     abstruct_ratio = 0.10
#     norm_data_set, ranges, min_vals = auto_norm(dating_data_matrix)
#     n = norm_data_set.shape[0]
#     num_test_data_set = int(n * abstruct_ratio)
#     error_count = 0.0
#     for i in range(num_test_data_set):
#         classifier_result = classifier_calculator(norm_data_set[i,:],norm_data_set[num_test_data_set:n,:],dating_lables[num_test_data_set:n],4)
#         print("分类结果：%s \t 真实类别：%s"   % (classifier_result,dating_lables[i]))
#         if classifier_result != dating_lables[i]:
#             error_count += 1.0
#     print("错误率：%f%%" %(error_count/float(num_test_data_set)*100))
#


def  classify_person():
    result_list = ["讨厌","有些喜欢","非常喜欢"]
    game_time = float(input("玩视频游戏所耗时间百分比:"))
    fly_miles = float(input("每年获得的飞行常客里程数:"))
    ice_cream = float(input("每周消费的冰激淋公升数:"))
    dating_data_matrix, dating_lables = file_matrix()
    norm_data_set, ranges, min_vals = auto_norm(dating_data_matrix)
    in_arr = np.array([game_time, fly_miles,ice_cream])
    #记住测试集也要进行归一化操作！
    norm_in_arr =(in_arr - min_vals)/ranges
    classifier_result = classifier_calculator(norm_in_arr,norm_data_set,dating_lables,5)
    print("你可能%s这个人" % ( result_list[classifier_result-1]))

















if __name__ == '__main__':

    #dating_data_matrix, dating_lables = file_matrix()
    #showdatas(dating_data_matrix, dating_lables)
    #norm_data_set, ranges, min_vals = auto_norm(dating_data_matrix)
    #print( norm_data_set)
    #print(ranges)
    #print(min_vals)
    #dataing_class_test()
    classify_person()