Kmeans数据类别划分——注释就是笔记

Kmeans是需要指定类别的不需要监督的学习

# 加载数据
import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
from sklearn.cluster import KMeans
from sklearn.metrics import accuracy_score
if __name__ == '__main__':

    data = pd.read_csv('data/data2.csv')
    data.head()
    # define X and y
    X = data.drop(['labels'], axis=1)      # axis意思是按照列
    y = data.loc[:, 'labels']            # :->所有行   ‘labels’这一列


    pd.value_counts(y)    # 这是察看这一列所有的值和出现次数


    fig1 = plt.figure()
    label0 =  plt.scatter(X.loc[:,'V1'][y==0],X.loc[:,'V2'][y==0])
    label1 =  plt.scatter(X.loc[:,'V1'][y==1],X.loc[:,'V2'][y==1])
    label2 =  plt.scatter(X.loc[:,'V1'][y==2],X.loc[:,'V2'][y==2])
    plt.title('un-labled data')
    plt.xlabel('V1')
    plt.ylabel('V2')
    plt.legend((label0,label1,label2),('label0','label1,','label2'))
    plt.show()


    # 创建模型
    KM = KMeans(n_clusters=3, random_state=0)
    KM.fit(X)



    # 得到中心点  和原来的图像放在一起观看
    centers = KM.cluster_centers_
    fig3 = plt.figure()
    label0 = plt.scatter(X.loc[:, 'V1'][y == 0], X.loc[:, 'V2'][y == 0])
    label1 = plt.scatter(X.loc[:, 'V1'][y == 1], X.loc[:, 'V2'][y == 1])
    label2 = plt.scatter(X.loc[:, 'V1'][y == 2], X.loc[:, 'V2'][y == 2])
    plt.title('un-labled data')
    plt.xlabel('V1')
    plt.ylabel('V2')
    plt.scatter(centers[:,0],centers[:,1])
    plt.legend((label0, label1, label2), ('label0', 'label1,', 'label2'))
    plt.show()


    # 预测结果 KM.predict([[80,60]])

    # 发现结果对但是标识顺序乱了
    y_predict = KM.predict(X)
    print(pd.value_counts(y_predict),pd.value_counts(y))


    #计算准确率   你会发现低的可怜  这是因为你的标识和颜色没有对上，需要修改
    accuracy = accuracy_score(y,y_predict)

    fig4 = plt.subplot(121)
    label0 = plt.scatter(X.loc[:, 'V1'][y_predict == 0], X.loc[:, 'V2'][y_predict == 0])
    label1 = plt.scatter(X.loc[:, 'V1'][y_predict == 1], X.loc[:, 'V2'][y_predict == 1])
    label2 = plt.scatter(X.loc[:, 'V1'][y_predict == 2], X.loc[:, 'V2'][y_predict == 2])
    plt.title('predict data')
    plt.xlabel('V1')
    plt.ylabel('V2')
    plt.legend((label0, label1, label2), ('label0', 'label1,', 'label2'))
    plt.scatter(centers[:,0],centers[:,1])


    fig5 = plt.subplot(122)
    label0 = plt.scatter(X.loc[:, 'V1'][y == 0], X.loc[:, 'V2'][y == 0])
    label1 = plt.scatter(X.loc[:, 'V1'][y == 1], X.loc[:, 'V2'][y == 1])
    label2 = plt.scatter(X.loc[:, 'V1'][y == 2], X.loc[:, 'V2'][y == 2])
    plt.title('un-labled data')
    plt.xlabel('V1')
    plt.ylabel('V2')
    plt.legend((label0, label1, label2), ('label0', 'label1,', 'label2'))
    plt.scatter(centers[:, 0], centers[:, 1])
    plt.show()


    # 无监督的学习 是没有标识的 需要修改
    y_corrected = []
    for i  in y_predict:
        if i==0:
            y_corrected.append(1)
        elif i == 1:
            y_corrected.append(2)
        else:
            y_corrected.append(0)