机器学习-kmeans的使用

import numpy as np
import pandas as pd
import matplotlib
from matplotlib import pyplot as plt
%matplotlib inline
matplotlib.rcParams['font.sans-serif'] = ['SimHei']
data = pd.read_csv('./010-data_multivar.csv',header=None)
#拆分数据
dataset_X,dataset_y = data.iloc[:,:-1],data.iloc[:,-1]
# print(dataset_X.head())
dataset_X = dataset_X.values
dataset_y = dataset_y.values

无标签数据集可视化，将第一列feature作为X，第二列feature作为y

def visual_2D_dataset_dist(dataset):
    '''将二维数据集dataset显示在散点图中'''
    assert dataset.shape[1]==2,'only support dataset with 2 features'
    plt.figure()
    X=dataset[:,0]
    Y=dataset[:,1]
    plt.scatter(X,Y,marker='v',c='g',label='dataset')
    
    X_min,X_max=np.min(X)-1,np.max(X)+1
    Y_min,Y_max=np.min(Y)-1,np.max(Y)+1
    plt.title('dataset distribution')
    plt.xlim(X_min,X_max)
    plt.ylim(Y_min,Y_max)
    plt.xlabel('feature_0')
    plt.ylabel('feature_1')
    plt.legend()
    
visual_2D_dataset_dist(dataset_X)

构造 kmeans

from sklearn.cluster import KMeans
#init
kmeans = KMeans(init='k-means++',n_clusters=4,n_init=5)
kmeans.fit(dataset_X)

将dataset_X聚类效果可视化

def visual_kmeans_effect(k_means,dataset):
    assert dataset.shape[1]==2,'only support dataset with 2 features'
    X=dataset[:,0]
    Y=dataset[:,1]
    X_min,X_max=np.min(X)-1,np.max(X)+1
    Y_min,Y_max=np.min(Y)-1,np.max(Y)+1
    # meshgrid 生成网格点坐标矩阵
    X_values,Y_values=np.meshgrid(np.arange(X_min,X_max,0.01),
                                  np.arange(Y_min,Y_max,0.01))
    # 预测网格点的标记
    predict_labels=k_means.predict(np.c_[X_values.ravel(),Y_values.ravel()])
    predict_labels=predict_labels.reshape(X_values.shape)
    plt.figure()
    plt.imshow(predict_labels,interpolation='nearest',
               extent=(X_values.min(),X_values.max(),
                       Y_values.min(),Y_values.max()),
               cmap=plt.cm.Paired,
               aspect='auto',
               origin='lower')
    
    # 将数据集绘制到图表中
    plt.scatter(X,Y,marker='v',facecolors='none',edgecolors='k',s=30)
    
    # 将中心点绘制到图中
    centroids=k_means.cluster_centers_
    plt.scatter(centroids[:,0],centroids[:,1],marker='o',
                s=100,linewidths=2,color='k',zorder=5,facecolors='b')
    plt.title('K-Means effect graph')
    plt.xlim(X_min,X_max)
    plt.ylim(Y_min,Y_max)
    plt.xlabel('feature_0')
    plt.ylabel('feature_1')
    plt.show()
    
visual_kmeans_effect(kmeans,dataset_X)

 

# 鸢尾花聚类

from sklearn.datasets import load_iris
datairis = load_iris()
dataset = datairis.data
from sklearn.cluster import KMeans
#init
kmeans = KMeans(init='k-means++',n_clusters=4,n_init=5)
kmeans.fit(dataset)
print(kmeans.labels_) #去除标签
print(datairis)