Skip to main content
 首页 » 编程设计

python之在 K 均值聚类中组织聚类

2024年12月31日15sharpest

我正在使用 python 对 Mnist 数据库 ( http://yann.lecun.com/exdb/mnist/) 进行 k 均值聚类。我能够成功地对数据进行聚类,但无法标记聚类。意思是,我看不到什么簇号包含什么数字。例如,簇 5 可以容纳数字 7。

在完成 k-means 聚类后,我需要编写代码来正确标记聚类。还需要在代码中添加图例。

from __future__ import division, print_function, absolute_import 
 
import tensorflow as tf  
import numpy as np 
import matplotlib.pyplot as plt 
from mpl_toolkits.mplot3d import Axes3D  #only needed for 3D plots  
#scikit learn 
from sklearn.cluster import KMeans 
 
#pandas to read excel file 
import pandas 
import xlrd 
# Import MNIST data 
from tensorflow.examples.tutorials.mnist import input_data 
 
 
Links: 
[MNIST Dataset] http://yann.lecun.com/exdb/mnist/ 
 
 
 
 
df = pandas.read_csv('test_encoded_with_label.csv',header=None,  
delim_whitespace=True) 
#df = pandas.read_excel('test_encoded_with_label.xls') 
#print column names 
print(df.columns) 
 
 
df1 = df.iloc[:,0:2] #0 and 1, the last index is not used for iloc 
labels = df.iloc[:,2] 
labels = labels.values 
 
 
dataset = df1.values 
#train indices - depends how many samples 
trainidx = np.arange(0,9999) 
testidx = np.arange(0,9999) 
train_data = dataset[trainidx,:] 
test_data = dataset[testidx,:] 
train_labels = labels[trainidx] #just 1D, no : 
tpredct_labels = labels[testidx] 
 
 
kmeans = KMeans(n_clusters=10, random_state=0).fit(train_data) 
kmeans.labels_  
#print(kmeans.labels_.shape) 
 
 
plt.scatter(train_data[:,0],train_data[:,1], c=kmeans.labels_) 
 
 
predct_labels = kmeans.predict(train_data) 
 
 
print(predct_labels) 
print('actual label', tpredct_labels) 
 
 
centers = kmeans.cluster_centers_ 
print(centers) 
 
plt.show() 

请您参考如下方法:

要创建标记来查找标记点簇,您可以使用 annotate方法

这是在 sklearn 数字数据集上运行的示例代码,我在其中尝试标记生成的聚类的质心。请注意,出于说明目的,我只是将集群标记为 0-9:

import numpy as np 
import matplotlib.pyplot as plt 
 
from sklearn.cluster import KMeans 
from sklearn.datasets import load_digits 
from sklearn.decomposition import PCA 
from sklearn.preprocessing import scale 
 
np.random.seed(42) 
 
digits = load_digits() 
data = scale(digits.data) 
 
n_samples, n_features = data.shape 
n_digits = len(np.unique(digits.target)) 
labels = digits.target 
h = .02 
reduced_data = PCA(n_components=2).fit_transform(data) 
kmeans = KMeans(init='k-means++', n_clusters=n_digits, n_init=10) 
kmeans.fit(reduced_data) 
 
centroids = kmeans.cluster_centers_ 
plt_data = plt.scatter(reduced_data[:, 0], reduced_data[:, 1], c=kmeans.labels_, cmap=plt.cm.get_cmap('Spectral', 10)) 
plt.colorbar() 
plt.scatter(centroids[:, 0], centroids[:, 1], 
            marker='x') 
plt.title('K-means clustering on the digits dataset (PCA-reduced data)\n' 
          'Centroids are marked with white cross') 
plt.xlabel('component 1') 
plt.ylabel('component 2') 
labels = ['{0}'.format(i) for i in range(10)] 
for i in range (10): 
    xy=(centroids[i, 0],centroids[i, 1]) 
    plt.annotate(labels[i],xy, horizontalalignment='right', verticalalignment='top') 
plt.show() 

这是你得到的结果: