机器学习——基础算法(九)
一、kMeans
# !/usr/bin/python
# -*- coding:utf-8 -*-
import numpy as np
import matplotlib.pyplot as plt
import sklearn.datasets as ds
import matplotlib.colors
from sklearn.cluster import KMeans
def expand(a, b):
d = (b - a) * 0.1
return a-d, b+d
if __name__ == "__main__":
N = 400
centers = 4
data, y = ds.make_blobs(N, n_features=2, centers=centers, random_state=2)
data2, y2 = ds.make_blobs(N, n_features=2, centers=centers, cluster_std=(1,2.5,0.5,2), random_state=2)
data3 = np.vstack((data[y == 0][:], data[y == 1][:50], data[y == 2][:20], data[y == 3][:5]))
y3 = np.array([0] * 100 + [1] * 50 + [2] * 20 + [3] * 5)
cls = KMeans(n_clusters=4, init='k-means++')
y_hat = cls.fit_predict(data)
y2_hat = cls.fit_predict(data2)
y3_hat = cls.fit_predict(data3)
m = np.array(((1, 1), (1, 3)))
data_r = data.dot(m)
y_r_hat = cls.fit_predict(data_r)
matplotlib.rcParams['font.sans-serif'] = [u'SimHei']
matplotlib.rcParams['axes.unicode_minus'] = False
cm = matplotlib.colors.ListedColormap(list('rgbm'))
plt.figure(figsize=(9, 10), facecolor='w')
plt.subplot(421)
plt.title(u'原始数据')
plt.scatter(data[:, 0], data[:, 1], c=y, s=30, cmap=cm, edgecolors='none')
x1_min, x2_min = np.min(data, axis=0)
x1_max, x2_max = np.max(data, axis=0)
x1_min, x1_max = expand(x1_min, x1_max)
x2_min, x2_max = expand(x2_min, x2_max)
plt.xlim((x1_min, x1_max))
plt.ylim((x2_min, x2_max))
plt.grid(True)
plt.subplot(422)
plt.title(u'KMeans++聚类')
plt.scatter(data[:, 0], data[:, 1], c=y_hat, s=30, cmap=cm, edgecolors='none')
plt.xlim((x1_min, x1_max))
plt.ylim((x2_min, x2_max))
plt.grid(True)
plt.subplot(423)
plt.title(u'旋转后数据')
plt.scatter(data_r[:, 0], data_r[:, 1], c=y, s=30, cmap=cm, edgecolors='none')
x1_min, x2_min = np.min(data_r, axis=0)
x1_max, x2_max = np.max(data_r, axis=0)
x1_min, x1_max = expand(x1_min, x1_max)
x2_min, x2_max = expand(x2_min, x2_max)
plt.xlim((x1_min, x1_max))
plt.ylim((x2_min, x2_max))
plt.grid(True)
plt.subplot(424)
plt.title(u'旋转后KMeans++聚类')
plt.scatter(data_r[:, 0], data_r[:, 1], c=y_r_hat, s=30, cmap=cm, edgecolors='none')
plt.xlim((x1_min, x1_max))
plt.ylim((x2_min, x2_max))
plt.grid(True)
plt.subplot(425)
plt.title(u'方差不相等数据')
plt.scatter(data2[:, 0], data2[:, 1], c=y2, s=30, cmap=cm, edgecolors='none')
x1_min, x2_min = np.min(data2, axis=0)
x1_max, x2_max = np.max(data2, axis=0)
x1_min, x1_max = expand(x1_min, x1_max)
x2_min, x2_max = expand(x2_min, x2_max)
plt.xlim((x1_min, x1_max))
plt.ylim((x2_min, x2_max))
plt.grid(True)
plt.subplot(426)
plt.title(u'方差不相等KMeans++聚类')
plt.scatter(data2[:, 0], data2[:, 1], c=y2_hat, s=30, cmap=cm, edgecolors='none')
plt.xlim((x1_min, x1_max))
plt.ylim((x2_min, x2_max))
plt.grid(True)
plt.subplot(427)
plt.title(u'数量不相等数据')
plt.scatter(data3[:, 0], data3[:, 1], s=30, c=y3, cmap=cm, edgecolors='none')
x1_min, x2_min = np.min(data3, axis=0)
x1_max, x2_max = np.max(data3, axis=0)
x1_min, x1_max = expand(x1_min, x1_max)
x2_min, x2_max = expand(x2_min, x2_max)
plt.xlim((x1_min, x1_max))
plt.ylim((x2_min, x2_max))
plt.grid(True)
plt.subplot(428)
plt.title(u'数量不相等KMeans++聚类')
plt.scatter(data3[:, 0], data3[:, 1], c=y3_hat, s=30, cmap=cm, edgecolors='none')
plt.xlim((x1_min, x1_max))
plt.ylim((x2_min, x2_max))
plt.grid(True)
plt.tight_layout(2, rect=(0, 0, 1, 0.97))
plt.suptitle(u'数据分布对KMeans聚类的影响', fontsize=18)
# https://github.com/matplotlib/matplotlib/issues/829
# plt.subplots_adjust(top=0.92)
plt.show()
二、SpectralClusterImage
# !/usr/bin/python
# -*- coding:utf-8 -*-
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.colors
from sklearn.cluster import spectral_clustering
from sklearn.feature_extraction import image
from PIL import Image
import time
if __name__ == "__main__":
matplotlib.rcParams['font.sans-serif'] = [u'SimHei']
matplotlib.rcParams['axes.unicode_minus'] = False
pic = Image.open('Chrome.png')
pic = pic.convert('L')
data = np.array(pic).astype(np.float) / 255
plt.figure(figsize=(10, 5), facecolor='w')
plt.subplot(121)
plt.imshow(pic, cmap=plt.cm.gray, interpolation='nearest')
plt.title(u'原始图片', fontsize=18)
n_clusters = 15
affinity = image.img_to_graph(data)
beta = 3
affinity.data = np.exp(-beta * affinity.data / affinity.data.std()) + 10e-5
# a = affinity.toarray()
# b = np.diag(a.diagonal())
# a -= b
print '开始谱聚类...'
y = spectral_clustering(affinity, n_clusters=n_clusters, assign_labels='kmeans', random_state=1)
print '谱聚类完成...'
y = y.reshape(data.shape)
for n in range(n_clusters):
data[y == n] = n
plt.subplot(122)
clrs = []
for c in np.linspace(16776960, 16711935, n_clusters):
clrs.append('#%06x' % c)
cm = matplotlib.colors.ListedColormap(clrs)
plt.imshow(data, cmap=cm, interpolation='nearest')
plt.title(u'谱聚类:%d簇' % n_clusters, fontsize=18)
plt.tight_layout()
plt.show()