非监督学习之聚类

1.概念

2.代码

kMeans.py

# !/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)
    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()

criteria,py

# !/usr/bin/python
# -*- coding:utf-8 -*-

from sklearn import metrics


if __name__ == "__main__":
    y = [0, 0, 0, 1, 1, 1]
    y_hat = [0, 0, 1, 1, 2, 2]
    h = metrics.homogeneity_score(y, y_hat)
    c = metrics.completeness_score(y, y_hat)
    print u'同一性(Homogeneity)：', h
    print u'完整性(Completeness)：', c
    v2 = 2 * c * h / (c + h)
    v = metrics.v_measure_score(y, y_hat)
    print u'V-Measure：', v2, v

    print
    y = [0, 0, 0, 1, 1, 1]
    y_hat = [0, 0, 1, 2, 3, 3]
    h = metrics.homogeneity_score(y, y_hat)
    c = metrics.completeness_score(y, y_hat)
    v = metrics.v_measure_score(y, y_hat)
    print u'同一性(Homogeneity)：', h
    print u'完整性(Completeness)：', c
    print u'V-Measure：', v

    # 允许不同值
    print
    y = [0, 0, 0, 1, 1, 1]
    y_hat = [1, 1, 1, 0, 0, 0]
    h = metrics.homogeneity_score(y, y_hat)
    c = metrics.completeness_score(y, y_hat)
    v = metrics.v_measure_score(y, y_hat)
    print u'同一性(Homogeneity)：', h
    print u'完整性(Completeness)：', c
    print u'V-Measure：', v

    y = [0, 0, 1, 1]
    y_hat = [0, 1, 0, 1]
    ari = metrics.adjusted_rand_score(y, y_hat)
    print ari

    y = [0, 0, 0, 1, 1, 1]
    y_hat = [0, 0, 1, 1, 2, 2]
    ari = metrics.adjusted_rand_score(y, y_hat)
    print ari

向量量化
VetorQuantization.py

# !/usr/bin/python
# -*- coding: utf-8 -*-

from PIL import Image
import numpy as np
from sklearn.cluster import KMeans
import matplotlib
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D


def restore_image(cb, cluster, shape):
    row, col, dummy = shape
    image = np.empty((row, col, 3))
    index = 0
    for r in range(row):
        for c in range(col):
            image[r, c] = cb[cluster[index]]
            index += 1
    return image


def show_scatter(a):
    N = 10
    print '原始数据：\n', a
    density, edges = np.histogramdd(a, bins=[N,N,N], range=[(0,1), (0,1), (0,1)])
    density /= density.max()
    x = y = z = np.arange(N)
    d = np.meshgrid(x, y, z)

    fig = plt.figure(1, facecolor='w')
    ax = fig.add_subplot(111, projection='3d')
    ax.scatter(d[1], d[0], d[2], c='r', s=100*density, marker='o', depthshade=True)
    ax.set_xlabel(u'红色分量')
    ax.set_ylabel(u'绿色分量')
    ax.set_zlabel(u'蓝色分量')
    plt.title(u'图像颜色三维频数分布', fontsize=20)

    plt.figure(2, facecolor='w')
    den = density[density > 0]
    den = np.sort(den)[::-1]
    t = np.arange(len(den))
    plt.plot(t, den, 'r-', t, den, 'go', lw=2)
    plt.title(u'图像颜色频数分布', fontsize=18)
    plt.grid(True)

    plt.show()


if __name__ == '__main__':
    matplotlib.rcParams['font.sans-serif'] = [u'SimHei']
    matplotlib.rcParams['axes.unicode_minus'] = False

    num_vq = 50
    im = Image.open('16.lena.png')     # 16.son.bmp(100)/16.flower2.png(200)/16.son.png(60)/16.lena.png(50)
    image = np.array(im).astype(np.float) / 255
    image = image[:, :, :3]
    image_v = image.reshape((-1, 3))
    model = KMeans(num_vq)
    show_scatter(image_v)

    N = image_v.shape[0]    # 图像像素总数
    # 选择足够多的样本(如1000个)，计算聚类中心
    idx = np.random.randint(0, N, size=1000)
    image_sample = image_v[idx]
    model.fit(image_sample)
    c = model.predict(image_v)  # 聚类结果
    print '聚类结果：\n', c
    print '聚类中心：\n', model.cluster_centers_

    plt.figure(figsize=(15, 8), facecolor='w')
    plt.subplot(121)
    plt.axis('off')
    plt.title(u'原始图片', fontsize=18)
    plt.imshow(image)
    # plt.savefig('1.png')

    plt.subplot(122)
    vq_image = restore_image(model.cluster_centers_, c, image.shape)
    plt.axis('off')
    plt.title(u'矢量量化后图片：%d色' % num_vq, fontsize=18)
    plt.imshow(vq_image)
    # plt.savefig('2.png')

    plt.tight_layout(1.2)
    plt.show()

AP.py

# !/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 AffinityPropagation
from sklearn.metrics import euclidean_distances


if __name__ == "__main__":
    N = 400
    centers = [[1, 2], [-1, -1], [1, -1], [-1, 1]]
    data, y = ds.make_blobs(N, n_features=2, centers=centers, cluster_std=[0.5, 0.25, 0.7, 0.5], random_state=0)
    m = euclidean_distances(data, squared=True)
    preference = -np.median(m)
    print 'Preference：', preference

    matplotlib.rcParams['font.sans-serif'] = [u'SimHei']
    matplotlib.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(12, 9), facecolor='w')
    for i, mul in enumerate(np.linspace(1, 4, 9)):
        print mul
        p = mul * preference
        model = AffinityPropagation(affinity='euclidean', preference=p)
        af = model.fit(data)
        center_indices = af.cluster_centers_indices_
        n_clusters = len(center_indices)
        print ('p = %.1f' % mul), p, '聚类簇的个数为：', n_clusters
        y_hat = af.labels_

        plt.subplot(3, 3, i+1)
        plt.title(u'Preference：%.2f，簇个数：%d' % (p, n_clusters))
        clrs = []
        for c in np.linspace(16711680, 255, n_clusters):
            clrs.append('#%06x' % c)
        # clrs = plt.cm.Spectral(np.linspace(0, 1, n_clusters))
        for k, clr in enumerate(clrs):
            cur = (y_hat == k)
            plt.scatter(data[cur, 0], data[cur, 1], c=clr, edgecolors='none')
            center = data[center_indices[k]]
            for x in data[cur]:
                plt.plot([x[0], center[0]], [x[1], center[1]], color=clr, zorder=1)
        plt.scatter(data[center_indices, 0], data[center_indices, 1], s=100, c=clrs, marker='*', edgecolors='k', zorder=2)
        plt.grid(True)
    plt.tight_layout()
    plt.suptitle(u'AP聚类', fontsize=20)
    plt.subplots_adjust(top=0.92)
    plt.show()

MeanShift.py

# !/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 MeanShift
from sklearn.metrics import euclidean_distances


if __name__ == "__main__":
    N = 1000
    centers = [[1, 2], [-1, -1], [1, -1], [-1, 1]]
    data, y = ds.make_blobs(N, n_features=2, centers=centers, cluster_std=[0.5, 0.25, 0.7, 0.5], random_state=0)

    matplotlib.rcParams['font.sans-serif'] = [u'SimHei']
    matplotlib.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(10, 9), facecolor='w')
    m = euclidean_distances(data, squared=True)
    bw = np.median(m)
    print bw
    for i, mul in enumerate(np.linspace(0.1, 0.4, 4)):
        band_width = mul * bw
        model = MeanShift(bin_seeding=True, bandwidth=band_width)
        ms = model.fit(data)
        centers = ms.cluster_centers_
        y_hat = ms.labels_
        n_clusters = np.unique(y_hat).size
        print '带宽：', mul, band_width, '聚类簇的个数为：', n_clusters

        plt.subplot(2, 2, i+1)
        plt.title(u'带宽：%.2f，聚类簇的个数为：%d' % (band_width, n_clusters))
        clrs = []
        for c in np.linspace(16711680, 255, n_clusters):
            clrs.append('#%06x' % c)
        # clrs = plt.cm.Spectral(np.linspace(0, 1, n_clusters))
        print clrs
        for k, clr in enumerate(clrs):
            cur = (y_hat == k)
            plt.scatter(data[cur, 0], data[cur, 1], c=clr, edgecolors='none')
        plt.scatter(centers[:, 0], centers[:, 1], s=150, c=clrs, marker='*', edgecolors='k')
        plt.grid(True)
    plt.tight_layout(2)
    plt.suptitle(u'MeanShift聚类', fontsize=20)
    plt.subplots_adjust(top=0.92)
    plt.show()

DBSCAN.py

# !/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 DBSCAN
from sklearn.preprocessing import StandardScaler


def expand(a, b):
    d = (b - a) * 0.1
    return a-d, b+d


if __name__ == "__main__":
    N = 1000
    centers = [[1, 2], [-1, -1], [1, -1], [-1, 1]]
    data, y = ds.make_blobs(N, n_features=2, centers=centers, cluster_std=[0.5, 0.25, 0.7, 0.5], random_state=0)
    data = StandardScaler().fit_transform(data)
    # 数据1的参数：(epsilon, min_sample)
    params = ((0.2, 5), (0.2, 10), (0.2, 15), (0.3, 5), (0.3, 10), (0.3, 15))

    # # 数据2
    # t = np.arange(0, 2*np.pi, 0.1)
    # data1 = np.vstack((np.cos(t), np.sin(t))).T
    # data2 = np.vstack((2*np.cos(t), 2*np.sin(t))).T
    # data3 = np.vstack((3*np.cos(t), 3*np.sin(t))).T
    # data = np.vstack((data1, data2, data3))
    # # 数据2的参数：(epsilon, min_sample)
    # params = ((0.5, 3), (0.5, 5), (0.5, 10), (1., 3), (1., 10), (1., 20))

    matplotlib.rcParams['font.sans-serif'] = [u'SimHei']
    matplotlib.rcParams['axes.unicode_minus'] = False

    plt.figure(figsize=(12, 8), facecolor='w')
    plt.suptitle(u'DBSCAN聚类', fontsize=20)

    for i in range(6):
        eps, min_samples = params[i]
        model = DBSCAN(eps=eps, min_samples=min_samples)
        model.fit(data)
        y_hat = model.labels_

        core_indices = np.zeros_like(y_hat, dtype=bool)
        core_indices[model.core_sample_indices_] = True

        y_unique = np.unique(y_hat)
        n_clusters = y_unique.size - (1 if -1 in y_hat else 0)
        print y_unique, '聚类簇的个数为：', n_clusters

        # clrs = []
        # for c in np.linspace(16711680, 255, y_unique.size):
        #     clrs.append('#%06x' % c)
        plt.subplot(2, 3, i+1)
        clrs = plt.cm.Spectral(np.linspace(0, 0.8, y_unique.size))
        for k, clr in zip(y_unique, clrs):
            cur = (y_hat == k)
            if k == -1:
                plt.scatter(data[cur, 0], data[cur, 1], s=20, c='k')
                continue
            plt.scatter(data[cur, 0], data[cur, 1], s=30, c=clr, edgecolors='k')
            plt.scatter(data[cur & core_indices][:, 0], data[cur & core_indices][:, 1], s=60, c=clr, marker='o', edgecolors='k')
        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.title(ur'$\epsilon$ = %.1f  m = %d，聚类数目：%d' % (eps, min_samples, n_clusters), fontsize=16)
    plt.tight_layout()
    plt.subplots_adjust(top=0.9)
    plt.show()

SC.py

# !/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 spectral_clustering
from sklearn.metrics import euclidean_distances


def expand(a, b):
    d = (b - a) * 0.1
    return a-d, b+d


if __name__ == "__main__":
    matplotlib.rcParams['font.sans-serif'] = [u'SimHei']
    matplotlib.rcParams['axes.unicode_minus'] = False

    t = np.arange(0, 2*np.pi, 0.1)
    data1 = np.vstack((np.cos(t), np.sin(t))).T
    data2 = np.vstack((2*np.cos(t), 2*np.sin(t))).T
    data3 = np.vstack((3*np.cos(t), 3*np.sin(t))).T
    data = np.vstack((data1, data2, data3))

    n_clusters = 3
    m = euclidean_distances(data, squared=True)
    sigma = np.median(m)

    plt.figure(figsize=(12, 8), facecolor='w')
    plt.suptitle(u'谱聚类', fontsize=20)
    clrs = plt.cm.Spectral(np.linspace(0, 0.8, n_clusters))
    for i, s in enumerate(np.logspace(-2, 0, 6)):
        print s
        af = np.exp(-m ** 2 / (s ** 2)) + 1e-6
        y_hat = spectral_clustering(af, n_clusters=n_clusters, assign_labels='kmeans', random_state=1)
        plt.subplot(2, 3, i+1)
        for k, clr in enumerate(clrs):
            cur = (y_hat == k)
            plt.scatter(data[cur, 0], data[cur, 1], s=40, c=clr, edgecolors='k')
        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.title(ur'$\sigma$ = %.2f' % s, fontsize=16)
    plt.tight_layout()
    plt.subplots_adjust(top=0.9)
    plt.show()

SpactralCluaterImage.py

# !/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('16.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()