-
Notifications
You must be signed in to change notification settings - Fork 3
/
ch11 - Clustering Analysis.py
339 lines (277 loc) · 10.2 KB
/
ch11 - Clustering Analysis.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
# Working with Unlabeled Data
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
%matplotlib inline
from sklearn.cluster import KMeans
import numpy as np
from matplotlib import cm
from sklearn.metrics import silhouette_samples
import pandas as pd
from scipy.spatial.distance import pdist, squareform
from scipy.cluster.hierarchy import linkage
from scipy.cluster.hierarchy import dendrogram
from sklearn.cluster import AgglomerativeClustering
from sklearn.datasets import make_moons
from sklearn.cluster import DBSCAN
# Grouping objects by similarity using k-means
X, y = make_blobs(n_samples=150,
n_features=2,
centers=3,
cluster_std=0.5,
shuffle=True,
random_state=0)
plt.scatter(X[:, 0], X[:, 1], c='white', marker='o', s=50)
plt.grid()
plt.tight_layout()
#plt.savefig('./figures/spheres.png', dpi=300)
plt.show()
# init = k-means++ by default
km = KMeans(n_clusters=3,
init='random',
n_init=10,
max_iter=300,
tol=1e-04,
random_state=0)
y_km = km.fit_predict(X)
plt.scatter(X[y_km == 0, 0],
X[y_km == 0, 1],
s=50,
c='lightgreen',
marker='s',
label='cluster 1')
plt.scatter(X[y_km == 1, 0],
X[y_km == 1, 1],
s=50,
c='orange',
marker='o',
label='cluster 2')
plt.scatter(X[y_km == 2, 0],
X[y_km == 2, 1],
s=50,
c='lightblue',
marker='v',
label='cluster 3')
plt.scatter(km.cluster_centers_[:, 0],
km.cluster_centers_[:, 1],
s=250,
marker='*',
c='red',
label='centroids')
plt.legend()
plt.grid()
plt.tight_layout()
#plt.savefig('./figures/centroids.png', dpi=300)
plt.show()
# Using the elbow method to find the optimal number of clusters
print('Distortion: %.2f' % km.inertia_)
distortions = []
for i in range(1, 11):
km = KMeans(n_clusters=i,
init='k-means++',
n_init=10,
max_iter=300,
random_state=0)
km.fit(X)
distortions.append(km.inertia_)
plt.plot(range(1, 11), distortions, marker='o')
plt.xlabel('Number of clusters')
plt.ylabel('Distortion')
plt.tight_layout()
#plt.savefig('./figures/elbow.png', dpi=300)
plt.show()
# Quantifying the quality of clustering via silhouette plots
km = KMeans(n_clusters=3,
init='k-means++',
n_init=10,
max_iter=300,
tol=1e-04,
random_state=0)
y_km = km.fit_predict(X)
cluster_labels = np.unique(y_km)
n_clusters = cluster_labels.shape[0]
silhouette_vals = silhouette_samples(X, y_km, metric='euclidean')
y_ax_lower, y_ax_upper = 0, 0
yticks = []
for i, c in enumerate(cluster_labels):
c_silhouette_vals = silhouette_vals[y_km == c]
c_silhouette_vals.sort()
y_ax_upper += len(c_silhouette_vals)
color = cm.jet(float(i) / n_clusters)
plt.barh(range(y_ax_lower, y_ax_upper), c_silhouette_vals, height=1.0,
edgecolor='none', color=color)
yticks.append((y_ax_lower + y_ax_upper) / 2.)
y_ax_lower += len(c_silhouette_vals)
silhouette_avg = np.mean(silhouette_vals)
plt.axvline(silhouette_avg, color="red", linestyle="--")
plt.yticks(yticks, cluster_labels + 1)
plt.ylabel('Cluster')
plt.xlabel('Silhouette coefficient')
plt.tight_layout()
# plt.savefig('./figures/silhouette.png', dpi=300)
plt.show()
# Comparison to "bad" clustering
km = KMeans(n_clusters=2,
init='k-means++',
n_init=10,
max_iter=300,
tol=1e-04,
random_state=0)
y_km = km.fit_predict(X)
plt.scatter(X[y_km == 0, 0],
X[y_km == 0, 1],
s=50,
c='lightgreen',
marker='s',
label='cluster 1')
plt.scatter(X[y_km == 1, 0],
X[y_km == 1, 1],
s=50,
c='orange',
marker='o',
label='cluster 2')
plt.scatter(km.cluster_centers_[:, 0], km.cluster_centers_[:, 1],
s=250, marker='*', c='red', label='centroids')
plt.legend()
plt.grid()
plt.tight_layout()
#plt.savefig('./figures/centroids_bad.png', dpi=300)
plt.show()
cluster_labels = np.unique(y_km)
n_clusters = cluster_labels.shape[0]
silhouette_vals = silhouette_samples(X, y_km, metric='euclidean')
y_ax_lower, y_ax_upper = 0, 0
yticks = []
for i, c in enumerate(cluster_labels):
c_silhouette_vals = silhouette_vals[y_km == c]
c_silhouette_vals.sort()
y_ax_upper += len(c_silhouette_vals)
color = cm.jet(float(i) / n_clusters)
plt.barh(range(y_ax_lower, y_ax_upper), c_silhouette_vals, height=1.0,
edgecolor='none', color=color)
yticks.append((y_ax_lower + y_ax_upper) / 2.)
y_ax_lower += len(c_silhouette_vals)
silhouette_avg = np.mean(silhouette_vals)
plt.axvline(silhouette_avg, color="red", linestyle="--")
plt.yticks(yticks, cluster_labels + 1)
plt.ylabel('Cluster')
plt.xlabel('Silhouette coefficient')
plt.tight_layout()
# plt.savefig('./figures/silhouette_bad.png', dpi=300)
plt.show()
# Organizing clusters as a hierarchical tree
# Generate random dataset
np.random.seed(123)
variables = ['X', 'Y', 'Z']
labels = ['ID_0', 'ID_1', 'ID_2', 'ID_3', 'ID_4']
X = np.random.random_sample([5, 3])*10
df = pd.DataFrame(X, columns=variables, index=labels)
df
row_dist = pd.DataFrame(squareform(pdist(df, metric='euclidean')),
columns=labels,
index=labels)
row_dist
# 1. incorrect approach: Squareform distance matrix
row_clusters = linkage(row_dist, method='complete', metric='euclidean')
pd.DataFrame(row_clusters,
columns=['row label 1', 'row label 2',
'distance', 'no. of items in clust.'],
index=['cluster %d' % (i + 1)
for i in range(row_clusters.shape[0])])
# 2. correct approach: Condensed distance matrix
row_clusters = linkage(pdist(df, metric='euclidean'), method='complete')
pd.DataFrame(row_clusters,
columns=['row label 1', 'row label 2',
'distance', 'no. of items in clust.'],
index=['cluster %d' % (i + 1)
for i in range(row_clusters.shape[0])])
# 3. correct approach: Input sample matrix
row_clusters = linkage(df.values, method='complete', metric='euclidean')
pd.DataFrame(row_clusters,
columns=['row label 1', 'row label 2',
'distance', 'no. of items in clust.'],
index=['cluster %d' % (i + 1)
for i in range(row_clusters.shape[0])])
# make dendrogram black (part 1/2)
# from scipy.cluster.hierarchy import set_link_color_palette
# set_link_color_palette(['black'])
row_dendr = dendrogram(row_clusters,
labels=labels,
# make dendrogram black (part 2/2)
# color_threshold=np.inf
)
plt.tight_layout()
plt.ylabel('Euclidean distance')
#plt.savefig('./figures/dendrogram.png', dpi=300,
# bbox_inches='tight')
plt.show()
# Attaching dendrograms to a heat map
# plot row dendrogram
fig = plt.figure(figsize=(8, 8), facecolor='white')
axd = fig.add_axes([0.09, 0.1, 0.2, 0.6])
# note: for matplotlib < v1.5.1, please use orientation='right'
row_dendr = dendrogram(row_clusters, orientation='left')
# reorder data with respect to clustering
df_rowclust = df.iloc[row_dendr['leaves'][::-1]]
axd.set_xticks([])
axd.set_yticks([])
# remove axes spines from dendrogram
for i in axd.spines.values():
i.set_visible(False)
# plot heatmap
axm = fig.add_axes([0.23, 0.1, 0.6, 0.6]) # x-pos, y-pos, width, height
cax = axm.matshow(df_rowclust, interpolation='nearest', cmap='hot_r')
fig.colorbar(cax)
axm.set_xticklabels([''] + list(df_rowclust.columns))
axm.set_yticklabels([''] + list(df_rowclust.index))
# plt.savefig('./figures/heatmap.png', dpi=300)
plt.show()
# Applying agglomerative clustering via scikit-learn
from sklearn.cluster import AgglomerativeClustering
ac = AgglomerativeClustering(n_clusters=2,
affinity='euclidean',
linkage='complete')
labels = ac.fit_predict(X)
print('Cluster labels: %s' % labels)
# Locating regions of high density via DBSCAN
from sklearn.datasets import make_moons
X, y = make_moons(n_samples=200, noise=0.07, random_state=0)
plt.scatter(X[:, 0], X[:, 1])
plt.tight_layout()
# plt.savefig('./figures/moons.png', dpi=300)
plt.show()
# K-means and hierarchical clustering
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(8, 3))
km = KMeans(n_clusters=2, random_state=0)
y_km = km.fit_predict(X)
ax1.scatter(X[y_km == 0, 0], X[y_km == 0, 1],
c='lightblue', marker='o', s=40, label='cluster 1')
ax1.scatter(X[y_km == 1, 0], X[y_km == 1, 1],
c='red', marker='s', s=40, label='cluster 2')
ax1.set_title('K-means clustering')
ac = AgglomerativeClustering(n_clusters=2,
affinity='euclidean',
linkage='complete')
y_ac = ac.fit_predict(X)
ax2.scatter(X[y_ac == 0, 0], X[y_ac == 0, 1], c='lightblue',
marker='o', s=40, label='cluster 1')
ax2.scatter(X[y_ac == 1, 0], X[y_ac == 1, 1], c='red',
marker='s', s=40, label='cluster 2')
ax2.set_title('Agglomerative clustering')
plt.legend()
plt.tight_layout()
#plt.savefig('./figures/kmeans_and_ac.png', dpi=300)
plt.show()
# Density-based clustering DBSCAN
from sklearn.cluster import DBSCAN
db = DBSCAN(eps=0.2, min_samples=5, metric='euclidean')
y_db = db.fit_predict(X)
plt.scatter(X[y_db == 0, 0], X[y_db == 0, 1],
c='lightblue', marker='o', s=40,
label='cluster 1')
plt.scatter(X[y_db == 1, 0], X[y_db == 1, 1],
c='red', marker='s', s=40,
label='cluster 2')
plt.legend()
plt.tight_layout()
#plt.savefig('./figures/moons_dbscan.png', dpi=300)
plt.show()