Mercurial > repos > bimib > marea

comparison marea-1.0.1/marea_cluster.py @ 15:d0e7f14b773f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Upload 1.0.1
author bimib
date Tue, 01 Oct 2019 06:03:12 -0400
parents
children
comparison
equal deleted inserted replaced
14:1a0c8c2780f2 15:d0e7f14b773f
1 # -*- coding: utf-8 -*-
2 """
3 Created on Mon Jun 3 19:51:00 2019
4
5 @author: Narger
6 """
7
8 import sys
9 import argparse
10 import os
11 from sklearn.datasets import make_blobs
12 from sklearn.cluster import KMeans, DBSCAN, AgglomerativeClustering
13 from sklearn.metrics import silhouette_samples, silhouette_score, davies_bouldin_score, cluster
14 import matplotlib.pyplot as plt
15 import scipy.cluster.hierarchy as shc
16 import matplotlib.cm as cm
17 import numpy as np
18 import pandas as pd
19
20 ################################# process args ###############################
21
22 def process_args(args):
23 parser = argparse.ArgumentParser(usage = '%(prog)s [options]',
24 description = 'process some value\'s' +
25 ' genes to create class.')
26
27 parser.add_argument('-ol', '--out_log',
28 help = "Output log")
29
30 parser.add_argument('-in', '--input',
31 type = str,
32 help = 'input dataset')
33
34 parser.add_argument('-cy', '--cluster_type',
35 type = str,
36 choices = ['kmeans', 'meanshift', 'dbscan', 'hierarchy'],
37 default = 'kmeans',
38 help = 'choose clustering algorythm')
39
40 parser.add_argument('-k1', '--k_min',
41 type = int,
42 default = 2,
43 help = 'choose minimun cluster number to be generated')
44
45 parser.add_argument('-k2', '--k_max',
46 type = int,
47 default = 7,
48 help = 'choose maximum cluster number to be generated')
49
50 parser.add_argument('-el', '--elbow',
51 type = str,
52 default = 'false',
53 choices = ['true', 'false'],
54 help = 'choose if you want to generate an elbow plot for kmeans')
55
56 parser.add_argument('-si', '--silhouette',
57 type = str,
58 default = 'false',
59 choices = ['true', 'false'],
60 help = 'choose if you want silhouette plots')
61
62 parser.add_argument('-db', '--davies',
63 type = str,
64 default = 'false',
65 choices = ['true', 'false'],
66 help = 'choose if you want davies bouldin scores')
67
68 parser.add_argument('-td', '--tool_dir',
69 type = str,
70 required = True,
71 help = 'your tool directory')
72
73 parser.add_argument('-ms', '--min_samples',
74 type = int,
75 help = 'min samples for dbscan (optional)')
76
77 parser.add_argument('-ep', '--eps',
78 type = int,
79 help = 'eps for dbscan (optional)')
80
81
82 args = parser.parse_args()
83 return args
84
85 ########################### warning ###########################################
86
87 def warning(s):
88 args = process_args(sys.argv)
89 with open(args.out_log, 'a') as log:
90 log.write(s + "\n\n")
91 print(s)
92
93 ########################## read dataset ######################################
94
95 def read_dataset(dataset):
96 try:
97 dataset = pd.read_csv(dataset, sep = '\t', header = 0)
98 except pd.errors.EmptyDataError:
99 sys.exit('Execution aborted: wrong format of dataset\n')
100 if len(dataset.columns) < 2:
101 sys.exit('Execution aborted: wrong format of dataset\n')
102 return dataset
103
104 ############################ rewrite_input ###################################
105
106 def rewrite_input(dataset):
107 #Riscrivo il dataset come dizionario di liste,
108 #non come dizionario di dizionari
109
110 for key, val in dataset.items():
111 l = []
112 for i in val:
113 if i == 'None':
114 l.append(None)
115 else:
116 l.append(float(i))
117
118 dataset[key] = l
119
120 return dataset
121
122 ############################## write to csv ##################################
123
124 def write_to_csv (dataset, labels, name):
125 list_labels = labels
126 list_values = dataset
127
128 list_values = list_values.tolist()
129 d = {'Label' : list_labels, 'Value' : list_values}
130
131 df = pd.DataFrame(d, columns=['Value','Label'])
132
133 dest = name + '.tsv'
134 df.to_csv(dest, sep = '\t', index = False,
135 header = ['Value', 'Label'])
136
137 ########################### trova il massimo in lista ########################
138 def max_index (lista):
139 best = -1
140 best_index = 0
141 for i in range(len(lista)):
142 if lista[i] > best:
143 best = lista [i]
144 best_index = i
145
146 return best_index
147
148 ################################ kmeans #####################################
149
150 def kmeans (k_min, k_max, dataset, elbow, silhouette, davies):
151 if not os.path.exists('clustering/kmeans_output'):
152 os.makedirs('clustering/kmeans_output')
153
154
155 if elbow == 'true':
156 elbow = True
157 else:
158 elbow = False
159
160 if silhouette == 'true':
161 silhouette = True
162 else:
163 silhouette = False
164
165 if davies == 'true':
166 davies = True
167 else:
168 davies = False
169
170
171 range_n_clusters = [i for i in range(k_min, k_max+1)]
172 distortions = []
173 scores = []
174 all_labels = []
175
176 for n_clusters in range_n_clusters:
177 clusterer = KMeans(n_clusters=n_clusters, random_state=10)
178 cluster_labels = clusterer.fit_predict(dataset)
179
180 all_labels.append(cluster_labels)
181 silhouette_avg = silhouette_score(dataset, cluster_labels)
182 scores.append(silhouette_avg)
183 distortions.append(clusterer.fit(dataset).inertia_)
184
185 best = max_index(scores) + k_min
186
187 for i in range(len(all_labels)):
188 prefix = ''
189 if (i + k_min == best):
190 prefix = '_BEST'
191
192 write_to_csv(dataset, all_labels[i], 'clustering/kmeans_output/kmeans_with_' + str(i + k_min) + prefix + '_clusters.tsv')
193
194 if davies:
195 with np.errstate(divide='ignore', invalid='ignore'):
196 davies_bouldin = davies_bouldin_score(dataset, all_labels[i])
197 warning("\nFor n_clusters = " + str(i + k_min) +
198 " The average davies bouldin score is: " + str(davies_bouldin))
199
200
201 if silhouette:
202 silihouette_draw(dataset, all_labels[i], i + k_min, 'clustering/kmeans_output/silhouette_with_' + str(i + k_min) + prefix + '_clusters.png')
203
204
205 if elbow:
206 elbow_plot(distortions, k_min,k_max)
207
208
209
210
211
212 ############################## elbow_plot ####################################
213
214 def elbow_plot (distortions, k_min, k_max):
215 plt.figure(0)
216 plt.plot(range(k_min, k_max+1), distortions, marker = 'o')
217 plt.xlabel('Number of cluster')
218 plt.ylabel('Distortion')
219 s = 'clustering/kmeans_output/elbow_plot.png'
220 fig = plt.gcf()
221 fig.set_size_inches(18.5, 10.5, forward = True)
222 fig.savefig(s, dpi=100)
223
224
225 ############################## silhouette plot ###############################
226 def silihouette_draw(dataset, labels, n_clusters, path):
227 silhouette_avg = silhouette_score(dataset, labels)
228 warning("For n_clusters = " + str(n_clusters) +
229 " The average silhouette_score is: " + str(silhouette_avg))
230
231 plt.close('all')
232 # Create a subplot with 1 row and 2 columns
233 fig, (ax1) = plt.subplots(1, 1)
234
235 fig.set_size_inches(18, 7)
236
237 # The 1st subplot is the silhouette plot
238 # The silhouette coefficient can range from -1, 1 but in this example all
239 # lie within [-0.1, 1]
240 ax1.set_xlim([-1, 1])
241 # The (n_clusters+1)*10 is for inserting blank space between silhouette
242 # plots of individual clusters, to demarcate them clearly.
243 ax1.set_ylim([0, len(dataset) + (n_clusters + 1) * 10])
244
245 # Compute the silhouette scores for each sample
246 sample_silhouette_values = silhouette_samples(dataset, labels)
247
248 y_lower = 10
249 for i in range(n_clusters):
250 # Aggregate the silhouette scores for samples belonging to
251 # cluster i, and sort them
252 ith_cluster_silhouette_values = \
253 sample_silhouette_values[labels == i]
254
255 ith_cluster_silhouette_values.sort()
256
257 size_cluster_i = ith_cluster_silhouette_values.shape[0]
258 y_upper = y_lower + size_cluster_i
259
260 color = cm.nipy_spectral(float(i) / n_clusters)
261 ax1.fill_betweenx(np.arange(y_lower, y_upper),
262 0, ith_cluster_silhouette_values,
263 facecolor=color, edgecolor=color, alpha=0.7)
264
265 # Label the silhouette plots with their cluster numbers at the middle
266 ax1.text(-0.05, y_lower + 0.5 * size_cluster_i, str(i))
267
268 # Compute the new y_lower for next plot
269 y_lower = y_upper + 10 # 10 for the 0 samples
270
271 ax1.set_title("The silhouette plot for the various clusters.")
272 ax1.set_xlabel("The silhouette coefficient values")
273 ax1.set_ylabel("Cluster label")
274
275 # The vertical line for average silhouette score of all the values
276 ax1.axvline(x=silhouette_avg, color="red", linestyle="--")
277
278 ax1.set_yticks([]) # Clear the yaxis labels / ticks
279 ax1.set_xticks([-0.1, 0, 0.2, 0.4, 0.6, 0.8, 1])
280
281
282 plt.suptitle(("Silhouette analysis for clustering on sample data "
283 "with n_clusters = " + str(n_clusters) + "\nAverage silhouette_score = " + str(silhouette_avg)), fontsize=12, fontweight='bold')
284
285
286 plt.savefig(path, bbox_inches='tight')
287
288 ######################## dbscan ##############################################
289
290 def dbscan(dataset, eps, min_samples):
291 if not os.path.exists('clustering/dbscan_output'):
292 os.makedirs('clustering/dbscan_output')
293
294 if eps is not None:
295 clusterer = DBSCAN(eps = eps, min_samples = min_samples)
296 else:
297 clusterer = DBSCAN()
298
299 clustering = clusterer.fit(dataset)
300
301 core_samples_mask = np.zeros_like(clustering.labels_, dtype=bool)
302 core_samples_mask[clustering.core_sample_indices_] = True
303 labels = clustering.labels_
304
305 # Number of clusters in labels, ignoring noise if present.
306 n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
307
308 silhouette_avg = silhouette_score(dataset, labels)
309 warning("For n_clusters =" + str(n_clusters_) +
310 "The average silhouette_score is :" + str(silhouette_avg))
311
312 ##TODO: PLOT SU DBSCAN (no centers) e HIERARCHICAL
313
314 # Black removed and is used for noise instead.
315 unique_labels = set(labels)
316 colors = [plt.cm.Spectral(each)
317 for each in np.linspace(0, 1, len(unique_labels))]
318 for k, col in zip(unique_labels, colors):
319 if k == -1:
320 # Black used for noise.
321 col = [0, 0, 0, 1]
322
323 class_member_mask = (labels == k)
324
325 xy = dataset[class_member_mask & core_samples_mask]
326 plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),
327 markeredgecolor='k', markersize=14)
328
329 xy = dataset[class_member_mask & ~core_samples_mask]
330 plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),
331 markeredgecolor='k', markersize=6)
332
333 plt.title('Estimated number of clusters: %d' % n_clusters_)
334 s = 'clustering/dbscan_output/dbscan_plot.png'
335 fig = plt.gcf()
336 fig.set_size_inches(18.5, 10.5, forward = True)
337 fig.savefig(s, dpi=100)
338
339
340 write_to_csv(dataset, labels, 'clustering/dbscan_output/dbscan_results.tsv')
341
342 ########################## hierachical #######################################
343
344 def hierachical_agglomerative(dataset, k_min, k_max):
345
346 if not os.path.exists('clustering/agglomerative_output'):
347 os.makedirs('clustering/agglomerative_output')
348
349 plt.figure(figsize=(10, 7))
350 plt.title("Customer Dendograms")
351 shc.dendrogram(shc.linkage(dataset, method='ward'))
352 fig = plt.gcf()
353 fig.savefig('clustering/agglomerative_output/dendogram.png', dpi=200)
354
355 range_n_clusters = [i for i in range(k_min, k_max+1)]
356
357 for n_clusters in range_n_clusters:
358
359 cluster = AgglomerativeClustering(n_clusters=n_clusters, affinity='euclidean', linkage='ward')
360 cluster.fit_predict(dataset)
361 cluster_labels = cluster.labels_
362
363 silhouette_avg = silhouette_score(dataset, cluster_labels)
364 warning("For n_clusters =", n_clusters,
365 "The average silhouette_score is :", silhouette_avg)
366
367 plt.clf()
368 plt.figure(figsize=(10, 7))
369 plt.title("Agglomerative Hierarchical Clustering\nwith " + str(n_clusters) + " clusters and " + str(silhouette_avg) + " silhouette score")
370 plt.scatter(dataset[:,0], dataset[:,1], c = cluster_labels, cmap='rainbow')
371 s = 'clustering/agglomerative_output/hierachical_' + str(n_clusters) + '_clusters.png'
372 fig = plt.gcf()
373 fig.set_size_inches(10, 7, forward = True)
374 fig.savefig(s, dpi=200)
375
376 write_to_csv(dataset, cluster_labels, 'clustering/agglomerative_output/agglomerative_hierarchical_with_' + str(n_clusters) + '_clusters.tsv')
377
378
379
380
381 ############################# main ###########################################
382
383
384 def main():
385 if not os.path.exists('clustering'):
386 os.makedirs('clustering')
387
388 args = process_args(sys.argv)
389
390 #Data read
391
392 X = read_dataset(args.input)
393 X = pd.DataFrame.to_dict(X, orient='list')
394 X = rewrite_input(X)
395 X = pd.DataFrame.from_dict(X, orient = 'index')
396
397 for i in X.columns:
398 tmp = X[i][0]
399 if tmp == None:
400 X = X.drop(columns=[i])
401
402 X = pd.DataFrame.to_numpy(X)
403
404
405 if args.cluster_type == 'kmeans':
406 kmeans(args.k_min, args.k_max, X, args.elbow, args.silhouette, args.davies)
407
408 if args.cluster_type == 'dbscan':
409 dbscan(X, args.eps, args.min_samples)
410
411 if args.cluster_type == 'hierarchy':
412 hierachical_agglomerative(X, args.k_min, args.k_max)
413
414 ##############################################################################
415
416 if __name__ == "__main__":
417 main()