def find_cluster_centroids(self, cluster_index): #print "Finding cluster centroids.." data_arr = array([self.restimes]) centroids, cmask = clustercentroids(data_arr, mask = self.masks, transpose = self.centroids_transpose, clusterid = cluster_index, method = self.method) return centroids
def cluster_sentences(cls, sentences, n):
"""Cluster the sentences into n clusters.
Args:
sentences: [IRSentence]
n: int, number of clusters
Returns:
[int], group id of each sentence in sentences
"""
vol = set()
for sentence in sentences:
tfidf = sentence.get_tfidf()
for term in tfidf:
vol.add(term)
vol = list(vol)
vecs = []
for sentence in sentences:
tfidf = sentence.get_tfidf()
vec = []
for term in vol:
if term in tfidf:
vec.append(tfidf[term])
else:
vec.append(0.0)
vecs.append(vec)
# call pycluster k-means
from Pycluster import kcluster, clustercentroids, distancematrix
labels, error, nfound = kcluster(vecs, nclusters=n, method='a',
dist='u')
centroids, cmask = clustercentroids(vecs, clusterid=labels, method='a')
sentence_ids = []
for centroid_index, centroid in enumerate(centroids):
# find vecs in the cluster
subvecs = [centroid]
subvecindexs = [-1]
for label_index, label in enumerate(labels):
if label == centroid_index:
subvecs.append(vecs[label_index])
subvecindexs.append(label_index)
# find the min dist vec
matrix = distancematrix(subvecs, dist='u')
minimum = 100000
minimum_index = 0
for i in xrange(1, subvecs.__len__()):
dist = matrix[i][0]
if dist < minimum:
minimum = dist
minimum_index = subvecindexs[i]
sentence_ids.append(minimum_index)
# method='a')
return labels, sentence_ids
def create_clustered_samples(points, nclusters, transpose):
print points[1:6]
labels, error, nfound= kcluster(points[1:4], nclusters, None, None, transpose, npass=1, method='a', dist='e', initialid=None)
cdata, cmask = clustercentroids(points[1:4], None, labels, 'a', transpose)
print cdata
clusteredpoints = list()
for i in range(nclusters):
clusteredpoints.append(list())
if transpose == 0:
for index in range(len(points)):
clusteredpoints[labels[index]].append(points[index])
return clusteredpoints, cdata
else:
for i in range(len(clusteredpoints)):
for types in range(len(points)):
clusteredpoints[i].append(list())
for index in range(len(labels)):
for item in range(len(points)):
clusteredpoints[labels[index]][item].append(points[item][index])
#print clusters and some element
x = cdata[1]
y = cdata[2]
# fig = figure()
# ax1 = fig.add_subplot(1,1,1)
# ax1.scatter(x, y, c='r')
# ax1.axis([0,max(x)+1,0,max(y)+1])
# ax1.set_xlabel('number of bodies')
# ax1.set_ylabel('number of steps')
# x0 = clusteredpoints[0][2]
# y0 = clusteredpoints[0][3]
#
# x1 = clusteredpoints[1][1]
# y1 = clusteredpoints[1][2]
#
# x2 = clusteredpoints[2][1]
# y2 = clusteredpoints[2][2]
#
# x3 = clusteredpoints[3][1]
# y3 = clusteredpoints[3][2]
#
# x4 = clusteredpoints[4][1]
# y4 = clusteredpoints[4][2]
#
# x5 = clusteredpoints[5][1]
# y5 = clusteredpoints[5][2]
#
# ax1.scatter(x0[1:20],y0[1:20], marker='s')
# ax1.scatter(x1[1:20],y1[1:20], marker='^')
# ax1.scatter(x2[1:15],y2[1:15], marker='<')
# ax1.scatter(x3[1:15],y3[1:15], marker='>')
# ax1.scatter(x4[1:15],y4[1:15], marker='p')
# ax1.scatter(x5[1:15],y5[1:15], marker='8')
# show()
return clusteredpoints, cdata
