kmeans update

solving_problems/kmeans_descriptions.py

@@ -32,7 +32,7 @@
     sys.exit(1)
 
 
-input_data = csv.reader(open('descriptions.csv','rb'))
+input_data = csv.reader(open('descriptions_100.csv','rb'))
 dataset_data = []
 dataset_target = []
 for row in input_data:
@@ -50,31 +50,21 @@
 
 print "done in %fs" % (time() - t0)
 print "n_samples: %d, n_features: %d" % X.shape
-print
 
 
 ###############################################################################
 # Do the actual clustering
 
-if opts.minibatch:
-    km = MiniBatchKMeans(k=true_k, init='k-means++', n_init=1,
-                         init_size=1000,
-                         batch_size=1000, verbose=1)
-else:
-    km = KMeans(k=true_k, init='random', max_iter=100, n_init=1, verbose=1)
+km = MiniBatchKMeans(k=true_k, init='k-means++', n_init=1,init_size=1000,batch_size=1000, verbose=1)
 
-print "Clustering sparse data with %s" % km
+print "Clustering with %s" % km
 t0 = time()
 km.fit(X)
-print "done in %0.3fs" % (time() - t0)
-print
-
-print "Homogeneity: %0.3f" % metrics.homogeneity_score(labels, km.labels_)
-print "Completeness: %0.3f" % metrics.completeness_score(labels, km.labels_)
-print "V-measure: %0.3f" % metrics.v_measure_score(labels, km.labels_)
-print "Adjusted Rand-Index: %.3f" % \
-    metrics.adjusted_rand_score(labels, km.labels_)
-print "Silhouette Coefficient: %0.3f" % metrics.silhouette_score(
-    X, labels, sample_size=1000)
-
-print
+print "done in %0.3fs\n" % (time() - t0)
+print km.labels_
+
+# print "Homogeneity: %0.3f" % metrics.homogeneity_score(labels, km.labels_)
+# print "Completeness: %0.3f" % metrics.completeness_score(labels, km.labels_)
+# print "V-measure: %0.3f" % metrics.v_measure_score(labels, km.labels_)
+
+