def biclustering(db):
#mydata = genfromtxt('/home/fan/intern/process_db/analysis/viewtime_matrix_524.csv',dtype=None,delimiter=',',names=True,skip_header=1)
df = pd.read_csv(
'/home/fan/intern/process_db/analysis/viewtime_matrix_501_0.1.csv')
dma = 501
#print df.head()
print df.shape
dev_list = df.ix[:, 0].values
prog_list = df.columns.values
#print type(dev_list)
#print type(prog_list)
df.drop(df.columns[0], axis=1, inplace=True)
#df[df==0] = 1
df = df.apply(fraction, axis=1)
#print df.head()
#print df.values
#print type(df.values)
#mydata = df.values
#mydata=np.delete(mydata, 0, axis=0)
#mydata=np.delete(mydata, 0, axis=1)
#mydata[mydata==0] = 0.01
#print 'data format is:',mydata,type(mydata)
# model=SpectralCoclustering(n_clusters=5, random_state=0)
#n_clusters=(1000,20) # 4*3 = 12 clusters
#model = SpectralBiclustering(random_state=None)
model = SpectralCoclustering(n_clusters=10)
model.fit(df)
#fit_data=mydata[np.argsort(model.row_labels_)]
#fit_data=fit_data[:,np.argsort(model.column_labels_)]
#plt.matshow(fit_data[0:40],cmap=plt.cm.Blues)
# plt.show()
print model.get_params()
for i in range(0, 5):
print 'Size of one cluster:', model.get_shape(i)
indices = model.get_indices(i)
#print indices[1]
print prog_list[indices[1]]
print model.get_submatrix(i, df.values)
dev_in_cluster = dev_list[indices[0]]
#print type(dev_in_cluster)
print 'number of devices within this cluster:', len(dev_in_cluster)
get_income(db, dma, dev_in_cluster.tolist())
col_complement = np.nonzero(np.logical_not(cocluster.columns_[i]))[0]
weight = X[rows[:, np.newaxis], cols].sum()
cut = (X[row_complement[:, np.newaxis], cols].sum() +
X[rows[:, np.newaxis], col_complement].sum())
return cut / weight
bicluster_ncuts = list(bicluster_ncut(i)
for i in xrange(len(newsgroups.target_names)))
best_idx = np.argsort(bicluster_ncuts)[:5]
print()
print("Best biclusters:")
print("----------------")
for idx, cluster in enumerate(best_idx):
n_rows, n_cols = cocluster.get_shape(cluster)
cluster_docs, cluster_words = cocluster.get_indices(cluster)
if not len(cluster_docs) or not len(cluster_words):
continue
# categories
cluster_categories = list(document_names[i] for i in cluster_docs)
counter = Counter(cluster_categories)
cat_string = ", ".join("{:.0f}% {}".format(float(c) / n_rows * 100,
name)
for name, c in counter.most_common()[:3])
# words
out_of_cluster_docs = cocluster.row_labels_ != cluster
out_of_cluster_docs = np.where(out_of_cluster_docs)[0]
word_col = X[:, cluster_words]
"""Items of a defaultdict(int) with the highest values.
Like Counter.most_common in Python >=2.7.
"""
return sorted(iteritems(d), key=operator.itemgetter(1), reverse=True)
bicluster_ncuts = list(bicluster_ncut(i)
for i in range(len(newsgroups.target_names)))
best_idx = np.argsort(bicluster_ncuts)[:5]
print()
print("Best biclusters:")
print("----------------")
for idx, cluster in enumerate(best_idx):
n_rows, n_cols = cocluster.get_shape(cluster)
cluster_docs, cluster_words = cocluster.get_indices(cluster)
if not len(cluster_docs) or not len(cluster_words):
continue
# categories
counter = defaultdict(int)
for i in cluster_docs:
counter[document_names[i]] += 1
cat_string = ", ".join("{:.0f}% {}".format(float(c) / n_rows * 100, name)
for name, c in most_common(counter)[:3])
# words
out_of_cluster_docs = cocluster.row_labels_ != cluster
out_of_cluster_docs = np.where(out_of_cluster_docs)[0]
word_col = X[:, cluster_words]
avg_data[row_sel, col_sel] = np.average(data[row_sel, col_sel])
avg_data = avg_data[np.argsort(model.row_labels_)]
avg_data = avg_data[:, np.argsort(model.column_labels_)]
plt.matshow(avg_data, cmap=plt.cm.Blues)
plt.title("Average cluster intensity")
plt.savefig('%s_averaged.png' % (identifier), bbox_inches='tight')
if args.write:
print "Writing clusters to database."
# No need to clean up here, just overwrite by _id.
for c in range(n_clusters):
(nr, nc) = model.get_shape(c)
(row_ind, col_ind) = model.get_indices(c)
cluster_val = None
if nr > 25 or nc > 50:
print "Nulling cluster %d: shape (%d, %d)" % (c, nr, nc)
else:
cluster_val = c
for ri in row_ind:
data_list[ri]['cluster'] = cluster_val
datastream.save(data_list[ri])
for ci in col_ind:
events_list[ci]['cluster'] = cluster_val
events.save(events_list[ci])
avg_data[row_sel, col_sel] = np.average(data[row_sel, col_sel])
avg_data = avg_data[np.argsort(model.row_labels_)]
avg_data = avg_data[:, np.argsort(model.column_labels_)]
plt.matshow(avg_data, cmap=plt.cm.Blues)
plt.title("Average cluster intensity")
plt.savefig('%s_averaged.png' % (identifier), bbox_inches='tight')
if args.write:
print "Writing clusters to database."
# No need to clean up here, just overwrite by _id.
for c in range(n_clusters):
(nr, nc) = model.get_shape(c)
(row_ind, col_ind) = model.get_indices(c)
cluster_val = None
if nr > 25 or nc > 50:
print "Nulling cluster %d: shape (%d, %d)" % (c, nr, nc)
else:
cluster_val = c
for ri in row_ind:
data_list[ri]['cluster'] = cluster_val
datastream.save(data_list[ri])
for ci in col_ind:
events_list[ci]['cluster'] = cluster_val
events.save(events_list[ci])
