def kmeans_euc(k, news):
matrix = tfidf(news)
centroid = start(k, matrix)
ii = 0
while ii < 10:
cluster = kernel_euc(centroid, matrix, k)
print rss(cluster, centroid)
centroid = new(cluster)
ii += 1
if ii == 10:
out = token__.labelize(news)
output(cluster, matrix, out)
def kernel(centroid, matrix, news):
cluster = []
for i in range(len(centroid)):
cluster.append([centroid[i]])
for i in matrix:
distance = []
for j in centroid:
distance.append(euclidean(matrix[i], j))
if sum(distance) == 0:
l = random.randint(0, len(centroid) - 1)
cluster[l].append(matrix[i])
cluster[l] = list(set(cluster[l]))
centroid = new(cluster)
else:
for m in range(len(distance)):
if distance[m] == min(distance) and matrix[i] not in cluster[m]:
cluster[m].append(matrix[i])
centroid = new(cluster)
print rss(cluster, centroid)
out = token__.labelize(news)
print out
output(cluster, matrix, out)