def init():
global clusters
Tweet.dim = 0
setupTweets()
print("computing initial centroids...")
Centroids = canopy(M, T1, T2)
# print len(Centroids)
arr_M = convert_to_array(M)
# print arr_M.shape
arr_cent = convert_to_array(Centroids)
# print arr_cent.shape
global code
print("performing k-means...")
code, center = k_means_init(arr_M, arr_cent)
clusters = [[None]] * len(center)
for i in range(len(clusters)):
clusters[i] = Cluster(TCV(0, 0, 0, 0, 0, []), [], center[i].tolist())
print("computing ft-set...")
for i in range(len(M)):
M[i].cluster = code[i]
clusters[code[i]].tweets.append(M[i])
clusters[code[i]].tcv.sum_v = [0] * Tweet.dim
clusters[code[i]].tcv.wsum_v = [0] * Tweet.dim
clusters[code[i]].tcv.n = len(clusters[code[i]].tweets)
if len(clusters[code[i]].tcv.ft_set) >= size_ftset:
get_ftset(code[i], M[i])
else:
clusters[code[i]].tcv.ft_set.append(M[i])
print("computing tweet cluster vectors...")
for i in range(len(clusters)):
for j in range(len(clusters[i].tweets)):
#print(clusters[i])
norm_fac = norm(clusters[i].tweets[j].tv)
clusters[i].tweets[j].normtv = norm_fac
if norm_fac == 0:
clusters[i].tweets[j].normtv = 1
norm_fac = 1
newList1 = [x / norm_fac for x in clusters[i].tweets[j].tv]
newList2 = [
x * clusters[i].tweets[j].w for x in clusters[i].tweets[j].tv
]
clusters[i].tcv.sum_v = [
x + y for x, y in zip(clusters[i].tcv.sum_v, newList1)
]
clusters[i].tcv.wsum_v = [
x + y for x, y in zip(clusters[i].tcv.wsum_v, newList2)
]
def init():
global clusters
Tweet.dim = 0
setupTweets()
print ("computing initial centroids...")
Centroids = canopy(M,T1,T2)
# print len(Centroids)
arr_M = convert_to_array(M)
# print arr_M.shape
arr_cent = convert_to_array(Centroids)
# print arr_cent.shape
global code
print ("performing k-means...")
code, center = k_means_init(arr_M, arr_cent)
clusters = [[None]] * len(center)
for i in range(len(clusters)):
clusters[i] = Cluster(TCV(0,0,0,0,0,[]),[],center[i].tolist())
print ("computing ft-set...")
for i in range(len(M)):
M[i].cluster = code[i]
clusters[code[i]].tweets.append(M[i])
clusters[code[i]].tcv.sum_v = [0] * Tweet.dim
clusters[code[i]].tcv.wsum_v = [0] * Tweet.dim
clusters[code[i]].tcv.n = len(clusters[code[i]].tweets)
if len(clusters[code[i]].tcv.ft_set) >= size_ftset:
get_ftset(code[i],M[i])
else:
clusters[code[i]].tcv.ft_set.append(M[i])
print ("computing tweet cluster vectors...")
for i in range(len(clusters)):
for j in range(len(clusters[i].tweets)):
#print(clusters[i])
norm_fac = norm(clusters[i].tweets[j].tv)
clusters[i].tweets[j].normtv = norm_fac
if norm_fac == 0:
clusters[i].tweets[j].normtv = 1
norm_fac = 1
newList1 = [x / norm_fac for x in clusters[i].tweets[j].tv]
newList2 = [x * clusters[i].tweets[j].w for x in clusters[i].tweets[j].tv]
clusters[i].tcv.sum_v = [x + y for x, y in zip(clusters[i].tcv.sum_v, newList1)]
clusters[i].tcv.wsum_v = [x + y for x, y in zip(clusters[i].tcv.wsum_v, newList2)]
def init(M): Centroids = canopy(M,1,10) arr_M = convert_to_array(M) arr_cent = convert_to_array(Centroids) code = k_means_init(arr_M, arr_cent)
def init(M):
Centroids = canopy(M, 1, 10)
arr_M = convert_to_array(M)
arr_cent = convert_to_array(Centroids)
code = k_means_init(arr_M, arr_cent)
