def find(self, X, labels, n_clusters):
self.diameter = utils.find_diameter(X)
self.centroids = cluster_centroid.cluster_centroid(
X, labels, n_clusters)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(
labels, n_clusters)
self.dists = [[0 for _ in range(len(labels))]
for _ in range(len(labels))]
self.centroid_dists = [0 for _ in range(len(labels))]
self.delta = [[0 for _ in range(n_clusters)]
for _ in range(n_clusters)]
minimum_dif_c = sys.float_info.max # min dist in different clusters
maximum_same_c = sys.float_info.min # max dist in the same cluster
self.sums = [0 for _ in range(n_clusters)]
for i in range(len(labels)):
self.centroid_dists[i] = utils.euclidian_dist(
X[i], self.centroids[labels[i]])
self.sums[labels[i]] += self.centroid_dists[i]
for i in range(len(labels) - 1):
for j in range(i + 1, len(labels)):
self.dists[i][j] = utils.euclidian_dist(X[i], X[j])
self.dists[j][i] = self.dists[i][j]
self.dists_same_c.append([i, j])
maximum_same_c = max(self.dists[i][j], maximum_same_c)
for i in range(n_clusters):
for j in range(n_clusters):
if i != j:
self.delta[i][j] = (self.sums[i] + self.sums[j]) / float(
self.cluster_sizes[i] + self.cluster_sizes[j])
minimum_dif_c = min(minimum_dif_c, self.delta[i][j])
return -(minimum_dif_c / maximum_same_c)
def update(self, X, n_clusters, labels, k, l, id):
point = X[id]
prev_centroids = np.copy(self.centroids)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(labels, n_clusters)
self.centroids = cluster_centroid.update_centroids(np.copy(self.centroids), np.copy(self.cluster_sizes), point, k, l)
delta = 10**(-math.log(len(X), 10) - 1)
for i in range(len(labels)):
if (labels[i] == k and utils.euclidian_dist(prev_centroids[k], self.centroids[k]) > delta * self.diameter
or labels[i] == l and utils.euclidian_dist(prev_centroids[l], self.centroids[l]) > delta * self.diameter):
self.dist_ps[i] = utils.d_ps(X, labels, X[i], labels[i], self.centroids)
if utils.euclidian_dist(prev_centroids[k], self.centroids[k]) > delta * self.diameter:
self.sym_s_clusters[k] = self.sym_s(X, labels, k, self.cluster_sizes, self.centroids)
if utils.euclidian_dist(prev_centroids[l], self.centroids[l]) > delta * self.diameter:
self.sym_s_clusters[l] = self.sym_s(X, labels, l, self.cluster_sizes, self.centroids)
db = 0
for i in range(n_clusters):
if i != k:
tm = utils.euclidian_dist(self.centroids[i], self.centroids[k])
self.fractions[i][k] = (self.sym_s_clusters[i] + self.sym_s_clusters[k]) / tm
self.fractions[k][i] = self.fractions[i][k]
if i != l:
tm = utils.euclidian_dist(self.centroids[i], self.centroids[l])
self.fractions[i][l] = (self.sym_s_clusters[i] + self.sym_s_clusters[l]) / tm
self.fractions[l][i] = self.fractions[i][l]
for i in range(n_clusters):
tmp = np.amax(self.fractions[i])
db += tmp
db /= float(n_clusters)
return db
def find(self, X, labels, n_clusters):
self.diameter = utils.find_diameter(X)
self.centroids = cluster_centroid.cluster_centroid(
X, labels, n_clusters)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(
labels, n_clusters)
self.dist_same_c = []
rows, colums = X.shape
self.dists = [[0. for _ in range(rows)] for _ in range(rows)]
minimum_dif_c = sys.float_info.max # min dist in different clusters
maximum_same_c = sys.float_info.min # max dist in the same cluster
centres_l = [[sys.float_info.max] * n_clusters] * n_clusters
self.centers = np.array(centres_l)
for i in range(n_clusters):
for j in range(n_clusters):
if i != j:
self.centers[i][j] = utils.euclidian_dist(
self.centroids[i], self.centroids[j])
for i in range(rows - 1):
for j in range(i + 1, rows):
self.dists[i][j] = utils.euclidian_dist(X[i], X[j])
self.dists[j][i] = self.dists[i][j]
if labels[i] != labels[j]:
dist = self.centers[labels[i]][labels[j]]
minimum_dif_c = min(dist, minimum_dif_c)
else:
self.dist_same_c.append([i, j])
maximum_same_c = max(self.dists[i][j], maximum_same_c)
return -(minimum_dif_c / maximum_same_c)
def find(self, X, labels, n_clusters):
self.diameter = utils.find_diameter(X)
self.centroids = cluster_centroid.cluster_centroid(
X, labels, n_clusters)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(
labels, n_clusters)
rows, colums = X.shape
self.sums = [0 for _ in range(n_clusters)]
minimum_dif_c = sys.float_info.max # min dist in different clusters
centres_l = [[sys.float_info.max] * n_clusters] * n_clusters
self.centers = np.array(centres_l)
self.centroid_dists = [0 for _ in range(len(labels))]
# self.centroid_dists = [utils.euclidian_dist(X[i], self.centroids[labels[i]]) for i in range(len(X))]
for i in range(len(labels)):
self.centroid_dists[i] = utils.euclidian_dist(
X[i], self.centroids[labels[i]])
self.sums[labels[i]] += self.centroid_dists[i]
for i in range(n_clusters):
for j in range(n_clusters):
if i != j:
self.centers[i][j] = utils.euclidian_dist(
self.centroids[i], self.centroids[j])
for i in range(rows):
for j in range(rows):
if labels[i] != labels[j]:
dist = self.centers[labels[i]][labels[j]]
minimum_dif_c = min(dist, minimum_dif_c)
denominator = list(self.sums)
for i in range(n_clusters):
denominator[i] *= (2 / self.cluster_sizes[i])
return -(minimum_dif_c / max(denominator))
def find(self, X, labels, n_clusters):
self.centroids = cluster_centroid.cluster_centroid(
X, labels, n_clusters)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(
labels, n_clusters)
self.diameter = utils.find_diameter(X)
self.dists = [[0. for _ in range(len(labels))]
for _ in range(len(labels))]
self.dist_same_c = []
rows, colums = X.shape
delta_l = [[0.0] * n_clusters] * n_clusters
self.delta = np.array(delta_l)
minimum_dif_c = sys.float_info.max # min dist in different clusters
maximum_same_c = sys.float_info.min # max dist in the same cluster
for i in range(rows - 1):
for j in range(i + 1, rows):
self.dists[i][j] = utils.euclidian_dist(X[i], X[j])
self.dists[j][i] = self.dists[i][j]
if labels[i] != labels[j]:
self.delta[labels[i]][labels[j]] += self.dists[i][j]
else:
self.dist_same_c.append([i, j])
maximum_same_c = max(self.dists[i][j], maximum_same_c)
for i in range(n_clusters - 1):
for j in range(i + 1, n_clusters):
self.delta[i][j] /= float(self.cluster_sizes[i] *
self.cluster_sizes[j])
if self.delta[i][j] != 0:
minimum_dif_c = min(minimum_dif_c, self.delta[i][j])
return -minimum_dif_c / maximum_same_c
def update(self, X, n_clusters, labels, k, l, id):
point = X[id]
prev_centroids = np.copy(self.centroids)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(
labels, n_clusters)
self.centroids = cluster_centroid.update_centroids(
np.copy(self.centroids), np.copy(self.cluster_sizes), point, k, l)
delta = 10**(-math.log(len(X), 10) - 1)
if utils.euclidian_dist(prev_centroids[k],
self.centroids[k]) > delta * self.diameter:
self.sigmas[k] = self.normed_cluster_sigma(X, labels, k)
if utils.euclidian_dist(prev_centroids[l],
self.centroids[l]) > delta * self.diameter:
self.sigmas[l] = self.normed_cluster_sigma(X, labels, l)
term1 = sum(self.sigmas) / (n_clusters * self.normed_sigma_x)
stdev_val = self.stdev(n_clusters)
if (utils.euclidian_dist(prev_centroids[k],
self.centroids[k]) > delta * self.diameter
or utils.euclidian_dist(prev_centroids[l], self.centroids[l]) >
delta * self.diameter):
self.dens = 0.0
for k in range(0, n_clusters):
for l in range(0, n_clusters):
self.dens += self.den2(X, labels, self.centroids, k, l, stdev_val) /\
max(self.den1(X, labels, self.centroids, k, stdev_val),
self.den1(X, labels, self.centroids, l, stdev_val))
self.dens /= n_clusters * (n_clusters - 1)
return (term1 + self.dens)
def find(self, X, labels, n_clusters):
self.centroids = cluster_centroid.cluster_centroid(X, labels, n_clusters)
self.dists = [[0. for _ in range(len(labels))] for _ in range(len(labels))]
self.sums = [0 for _ in range(n_clusters)]
rows, colums = X.shape
self.point_in_c = cluster_centroid.count_cluster_sizes(labels, n_clusters)
self.delta_l = [[0.0] * n_clusters] * n_clusters
self.delta = np.array(self.delta_l)
self.centroid_dists = [0 for _ in range(len(labels))]
#self.centroid_dists = [utils.euclidian_dist(X[i], self.centroids[labels[i]]) for i in range(len(X))]
minimum_dif_c = sys.float_info.max
for i in range(len(labels)):
self.centroid_dists[i] = utils.euclidian_dist(X[i], self.centroids[labels[i]])
self.sums[labels[i]] += self.centroid_dists[i]
for i in range(rows - 1):
for j in range(i + 1, rows):
self.dists[i][j] = utils.euclidian_dist(X[i], X[j])
self.dists[j][i] = self.dists[i][j]
if labels[i] != labels[j]:
self.delta[labels[i]][labels[j]] += self.dists[i][j]
for i in range(n_clusters):
for j in range(n_clusters):
self.delta[i][j] /= float(self.point_in_c[i] * self.point_in_c[j])
if self.delta[i][j] != 0:
minimum_dif_c = min(minimum_dif_c, self.delta[i][j])
self.sums[i] *= (2 / self.point_in_c[i])
#print(max(self.sums))
return -(minimum_dif_c / max(self.sums))
def update(self, X, n_clusters, labels, k, l, id):
point = X[id]
self.cluster_sizes = cluster_centroid.count_cluster_sizes(
labels, n_clusters)
self.centroids = cluster_centroid.update_centroids(
np.copy(self.centroids), np.copy(self.cluster_sizes), point, k, l)
self.numerators[k] = 0.0
self.numerators[l] = 0.0
for i in range(len(labels)):
if labels[i] == k or labels[i] == l:
self.numerators[labels[i]] += utils.euclidian_dist(
X[i], self.centroids[labels[i]])
for i in range(len(labels)):
if labels[i] == k:
self.inner_max_dists[i][id] = utils.euclidian_dist(X[i], X[id])
self.inner_max_dists[id][i] = self.inner_max_dists[i][id]
if labels[i] == l:
self.inner_max_dists[i][id] = 0
self.inner_max_dists[id][i] = 0
self.outer_min_dists[l][id] = sys.float_info.max
for c in [k, l]:
for i in range(len(labels)):
if labels[i] == c:
continue
inner_max_dist = 0
for j in range(len(self.inner_max_dists[i])):
if labels[j] == c:
inner_max_dist = max(inner_max_dist,
self.inner_max_dists[i][j])
if inner_max_dist != 0:
self.outer_min_dists[c][i] = inner_max_dist
outer_min_dist = np.amin(self.outer_min_dists[c])
self.accumulator[c] = self.numerators[c] / outer_min_dist
return sum(self.accumulator) / len(labels)
def sv(X, labels, n_clusters):
centroids = cluster_centroid.cluster_centroid(X, labels, n_clusters)
cluster_sizes = cluster_centroid.count_cluster_sizes(labels, n_clusters)
numerator = 0.0
for k in range(0, n_clusters - 1):
min_dist = sys.float_info.max
for l in range(k + 1, n_clusters):
min_dist = min(min_dist,
utils.euclidian_dist(centroids[k], centroids[l]))
numerator += min_dist
denominator = 0.0
for k in range(0, n_clusters):
list = []
for i in range(0, len(labels)):
if labels[i] != k:
continue
list.append(utils.euclidian_dist(X[i], centroids[k]))
# get sum of 0.1*|Ck| largest elements
acc = 0.0
max_n = heapq.nlargest(int(math.ceil(0.1 * cluster_sizes[k])), list)
for i in range(0, len(max_n)):
acc += max_n[i]
denominator += acc * 10.0 / cluster_sizes[k]
return -numerator / denominator
def cs_index(X, labels, n_clusters):
elements, ignore_columns = X.shape
centroids = cluster_centroid.cluster_centroid(X, labels, n_clusters)
cluster_sizes = cluster_centroid.count_cluster_sizes(labels, n_clusters)
max_dists = [sys.float_info.min] * elements
for i in range(0, elements): # for every element
for j in range(i, elements - 1): # for every other
if labels[i] != labels[j]:
continue # if they are in the same cluster
# update the distance to the farthest element in the same cluster
max_dists[i] = max(max_dists[i], utils.euclidian_dist(X[i], X[j]))
# max_dists contain for each element the farthest the his cluster
numerator = 0.0
for i in range(0, elements):
numerator += max_dists[i] / cluster_sizes[labels[i]]
denominator = 0.0
for i in range(0, n_clusters):
min_centroids_dist = sys.float_info.max
for j in range(i + 1, n_clusters):
min_centroids_dist = min(
utils.euclidian_dist(centroids[i], centroids[j]),
min_centroids_dist)
denominator += min_centroids_dist
assert denominator != 0.0
return numerator / denominator
def update(self, X, n_clusters, labels, k, l, id):
point = X[id]
prev_centroids = np.copy(self.centroids)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(labels, n_clusters)
self.centroids = cluster_centroid.update_centroids(np.copy(self.centroids), np.copy(self.cluster_sizes), point, k, l)
for i in range(n_clusters):
if i > k:
self.centroid_dists[k][i] = utils.euclidian_dist(self.centroids[i], self.centroids[k])
self.centroid_dists[i][k] = self.centroid_dists[k][i]
if i > l:
self.centroid_dists[l][i] = utils.euclidian_dist(self.centroids[i], self.centroids[l])
self.centroid_dists[i][l] = self.centroid_dists[l][i]
numerator = 0.0
for i in range(n_clusters):
min_dist = np.amin(self.centroid_dists[i])
numerator += min_dist
denominator = 0.0
self.dists[k][id] = 0.
delta = 10**(-math.log(len(X), 10) - 1)
for i in range(len(labels)):
if (labels[i] == k and utils.euclidian_dist(prev_centroids[k], self.centroids[k]) > delta * self.diameter
or labels[i] == l and utils.euclidian_dist(prev_centroids[l], self.centroids[l]) > delta * self.diameter):
self.dists[labels[i]][i] = utils.euclidian_dist(X[i], self.centroids[labels[i]])
for c in range(n_clusters):
# get sum of 0.1*|Ck| largest elements
acc = 0.0
max_n = heapq.nlargest(int(math.ceil(0.1 * self.cluster_sizes[c])), self.dists[c])
for i in range(0, len(max_n)):
acc += max_n[i]
denominator += acc * 10.0 / self.cluster_sizes[c]
return -(numerator / denominator)
def c_ind(X, labels, n_clusters):
rows, colums = X.shape
s_c = 0
for i in range(0, rows):
for j in range(0, int(math.ceil(float(rows) / 2.0))):
s_c += utils.euclidian_dist(X[i], X[j])
cluster_sizes = cluster_centroid.count_cluster_sizes(labels, n_clusters)
n_w = 0
for k in range(0, n_clusters):
n_w += cluster_sizes[k] * (cluster_sizes[k] - 1) / 2
distances = []
for i in range(0, len(labels) - 1):
for j in range(i + 1, len(labels)):
distances.append(utils.euclidian_dist(X[i], X[j]))
s_min = heapq.nsmallest(int(n_w), distances)
s_max = heapq.nlargest(int(n_w), distances)
ones = [1] * int(n_w)
s_min_c = np.dot(s_min, np.transpose(ones))
s_max_c = np.dot(s_max, np.transpose(ones))
# TODO check dot product correct
return (s_c - s_min_c) / (s_max_c - s_min_c)
def update(self, X, n_clusters, labels, k, l, id):
point = X[id]
prev_centroids = np.copy(self.centroids)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(
labels, n_clusters)
self.centroids = cluster_centroid.update_centroids(
np.copy(self.centroids), np.copy(self.cluster_sizes), point, k, l)
for i in range(n_clusters):
if i > k:
self.dist_centroids[k][i] = utils.euclidian_dist(
self.centroids[i], self.centroids[k])
if i > l:
self.dist_centroids[l][i] = utils.euclidian_dist(
self.centroids[i], self.centroids[l])
numerator = np.amax(self.dist_centroids)
delta = 10**(-math.log(len(X), 10) - 1)
for i in range(len(labels)):
if (labels[i] == k and
utils.euclidian_dist(prev_centroids[k], self.centroids[k])
> delta * self.diameter or labels[i] == l and
utils.euclidian_dist(prev_centroids[l], self.centroids[l])
> delta * self.diameter):
self.dist_ps[i] = utils.d_ps(X, labels, X[i], labels[i],
self.centroids)
denominator = sum(self.dist_ps)
return -(numerator / (denominator * n_clusters))
def update(self, X, n_clusters, labels, k, l, id):
self.cluster_sizes = cluster_centroid.count_cluster_sizes(labels, n_clusters)
self.centroids = cluster_centroid.update_centroids(np.copy(self.centroids), np.copy(self.cluster_sizes),
X[id], k, l)
#self.cluster_sizes[k] -= 1
#self.cluster_sizes[l] += 1
for i in range(len(labels)):
if labels[i] == k:
self.s_c -= utils.euclidian_dist(X[i], X[id])
if labels[i] == l:
self.s_c += utils.euclidian_dist(X[i], X[id])
prev_n_w = self.n_w
self.n_w = self.n_w - (self.cluster_sizes[k] + 1) * self.cluster_sizes[k] / 2 + self.cluster_sizes[k] * (self.cluster_sizes[k] - 1) / 2 \
- (self.cluster_sizes[l] - 1) * (self.cluster_sizes[l] - 2) / 2 + self.cluster_sizes[l] * (self.cluster_sizes[l] - 1) / 2
delta = 0.1
#print(prev_n_w)
#print(self.n_w)
#print(delta * len(labels))
if abs(self.n_w - prev_n_w) > delta * len(labels):
self.s_min = heapq.nsmallest(int(self.n_w), self.distances)
self.s_max = heapq.nlargest(int(self.n_w), self.distances)
#ones = [1] * int(self.n_w)
#s_min_c = np.dot(self.s_min, np.transpose(ones))
#s_max_c = np.dot(self.s_max, np.transpose(ones))
s_min_c = sum(self.s_min)
s_max_c = sum(self.s_max)
return (self.s_c - s_min_c) / (s_max_c - s_min_c)
def find(self, X, labels, n_clusters):
self.centroids = cluster_centroid.cluster_centroid(X, labels, n_clusters)
self.diameter = utils.find_diameter(X)
self.cluster_sizes = []
self.distances = []
self.s_c = 0
self.n_w = 0
rows, colums = X.shape
for i in range(rows - 1):
for j in range(i + 1, rows):
if labels[i] == labels[j]:
self.s_c += utils.euclidian_dist(X[i], X[j])
self.cluster_sizes = cluster_centroid.count_cluster_sizes(labels, n_clusters)
for k in range(0, n_clusters):
self.n_w += self.cluster_sizes[k] * (self.cluster_sizes[k] - 1) / 2
for i in range(0, len(labels) - 1):
for j in range(i + 1, len(labels)):
self.distances.append(utils.euclidian_dist(X[i], X[j]))
self.s_min = heapq.nsmallest(int(self.n_w), self.distances)
self.s_max = heapq.nlargest(int(self.n_w), self.distances)
#ones = [1] * int(self.n_w)
#s_min_c = np.dot(self.s_min, np.transpose(ones))
#s_max_c = np.dot(self.s_max, np.transpose(ones))
s_min_c = sum(self.s_min)
s_max_c = sum(self.s_max)
return (self.s_c - s_min_c) / (s_max_c - s_min_c)
def find(self, X, labels, n_clusters):
self.diameter = utils.find_diameter(X)
self.centroids = cluster_centroid.cluster_centroid(X, labels, n_clusters)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(labels, n_clusters)
self.centroid_dists = [[sys.float_info.max for _ in range(n_clusters)] for _ in range(n_clusters)]
self.dists = [[0 for _ in range(len(labels))] for _ in range(n_clusters)]
numerator = 0.0
for k in range(0, n_clusters - 1):
for l in range(k + 1, n_clusters):
self.centroid_dists[k][l] = utils.euclidian_dist(self.centroids[k], self.centroids[l])
self.centroid_dists[l][k] = self.centroid_dists[k][l]
for i in range(n_clusters):
min_dist = np.amin(self.centroid_dists[i])
numerator += min_dist
denominator = 0.0
for k in range(n_clusters):
for i in range(len(labels)):
if labels[i] != k:
continue
self.dists[k][i] = utils.euclidian_dist(X[i], self.centroids[k])
for k in range(n_clusters):
# get sum of 0.1*|Ck| largest elements
acc = 0.0
max_n = heapq.nlargest(int(math.ceil(0.1 * self.cluster_sizes[k])), self.dists[k])
for i in range(0, len(max_n)):
acc += max_n[i]
denominator += acc * 10.0 / self.cluster_sizes[k]
return -(numerator / denominator)
def os(X, labels, n_clusters):
centroids = cluster_centroid.cluster_centroid(X, labels, n_clusters)
cluster_sizes = cluster_centroid.count_cluster_sizes(labels, n_clusters)
numerator = 0.0
for k in range(0, n_clusters):
for i in range(0, len(labels)):
if labels[i] != k: continue
numerator += ov(X, labels, X[i], k)
denominator = 0.0
for k in range(0, n_clusters):
l = []
for i in range(0, len(labels)):
if labels[i] != k:
continue
l.append(utils.euclidian_dist(X[i], centroids[k]))
# get sum of 0.1*|Ck| largest elements
acc = 0.0
max_n = heapq.nlargest(int(math.ceil(0.1 * cluster_sizes[k])), l)
for i in range(0, len(max_n)):
acc += max_n[i]
denominator += acc * 10.0 / cluster_sizes[k]
return -numerator / denominator
def find(self, X, labels, n_clusters):
self.diameter = utils.find_diameter(X)
self.s_clusters = [0. for _ in range(n_clusters)]
self.centroids = cluster_centroid.cluster_centroid(
X, labels, n_clusters)
db = 0
self.points_in_clusters = cluster_centroid.count_cluster_sizes(
labels, n_clusters)
for i in range(n_clusters):
self.s_clusters[i] = self.s(X, i, self.points_in_clusters, labels,
self.centroids)
self.sums = [[0 for _ in range(n_clusters)] for _ in range(n_clusters)]
for i in range(0, n_clusters):
for j in range(0, n_clusters):
if i != j:
tm = utils.euclidian_dist(self.centroids[i],
self.centroids[j])
if tm != 0:
self.sums[i][j] = (self.s_clusters[i] +
self.s_clusters[j]) / tm
else:
pass
#a = -Constants.bad_cluster
tmp = np.amax(self.sums[i])
db += tmp
db /= float(n_clusters)
return db
def sf(X, labels, n_clusters):
centroids = cluster_centroid.cluster_centroid(X, labels, n_clusters)
cluster_sizes = cluster_centroid.count_cluster_sizes(labels, n_clusters)
bcd = bcd_score(X, labels, n_clusters, centroids, cluster_sizes)
wcd = wcd_score(X, labels, n_clusters, centroids, cluster_sizes)
p = math.exp(-bcd - wcd) #?????
return -(1.0 - 1.0 / math.exp(p))
def update(self, X, n_clusters, labels, k, l, id):
point = X[id]
prev_cluster_sizes = list(self.cluster_sizes)
prev_centroids = np.copy(self.centroids)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(np.copy(labels), n_clusters)
self.centroids = cluster_centroid.update_centroids(self.centroids, self.cluster_sizes, point, k, l)
minimum_dif_c = sys.float_info.max # min dist in different clusters
#update numerator
new_centroid_dists = list(self.centroid_dists)
dell = 10**(-math.log(len(X), 10) - 1)
for i in range(len(labels)):
if (labels[i] == k and utils.euclidian_dist(prev_centroids[k], self.centroids[k]) > dell * self.diameter
or labels[i] == l and utils.euclidian_dist(prev_centroids[l], self.centroids[l]) > dell * self.diameter):
new_centroid_dists[i] = utils.euclidian_dist(X[i], self.centroids[labels[i]])
for i in range(n_clusters):
for j in range(n_clusters):
self.delta[i][j] *= (prev_cluster_sizes[i] + prev_cluster_sizes[j])
new_sums = [0 for _ in range(n_clusters)]
for i in range(n_clusters):
if i != k and i != l:
new_sums[i] = self.sums[i]
for i in range(len(labels)):
if labels[i] == k or labels[i] == l:
new_sums[labels[i]] += new_centroid_dists[i]
for i in range(n_clusters):
for j in range(n_clusters):
if i != j:
if self.cluster_sizes[i] + self.cluster_sizes[j] == 0:
self.delta[i][j] = float('inf')
else:
self.delta[i][j] = (new_sums[i] + new_sums[j]) / float(self.cluster_sizes[i] + self.cluster_sizes[j])
minimum_dif_c = min(minimum_dif_c, self.delta[i][j])
#update denominator
denominator = list(new_sums)
#print(denominator)
for i in range(n_clusters):
if self.cluster_sizes[i] == 0:
denominator[i] = float('inf')
else:
denominator[i] *= (2 / self.cluster_sizes[i])
return -(minimum_dif_c / max(denominator))
def update(self, X, n_clusters, labels, k, l, id):
self.diameter = utils.find_diameter(X)
prev_point_in_c = list(self.point_in_c)
prev_centroids = np.copy(self.centroids)
self.point_in_c = cluster_centroid.count_cluster_sizes(labels, n_clusters)
self.centroids = cluster_centroid.update_centroids(np.copy(self.centroids), np.copy(self.point_in_c), X[id], k, l)
minimum_dif_c = sys.float_info.max # min dist in different clusters
#update numerator
for i in range(n_clusters):
for j in range(n_clusters):
self.delta[i][j] *= (prev_point_in_c[i] * prev_point_in_c[j])
for i in range(len(labels)):
if labels[i] != k and id < i:
self.delta[k][labels[i]] -= self.dists[id][i]
if labels[i] != k and id > i:
self.delta[labels[i]][k] -= self.dists[i][id]
if labels[i] != l and id < i:
self.delta[l][labels[i]] += self.dists[id][i]
if labels[i] != l and id > i:
self.delta[labels[i]][l] += self.dists[i][id]
for i in range(n_clusters - 1):
for j in range(i + 1, n_clusters):
self.delta[i][j] /= float(self.point_in_c[i] * self.point_in_c[j])
if self.delta[i][j] != 0:
minimum_dif_c = min(minimum_dif_c, self.delta[i][j])
# update denominator
new_centroid_dists = list(self.centroid_dists)
dell = 10 ** (-math.log(len(X), 10) - 1)
for i in range(len(labels)):
if (labels[i] == k and utils.euclidian_dist(prev_centroids[k], self.centroids[k]) > dell * self.diameter
or labels[i] == l and utils.euclidian_dist(prev_centroids[l],
self.centroids[l]) > dell * self.diameter):
new_centroid_dists[i] = utils.euclidian_dist(X[i], self.centroids[labels[i]])
new_sums = [0 for _ in range(n_clusters)]
for i in range(n_clusters):
if i != k and i != l:
new_sums[i] = self.sums[i]
for i in range(len(labels)):
if labels[i] == k or labels[i] == l:
new_sums[labels[i]] += new_centroid_dists[i]
denominator = list(new_sums)
for i in range(n_clusters):
if self.point_in_c[i] != 0:
denominator[i] *= (2 / self.point_in_c[i])
return -(minimum_dif_c / max(denominator))
def sym_db(X, labels, n_clusters):
centroids = cluster_centroid.cluster_centroid(X, labels, n_clusters)
db = 0
cluster_sizes = cluster_centroid.count_cluster_sizes(labels, n_clusters)
max_fraction = sys.float_info.min
for k in range(0, n_clusters):
for l in range(0, n_clusters):
if k != l:
fraction = ((sym_s(X, labels, k, cluster_sizes, centroids) +
sym_s(X, labels, l, cluster_sizes, centroids)) /
utils.euclidian_dist(centroids[k], centroids[l]))
max_fraction = max(max_fraction, fraction)
db += max_fraction
db /= float(n_clusters)
return db
def update(self, X, n_clusters, labels, k, l, id):
point = X[id]
# prev_cluster_sizes = list(self.cluster_sizes)
prev_centroids = np.copy(self.centroids)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(
np.copy(labels), n_clusters)
self.centroids = cluster_centroid.update_centroids(
np.copy(self.centroids), np.copy(self.cluster_sizes), point, k, l)
# update denominator
new_centroid_dists = list(self.centroid_dists)
dell = 10**(-math.log(len(X), 10) - 1)
for i in range(len(labels)):
if (labels[i] == k and
utils.euclidian_dist(prev_centroids[k], self.centroids[k])
> dell * self.diameter or labels[i] == l and
utils.euclidian_dist(prev_centroids[l], self.centroids[l])
> dell * self.diameter):
new_centroid_dists[i] = utils.euclidian_dist(
X[i], self.centroids[labels[i]])
new_sums = [0 for _ in range(n_clusters)]
for i in range(n_clusters):
if i != k and i != l:
new_sums[i] = self.sums[i]
for i in range(len(labels)):
if labels[i] == k or labels[i] == l:
new_sums[labels[i]] += new_centroid_dists[i]
denominator = list(new_sums)
for i in range(n_clusters):
if self.cluster_sizes[i] != 0:
denominator[i] *= (2 / self.cluster_sizes[i])
# update numerator
for i in range(n_clusters):
if i != k:
self.centers[i][k] = utils.euclidian_dist(
self.centroids[i], self.centroids[k])
self.centers[k][i] = self.centers[i][k]
if i != l:
self.centers[i][l] = utils.euclidian_dist(
self.centroids[i], self.centroids[l])
self.centers[l][i] = self.centers[i][l]
minimum_dif_c = np.amin(self.centers)
return -(minimum_dif_c / max(denominator))
def find(self, X, labels, n_clusters):
self.centroids = cluster_centroid.cluster_centroid(X, labels, n_clusters)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(labels, n_clusters)
self.max_s_sum = [[sys.float_info.min for _ in range(n_clusters)] for _ in range(n_clusters)]
self.min_centroids_dist = [[sys.float_info.max for _ in range(n_clusters)] for _ in range(n_clusters)]
self.s_clusters = [0 for _ in range(n_clusters)]
self.diameter = utils.find_diameter(X)
for i in range(n_clusters):
self.s_clusters[i] = self.s(X, i, self.cluster_sizes, labels, self.centroids)
numerator = 0.0
for k in range(0, n_clusters):
for l in range(k + 1, n_clusters):
self.max_s_sum[k][l] = self.s_clusters[k] + self.s_clusters[l]
self.min_centroids_dist[k][l] = utils.euclidian_dist(self.centroids[k], self.centroids[l])
numerator += np.max(self.max_s_sum[k]) / np.min(self.min_centroids_dist[k])
return numerator / n_clusters
def db_star_index(X, labels, n_clusters):
centroids = cluster_centroid.cluster_centroid(X, labels, n_clusters)
cluster_sizes = cluster_centroid.count_cluster_sizes(labels, n_clusters)
numerator = 0.0
for k in range(0, n_clusters):
max_s_sum = sys.float_info.min
min_centroids_dist = sys.float_info.max
for l in range(k + 1, n_clusters):
max_s_sum = max(
max_s_sum,
s(X, k, cluster_sizes, labels, centroids) +
s(X, l, cluster_sizes, labels, centroids))
min_centroids_dist = min(
min_centroids_dist,
utils.euclidian_dist(centroids[k], centroids[l]))
numerator += max_s_sum / min_centroids_dist
return numerator / n_clusters
def update(self, X, n_clusters, labels, k, l, id):
prev_cluster_sizes = list(self.cluster_sizes)
self.centroids = cluster_centroid.update_centroids(
list(self.centroids), list(self.cluster_sizes), X[id], k, l)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(
labels, n_clusters)
minimum_dif_c = sys.float_info.max # min dist in different clusters
maximum_same_c = sys.float_info.min # max dist in the same cluster
delete_from_same = []
for i in range(0, len(labels)):
if labels[i] == k:
delete_from_same.append([i, id])
delete_from_same.append([id, i])
if labels[i] == l and i != id:
self.dist_same_c.append([i, id])
self.dist_same_c.append([id, i])
for pair in self.dist_same_c:
cur = self.dists[pair[0]][pair[1]]
if cur > maximum_same_c:
if pair not in delete_from_same:
maximum_same_c = cur
for i in range(n_clusters - 1):
for j in range(i + 1, n_clusters):
self.delta[i][j] *= (prev_cluster_sizes[i] *
prev_cluster_sizes[j])
for i in range(len(labels)):
if labels[i] != k and id < i:
self.delta[k][labels[i]] -= self.dists[id][i]
if labels[i] != k and id > i:
self.delta[labels[i]][k] -= self.dists[i][id]
if labels[i] != l and id < i:
self.delta[l][labels[i]] += self.dists[id][i]
if labels[i] != l and id > i:
self.delta[labels[i]][l] += self.dists[i][id]
for i in range(n_clusters - 1):
for j in range(i + 1, n_clusters):
self.delta[i][j] /= float(self.cluster_sizes[i] *
self.cluster_sizes[j])
if self.delta[i][j] != 0:
minimum_dif_c = min(minimum_dif_c, self.delta[i][j])
return -minimum_dif_c / maximum_same_c
def davies_bouldin(X, n_clusters, labels):
centroids = cluster_centroid.cluster_centroid(X, labels, n_clusters)
db = 0
point_in_c = cluster_centroid.count_cluster_sizes(labels, n_clusters)
tmp = sys.float_info.min
for i in range(0, n_clusters):
for j in range(0, n_clusters):
if i != j:
tm = utils.euclidian_dist(centroids[i], centroids[j])
if tm != 0:
a = (s(X, i, point_in_c, labels, centroids) +
s(X, j, point_in_c, labels, centroids)) / tm
else:
pass
#a = -Constants.bad_cluster
tmp = max(tmp, a)
db += tmp
db /= float(n_clusters)
return db
def update(self, X, n_clusters, labels, k, l, id):
self.cluster_sizes = cluster_centroid.count_cluster_sizes(
labels, n_clusters)
self.centroids = cluster_centroid.update_centroids(
np.copy(self.centroids), np.copy(self.cluster_sizes), X[id], k, l)
self.a_ss[id] = self.a(X, labels, id, l)
self.b_ss[id] = self.b(X, n_clusters, labels, id, l)
for i in range(len(labels)):
if i == id:
continue
if labels[i] == k:
self.a_ss[i] *= (self.cluster_sizes[k] + 1)
self.a_ss[i] -= self.dists_e[i][id]
if self.cluster_sizes[k] == 0:
self.a_ss[i] = float('inf')
else:
self.a_ss[i] /= self.cluster_sizes[k]
if labels[i] == l:
self.a_ss[i] *= (self.cluster_sizes[l] - 1)
self.a_ss[i] += self.dists_e[i][id]
if self.cluster_sizes[l] == 0:
self.a_ss[i] = float('inf')
else:
self.a_ss[i] /= self.cluster_sizes[l]
self.dists_for_b[i][l] *= (self.cluster_sizes[l] - 1)
self.dists_for_b[i][l] += self.dists_e[i][id]
if self.cluster_sizes[l] == 0:
self.dists_for_b[i][l] = float('inf')
else:
self.dists_for_b[i][l] /= self.cluster_sizes[l]
self.dists_for_b[i][k] *= (self.cluster_sizes[k] + 1)
self.dists_for_b[i][k] -= self.dists_e[i][id]
if self.cluster_sizes[k] == 0:
self.dists_for_b[i][k] = float('inf')
else:
self.dists_for_b[i][k] /= self.cluster_sizes[k]
self.b_ss[i] = min(self.dists_for_b[i])
ch = 0
for i in range(len(labels)):
ch += (self.b_ss[i] - self.a_ss[i]) / max(self.b_ss[i],
self.a_ss[i])
return -(ch / float(len(labels)))
def find(self, X, labels, n_clusters):
self.diameter = utils.find_diameter(X)
self.centroids = cluster_centroid.cluster_centroid(
X, labels, n_clusters)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(
labels, n_clusters)
self.numerators = [0.0] * n_clusters
for i in range(0, len(labels)):
self.numerators[labels[i]] += utils.euclidian_dist(
X[i], self.centroids[labels[i]])
self.inner_max_dists = [[0 for _ in range(len(labels))]
for _ in range(len(labels))]
self.outer_min_dists = [[
sys.float_info.max for _ in range(len(labels))
] for _ in range(n_clusters)]
self.accumulator = [0 for _ in range(n_clusters)]
for k in range(0, n_clusters):
for i in range(len(labels)): # iterate elements outside cluster
if labels[i] == k:
continue
for j in range(len(labels)): # iterate inside cluster
if labels[j] != k:
continue
self.inner_max_dists[i][j] = utils.euclidian_dist(
X[i], X[j])
self.inner_max_dists[j][i] = self.inner_max_dists[i][j]
for c in range(n_clusters):
for i in range(len(labels)):
if labels[i] == c:
continue
inner_max_dist = 0
for j in range(len(self.inner_max_dists[i])):
if labels[j] == c:
inner_max_dist = max(inner_max_dist,
self.inner_max_dists[i][j])
if inner_max_dist != 0:
self.outer_min_dists[c][i] = inner_max_dist
outer_min_dist = np.amin(self.outer_min_dists[c])
self.accumulator[c] = self.numerators[c] / outer_min_dist
return sum(self.accumulator) / len(labels)
def find(self, X, labels, n_clusters):
self.diameter = utils.find_diameter(X)
self.dist_centroids = [[0 for _ in range(n_clusters)]
for _ in range(n_clusters)]
self.dist_ps = [0 for _ in range(len(labels))]
self.centroids = cluster_centroid.cluster_centroid(
X, labels, n_clusters)
self.cluster_sizes = cluster_centroid.count_cluster_sizes(
labels, n_clusters)
for k in range(0, n_clusters - 1):
for l in range(k + 1, n_clusters):
self.dist_centroids[k][l] = utils.euclidian_dist(
self.centroids[k], self.centroids[l])
numerator = np.amax(self.dist_centroids)
for i in range(0, len(labels)):
self.dist_ps[i] = utils.d_ps(X, labels, X[i], labels[i],
self.centroids)
denominator = sum(self.dist_ps)
return -(numerator / (denominator * n_clusters))
