def __minimum_noiseless_description_length(data, clusters, centers):
"""
@brief Calculates splitting criterion for input clusters using minimum noiseless description length criterion.
@param[in] clusters (list): Clusters for which splitting criterion should be calculated.
@param[in] centers (list): Centers of the clusters.
@return (double) Returns splitting criterion in line with bayesian information criterion.
Low value of splitting cretion means that current structure is much better.
"""
scores = [0.0] * len(clusters)
W = 0.0
K = len(clusters)
N = 0.0
sigma_sqrt = 0.0
alpha = 0.9
betta = 0.9
for index_cluster in range(0, len(clusters), 1):
for index_object in clusters[index_cluster]:
delta_vector = list_math_subtraction(data[index_object],
centers[index_cluster])
delta_sqrt = sum(
list_math_multiplication(delta_vector, delta_vector))
W += delta_sqrt
sigma_sqrt += delta_sqrt
N += len(clusters[index_cluster])
if (N - K != 0):
W /= N
sigma_sqrt /= (N - K)
sigma = sigma_sqrt**0.5
for index_cluster in range(0, len(clusters), 1):
Kw = (1.0 - K / N) * sigma_sqrt
Ks = (2.0 * alpha * sigma / (N**0.5)) + (
(alpha**2.0) * sigma_sqrt / N + W - Kw / 2.0)**0.5
U = W - Kw + 2.0 * (alpha**2.0) * sigma_sqrt / N + Ks
Z = K * sigma_sqrt / N + U + betta * (
(2.0 * K)**0.5) * sigma_sqrt / N
if (Z == 0.0):
scores[index_cluster] = float("inf")
else:
scores[index_cluster] = Z
else:
scores = [float("inf")] * len(clusters)
return sum(scores)
def __minimum_noiseless_description_length(self, clusters, centers):
"""!
@brief Calculates splitting criterion for input clusters using minimum noiseless description length criterion.
@param[in] clusters (list): Clusters for which splitting criterion should be calculated.
@param[in] centers (list): Centers of the clusters.
@return (double) Returns splitting criterion in line with bayesian information criterion.
Low value of splitting cretion means that current structure is much better.
@see __bayesian_information_criterion(clusters, centers)
"""
scores = [0.0] * len(clusters);
W = 0.0;
K = len(clusters);
N = 0.0;
sigma_sqrt = 0.0;
alpha = 0.9;
betta = 0.9;
for index_cluster in range(0, len(clusters), 1):
for index_object in clusters[index_cluster]:
delta_vector = list_math_subtraction(self.__pointer_data[index_object], centers[index_cluster]);
delta_sqrt = sum(list_math_multiplication(delta_vector, delta_vector));
W += delta_sqrt;
sigma_sqrt += delta_sqrt;
N += len(clusters[index_cluster]);
if (N - K != 0):
W /= N;
sigma_sqrt /= (N - K);
sigma = sigma_sqrt ** 0.5;
for index_cluster in range(0, len(clusters), 1):
Kw = (1.0 - K / N) * sigma_sqrt;
Ks = ( 2.0 * alpha * sigma / (N ** 0.5) ) + ( (alpha ** 2.0) * sigma_sqrt / N + W - Kw / 2.0 ) ** 0.5;
U = W - Kw + 2.0 * (alpha ** 2.0) * sigma_sqrt / N + Ks;
Z = K * sigma_sqrt / N + U + betta * ( (2.0 * K) ** 0.5 ) * sigma_sqrt / N;
if (Z == 0.0):
scores[index_cluster] = float("inf");
else:
scores[index_cluster] = Z;
else:
scores = [float("inf")] * len(clusters);
return sum(scores);
def __minimum_noiseless_description_length(self, clusters, centers):
"""!
@brief Calculates splitting criterion for input clusters using minimum noiseless description length criterion.
@param[in] clusters (list): Clusters for which splitting criterion should be calculated.
@param[in] centers (list): Centers of the clusters.
@return (double) Returns splitting criterion in line with bayesian information criterion.
Low value of splitting cretion means that current structure is much better.
@see __bayesian_information_criterion(clusters, centers)
"""
scores = [0.0] * len(clusters);
W = 0.0;
K = len(clusters);
N = 0.0;
sigma_sqrt = 0.0;
alpha = 0.9;
betta = 0.9;
for index_cluster in range(0, len(clusters), 1):
for index_object in clusters[index_cluster]:
delta_vector = list_math_subtraction(self.__pointer_data[index_object], centers[index_cluster]);
delta_sqrt = sum(list_math_multiplication(delta_vector, delta_vector));
W += delta_sqrt;
sigma_sqrt += delta_sqrt;
N += len(clusters[index_cluster]);
if (N - K != 0):
W /= N;
sigma_sqrt /= (N - K);
sigma = sigma_sqrt ** 0.5;
for index_cluster in range(0, len(clusters), 1):
Kw = (1.0 - K / N) * sigma_sqrt;
Ks = ( 2.0 * alpha * sigma / (N ** 0.5) ) + ( (alpha ** 2.0) * sigma_sqrt / N + W - Kw / 2.0 ) ** 0.5;
U = W - Kw + 2.0 * (alpha ** 2.0) * sigma_sqrt / N + Ks;
Z = K * sigma_sqrt / N + U + betta * ( (2.0 * K) ** 0.5 ) * sigma_sqrt / N;
if (Z == 0.0):
scores[index_cluster] = float("inf");
else:
scores[index_cluster] = Z;
else:
scores = [float("inf")] * len(clusters);
return sum(scores);
def __sub__(self, entry):
"""!
@brief Overloaded operator sub. Performs substraction of two clustering features.
@details Substraction can't be performed with clustering feature whose description is less then substractor.
@param[in] entry (cfentry): Entry that is substracted from the current.
@return (cfentry) Result of substraction of two clustering features.
"""
number_points = self.number_points - entry.number_points
result_linear_sum = list_math_subtraction(self.linear_sum, entry.linear_sum)
result_square_sum = self.square_sum - entry.square_sum
if (number_points < 0) or (result_square_sum < 0):
raise NameError("Substruction with negative result is not possible for clustering features.")
return cfentry(number_points, result_linear_sum, result_square_sum)
def __sub__(self, entry):
"""!
@brief Overloaded operator sub. Performs substraction of two clustering features.
@details Substraction can't be performed with clustering feature whose description is less then substractor.
@param[in] entry (cfentry): Entry that is substracted from the current.
@return (cfentry) Result of substraction of two clustering features.
"""
number_points = self.number_points - entry.number_points;
linear_sum = list_math_subtraction(self.linear_sum, entry.linear_sum);
square_sum = self.square_sum - entry.square_sum;
if ( (number_points < 0) or (square_sum < 0) ):
raise NameError("Substruction with negative result is not possible for clustering features.");
return cfentry(number_points, linear_sum, square_sum);
