def __get_average_intra_cluster_distance(self, entry):
"""!
@brief Calculates average intra cluster distance between current and specified clusters.
@param[in] entry (cfentry): Clustering feature to which distance should be obtained.
@return (double) Average intra cluster distance.
"""
linear_part_first = list_math_addition(
self.linear_sum, entry.linear_sum
)
linear_part_second = linear_part_first
linear_part_distance = sum(
list_math_multiplication(linear_part_first, linear_part_second)
)
general_part_distance = (
2.0
* (self.number_points + entry.number_points)
* (self.square_sum + entry.square_sum)
- 2.0 * linear_part_distance
)
return (
general_part_distance
/ (
(self.number_points + entry.number_points)
* (self.number_points + entry.number_points - 1.0)
)
) ** 0.5
def __get_variance_increase_distance(self, entry):
"""!
@brief Calculates variance increase distance between current and specified clusters.
@param[in] entry (cfentry): Clustering feature to which distance should be obtained.
@return (double) Variance increase distance.
"""
linear_part_12 = list_math_addition(self.linear_sum, entry.linear_sum)
variance_part_first = (self.square_sum + entry.square_sum) - \
2.0 * sum(list_math_multiplication(linear_part_12, linear_part_12)) / (self.number_points + entry.number_points) + \
(self.number_points + entry.number_points) * sum(list_math_multiplication(linear_part_12, linear_part_12)) / (self.number_points + entry.number_points)**2.0
linear_part_11 = sum(
list_math_multiplication(self.linear_sum, self.linear_sum))
variance_part_second = -(self.square_sum -
(2.0 * linear_part_11 / self.number_points) +
(linear_part_11 / self.number_points))
linear_part_22 = sum(
list_math_multiplication(entry.linear_sum, entry.linear_sum))
variance_part_third = -(
entry.square_sum - (2.0 / entry.number_points) * linear_part_22 +
entry.number_points *
(1.0 / entry.number_points**2.0) * linear_part_22)
return (variance_part_first + variance_part_second +
variance_part_third)
def __add__(self, entry):
"""!
@brief Overloaded operator add. Performs addition of two clustering features.
@param[in] entry (cfentry): Entry that is added to the current.
@return (cfentry) Result of addition of two clustering features.
"""
number_points = self.number_points + entry.number_points
result_linear_sum = list_math_addition(self.linear_sum, entry.linear_sum)
result_square_sum = self.square_sum + entry.square_sum
return cfentry(number_points, result_linear_sum, result_square_sum)
def __add__(self, entry):
"""!
@brief Overloaded operator add. Performs addition of two clustering features.
@param[in] entry (cfentry): Entry that is added to the current.
@return (cfentry) Result of addition of two clustering features.
"""
number_points = self.number_points + entry.number_points;
linear_sum = list_math_addition(self.linear_sum, entry.linear_sum);
square_sum = self.square_sum + entry.square_sum;
return cfentry(number_points, linear_sum, square_sum);
def __get_average_intra_cluster_distance(self, entry):
"""!
@brief Calculates average intra cluster distance between current and specified clusters.
@param[in] entry (cfentry): Clustering feature to which distance should be obtained.
@return (double) Average intra cluster distance.
"""
linear_part_first = list_math_addition(self.linear_sum, entry.linear_sum);
linear_part_second = linear_part_first;
linear_part_distance = sum(list_math_multiplication(linear_part_first, linear_part_second));
general_part_distance = 2.0 * (self.number_points + entry.number_points) * (self.square_sum + entry.square_sum) - 2.0 * linear_part_distance;
return (general_part_distance / ( (self.number_points + entry.number_points) * (self.number_points + entry.number_points - 1.0) )) ** 0.5;
def __update_centers(self):
"""!
@brief Calculate centers of clusters in line with contained objects.
@return (list) Updated centers as list of centers.
"""
centers = [[] for i in range(len(self.__clusters))];
for index in range(len(self.__clusters)):
point_sum = [0] * len(self.__pointer_data[0]);
for index_point in self.__clusters[index]:
point_sum = list_math_addition(point_sum, self.__pointer_data[index_point]);
centers[index] = list_math_division_number(point_sum, len(self.__clusters[index]));
return centers;
def __update_centers(self):
"""!
@brief Calculate centers of clusters in line with contained objects.
@return (list) Updated centers as list of centers.
"""
centers = [[] for i in range(len(self.__clusters))];
for index in range(len(self.__clusters)):
point_sum = [0] * len(self.__pointer_data[0]);
for index_point in self.__clusters[index]:
point_sum = list_math_addition(point_sum, self.__pointer_data[index_point]);
centers[index] = list_math_division_number(point_sum, len(self.__clusters[index]));
return centers;
def __get_centers(data, clusters):
"""
@brief Centers of clusters in line with contained objects.
@param[in] clusters (list): Clusters that contain indexes of objects from data.
@return (list) Centers.
"""
centers = [[] for i in range(len(clusters))]
dimension = len(data[0])
for index in range(len(clusters)):
point_sum = [0.0] * dimension
for index_point in clusters[index]:
point_sum = list_math_addition(point_sum, data[index_point])
centers[index] = list_math_division_number(point_sum,
len(clusters[index]))
return centers
def __update_centers(self, clusters):
"""!
@brief Updates centers of clusters in line with contained objects.
@param[in] clusters (list): Clusters that contain indexes of objects from data.
@return (list) Updated centers.
"""
centers = [[] for _ in range(len(clusters))];
dimension = len(self.__pointer_data[0])
for index in range(len(clusters)):
point_sum = [0.0] * dimension;
for index_point in clusters[index]:
point_sum = list_math_addition(point_sum, self.__pointer_data[index_point]);
centers[index] = list_math_division_number(point_sum, len(clusters[index]));
return centers;
def __update_centers(self, clusters):
"""!
@brief Updates centers of clusters in line with contained objects.
@param[in] clusters (list): Clusters that contain indexes of objects from data.
@return (list) Updated centers.
"""
centers = [[] for i in range(len(clusters))];
dimension = len(self.__pointer_data[0])
for index in range(len(clusters)):
point_sum = [0.0] * dimension;
for index_point in clusters[index]:
point_sum = list_math_addition(point_sum, self.__pointer_data[index_point]);
centers[index] = list_math_division_number(point_sum, len(clusters[index]));
return centers;
def __get_variance_increase_distance(self, entry):
"""!
@brief Calculates variance increase distance between current and specified clusters.
@param[in] entry (cfentry): Clustering feature to which distance should be obtained.
@return (double) Variance increase distance.
"""
linear_part_12 = list_math_addition(self.linear_sum, entry.linear_sum);
variance_part_first = (self.square_sum + entry.square_sum) - \
2.0 * sum(list_math_multiplication(linear_part_12, linear_part_12)) / (self.number_points + entry.number_points) + \
(self.number_points + entry.number_points) * sum(list_math_multiplication(linear_part_12, linear_part_12)) / (self.number_points + entry.number_points)**2.0;
linear_part_11 = sum(list_math_multiplication(self.linear_sum, self.linear_sum));
variance_part_second = -( self.square_sum - (2.0 * linear_part_11 / self.number_points) + (linear_part_11 / self.number_points) );
linear_part_22 = sum(list_math_multiplication(entry.linear_sum, entry.linear_sum));
variance_part_third = -( entry.square_sum - (2.0 / entry.number_points) * linear_part_22 + entry.number_points * (1.0 / entry.number_points ** 2.0) * linear_part_22 );
return (variance_part_first + variance_part_second + variance_part_third);
