annoviko /
pyclustering
| @@ 101-130 (lines=30) @@ | ||
| 98 | """ |
|
| 99 | ||
| 100 | ||
| 101 | def __init__(self, data, initial_index_medoids, tolerance=0.001, ccore=True, **kwargs): |
|
| 102 | """! |
|
| 103 | @brief Constructor of clustering algorithm K-Medoids. |
|
| 104 | ||
| 105 | @param[in] data (list): Input data that is presented as list of points (objects), each point should be represented by list or tuple. |
|
| 106 | @param[in] initial_index_medoids (list): Indexes of intial medoids (indexes of points in input data). |
|
| 107 | @param[in] tolerance (double): Stop condition: if maximum value of distance change of medoids of clusters is less than tolerance than algorithm will stop processing. |
|
| 108 | @param[in] ccore (bool): If specified than CCORE library (C++ pyclustering library) is used for clustering instead of Python code. |
|
| 109 | @param[in] **kwargs: Arbitrary keyword arguments (available arguments: 'metric', 'data_type'). |
|
| 110 | ||
| 111 | <b>Keyword Args:</b><br> |
|
| 112 | - metric (distance_metric): Metric that is used for distance calculation between two points. |
|
| 113 | - data_type (string): Data type of input sample 'data' that is processed by the algorithm ('points', 'distance_matrix').
|
|
| 114 | ||
| 115 | """ |
|
| 116 | self.__pointer_data = data |
|
| 117 | self.__clusters = [] |
|
| 118 | self.__medoid_indexes = initial_index_medoids |
|
| 119 | self.__tolerance = tolerance |
|
| 120 | ||
| 121 | self.__metric = kwargs.get('metric', distance_metric(type_metric.EUCLIDEAN_SQUARE))
|
|
| 122 | if self.__metric is None: |
|
| 123 | self.__metric = distance_metric(type_metric.EUCLIDEAN_SQUARE) |
|
| 124 | ||
| 125 | self.__data_type = kwargs.get('data_type', 'points')
|
|
| 126 | self.__distance_calculator = self.__create_distance_calculator() |
|
| 127 | ||
| 128 | self.__ccore = ccore and self.__metric.get_type() != type_metric.USER_DEFINED |
|
| 129 | if self.__ccore: |
|
| 130 | self.__ccore = ccore_library.workable() |
|
| 131 | ||
| 132 | ||
| 133 | def process(self): |
|
| @@ 62-87 (lines=26) @@ | ||
| 59 | ||
| 60 | """ |
|
| 61 | ||
| 62 | def __init__(self, data, initial_centers, tolerance=0.001, ccore=True, **kwargs): |
|
| 63 | """! |
|
| 64 | @brief Constructor of clustering algorithm K-Medians. |
|
| 65 | ||
| 66 | @param[in] data (list): Input data that is presented as list of points (objects), each point should be represented by list or tuple. |
|
| 67 | @param[in] initial_centers (list): Initial coordinates of medians of clusters that are represented by list: [center1, center2, ...]. |
|
| 68 | @param[in] tolerance (double): Stop condition: if maximum value of change of centers of clusters is less than tolerance than algorithm will stop processing |
|
| 69 | @param[in] ccore (bool): Defines should be CCORE library (C++ pyclustering library) used instead of Python code or not. |
|
| 70 | @param[in] **kwargs: Arbitrary keyword arguments (available arguments: 'metric'). |
|
| 71 | ||
| 72 | <b>Keyword Args:</b><br> |
|
| 73 | - metric (distance_metric): Metric that is used for distance calculation between two points. |
|
| 74 | ||
| 75 | """ |
|
| 76 | self.__pointer_data = data |
|
| 77 | self.__clusters = [] |
|
| 78 | self.__medians = initial_centers[:] |
|
| 79 | self.__tolerance = tolerance |
|
| 80 | ||
| 81 | self.__metric = kwargs.get('metric', distance_metric(type_metric.EUCLIDEAN_SQUARE))
|
|
| 82 | if self.__metric is None: |
|
| 83 | self.__metric = distance_metric(type_metric.EUCLIDEAN_SQUARE) |
|
| 84 | ||
| 85 | self.__ccore = ccore and self.__metric.get_type() != type_metric.USER_DEFINED |
|
| 86 | if self.__ccore: |
|
| 87 | self.__ccore = ccore_library.workable() |
|
| 88 | ||
| 89 | ||
| 90 | def process(self): |
|
