Python metric.distance_metric函数代码示例

    def __init__(self, data, initial_centers, tolerance=0.001, ccore=True, **kwargs):
        """!
        @brief Constructor of clustering algorithm K-Medians.
        
        @param[in] data (list): Input data that is presented as list of points (objects), each point should be represented by list or tuple.
        @param[in] initial_centers (list): Initial coordinates of medians of clusters that are represented by list: [center1, center2, ...].
        @param[in] tolerance (double): Stop condition: if maximum value of change of centers of clusters is less than tolerance than algorithm will stop processing
        @param[in] ccore (bool): Defines should be CCORE library (C++ pyclustering library) used instead of Python code or not.
        @param[in] **kwargs: Arbitrary keyword arguments (available arguments: 'metric', 'itermax').

        <b>Keyword Args:</b><br>
            - metric (distance_metric): Metric that is used for distance calculation between two points.
            - itermax (uint): Maximum number of iterations for cluster analysis.
        
        """
        self.__pointer_data = data
        self.__clusters = []
        self.__medians = initial_centers[:]
        self.__tolerance = tolerance

        self.__itermax = kwargs.get('itermax', 100)
        self.__metric = kwargs.get('metric', distance_metric(type_metric.EUCLIDEAN_SQUARE))
        if self.__metric is None:
            self.__metric = distance_metric(type_metric.EUCLIDEAN_SQUARE)

        self.__ccore = ccore and self.__metric.get_type() != type_metric.USER_DEFINED
        if self.__ccore:
            self.__ccore = ccore_library.workable()

    def __init__(self, data, maximum_clusters, threshold, ccore=True, **kwargs):
        """!
        @brief Creates classical BSAS algorithm.

        @param[in] data (list): Input data that is presented as list of points (objects), each point should be represented by list or tuple.
        @param[in] maximum_clusters: Maximum allowable number of clusters that can be allocated during processing.
        @param[in] threshold: Threshold of dissimilarity (maximum distance) between points.
        @param[in] ccore (bool): If True than DLL CCORE (C++ solution) will be used for solving.
        @param[in] **kwargs: Arbitrary keyword arguments (available arguments: 'metric').

        <b>Keyword Args:</b><br>
            - metric (distance_metric): Metric that is used for distance calculation between two points.

        """

        self._data = data;
        self._amount = maximum_clusters;
        self._threshold = threshold;
        self._metric = kwargs.get('metric', distance_metric(type_metric.EUCLIDEAN));
        self._ccore = ccore and self._metric.get_type() != type_metric.USER_DEFINED;

        self._clusters = [];
        self._representatives = [];

        if self._ccore is True:
            self._ccore = ccore_library.workable();

    def __init__(self, data, initial_index_medoids, tolerance=0.001, ccore=True, **kwargs):
        """!
        @brief Constructor of clustering algorithm K-Medoids.
        
        @param[in] data (list): Input data that is presented as list of points (objects), each point should be represented by list or tuple.
        @param[in] initial_index_medoids (list): Indexes of intial medoids (indexes of points in input data).
        @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.
        @param[in] ccore (bool): If specified than CCORE library (C++ pyclustering library) is used for clustering instead of Python code.
        @param[in] **kwargs: Arbitrary keyword arguments (available arguments: 'metric', 'data_type', 'itermax').

        <b>Keyword Args:</b><br>
            - metric (distance_metric): Metric that is used for distance calculation between two points.
            - data_type (string): Data type of input sample 'data' that is processed by the algorithm ('points', 'distance_matrix').
            - itermax (uint): Maximum number of iteration for cluster analysis.

        """
        self.__pointer_data = data
        self.__clusters = []
        self.__medoid_indexes = initial_index_medoids
        self.__tolerance = tolerance

        self.__metric = kwargs.get('metric', distance_metric(type_metric.EUCLIDEAN_SQUARE))
        self.__data_type = kwargs.get('data_type', 'points')
        self.__itermax = kwargs.get('itermax', 200)

        self.__distance_calculator = self.__create_distance_calculator()

        self.__ccore = ccore and self.__metric.get_type() != type_metric.USER_DEFINED
        if self.__ccore:
            self.__ccore = ccore_library.workable()

    def templateLengthProcessData(path_to_file, start_centers, expected_cluster_length, ccore, **kwargs):
        sample = read_sample(path_to_file)

        metric = kwargs.get('metric', distance_metric(type_metric.EUCLIDEAN_SQUARE))
        itermax = kwargs.get('itermax', 200)
        
        kmeans_instance = kmeans(sample, start_centers, 0.001, ccore, metric=metric, itermax=itermax)
        kmeans_instance.process()
        
        clusters = kmeans_instance.get_clusters()
        centers = kmeans_instance.get_centers()
        wce = kmeans_instance.get_total_wce()

        if itermax == 0:
            assertion.eq(start_centers, centers)
            assertion.eq([], clusters)
            assertion.eq(0.0, wce)
            return

        obtained_cluster_sizes = [len(cluster) for cluster in clusters]
        assertion.eq(len(sample), sum(obtained_cluster_sizes))
        
        assertion.eq(len(clusters), len(centers))
        for center in centers:
            assertion.eq(len(sample[0]), len(center))
        
        if expected_cluster_length is not None:
            obtained_cluster_sizes.sort()
            expected_cluster_length.sort()
            assertion.eq(obtained_cluster_sizes, expected_cluster_length)

    def clustering(path, amount, threshold, expected, ccore, **kwargs):
        metric = kwargs.get('metric', distance_metric(type_metric.EUCLIDEAN));

        sample = read_sample(path);

        bsas_instance = bsas(sample, amount, threshold, ccore=ccore, metric=metric);
        bsas_instance.process();

        clusters = bsas_instance.get_clusters();
        representatives = bsas_instance.get_representatives();

        obtained_length = 0;
        obtained_cluster_length = [];
        for cluster in clusters:
            obtained_length += len(cluster);
            obtained_cluster_length.append(len(cluster));

        assertion.eq(len(sample), obtained_length);
        assertion.eq(len(expected), len(clusters));
        assertion.eq(len(expected), len(representatives));
        assertion.ge(amount, len(clusters));

        dimension = len(sample[0]);
        for rep in representatives:
            assertion.eq(dimension, len(rep));

        expected.sort();
        obtained_cluster_length.sort();

        assertion.eq(expected, obtained_cluster_length);

    def testCalculateMetric(self):
        assertion.eq(1.0, metric.distance_metric(metric.type_metric.EUCLIDEAN)([0.0, 1.0], [0.0, 0.0]))
        assertion.eq(4.0, metric.distance_metric(metric.type_metric.EUCLIDEAN_SQUARE)([2.0, 2.0], [4.0, 2.0]))
        assertion.eq(4.0, metric.distance_metric(metric.type_metric.MANHATTAN)([1.0, 1.0], [-1.0, -1.0]))
        assertion.eq(2.0, metric.distance_metric(metric.type_metric.CHEBYSHEV)([2.0, -2.0], [0.0, 0.0]))
        assertion.eq(2.0, metric.distance_metric(metric.type_metric.MINKOWSKI)([-3.0, -3.0], [-5.0, -3.0]))
        assertion.eq(2.0, metric.distance_metric(metric.type_metric.MINKOWSKI, degree=2)([-3.0, -3.0], [-5.0, -3.0]))
        assertion.eq(4.0, metric.distance_metric(metric.type_metric.USER_DEFINED, func=metric.euclidean_distance_square)([2.0, 2.0], [4.0, 2.0]))

        user_function = lambda point1, point2: point1[0] + point2[0] + 2
        assertion.eq(5.0, metric.distance_metric(metric.type_metric.USER_DEFINED, func=user_function)([2.0, 3.0], [1.0, 3.0]))

    def templateLengthProcessWithMetric(path_to_file, initial_medoids, expected_cluster_length, metric, ccore_flag, **kwargs):
        sample = read_sample(path_to_file)
        data_type = kwargs.get('data_type', 'points')
        input_type = kwargs.get('input_type', 'list')
        initialize_medoids = kwargs.get('initialize_medoids', None)
        itermax = kwargs.get('itermax', 200)

        if metric is None:
            metric = distance_metric(type_metric.EUCLIDEAN_SQUARE)

        input_data = sample
        if data_type == 'distance_matrix':
            input_data = calculate_distance_matrix(sample)

            if input_type == 'numpy':
                input_data = numpy.array(input_data)

        testing_result = False
        testing_attempts = 1
        if initialize_medoids is not None:  # in case center initializer randomization appears
            testing_attempts = 10

        for _ in range(testing_attempts):
            if initialize_medoids is not None:
                initial_medoids = kmeans_plusplus_initializer(sample, initialize_medoids).initialize(return_index=True)

            kmedoids_instance = kmedoids(input_data, initial_medoids, 0.001, ccore_flag, metric=metric, data_type=data_type, itermax=itermax)
            kmedoids_instance.process()

            clusters = kmedoids_instance.get_clusters()
            medoids = kmedoids_instance.get_medoids()

            if itermax == 0:
                assertion.eq([], clusters)
                assertion.eq(medoids, initial_medoids)
                return

            if len(clusters) != len(medoids):
                continue

            if len(set(medoids)) != len(medoids):
                continue

            obtained_cluster_sizes = [len(cluster) for cluster in clusters]
            if len(sample) != sum(obtained_cluster_sizes):
                continue

            if expected_cluster_length is not None:
                obtained_cluster_sizes.sort()
                expected_cluster_length.sort()
                if obtained_cluster_sizes != expected_cluster_length:
                    continue

            testing_result = True

        assertion.true(testing_result)

def template_clustering(path, amount, threshold, **kwargs):
    metric = kwargs.get('metric', distance_metric(type_metric.EUCLIDEAN_SQUARE));
    ccore = kwargs.get('ccore', False);
    draw = kwargs.get('draw', True);

    sample = read_sample(path);

    print("Sample: ", path);

    bsas_instance = bsas(sample, amount, threshold, ccore=ccore, metric=metric);
    bsas_instance.process();

    clusters = bsas_instance.get_clusters();
    representatives = bsas_instance.get_representatives();

    if draw is True:
        bsas_visualizer.show_clusters(sample, clusters, representatives);

def template_clustering(start_centers, path, tolerance = 0.25, ccore = False):
    sample = read_sample(path)
    dimension = len(sample[0])

    metric = distance_metric(type_metric.MANHATTAN)

    observer = kmeans_observer()
    kmeans_instance = kmeans(sample, start_centers, tolerance, ccore, observer=observer, metric=metric)
    (ticks, _) = timedcall(kmeans_instance.process)
    
    clusters = kmeans_instance.get_clusters()
    centers = kmeans_instance.get_centers()
    
    print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")

    visualizer = cluster_visualizer_multidim()
    visualizer.append_clusters(clusters, sample)
    visualizer.show()

    if dimension > 3:
        kmeans_visualizer.show_clusters(sample, clusters, centers, start_centers)
        kmeans_visualizer.animate_cluster_allocation(sample, observer)

    def __init__(self, data, initial_centers, tolerance=0.001, ccore=True, **kwargs):
        """!
        @brief Constructor of clustering algorithm K-Means.
        @details Center initializer can be used for creating initial centers, for example, K-Means++ method.
        
        @param[in] data (array_like): Input data that is presented as array of points (objects), each point should be represented by array_like data structure.
        @param[in] initial_centers (array_like): Initial coordinates of centers of clusters that are represented by array_like data structure: [center1, center2, ...].
        @param[in] tolerance (double): Stop condition: if maximum value of change of centers of clusters is less than tolerance then algorithm stops processing.
        @param[in] ccore (bool): Defines should be CCORE library (C++ pyclustering library) used instead of Python code or not.
        @param[in] **kwargs: Arbitrary keyword arguments (available arguments: 'observer', 'metric', 'itermax').
        
        <b>Keyword Args:</b><br>
            - observer (kmeans_observer): Observer of the algorithm to collect information about clustering process on each iteration.
            - metric (distance_metric): Metric that is used for distance calculation between two points (by default euclidean square distance).
            - itermax (uint): Maximum number of iterations that is used for clustering process (by default: 200).
        
        @see center_initializer
        
        """
        self.__pointer_data = numpy.array(data)
        self.__clusters = []
        self.__centers = numpy.array(initial_centers)
        self.__tolerance = tolerance
        self.__total_wce = 0

        self.__observer = kwargs.get('observer', None)
        self.__metric = kwargs.get('metric', distance_metric(type_metric.EUCLIDEAN_SQUARE))
        self.__itermax = kwargs.get('itermax', 100)

        if self.__metric.get_type() != type_metric.USER_DEFINED:
            self.__metric.enable_numpy_usage()
        else:
            self.__metric.disable_numpy_usage()
        
        self.__ccore = ccore and self.__metric.get_type() != type_metric.USER_DEFINED
        if self.__ccore is True:
            self.__ccore = ccore_library.workable()

 def testClusterAllocationSampleSimple1MinkowskiDistanceMatrixByCore(self):
     metric = distance_metric(type_metric.MINKOWSKI, degree=2.0)
     KmedoidsTestTemplates.templateLengthProcessWithMetric(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [2, 9], [5, 5], metric, True, data_type='distance_matrix')

 def testClusterAllocationSampleSimple1ChebyshevDistanceMatrixByCore(self):
     metric = distance_metric(type_metric.CHEBYSHEV)
     KmedoidsTestTemplates.templateLengthProcessWithMetric(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [2, 9], [5, 5], metric, True, data_type='distance_matrix')

 def testClusterAllocationSampleSimple1ManhattanDistanceMatrixByCore(self):
     metric = distance_metric(type_metric.MANHATTAN)
     KmedoidsTestTemplates.templateLengthProcessWithMetric(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [2, 9], [5, 5], metric, True, data_type='distance_matrix')

 def testClusterAllocationSampleSimple1SquareEuclideanDistanceMatrixByCore(self):
     metric = distance_metric(type_metric.EUCLIDEAN_SQUARE)
     KmedoidsTestTemplates.templateLengthProcessWithMetric(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [2, 9], [5, 5], metric, True, data_type='distance_matrix')

 def testClusterAllocationSampleSimple1EuclideanByCore(self):
     metric = distance_metric(type_metric.EUCLIDEAN)
     KmedoidsTestTemplates.templateLengthProcessWithMetric(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [2, 9], [5, 5], metric, True)