How to use the biosppy.metrics.pdist function in biosppy

Additional keyword arguments to pass to the distance function.

    Returns
    -------
    indices : array
        Indices that sort the computed mean distances.
    mdist : array
        Mean distance characterizing each data sample.

    """

    if metric_args is None:
        metric_args = {}

    # compute distances
    D = metrics.pdist(data, metric=metric, **metric_args)
    D = metrics.squareform(D)

    # compute mean
    mdist = np.mean(D, axis=0)

    # sort
    indices = np.argsort(mdist)

    return indices, mdist

.. [EKSX96] M. Ester, H. P. Kriegel, J. Sander, and X. Xu,
       “A Density-Based Algorithm for Discovering Clusters in Large Spatial
       Databases with Noise”, Proceedings of the 2nd International
       Conf. on Knowledge Discovery and Data Mining, pp. 226-231, 1996.

    """

    # check inputs
    if data is None:
        raise TypeError("Please specify input data.")

    if metric_args is None:
        metric_args = {}

    # compute distances
    D = metrics.pdist(data, metric=metric, **metric_args)
    D = metrics.squareform(D)

    # fit
    db = skc.DBSCAN(eps=eps, min_samples=min_samples, metric='precomputed')
    labels = db.fit_predict(D)

    # get cluster indices
    clusters = _extract_clusters(labels)

    return utils.ReturnTuple((clusters,), ('clusters',))

def __init__(self, k=3, metric='euclidean', metric_args=None):
        # parent __init__
        super(KNN, self).__init__()

        # algorithm self things
        self.k = k
        self.metric = metric
        if metric_args is None:
            metric_args = {}
        self.metric_args = metric_args

        # test metric args
        _ = metrics.pdist(np.zeros((2, 2)), metric, **metric_args)

        # minimum threshold
        self.min_thr = 10 * np.finfo('float').eps

N = len(data)
    if k > N:
        raise ValueError("Number of clusters 'k' is higher than the number" \
                          " of input samples.")

    if metric_args is None:
        metric_args = {}

    if linkage in ['centroid', 'median', 'ward']:
        if metric != 'euclidean':
            raise TypeError("Linkage '{}' requires the distance metric to be" \
                            " 'euclidean'.".format(linkage))
        Z = sch.linkage(data, method=linkage)
    else:
        # compute distances
        D = metrics.pdist(data, metric=metric, **metric_args)

        # build linkage
        Z = sch.linkage(D, method=linkage)

    if k < 0:
        k = 0

    # extract clusters
    if k == 0:
        # life-time
        labels = _life_time(Z, N)
    else:
        labels = sch.fcluster(Z, k, 'maxclust')

    # get cluster indices
    clusters = _extract_clusters(labels)