utils.py 文件源码

def hierarchical_ordering_indices(columns, correlation_matrix):
    """Return array with hierarchical cluster ordering of columns

    Parameters
    ----------
    columns: iterable of str
        Names of columns.
    correlation_matrix: np.ndarray
        Matrix of correlation coefficients between columns.

    Returns
    -------
    indices: iterable of int
        Indices with order of columns
    """
    if len(columns) > 2:
        pairwise_dists = distance.pdist(
            np.where(np.isnan(correlation_matrix), 0, correlation_matrix),
            metric='euclidean')
        linkage = hierarchy.linkage(pairwise_dists, method='average')
        dendogram = hierarchy.dendrogram(
            linkage, no_plot=True, color_threshold=-np.inf)
        idx = dendogram['leaves']
    else:
        idx = list(range(len(columns)))

    return idx