_cluster.py 文件源码

def normalize_simple(matrix, mask):
    """Normalizes a matrix by columns, and then by rows. With multiple
    time-series, the data are normalized to the within-series total, not the
    entire data set total.

    Parameters
    ----------
    matrix: np.matrix
        Time-series matrix of abundance counts. Rows are sequences, columns
        are samples/time-points.
    mask: list or np.array
        List of objects with length matching the number of timepoints, where
        unique values delineate multiple time-series. If there is only one
        time-series in the data set, it's a list of identical objects.

    Returns
    -------
    normal_matrix: np.matrix
        Matrix where the columns (within-sample) have been converted to 
        proportions, then the rows are normalized to sum to 1.
    """
    normal_matrix = matrix / matrix.sum(0)
    normal_matrix[np.invert(np.isfinite(normal_matrix))] = 0
    for mask_val in np.unique(mask):
        y = normal_matrix[:, np.where(mask == mask_val)[0]]
        y = np.apply_along_axis(zscore, 1, y)
        normal_matrix[:, np.where(mask == mask_val)[0]] = y
        del y
    return normal_matrix