graspologic/cluster/autogmm.py [311:335]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if isinstance(covariance_type, (np.ndarray, list)):
            covariance_type = np.unique(covariance_type)
        elif isinstance(covariance_type, str):
            if covariance_type == "all":
                covariance_type = ["spherical", "diag", "tied", "full"]
            else:
                covariance_type = [covariance_type]
        else:
            msg = "covariance_type must be a numpy array, a list, or "
            msg += "string, not {}".format(type(covariance_type))
            raise TypeError(msg)

        for cov in covariance_type:
            if cov not in ["spherical", "diag", "tied", "full"]:
                msg = (
                    "covariance structure must be one of "
                    + '["spherical", "diag", "tied", "full"]'
                )
                msg += " not {}".format(cov)
                raise ValueError(msg)

        new_covariance_type = []
        for cov in ["spherical", "diag", "tied", "full"]:
            if cov in covariance_type:
                new_covariance_type.append(cov)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



graspologic/cluster/gclust.py [147:171]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if isinstance(covariance_type, (np.ndarray, list)):
            covariance_type = np.unique(covariance_type)
        elif isinstance(covariance_type, str):
            if covariance_type == "all":
                covariance_type = ["spherical", "diag", "tied", "full"]
            else:
                covariance_type = [covariance_type]
        else:
            msg = "covariance_type must be a numpy array, a list, or "
            msg += "string, not {}".format(type(covariance_type))
            raise TypeError(msg)

        for cov in covariance_type:
            if cov not in ["spherical", "diag", "tied", "full"]:
                msg = (
                    "covariance structure must be one of "
                    + '["spherical", "diag", "tied", "full"]'
                )
                msg += " not {}".format(cov)
                raise ValueError(msg)

        new_covariance_type = []
        for cov in ["spherical", "diag", "tied", "full"]:
            if cov in covariance_type:
                new_covariance_type.append(cov)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -