Function validate_distance_matrix

bertopic/_utils.py:106–152

Validate the distance matrix and convert it to a condensed distance matrix if necessary. A valid distance matrix is either a square matrix of shape (n_samples, n_samples) with zeros on the diagonal and non-negative values or condensed distance matrix of shape (n_samples * (n_samples

(X, n_samples)

def validate_distance_matrix(X, n_samples):
    """Validate the distance matrix and convert it to a condensed distance matrix
    if necessary.

    A valid distance matrix is either a square matrix of shape (n_samples, n_samples)
    with zeros on the diagonal and non-negative values or condensed distance matrix
    of shape (n_samples * (n_samples - 1) / 2,) containing the upper triangular of the
    distance matrix.

    Arguments:
        X: Distance matrix to validate.
        n_samples: Number of samples in the dataset.

    Returns:
        X: Validated distance matrix.

    Raises:
        ValueError: If the distance matrix is not valid.
    """
    # Make sure it is the 1-D condensed distance matrix with zeros on the diagonal
    s = X.shape
    if len(s) == 1:
        # check it has correct size
        n = s[0]
        if n != (n_samples * (n_samples - 1) / 2):
            raise ValueError("The condensed distance matrix must have shape (n*(n-1)/2,).")
    elif len(s) == 2:
        # check it has correct size
        if (s[0] != n_samples) or (s[1] != n_samples):
            raise ValueError("The distance matrix must be of shape (n, n) where n is the number of samples.")
        # force zero diagonal and convert to condensed
        np.fill_diagonal(X, 0)
        X = squareform(X)
    else:
        raise ValueError(
            "The distance matrix must be either a 1-D condensed "
            "distance matrix of shape (n*(n-1)/2,) or a "
            "2-D square distance matrix of shape (n, n)."
            "where n is the number of documents."
            "Got a distance matrix of shape %s" % str(s)
        )

    # Make sure its entries are non-negative
    if np.any(X < 0):
        raise ValueError("Distance matrix cannot contain negative values.")

    return X


def get_unique_distances(dists: np.array, noise_max=1e-7) -> np.array: