utils

navis.nbl.utils.make_linkage

Make linkage from input. If input looks like linkage it is passed through.

Source code in navis/nbl/utils.py

def make_linkage(x, method='single', optimal_ordering=False):
    """Make linkage from input. If input looks like linkage it is passed through."""
    if isinstance(x, pd.DataFrame):
        # Make sure it is symmetric
        if x.shape[0] != x.shape[1]:
            raise ValueError(f'Scores must be symmetric, got shape {x.shape}')
        # A cheap check for whether these are mean scores
        if any(x.values[0].round(5) != x.values[:, 0].round(5)):
            logger.warning(f'Symmetrizing scores because they do not look like mean scores!')
            x = (x + x.values.T) / 2

        dists = squareform(1 - x.values, checks=False)
        Z = sch.linkage(dists, method=method, optimal_ordering=optimal_ordering)
    elif isinstance(x, np.ndarray):
        Z = x
    else:
        raise TypeError(f'Expected scores) (DataFrame) or linkage (array), got {type(x)}')

    return Z

navis.nbl.utils.most

Check if most (as opposed to all) entries are True.

Source code in navis/nbl/utils.py

def most(x, f=.9):
    """Check if most (as opposed to all) entries are True."""
    if x.sum() >= (x.shape[0] * f):
        return True
    return False

navis.nbl.utils.nblast_prime

Generate a smoothed version of the NBLAST scores.

In brief: 1. Run PCA on the NBLAST scores and extract the first N components. 2. From that calulate a new similarity matrix.

Requires scikit-learn.

PARAMETER	DESCRIPTION
scores	The all-by-all NBLAST scores. TYPE: pandas.DataFrame
n_dim	The number of dimensions to use. If float (0 < n_dim < 1) will use `scores.shape[0] * n_dim`. TYPE: float | int DEFAULT: 0.2
metric	Which distance metric to use. Directly passed through to the `scipy.spatial.distance.pdist` function. TYPE: str DEFAULT: 'euclidean'

RETURNS	DESCRIPTION
scores_new

Source code in navis/nbl/utils.py

def nblast_prime(scores, n_dim=.2, metric='euclidean'):
    """Generate a smoothed version of the NBLAST scores.

    In brief:
     1. Run PCA on the NBLAST scores and extract the first N components.
     2. From that calulate a new similarity matrix.

    Requires scikit-learn.

    Parameters
    ----------
    scores :    pandas.DataFrame
                The all-by-all NBLAST scores.
    n_dim :     float | int
                The number of dimensions to use. If float (0 < n_dim < 1) will
                use `scores.shape[0] * n_dim`.
    metric :    str
                Which distance metric to use. Directly passed through to the
                `scipy.spatial.distance.pdist` function.

    Returns
    -------
    scores_new

    """
    try:
        from sklearn.decomposition import PCA
    except ModuleNotFoundError:
        raise ModuleNotFoundError(
            'Please install scikit-learn to use `nblast_prime`:\n'
            '  pip3 install scikit-learn -U'
            )

    if not isinstance(scores, pd.DataFrame):
        raise TypeError(f'`scores` must be pandas DataFrame, got "{type(scores)}"')

    if (scores.shape[0] != scores.shape[1]) or ~np.all(scores.columns == scores.index):
        logger.warning('NBLAST matrix is not symmetric - are you sure this is '
                       'an all-by-all matrix?')

    if n_dim < 1:
        n_dim = int(scores.shape[1] * n_dim)

    pca = PCA(n_components=n_dim)
    X_new = pca.fit_transform(scores.values)

    dist = pdist(X_new, metric=metric)

    return pd.DataFrame(1 - squareform(dist), index=scores.index, columns=scores.columns)