def significance(
TTM: sp.csc_matrix,
metric: Union[Callable, KeynessMetric],
normalize: bool = False,
n_contexts=None,
n_words=None,
) -> sp.csc_matrix:
"""Computes statistical significance tf co-occurrences using `metric`.
Args:
TTM (sp.csc_matrix): [description]
normalize (bool, optional): [description]. Defaults to False.
Returns:
sp.csc_matrix: [description]
"""
metric = metric if callable(metric) else METRIC_FUNCTION.get(
metric, _undefined)
K: float = n_contexts
N: float = n_words
"""Total number of observations (counts)"""
Z: float = float(TTM.sum())
"""Number of observations per context (document, row sum)"""
Zr = np.array(TTM.sum(axis=1), dtype=np.float64).flatten()
"""Row and column indices of non-zero elements."""
ii, jj = TTM.nonzero()
Cij: np.ndarray = np.array(TTM[ii, jj], dtype=np.float64).flatten()
"""Compute weights (with optional normalize)."""
weights: np.ndarray = metric(Cij=Cij,
Z=Z,
Zr=Zr,
ii=ii,
jj=jj,
K=K,
N=N,
normalize=normalize)
np.nan_to_num(
weights,
copy=False,
posinf=0.0,
neginf=0.0,
nan=0.0,
)
nz_indices: np.ndarray = weights.nonzero()
return (weights[nz_indices], (ii[nz_indices], jj[nz_indices]))
def get_distances(node: Tuple[int, int],
nodes: sparse.csc_matrix) -> List[int]:
non_zero = [coord for coord in zip(*nodes.nonzero())]
distances = spatial.distance.cdist([node], non_zero,
metric='cityblock').flatten().tolist()
return distances