def fit(self, biadjacency: Union[sparse.csr_matrix, np.ndarray],
seeds_row: Optional[Union[dict, np.ndarray]] = None,
seeds_col: Optional[Union[dict, np.ndarray]] = None) -> 'CoPageRank':
"""Fit algorithm to data.
Parameters
----------
biadjacency :
Biadjacency matrix.
seeds_row :
Seed rows, as a dict or a vector.
seeds_col :
Seed columns, as a dict or a vector.
If both seeds_row and seeds_col are ``None``, the uniform distribution is used.
Returns
-------
self: :class:`CoPageRank`
"""
biadjacency = check_format(biadjacency)
n_row, n_col = biadjacency.shape
operator = CoNeighborsOperator(biadjacency, True)
seeds_row = seeds2probs(n_row, seeds_row)
self.scores_row_ = get_pagerank(operator, seeds_row, damping_factor=self.damping_factor, solver=self.solver,
n_iter=self.n_iter, tol=self.tol)
operator = CoNeighborsOperator(biadjacency.T.tocsr(), True)
seeds_col = seeds2probs(n_col, seeds_col)
self.scores_col_ = get_pagerank(operator, seeds_col, damping_factor=self.damping_factor, solver=self.solver,
n_iter=self.n_iter, tol=self.tol)
self.scores_ = self.scores_row_
return self
def test_seeds2probs(self):
n = 4
seeds_array = np.array([0, 1, -1, 0])
seeds_dict = {0: 0, 1: 1, 3: 0}
probs1 = seeds2probs(n, seeds_array)
probs2 = seeds2probs(n, seeds_dict)
self.assertTrue(np.allclose(probs1, probs2))
bad_input = np.array([0, 0, -1, 0])
with self.assertRaises(ValueError):
seeds2probs(n, bad_input)
def fit(self, adjacency: Union[sparse.csr_matrix, np.ndarray, LinearOperator],
seeds: Optional[Union[dict, np.ndarray]] = None) -> 'PageRank':
"""Fit algorithm to data.
Parameters
----------
adjacency :
Adjacency matrix.
seeds :
Parameter to be used for Personalized PageRank.
Restart distribution as a vector or a dict (node: weight).
If ``None``, the uniform distribution is used (no personalization, default).
Returns
-------
self: :class:`PageRank`
"""
if not isinstance(adjacency, LinearOperator):
adjacency = check_format(adjacency)
check_square(adjacency)
seeds = seeds2probs(adjacency.shape[0], seeds)
self.scores_ = get_pagerank(adjacency, seeds, damping_factor=self.damping_factor, n_iter=self.n_iter,
solver=self.solver, tol=self.tol)
return self
def fit(self, adjacency: Union[sparse.csr_matrix, np.ndarray, LinearOperator],
seeds: Optional[Union[dict, np.ndarray]] = None) -> 'PageRank':
"""Fit algorithm to data.
Parameters
----------
adjacency :
Adjacency matrix.
seeds :
If ``None``, the uniform distribution is used.
Otherwise, a non-negative, non-zero vector or a dictionary must be provided.
Returns
-------
self: :class:`PageRank`
"""
if not isinstance(adjacency, LinearOperator):
adjacency = check_format(adjacency)
check_square(adjacency)
seeds = seeds2probs(adjacency.shape[0], seeds)
self.scores_ = get_pagerank(adjacency, seeds, damping_factor=self.damping_factor, n_iter=self.n_iter,
solver=self.solver, tol=self.tol)
return self
fast_format=False)
adjacency = graph.adjacency
time_end = time.time()
print("Sknetwork load graph time:", time_end - time_start, "seconds")
# read names of pages
pages = pd.read_table('data/wiki_pageNum.txt', encoding='utf-8',
header=None).values.tolist()
# parameters
# seeds = {2597: 1, 26634: 1, 229857: 1}
seeds = None
seeds = seeds2probs(adjacency.shape[0], seeds)
tol = 1e-1
damping_factor = 0.85
# beginning push algorithm
time_start = time.time()
n = adjacency.shape[0]
degrees = adjacency.dot(np.ones(n)).astype(np.int32)
rev_adjacency = adjacency.transpose().tocsr()
indptr = adjacency.indptr.astype(np.int32)
indices = adjacency.indices.astype(np.int32)
rev_indptr = rev_adjacency.indptr.astype(np.int32)
rev_indices = rev_adjacency.indices.astype(np.int32)
scores = push_pagerank(n, degrees, indptr, indices, rev_indptr, rev_indices,