def metapath_to_degree_dicts(graph, metapath):
metapath = graph.metagraph.get_metapath(metapath)
_, _, source_adj_mat = metaedge_to_adjacency_matrix(graph,
metapath[0],
dense_threshold=0.7)
_, _, target_adj_mat = metaedge_to_adjacency_matrix(graph,
metapath[-1],
dense_threshold=0.7)
source_degrees = source_adj_mat.sum(axis=1).flat
target_degrees = target_adj_mat.sum(axis=0).flat
source_degree_to_ind = degrees_to_degree_to_ind(source_degrees)
target_degree_to_ind = degrees_to_degree_to_ind(target_degrees)
return source_degree_to_ind, target_degree_to_ind
def dwpc_to_degrees(graph, metapath, damping=0.5, ignore_zeros=False):
"""
Yield a description of each cell in a DWPC matrix adding source and target
node degree info as well as the corresponding path count.
"""
metapath = graph.metagraph.get_metapath(metapath)
_, _, source_adj_mat = metaedge_to_adjacency_matrix(graph,
metapath[0],
dense_threshold=0.7)
_, _, target_adj_mat = metaedge_to_adjacency_matrix(graph,
metapath[-1],
dense_threshold=0.7)
source_degrees = source_adj_mat.sum(axis=1).flat
target_degrees = target_adj_mat.sum(axis=0).flat
del source_adj_mat, target_adj_mat
source_path = graph.get_nodes_path(metapath.source(), file_format='tsv')
source_node_df = pandas.read_table(source_path)
source_node_names = list(source_node_df['name'])
target_path = graph.get_nodes_path(metapath.target(), file_format='tsv')
target_node_df = pandas.read_table(target_path)
target_node_names = list(target_node_df['name'])
row_names, col_names, dwpc_matrix = graph.read_path_counts(
metapath, 'dwpc', damping)
dwpc_matrix = numpy.arcsinh(dwpc_matrix / dwpc_matrix.mean())
if scipy.sparse.issparse(dwpc_matrix):
dwpc_matrix = dwpc_matrix.toarray()
_, _, path_count = graph.read_path_counts(metapath, 'dwpc', 0.0)
if scipy.sparse.issparse(path_count):
path_count = path_count.toarray()
row_inds, col_inds = range(len(row_names)), range(len(col_names))
for row_ind, col_ind in itertools.product(row_inds, col_inds):
dwpc_value = dwpc_matrix[row_ind, col_ind]
if ignore_zeros and dwpc_value == 0:
continue
row = {
'source_id': row_names[row_ind],
'target_id': col_names[col_ind],
'source_name': source_node_names[row_ind],
'target_name': target_node_names[col_ind],
'source_degree': source_degrees[row_ind],
'target_degree': target_degrees[col_ind],
'path_count': path_count[row_ind, col_ind],
'dwpc': dwpc_value,
}
yield collections.OrderedDict(row)
def metaedge_to_data_array(graph, metaedge, dtype=numpy.bool_):
"""
Return an xarray.DataArray that's an adjacency matrix where source nodes
are columns and target nodes are rows.
"""
source_node_ids, target_node_ids, adjacency_matrix = (
metaedge_to_adjacency_matrix(graph, metaedge, dtype=dtype))
dims = metaedge.source.identifier, metaedge.target.identifier
coords = source_node_ids, target_node_ids
data_array = xarray.DataArray(adjacency_matrix,
coords=coords,
dims=dims,
name=metaedge.get_unicode_str())
return data_array
def dwpc_to_degrees(graph,
metapath,
damping=0.5,
ignore_zeros=False,
ignore_redundant=True):
"""
Yield a description of each cell in a DWPC matrix adding source and target
node degree info as well as the corresponding path count.
Parameters
----------
ignore_redundant: bool
When metapath is symmetric, only return a single orientation of a node pair.
For example, yield source-target but not also target-source, which should have
the same DWPC.
"""
metapath = graph.metagraph.get_metapath(metapath)
_, _, source_adj_mat = metaedge_to_adjacency_matrix(graph,
metapath[0],
dense_threshold=0.7)
_, _, target_adj_mat = metaedge_to_adjacency_matrix(graph,
metapath[-1],
dense_threshold=0.7)
source_degrees = source_adj_mat.sum(axis=1).flat
target_degrees = target_adj_mat.sum(axis=0).flat
del source_adj_mat, target_adj_mat
source_path = graph.get_nodes_path(metapath.source(), file_format='tsv')
source_node_df = pandas.read_csv(source_path, sep='\t')
source_node_names = list(source_node_df['name'])
target_path = graph.get_nodes_path(metapath.target(), file_format='tsv')
target_node_df = pandas.read_csv(target_path, sep='\t')
target_node_names = list(target_node_df['name'])
row_names, col_names, dwpc_matrix = graph.read_path_counts(
metapath, 'dwpc', damping)
dwpc_matrix = numpy.arcsinh(dwpc_matrix / dwpc_matrix.mean())
if scipy.sparse.issparse(dwpc_matrix):
dwpc_matrix = dwpc_matrix.toarray()
_, _, path_count = graph.read_path_counts(metapath, 'dwpc', 0.0)
if scipy.sparse.issparse(path_count):
path_count = path_count.toarray()
if ignore_redundant and metapath.is_symmetric():
pairs = itertools.combinations_with_replacement(
range(len(row_names)), 2)
else:
pairs = itertools.product(range(len(row_names)), range(len(col_names)))
for row_ind, col_ind in pairs:
dwpc_value = dwpc_matrix[row_ind, col_ind]
if ignore_zeros and dwpc_value == 0:
continue
row = {
'source_id': row_names[row_ind],
'target_id': col_names[col_ind],
'source_name': source_node_names[row_ind],
'target_name': target_node_names[col_ind],
'source_degree': source_degrees[row_ind],
'target_degree': target_degrees[col_ind],
'path_count': path_count[row_ind, col_ind],
'dwpc': dwpc_value,
}
yield collections.OrderedDict(row)