def test_bipartite_edge_list(self):
self.stub_data_9 = 'stub_9.txt'
with open(self.stub_data_9, "w") as text_file:
text_file.write('%stub\n1 3\n4 5\n0 3')
graph = parse.load_edge_list(self.stub_data_9, bipartite=True)
biadjacency = graph.biadjacency
self.assertTrue((biadjacency.indices == [0, 0, 1]).all())
self.assertTrue((biadjacency.indptr == [0, 1, 2, 3]).all())
self.assertTrue((biadjacency.data == [1, 1, 1]).all())
remove(self.stub_data_9)
def test_unlabeled_unweighted(self):
self.stub_data_1 = 'stub_1.txt'
with open(self.stub_data_1, "w") as text_file:
text_file.write('%stub\n1 3\n4 5\n0 2')
graph = parse.load_edge_list(self.stub_data_1)
adjacency = graph.adjacency
self.assertTrue((adjacency.indices == [2, 3, 0, 1, 5, 4]).all())
self.assertTrue((adjacency.indptr == [0, 1, 2, 3, 4, 5, 6]).all())
self.assertTrue((adjacency.data == [1, 1, 1, 1, 1, 1]).all())
remove(self.stub_data_1)
def test_auto_reindex(self):
self.stub_data_4 = 'stub_4.txt'
with open(self.stub_data_4, "w") as text_file:
text_file.write('%stub\n14 31\n42 50\n0 12')
graph = parse.load_edge_list(self.stub_data_4)
adjacency = graph.adjacency
names = graph.names
self.assertTrue((adjacency.indices == [1, 0, 3, 2, 5, 4]).all())
self.assertTrue((adjacency.indptr == [0, 1, 2, 3, 4, 5, 6]).all())
self.assertTrue((adjacency.data == [1, 1, 1, 1, 1, 1]).all())
self.assertTrue((names == [0, 12, 14, 31, 42, 50]).all())
remove(self.stub_data_4)
def test_labeled_weighted(self):
self.stub_data_2 = 'stub_2.txt'
with open(self.stub_data_2, "w") as text_file:
text_file.write('%stub\nf, e, 5\na, d, 6\nc, b, 1')
graph = parse.load_edge_list(self.stub_data_2)
adjacency = graph.adjacency
names = graph.names
self.assertTrue((adjacency.indices == [4, 3, 5, 1, 0, 2]).all())
self.assertTrue((adjacency.indptr == [0, 1, 2, 3, 4, 5, 6]).all())
self.assertTrue((adjacency.data == [1, 6, 5, 6, 1, 5]).all())
self.assertTrue((names == [' b', ' d', ' e', 'a', 'c', 'f']).all())
remove(self.stub_data_2)
def load_konect(dataset: str, data_home: Optional[Union[str, Path]] = None, auto_numpy_bundle: bool = True,
verbose: bool = True) -> Bunch:
"""Load a dataset from the `Konect database
<http://konect.cc/networks/>`_.
Parameters
----------
dataset : str
The internal name of the dataset as specified on the Konect website (e.g. for the Zachary Karate club dataset,
the corresponding name is ``'ucidata-zachary'``).
data_home : str or :class:`pathlib.Path`
The folder to be used for dataset storage
auto_numpy_bundle : bool
Denotes if the dataset should be stored in its default format (False) or using Numpy files for faster
subsequent access to the dataset (True).
verbose : bool
Enable verbosity.
Returns
-------
graph : :class:`Bunch`
An object with the following attributes:
* `adjacency` or `biadjacency`: the adjacency/biadjacency matrix for the dataset
* `meta`: a dictionary containing the metadata as specified by Konect
* each attribute specified by Konect (ent.* file)
Notes
-----
An attribute `meta` of the `Bunch` class is used to store information about the dataset if present. In any case,
`meta` has the attribute `name` which, if not given, is equal to the name of the dataset as passed to this function.
References
----------
Kunegis, J. (2013, May).
`Konect: the Koblenz network collection.
<https://dl.acm.org/doi/abs/10.1145/2487788.2488173>`_
In Proceedings of the 22nd International Conference on World Wide Web (pp. 1343-1350).
"""
logger = Log(verbose)
if dataset == '':
raise ValueError("Please specify the dataset. "
+ "\nExamples include 'actor-movie' and 'ego-facebook'."
+ "\n See 'http://konect.cc/networks/' for the full list.")
data_home = get_data_home(data_home)
data_path = data_home / dataset
if not data_path.exists():
logger.print('Downloading', dataset, 'from Konect...')
makedirs(data_path, exist_ok=True)
try:
urlretrieve('http://konect.cc/files/download.tsv.' + dataset + '.tar.bz2',
data_home / (dataset + '.tar.bz2'))
with tarfile.open(data_home / (dataset + '.tar.bz2'), 'r:bz2') as tar_ref:
logger.print('Unpacking archive...')
tar_ref.extractall(data_home)
except (HTTPError, tarfile.ReadError):
rmdir(data_path)
raise ValueError('Invalid dataset ' + dataset + '.'
+ "\nExamples include 'actor-movie' and 'ego-facebook'."
+ "\n See 'http://konect.cc/networks/' for the full list.")
except (URLError, ConnectionResetError): # pragma: no cover
rmdir(data_path)
raise RuntimeError("Could not reach Konect.")
finally:
if exists(data_home / (dataset + '.tar.bz2')):
remove(data_home / (dataset + '.tar.bz2'))
elif exists(data_path / (dataset + '_bundle')):
logger.print('Loading from local bundle...')
return load_from_numpy_bundle(dataset + '_bundle', data_path)
data = Bunch()
files = [file for file in listdir(data_path) if dataset in file]
logger.print('Parsing files...')
matrix = [file for file in files if 'out.' in file]
if matrix:
file = matrix[0]
directed, bipartite, weighted = load_header(data_path / file)
if bipartite:
graph = load_edge_list(data_path / file, directed=directed, bipartite=bipartite, weighted_input=weighted)
data.biadjacency = graph.biadjacency
else:
graph = load_edge_list(data_path / file, directed=directed, bipartite=bipartite, weighted_input=weighted)
data.adjacency = graph.adjacency
metadata = [file for file in files if 'meta.' in file]
if metadata:
file = metadata[0]
data.meta = load_metadata(data_path / file)
attributes = [file for file in files if 'ent.' + dataset in file]
if attributes:
for file in attributes:
attribute_name = file.split('.')[-1]
data[attribute_name] = load_labels(data_path / file)
if hasattr(data, 'meta'):
if hasattr(data.meta, 'name'):
pass
else:
data.meta.name = dataset
else:
data.meta = Bunch()
data.meta.name = dataset
if auto_numpy_bundle:
save_to_numpy_bundle(data, dataset + '_bundle', data_path)
return data
def load_konect(dataset: str,
data_home: Optional[Union[str, Path]] = None,
auto_numpy_bundle: bool = True) -> Bunch:
"""Load a dataset from the `Konect database
<http://konect.uni-koblenz.de>`_.
Parameters
----------
dataset : str
The name of the dataset as specified in the download link (e.g. for the Actor movies dataset, the corresponding
name is ``'actor-movie'``).
data_home : str or :class:`pathlib.Path`
The folder to be used for dataset storage
auto_numpy_bundle : bool
Denotes if the dataset should be stored in its default format (False) or using Numpy files for faster
subsequent access to the dataset (True).
Returns
-------
graph : :class:`Bunch`
An object with the following attributes:
* `adjacency` or `biadjacency`: the adjacency/biadjacency matrix for the dataset
* `meta`: a dictionary containing the metadata as specified by Konect
* each attribute specified by Konect (ent.* file)
Example
-------
>>> from sknetwork.data import load_konect
>>> graph = load_konect('dolphins')
>>> graph.adjacency.shape
(62, 62)
Notes
-----
An attribute `meta` of the `Bunch` class is used to store information about the dataset if present. In any case,
`meta` has the attribute `name` which, if not given, is equal to the name of the dataset as passed to this function.
"""
if dataset == '':
raise ValueError(
"Please specify the dataset. " +
"\nExamples include 'actor-movie' and 'ego-facebook'." +
"\n See 'http://konect.uni-koblenz.de' for the full list.")
data_home = get_data_home(data_home)
data_path = data_home / dataset
if not data_path.exists():
makedirs(data_path, exist_ok=True)
try:
urlretrieve(
'http://konect.uni-koblenz.de/downloads/tsv/' + dataset +
'.tar.bz2', data_home / (dataset + '.tar.bz2'))
with tarfile.open(data_home / (dataset + '.tar.bz2'),
'r:bz2') as tar_ref:
tar_ref.extractall(data_home)
except (HTTPError, tarfile.ReadError):
rmdir(data_path)
raise ValueError(
'Invalid dataset ' + dataset + '.' +
"\nExamples include 'actor-movie' and 'ego-facebook'." +
"\n See 'http://konect.uni-koblenz.de' for the full list.")
finally:
remove(data_home / (dataset + '.tar.bz2'))
elif exists(data_path / (dataset + '_bundle')):
return load_from_numpy_bundle(dataset + '_bundle', data_path)
data = Bunch()
files = [file for file in listdir(data_path) if dataset in file]
matrix = [file for file in files if 'out.' in file]
if matrix:
file = matrix[0]
directed, bipartite, weighted = load_header(data_path / file)
if bipartite:
graph = load_edge_list(data_path / file,
directed=directed,
bipartite=bipartite,
weighted=weighted)
data.biadjacency = graph.biadjacency
else:
graph = load_edge_list(data_path / file,
directed=directed,
bipartite=bipartite,
weighted=weighted)
data.adjacency = graph.adjacency
metadata = [file for file in files if 'meta.' in file]
if metadata:
file = metadata[0]
data.meta = load_metadata(data_path / file)
attributes = [file for file in files if 'ent.' + dataset in file]
if attributes:
for file in attributes:
attribute_name = file.split('.')[-1]
data[attribute_name] = load_labels(data_path / file)
if hasattr(data, 'meta'):
if hasattr(data.meta, 'name'):
pass
else:
data.meta.name = dataset
else:
data.meta = Bunch()
data.meta.name = dataset
if auto_numpy_bundle:
save_to_numpy_bundle(data, dataset + '_bundle', data_path)
return data
