scikit-network 0.32.1__cp311-cp311-win_amd64.whl → 0.33.0__cp311-cp311-win_amd64.whl

sknetwork/data/load.py

@@ -19,15 +19,12 @@ import numpy as np
 from scipy import sparse
 
 from sknetwork.data.parse import from_csv, load_labels, load_header, load_metadata
-from sknetwork.data.base import Bunch
+from sknetwork.data.base import Dataset
 from sknetwork.utils.check import is_square
 from sknetwork.log import Log
 
 NETSET_URL = 'https://netset.telecom-paris.fr'
 
-# former name of Dataset
-Bunch = Bunch
-
 
 def is_within_directory(directory, target):
     """Utility function."""
@@ -89,7 +86,7 @@ def clean_data_home(data_home: Optional[Union[str, Path]] = None):
 
 
 def load_netset(name: Optional[str] = None, data_home: Optional[Union[str, Path]] = None,
-                verbose: bool = True) -> Optional[Bunch]:
+                verbose: bool = True) -> Optional[Dataset]:
     """Load a dataset from the `NetSet collection
     <https://netset.telecom-paris.fr/>`_.
 
@@ -105,10 +102,10 @@ def load_netset(name: Optional[str] = None, data_home: Optional[Union[str, Path]
 
     Returns
     -------
-    dataset : :class:`Bunch`
+    dataset : :class:`Dataset`
         Returned dataset.
     """
-    dataset = Bunch()
+    dataset = Dataset()
     dataset_folder = NETSET_URL + '/datasets/'
     folder_npz = NETSET_URL + '/datasets_npz/'
 
@@ -167,7 +164,7 @@ def load_netset(name: Optional[str] = None, data_home: Optional[Union[str, Path]
 
 
 def load_konect(name: str, data_home: Optional[Union[str, Path]] = None, auto_numpy_bundle: bool = True,
-                verbose: bool = True) -> Bunch:
+                verbose: bool = True) -> Dataset:
     """Load a dataset from the `Konect database
     <http://konect.cc/networks/>`_.
 
@@ -186,7 +183,7 @@ def load_konect(name: str, data_home: Optional[Union[str, Path]] = None, auto_nu
 
     Returns
     -------
-    dataset : :class:`Bunch`
+    dataset : :class:`Dataset`
         Object with the following attributes:
 
              * `adjacency` or `biadjacency`: the adjacency/biadjacency matrix for the dataset
@@ -240,7 +237,7 @@ def load_konect(name: str, data_home: Optional[Union[str, Path]] = None, auto_nu
         logger.print_log('Loading from local bundle...')
         return load_from_numpy_bundle(name + '_bundle', data_path)
 
-    dataset = Bunch()
+    dataset = Dataset()
     path = data_konect / name / name
     if not path.exists() or len(listdir(path)) == 0:
         raise Exception("No data downloaded.")
@@ -269,7 +266,7 @@ def load_konect(name: str, data_home: Optional[Union[str, Path]] = None, auto_nu
         else:
             dataset.meta.name = name
     else:
-        dataset.meta = Bunch()
+        dataset.meta = Dataset()
         dataset.meta.name = name
 
     if auto_numpy_bundle:
@@ -280,12 +277,12 @@ def load_konect(name: str, data_home: Optional[Union[str, Path]] = None, auto_nu
     return dataset
 
 
-def save_to_numpy_bundle(data: Bunch, bundle_name: str, data_home: Optional[Union[str, Path]] = None):
+def save_to_numpy_bundle(data: Dataset, bundle_name: str, data_home: Optional[Union[str, Path]] = None):
     """Save a dataset in the specified data home to a collection of Numpy and Pickle files for faster subsequent loads.
 
     Parameters
     ----------
-    data: Bunch
+    data: Dataset
         Data to save.
     bundle_name: str
         Name to be used for the bundle folder.
@@ -317,7 +314,7 @@ def load_from_numpy_bundle(bundle_name: str, data_home: Optional[Union[str, Path
 
     Returns
     -------
-    data: Bunch
+    data: Dataset
         Data.
     """
     data_home = get_data_home(data_home)
@@ -326,7 +323,7 @@ def load_from_numpy_bundle(bundle_name: str, data_home: Optional[Union[str, Path
         raise FileNotFoundError('No bundle at ' + str(data_path))
     else:
         files = listdir(data_path)
-        data = Bunch()
+        data = Dataset()
         for file in files:
             if len(file.split('.')) == 2:
                 file_name, file_extension = file.split('.')
@@ -340,7 +337,7 @@ def load_from_numpy_bundle(bundle_name: str, data_home: Optional[Union[str, Path
         return data
 
 
-def save(folder: Union[str, Path], data: Union[sparse.csr_matrix, Bunch]):
+def save(folder: Union[str, Path], data: Union[sparse.csr_matrix, Dataset]):
     """Save a dataset or a CSR matrix in the current directory to a collection of Numpy and Pickle files for faster
     subsequent loads. Supported attribute types include sparse matrices, NumPy arrays, strings and objects Dataset.
 
@@ -348,13 +345,13 @@ def save(folder: Union[str, Path], data: Union[sparse.csr_matrix, Bunch]):
     ----------
     folder : str or :class:`pathlib.Path`
         Name of the bundle folder.
-    data : Union[sparse.csr_matrix, Bunch]
+    data : Union[sparse.csr_matrix, Dataset]
         Data to save.
 
     Example
     -------
     >>> from sknetwork.data import save
-    >>> dataset = Bunch()
+    >>> dataset = Dataset()
     >>> dataset.adjacency = sparse.csr_matrix(np.random.random((3, 3)) < 0.5)
     >>> dataset.names = np.array(['a', 'b', 'c'])
     >>> save('dataset', dataset)
@@ -366,7 +363,7 @@ def save(folder: Union[str, Path], data: Union[sparse.csr_matrix, Bunch]):
     if folder.exists():
         shutil.rmtree(folder)
     if isinstance(data, sparse.csr_matrix):
-        dataset = Bunch()
+        dataset = Dataset()
         if is_square(data):
             dataset.adjacency = data
         else:
@@ -388,13 +385,13 @@ def load(folder: Union[str, Path]):
 
     Returns
     -------
-    data: Bunch
+    data: Dataset
         Data.
 
     Example
     -------
     >>> from sknetwork.data import save
-    >>> dataset = Bunch()
+    >>> dataset = Dataset()
     >>> dataset.adjacency = sparse.csr_matrix(np.random.random((3, 3)) < 0.5)
     >>> dataset.names = np.array(['a', 'b', 'c'])
     >>> save('dataset', dataset)

sknetwork/data/models.py

@@ -12,7 +12,7 @@ from typing import Union, Optional, Iterable
 import numpy as np
 from scipy import sparse
 
-from sknetwork.data.base import Bunch
+from sknetwork.data.base import Dataset
 from sknetwork.data.parse import from_edge_list
 from sknetwork.utils.check import check_random_state
 from sknetwork.utils.format import directed2undirected
@@ -20,7 +20,7 @@ from sknetwork.utils.format import directed2undirected
 
 def block_model(sizes: Iterable, p_in: Union[float, list, np.ndarray] = .2, p_out: float = .05,
                 directed: bool = False, self_loops: bool = False, metadata: bool = False, seed: Optional[int] = None) \
-                -> Union[sparse.csr_matrix, Bunch]:
+                -> Union[sparse.csr_matrix, Dataset]:
     """Stochastic block model.
 
     Parameters
@@ -83,7 +83,7 @@ def block_model(sizes: Iterable, p_in: Union[float, list, np.ndarray] = .2, p_ou
     else:
         adjacency = directed2undirected(sparse.csr_matrix(sparse.triu(adjacency)), weighted=False)
     if metadata:
-        graph = Bunch()
+        graph = Dataset()
         graph.adjacency = adjacency
         labels = np.repeat(np.arange(len(sizes)), sizes)
         graph.labels = labels
@@ -129,7 +129,7 @@ def erdos_renyi(n: int = 20, p: float = .3, directed: bool = False, self_loops:
     return block_model([n], p, 0., directed=directed, self_loops=self_loops, metadata=False, seed=seed)
 
 
-def linear_digraph(n: int = 3, metadata: bool = False) -> Union[sparse.csr_matrix, Bunch]:
+def linear_digraph(n: int = 3, metadata: bool = False) -> Union[sparse.csr_matrix, Dataset]:
     """Linear graph (directed).
 
     Parameters
@@ -158,7 +158,7 @@ def linear_digraph(n: int = 3, metadata: bool = False) -> Union[sparse.csr_matri
     if metadata:
         x = np.arange(n)
         y = np.zeros(n)
-        graph = Bunch()
+        graph = Dataset()
         graph.adjacency = adjacency
         graph.position = np.array((x, y)).T
         return graph
@@ -166,7 +166,7 @@ def linear_digraph(n: int = 3, metadata: bool = False) -> Union[sparse.csr_matri
         return adjacency
 
 
-def linear_graph(n: int = 3, metadata: bool = False) -> Union[sparse.csr_matrix, Bunch]:
+def linear_graph(n: int = 3, metadata: bool = False) -> Union[sparse.csr_matrix, Dataset]:
     """Linear graph (undirected).
 
     Parameters
@@ -218,7 +218,7 @@ def cyclic_position(n: int) -> np.ndarray:
     return position
 
 
-def cyclic_digraph(n: int = 3, metadata: bool = False) -> Union[sparse.csr_matrix, Bunch]:
+def cyclic_digraph(n: int = 3, metadata: bool = False) -> Union[sparse.csr_matrix, Dataset]:
     """Cyclic graph (directed).
 
     Parameters
@@ -245,7 +245,7 @@ def cyclic_digraph(n: int = 3, metadata: bool = False) -> Union[sparse.csr_matri
     adjacency = sparse.csr_matrix((np.ones(len(row), dtype=int), (row, col)), shape=(n, n))
 
     if metadata:
-        graph = Bunch()
+        graph = Dataset()
         graph.adjacency = adjacency
         graph.position = cyclic_position(n)
         return graph
@@ -253,7 +253,7 @@ def cyclic_digraph(n: int = 3, metadata: bool = False) -> Union[sparse.csr_matri
         return adjacency
 
 
-def cyclic_graph(n: int = 3, metadata: bool = False) -> Union[sparse.csr_matrix, Bunch]:
+def cyclic_graph(n: int = 3, metadata: bool = False) -> Union[sparse.csr_matrix, Dataset]:
     """Cyclic graph (undirected).
 
     Parameters
@@ -283,7 +283,7 @@ def cyclic_graph(n: int = 3, metadata: bool = False) -> Union[sparse.csr_matrix,
         return graph.adjacency
 
 
-def grid(n1: int = 10, n2: int = 10, metadata: bool = False) -> Union[sparse.csr_matrix, Bunch]:
+def grid(n1: int = 10, n2: int = 10, metadata: bool = False) -> Union[sparse.csr_matrix, Dataset]:
     """Grid (undirected).
 
     Parameters
@@ -312,7 +312,7 @@ def grid(n1: int = 10, n2: int = 10, metadata: bool = False) -> Union[sparse.csr
     edges = list(map(lambda edge: (node_id[edge[0]], node_id[edge[1]]), edges))
     adjacency = from_edge_list(edges, reindex=False, matrix_only=True)
     if metadata:
-        graph = Bunch()
+        graph = Dataset()
         graph.adjacency = adjacency
         graph.position = np.array(nodes)
         return graph
@@ -320,7 +320,7 @@ def grid(n1: int = 10, n2: int = 10, metadata: bool = False) -> Union[sparse.csr
         return adjacency
 
 
-def star(n_branches: int = 3, metadata: bool = False) -> Union[sparse.csr_matrix, Bunch]:
+def star(n_branches: int = 3, metadata: bool = False) -> Union[sparse.csr_matrix, Dataset]:
     """Star (undirected).
 
     Parameters
@@ -345,7 +345,7 @@ def star(n_branches: int = 3, metadata: bool = False) -> Union[sparse.csr_matrix
     edges = [(0, i+1) for i in range(n_branches)]
     adjacency = from_edge_list(edges, reindex=False, matrix_only=True)
     if metadata:
-        graph = Bunch()
+        graph = Dataset()
         graph.adjacency = adjacency
         angles = 2 * np.pi * np.arange(n_branches) / n_branches
         x = [0] + list(np.cos(angles))
@@ -402,7 +402,7 @@ def albert_barabasi(n: int = 100, degree: int = 3, directed: bool = False, seed:
 
 
 def watts_strogatz(n: int = 100, degree: int = 6, prob: float = 0.05, seed: Optional[int] = None,
-                   metadata: bool = False) -> Union[sparse.csr_matrix, Bunch]:
+                   metadata: bool = False) -> Union[sparse.csr_matrix, Dataset]:
     """Watts-Strogatz model.
 
     Parameters
@@ -451,7 +451,7 @@ def watts_strogatz(n: int = 100, degree: int = 6, prob: float = 0.05, seed: Opti
                 adjacency[j, i] = 0
     adjacency = sparse.csr_matrix(adjacency, shape=adjacency.shape)
     if metadata:
-        graph = Bunch()
+        graph = Dataset()
         graph.adjacency = adjacency
         graph.position = cyclic_position(n)
         return graph

sknetwork/data/parse.py

@@ -14,13 +14,13 @@ from xml.etree import ElementTree
 import numpy as np
 from scipy import sparse
 
-from sknetwork.data.base import Bunch
+from sknetwork.data.base import Dataset
 from sknetwork.utils.format import directed2undirected
 
 
 def from_edge_list(edge_list: Union[np.ndarray, List[Tuple]], directed: bool = False,
                    bipartite: bool = False, weighted: bool = True, reindex: bool = False, shape: Optional[tuple] = None,
-                   sum_duplicates: bool = True, matrix_only: bool = None) -> Union[Bunch, sparse.csr_matrix]:
+                   sum_duplicates: bool = True, matrix_only: bool = None) -> Union[Dataset, sparse.csr_matrix]:
     """Load a graph from an edge list.
 
     Parameters
@@ -93,7 +93,7 @@ def from_edge_list(edge_list: Union[np.ndarray, List[Tuple]], directed: bool = F
 def from_adjacency_list(adjacency_list: Union[List[List], Dict[str, List]], directed: bool = False,
                         bipartite: bool = False, weighted: bool = True, reindex: bool = False,
                         shape: Optional[tuple] = None, sum_duplicates: bool = True, matrix_only: bool = None) \
-                        -> Union[Bunch, sparse.csr_matrix]:
+                        -> Union[Dataset, sparse.csr_matrix]:
     """Load a graph from an adjacency list.
 
     Parameters
@@ -147,7 +147,7 @@ def from_adjacency_list(adjacency_list: Union[List[List], Dict[str, List]], dire
 
 def from_edge_array(edge_array: np.ndarray, weights: np.ndarray = None, directed: bool = False, bipartite: bool = False,
                     weighted: bool = True, reindex: bool = False, shape: Optional[tuple] = None,
-                    sum_duplicates: bool = True, matrix_only: bool = None) -> Union[Bunch, sparse.csr_matrix]:
+                    sum_duplicates: bool = True, matrix_only: bool = None) -> Union[Dataset, sparse.csr_matrix]:
     """Load a graph from an edge array of shape (n_edges, 2) and weights (optional).
 
     Parameters
@@ -202,7 +202,7 @@ def from_edge_array(edge_array: np.ndarray, weights: np.ndarray = None, directed
         _, index = np.unique(edge_array, axis=0, return_index=True)
         edge_array = edge_array[index]
         weights = weights[index]
-    graph = Bunch()
+    graph = Dataset()
     if bipartite:
         row = edge_array[:, 0]
         col = edge_array[:, 1]
@@ -224,6 +224,7 @@ def from_edge_array(edge_array: np.ndarray, weights: np.ndarray = None, directed
         else:
             n_col = max(col) + 1
         matrix = sparse.csr_matrix((weights, (row, col)), shape=(n_row, n_col))
+        matrix.sum_duplicates()
         graph.biadjacency = matrix
     else:
         nodes = edge_array.ravel()
@@ -241,6 +242,7 @@ def from_edge_array(edge_array: np.ndarray, weights: np.ndarray = None, directed
         matrix = sparse.csr_matrix((weights, (row, col)), shape=(n, n))
         if not directed:
             matrix = directed2undirected(matrix)
+        matrix.sum_duplicates()
         graph.adjacency = matrix
     if matrix_only or (matrix_only is None and len(graph) == 1):
         return matrix
@@ -251,7 +253,7 @@ def from_edge_array(edge_array: np.ndarray, weights: np.ndarray = None, directed
 def from_csv(file_path: str, delimiter: str = None, sep: str = None, comments: str = '#%',
              data_structure: str = None, directed: bool = False, bipartite: bool = False, weighted: bool = True,
              reindex: bool = False, shape: Optional[tuple] = None, sum_duplicates: bool = True,
-             matrix_only: bool = None) -> Union[Bunch, sparse.csr_matrix]:
+             matrix_only: bool = None) -> Union[Dataset, sparse.csr_matrix]:
     """Load a graph from a CSV or TSV file.
     The delimiter can be specified (e.g., ' ' for space-separated values).
 
@@ -432,9 +434,9 @@ def load_header(file: str):
     return directed, bipartite, weighted
 
 
-def load_metadata(file: str, delimiter: str = ': ') -> Bunch:
+def load_metadata(file: str, delimiter: str = ': ') -> Dataset:
     """Extract metadata from the file."""
-    metadata = Bunch()
+    metadata = Dataset()
     with open(file, 'r', encoding='utf-8') as f:
         for row in f:
             parts = row.split(delimiter)
@@ -443,7 +445,7 @@ def load_metadata(file: str, delimiter: str = ': ') -> Bunch:
     return metadata
 
 
-def from_graphml(file_path: str, weight_key: str = 'weight', max_string_size: int = 512) -> Bunch:
+def from_graphml(file_path: str, weight_key: str = 'weight', max_string_size: int = 512) -> Dataset:
     """Load graph from GraphML file.
 
     Hyperedges and nested graphs are not supported.
@@ -459,7 +461,7 @@ def from_graphml(file_path: str, weight_key: str = 'weight', max_string_size: in
 
     Returns
     -------
-    data: :class:`Bunch`
+    data: :class:`Dataset`
         The dataset in a Dataset with the adjacency as a CSR matrix.
     """
     # see http://graphml.graphdrawing.org/primer/graphml-primer.html
@@ -475,12 +477,12 @@ def from_graphml(file_path: str, weight_key: str = 'weight', max_string_size: in
     # indices in the graph tree
     node_indices = []
     edge_indices = []
-    data = Bunch()
+    data = Dataset()
     graph = None
     file_description = None
-    attribute_descriptions = Bunch()
-    attribute_descriptions.node = Bunch()
-    attribute_descriptions.edge = Bunch()
+    attribute_descriptions = Dataset()
+    attribute_descriptions.node = Dataset()
+    attribute_descriptions.edge = Dataset()
     keys = {}
     for file_element in tree.getroot():
         if file_element.tag.endswith('graph'):
@@ -518,7 +520,7 @@ def from_graphml(file_path: str, weight_key: str = 'weight', max_string_size: in
                 if file_element.attrib['for'] == 'node':
                     size = n_nodes
                     if 'node_attribute' not in data:
-                        data.node_attribute = Bunch()
+                        data.node_attribute = Dataset()
                     for key_element in file_element:
                         if key_element.tag.endswith('desc'):
                             attribute_descriptions.node[attribute_name] = key_element.text
@@ -535,7 +537,7 @@ def from_graphml(file_path: str, weight_key: str = 'weight', max_string_size: in
                 elif file_element.attrib['for'] == 'edge':
                     size = n_edges
                     if 'edge_attribute' not in data:
-                        data.edge_attribute = Bunch()
+                        data.edge_attribute = Dataset()
                     for key_element in file_element:
                         if key_element.tag.endswith('desc'):
                             attribute_descriptions.edge[attribute_name] = key_element.text
@@ -553,7 +555,7 @@ def from_graphml(file_path: str, weight_key: str = 'weight', max_string_size: in
         elif file_element.tag.endswith('desc'):
             file_description = file_element.text
     if file_description or attribute_descriptions.node or attribute_descriptions.edge:
-        data.meta = Bunch()
+        data.meta = Dataset()
         if file_description:
             data.meta['description'] = file_description
         if attribute_descriptions.node or attribute_descriptions.edge:

sknetwork/data/tests/test_API.py

@@ -8,7 +8,7 @@ import warnings
 
 from sknetwork.data.load import *
 from sknetwork.data.toy_graphs import *
-from sknetwork.data import Bunch
+from sknetwork.data import Dataset
 
 
 class TestDataAPI(unittest.TestCase):
@@ -17,14 +17,14 @@ class TestDataAPI(unittest.TestCase):
         toy_graphs = [karate_club, painters, bow_tie, house, miserables]
         for toy_graph in toy_graphs:
             self.assertEqual(type(toy_graph()), sparse.csr_matrix)
-            self.assertEqual(type(toy_graph(metadata=True)), Bunch)
+            self.assertEqual(type(toy_graph(metadata=True)), Dataset)
 
     def test_load(self):
         tmp_data_dir = tempfile.gettempdir() + '/stub'
         clear_data_home(tmp_data_dir)
         try:
             graph = load_netset('stub', tmp_data_dir)
-            self.assertEqual(type(graph), Bunch)
+            self.assertEqual(type(graph), Dataset)
         except URLError:  # pragma: no cover
             warnings.warn('Could not reach NetSet. Corresponding test has not been performed.', RuntimeWarning)
             return

sknetwork/data/tests/test_base.py

@@ -3,12 +3,12 @@
 
 import unittest
 
-from sknetwork.data.base import Bunch
+from sknetwork.data.base import Dataset
 
 
 class TestDataset(unittest.TestCase):
 
     def test(self):
-        dataset = Bunch(name='dataset')
+        dataset = Dataset(name='dataset')
         self.assertEqual(dataset.name, 'dataset')
         self.assertEqual(dataset['name'], 'dataset')

sknetwork/data/tests/test_toy_graphs.py

@@ -16,22 +16,22 @@ class TestToys(unittest.TestCase):
         adjacency = house()
         self.assertEqual(adjacency.shape, (5, 5))
 
-        graph = house(metadata=True)
-        self.assertEqual(graph.position.shape, (5, 2))
+        dataset = house(metadata=True)
+        self.assertEqual(dataset.position.shape, (5, 2))
 
         adjacency = bow_tie()
         self.assertEqual(adjacency.shape, (5, 5))
 
-        graph = bow_tie(metadata=True)
-        self.assertEqual(graph.position.shape, (5, 2))
+        dataset = bow_tie(metadata=True)
+        self.assertEqual(dataset.position.shape, (5, 2))
 
-        graph = karate_club(True)
-        self.assertEqual(graph.adjacency.shape, (34, 34))
-        self.assertEqual(len(graph.labels), 34)
+        dataset = karate_club(True)
+        self.assertEqual(dataset.adjacency.shape, (34, 34))
+        self.assertEqual(len(dataset.labels), 34)
 
-        graph = miserables(True)
-        self.assertEqual(graph.adjacency.shape, (77, 77))
-        self.assertEqual(len(graph.names), 77)
+        dataset = miserables(True)
+        self.assertEqual(dataset.adjacency.shape, (77, 77))
+        self.assertEqual(len(dataset.names), 77)
 
     def test_directed(self):
         adjacency = painters()
@@ -40,29 +40,29 @@ class TestToys(unittest.TestCase):
         adjacency = art_philo_science()
         self.assertEqual(adjacency.shape, (30, 30))
 
-        graph = painters(True)
-        self.assertEqual(graph.adjacency.shape, (14, 14))
-        self.assertEqual(len(graph.names), 14)
+        dataset = painters(True)
+        self.assertEqual(dataset.adjacency.shape, (14, 14))
+        self.assertEqual(len(dataset.names), 14)
 
-        graph = art_philo_science(True)
-        self.assertEqual(graph.adjacency.shape, (30, 30))
-        self.assertEqual(len(graph.names), 30)
+        dataset = art_philo_science(True)
+        self.assertEqual(dataset.adjacency.shape, (30, 30))
+        self.assertEqual(len(dataset.names), 30)
 
     def test_bipartite(self):
-        graph = star_wars(True)
-        self.assertEqual(graph.biadjacency.shape, (4, 3))
-        self.assertEqual(len(graph.names), 4)
-        self.assertEqual(len(graph.names_col), 3)
-
-        graph = movie_actor(True)
-        self.assertEqual(graph.biadjacency.shape, (15, 16))
-        self.assertEqual(len(graph.names), 15)
-        self.assertEqual(len(graph.names_col), 16)
-
-        graph = hourglass(True)
-        self.assertEqual(graph.biadjacency.shape, (2, 2))
-
-        graph = art_philo_science(True)
-        self.assertEqual(graph.biadjacency.shape, (30, 11))
-        self.assertEqual(len(graph.names), 30)
-        self.assertEqual(len(graph.names_col), 11)
+        dataset = star_wars(True)
+        self.assertEqual(dataset.biadjacency.shape, (4, 3))
+        self.assertEqual(len(dataset.names), 4)
+        self.assertEqual(len(dataset.names_col), 3)
+
+        dataset = movie_actor(True)
+        self.assertEqual(dataset.biadjacency.shape, (15, 17))
+        self.assertEqual(len(dataset.names), 15)
+        self.assertEqual(len(dataset.names_col), 17)
+
+        dataset = hourglass(True)
+        self.assertEqual(dataset.biadjacency.shape, (2, 2))
+
+        dataset = art_philo_science(True)
+        self.assertEqual(dataset.biadjacency.shape, (30, 11))
+        self.assertEqual(len(dataset.names), 30)
+        self.assertEqual(len(dataset.names_col), 11)