scikit-network 0.31.0__cp39-cp39-win_amd64.whl → 0.33.0__cp39-cp39-win_amd64.whl

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

@@ -8,19 +8,19 @@ Created in December 2018
 """
 
 from csv import reader
-from typing import Dict, List, Tuple, Union
+from typing import Dict, List, Tuple, Union, Optional
 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 = True,
-                   sum_duplicates: bool = True, matrix_only: bool = None) -> Union[Bunch, sparse.csr_matrix]:
+                   bipartite: bool = False, weighted: bool = True, reindex: bool = False, shape: Optional[tuple] = None,
+                   sum_duplicates: bool = True, matrix_only: bool = None) -> Union[Dataset, sparse.csr_matrix]:
     """Load a graph from an edge list.
 
     Parameters
@@ -37,6 +37,9 @@ def from_edge_list(edge_list: Union[np.ndarray, List[Tuple]], directed: bool = F
     reindex : bool
         If ``True``, reindex nodes and returns the original node indices as names.
         Reindexing is enforced if nodes are not integers.
+    shape : tuple
+        Shape of the adjacency or biadjacency matrix.
+        If not specified or if nodes are reindexed, the shape is the smallest compatible with node indices.
     sum_duplicates : bool
         If ``True`` (default), sums weights of duplicate edges.
         Otherwise, the weight of each edge is that of the first occurrence of this edge.
@@ -83,12 +86,14 @@ def from_edge_list(edge_list: Union[np.ndarray, List[Tuple]], directed: bool = F
     else:
         raise TypeError('The edge list must be given as a NumPy array or a list of tuples.')
     return from_edge_array(edge_array=edge_array, weights=weights, directed=directed, bipartite=bipartite,
-                           weighted=weighted, reindex=reindex, sum_duplicates=sum_duplicates, matrix_only=matrix_only)
+                           weighted=weighted, reindex=reindex, shape=shape, sum_duplicates=sum_duplicates,
+                           matrix_only=matrix_only)
 
 
 def from_adjacency_list(adjacency_list: Union[List[List], Dict[str, List]], directed: bool = False,
-                        bipartite: bool = False, weighted: bool = True, reindex: bool = True,
-                        sum_duplicates: bool = True, matrix_only: bool = None) -> Union[Bunch, sparse.csr_matrix]:
+                        bipartite: bool = False, weighted: bool = True, reindex: bool = False,
+                        shape: Optional[tuple] = None, sum_duplicates: bool = True, matrix_only: bool = None) \
+                        -> Union[Dataset, sparse.csr_matrix]:
     """Load a graph from an adjacency list.
 
     Parameters
@@ -104,6 +109,9 @@ def from_adjacency_list(adjacency_list: Union[List[List], Dict[str, List]], dire
     reindex : bool
         If ``True``, reindex nodes and returns the original node indices as names.
         Reindexing is enforced if nodes are not integers.
+    shape : tuple
+        Shape of the adjacency or biadjacency matrix.
+        If not specified or if nodes are reindexed, the shape is the smallest compatible with node indices.
     sum_duplicates : bool
         If ``True`` (default), sums weights of duplicate edges.
         Otherwise, the weight of each edge is that of the first occurrence of this edge.
@@ -134,12 +142,12 @@ def from_adjacency_list(adjacency_list: Union[List[List], Dict[str, List]], dire
     else:
         raise TypeError('The adjacency list must be given as a list of lists or a dict of lists.')
     return from_edge_list(edge_list=edge_list, directed=directed, bipartite=bipartite, weighted=weighted,
-                          reindex=reindex, sum_duplicates=sum_duplicates, matrix_only=matrix_only)
+                          reindex=reindex, shape=shape, sum_duplicates=sum_duplicates, matrix_only=matrix_only)
 
 
 def from_edge_array(edge_array: np.ndarray, weights: np.ndarray = None, directed: bool = False, bipartite: bool = False,
-                    weighted: bool = True, reindex: bool = True, sum_duplicates: bool = True,
-                    matrix_only: bool = None) -> Union[Bunch, sparse.csr_matrix]:
+                    weighted: bool = True, reindex: bool = False, shape: Optional[tuple] = None,
+                    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
@@ -157,6 +165,9 @@ def from_edge_array(edge_array: np.ndarray, weights: np.ndarray = None, directed
     reindex : bool
         If ``True``, reindex nodes and returns the original node indices as names.
         Reindexing is enforced if nodes are not integers.
+    shape : tuple
+        Shape of the adjacency or biadjacency matrix.
+        If not specified or if nodes are reindexed, the shape is the smallest compatible with node indices.
     sum_duplicates : bool
         If ``True`` (default), sums weights of duplicate edges.
         Otherwise, the weight of each edge is that of the first occurrence of this edge.
@@ -191,32 +202,39 @@ 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]
-        if row.dtype != int or (reindex and len(set(row)) < max(row) + 1):
+        if row.dtype != int or reindex:
             names_row, row = np.unique(row, return_inverse=True)
             graph.names_row = names_row
             graph.names = names_row
             n_row = len(names_row)
+        elif shape is not None:
+            n_row = max(shape[0], max(row) + 1)
         else:
             n_row = max(row) + 1
-        if col.dtype != int or (reindex and len(set(col)) < max(col) + 1):
+        if col.dtype != int or reindex:
             names_col, col = np.unique(col, return_inverse=True)
             graph.names_col = names_col
             n_col = len(names_col)
+        elif shape is not None:
+            n_col = max(shape[1], max(col) + 1)
         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()
-        if nodes.dtype != int or (reindex and len(set(nodes)) < max(nodes) + 1):
+        if nodes.dtype != int or reindex:
             names, nodes = np.unique(nodes, return_inverse=True)
             graph.names = names
             n = len(names)
             edge_array = nodes.reshape(-1, 2)
+        elif shape is not None:
+            n = max(shape[0], max(nodes) + 1)
         else:
             n = max(nodes) + 1
         row = edge_array[:, 0]
@@ -224,6 +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
@@ -233,8 +252,8 @@ 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 = True, sum_duplicates: bool = True, matrix_only: bool = None) \
-        -> Union[Bunch, sparse.csr_matrix]:
+             reindex: bool = False, shape: Optional[tuple] = None, sum_duplicates: bool = True,
+             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).
 
@@ -249,9 +268,10 @@ def from_csv(file_path: str, delimiter: str = None, sep: str = None, comments: s
     comments : str
         Characters for comment lines.
     data_structure : str
-        If 'edge_list', considers each row of the file as an edge (tuple of size 2 or 3).
-        If 'adjacency_list', considers each row of the file as an adjacency list (list of neighbors).
-        If 'adjacency_dict', considers each row of the file as an adjacency dictionary with key
+        If 'edge_list', consider each row of the file as an edge (tuple of size 2 or 3).
+        If 'adjacency_list', consider each row of the file as an adjacency list (list of neighbors,
+        in the order of node indices; an empty line means no neighbor).
+        If 'adjacency_dict', consider each row of the file as an adjacency dictionary with key
         given by the first column (node: list of neighbors).
         If ``None`` (default), data_structure is guessed from the first rows of the file.
     directed : bool
@@ -263,6 +283,9 @@ def from_csv(file_path: str, delimiter: str = None, sep: str = None, comments: s
     reindex : bool
         If ``True``, reindex nodes and returns the original node indices as names.
         Reindexing is enforced if nodes are not integers.
+    shape : tuple
+        Shape of the adjacency or biadjacency matrix.
+        If not specified or if nodes are reindexed, the shape is the smallest compatible with node indices.
     sum_duplicates : bool
         If ``True`` (default), sums weights of duplicate edges.
         Otherwise, the weight of each edge is that of the first occurrence of this edge.
@@ -295,7 +318,7 @@ def from_csv(file_path: str, delimiter: str = None, sep: str = None, comments: s
             else:
                 weights = None
             return from_edge_array(edge_array=edge_array, weights=weights, directed=directed, bipartite=bipartite,
-                                   weighted=weighted, reindex=reindex, sum_duplicates=sum_duplicates,
+                                   weighted=weighted, reindex=reindex, shape=shape, sum_duplicates=sum_duplicates,
                                    matrix_only=matrix_only)
         except TypeError:
             pass
@@ -306,17 +329,17 @@ def from_csv(file_path: str, delimiter: str = None, sep: str = None, comments: s
         if data_structure == 'edge_list':
             edge_list = [tuple(row) for row in csv_reader]
             return from_edge_list(edge_list=edge_list, directed=directed, bipartite=bipartite,
-                                  weighted=weighted, reindex=reindex, sum_duplicates=sum_duplicates,
+                                  weighted=weighted, reindex=reindex, shape=shape, sum_duplicates=sum_duplicates,
                                   matrix_only=matrix_only)
         elif data_structure == 'adjacency_list':
             adjacency_list = [row for row in csv_reader]
             return from_adjacency_list(adjacency_list=adjacency_list, directed=directed, bipartite=bipartite,
-                                       weighted=weighted, reindex=reindex, sum_duplicates=sum_duplicates,
+                                       weighted=weighted, reindex=reindex, shape=shape, sum_duplicates=sum_duplicates,
                                        matrix_only=matrix_only)
         elif data_structure == 'adjacency_dict':
             adjacency_list = {row[0]: row[1:] for row in csv_reader}
             return from_adjacency_list(adjacency_list=adjacency_list, directed=directed, bipartite=bipartite,
-                                       weighted=weighted, reindex=reindex, sum_duplicates=sum_duplicates,
+                                       weighted=weighted, reindex=reindex, shape=shape, sum_duplicates=sum_duplicates,
                                        matrix_only=matrix_only)
 
 
@@ -411,9 +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)
@@ -422,7 +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.
@@ -438,7 +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
@@ -454,12 +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'):
@@ -497,7 +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
@@ -514,7 +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
@@ -532,7 +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_parse.py

@@ -20,6 +20,10 @@ class TestParser(unittest.TestCase):
         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())
+        adjacency = parse.from_csv(self.stub_data_1, shape=(7, 7))
+        self.assertTrue((adjacency.shape == (7, 7)))
+        biadjacency = parse.from_csv(self.stub_data_1, bipartite=True, shape=(7, 9))
+        self.assertTrue((biadjacency.shape == (7, 9)))
         remove(self.stub_data_1)
 
     def test_labeled_weighted(self):
@@ -33,13 +37,14 @@ class TestParser(unittest.TestCase):
         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 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.from_csv(self.stub_data_4)
+        graph = parse.from_csv(self.stub_data_4, reindex=True)
         adjacency = graph.adjacency
         names = graph.names
         self.assertTrue((adjacency.data == [1, 1, 1, 1, 1, 1]).all())
@@ -164,23 +169,15 @@ class TestParser(unittest.TestCase):
         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.from_csv(self.stub_data_9, bipartite=True)
+        graph = parse.from_csv(self.stub_data_9, bipartite=True, reindex=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())
+        biadjacency = parse.from_csv(self.stub_data_9, bipartite=True)
+        self.assertTrue(biadjacency.shape == (5, 6))
         remove(self.stub_data_9)
 
-    def test_csv_adjacency_bipartite(self):
-        self.stub_data_10 = 'stub_10.txt'
-        with open(self.stub_data_10, "w") as text_file:
-            text_file.write('%stub\n3\n3\n0')
-        graph = parse.from_csv(self.stub_data_10, bipartite=True)
-        biadjacency = graph.biadjacency
-        self.assertTupleEqual(biadjacency.shape, (3, 2))
-        self.assertTrue((biadjacency.data == [1, 1, 1]).all())
-        remove(self.stub_data_10)
-
     def test_edge_list(self):
         edge_list_1 = [('Alice', 'Bob'), ('Carol', 'Alice')]
         graph = parse.from_edge_list(edge_list_1)

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)