Rename Bunch as Dataset

sknetwork/clustering/leiden.py

@@ -76,7 +76,8 @@ class Leiden(Louvain):
     References
     ----------
     * Traag, V. A., Waltman, L., & Van Eck, N. J. (2019).
-     `From Louvain to Leiden: guaranteeing well-connected communities`, Scientific reports.
+      `From Louvain to Leiden: guaranteeing well-connected communities`, Scientific reports.
+
     """
 
     def __init__(self, resolution: float = 1, modularity: str = 'dugue', tol_optimization: float = 1e-3,

sknetwork/clustering/tests/test_kcenters.py

@@ -4,7 +4,6 @@
 import unittest
 
 from sknetwork.clustering import KCenters
-from sknetwork.data import karate_club, painters, star_wars
 from sknetwork.data.test_graphs import *
 
 
@@ -13,7 +12,7 @@ class TestKCentersClustering(unittest.TestCase):
     def test_kcenters(self):
         # Test undirected graph
         n_clusters = 2
-        adjacency = karate_club()
+        adjacency = test_graph()
         n_row = adjacency.shape[0]
         kcenters = KCenters(n_clusters=n_clusters)
         labels = kcenters.fit_predict(adjacency)
@@ -22,7 +21,7 @@ def test_kcenters(self):
 
         # Test directed graph
         n_clusters = 3
-        adjacency = painters()
+        adjacency = test_digraph()
         n_row = adjacency.shape[0]
         kcenters = KCenters(n_clusters=n_clusters, directed=True)
         labels = kcenters.fit_predict(adjacency)
@@ -31,7 +30,7 @@ def test_kcenters(self):
 
         # Test bipartite graph
         n_clusters = 2
-        biadjacency = star_wars()
+        biadjacency = test_bigraph()
         n_row, n_col = biadjacency.shape
         kcenters = KCenters(n_clusters=n_clusters)
         kcenters.fit(biadjacency)
@@ -40,41 +39,10 @@ def test_kcenters(self):
         self.assertEqual(len(kcenters.labels_col_), n_col)
         self.assertEqual(len(set(labels)), n_clusters)
 
-    def test_kcenters_centers(self):
-        # Test centers for undirected graphs
-        n_clusters = 2
-        adjacency = karate_club()
-        kcenters = KCenters(n_clusters=n_clusters)
-        kcenters.fit(adjacency)
-        centers = kcenters.centers_
-        self.assertEqual(n_clusters, len(set(centers)))
-
-        # Test centers for bipartite graphs
-        n_clusters = 2
-        biadjacency = star_wars()
-        n_row, n_col = biadjacency.shape
-        for position in ["row", "col", "both"]:
-            kcenters = KCenters(n_clusters=n_clusters, center_position=position)
-            kcenters.fit(biadjacency)
-            centers_row = kcenters.centers_row_
-            centers_col = kcenters.centers_col_
-            if position == "row":
-                self.assertEqual(n_clusters, len(set(centers_row)))
-                self.assertTrue(np.all(centers_row < n_row))
-                self.assertTrue(centers_col is None)
-            if position == "col":
-                self.assertEqual(n_clusters, len(set(centers_col)))
-                self.assertTrue(np.all((centers_col < n_col) & (0 <= centers_col)))
-                self.assertTrue(centers_row is None)
-            if position == "both":
-                self.assertEqual(n_clusters, len(set(centers_row)) + len(set(centers_col)))
-                self.assertTrue(np.all(centers_row < n_row))
-                self.assertTrue(np.all((centers_col < n_col) & (0 <= centers_col)))
-
     def test_kcenters_error(self):
         # Test value errors
-        adjacency = karate_club()
-        biadjacency = star_wars()
+        adjacency = test_graph()
+        biadjacency = test_bigraph()
 
         # test n_clusters error
         kcenters = KCenters(n_clusters=1)

sknetwork/data/__init__.py

@@ -1,5 +1,5 @@
 """data module"""
-from sknetwork.data.base import Bunch
+from sknetwork.data.base import *
 from sknetwork.data.load import *
 from sknetwork.data.models import *
 from sknetwork.data.parse import from_edge_list, from_adjacency_list, from_csv, from_graphml

sknetwork/data/base.py

@@ -6,10 +6,10 @@
 """
 
 
-class Bunch(dict):
+class Dataset(dict):
     """Container object for datasets.
     Dictionary-like object that exposes its keys as attributes.
-    >>> dataset = Bunch(name='dataset')
+    >>> dataset = Dataset(name='dataset')
     >>> dataset['name']
     'dataset'
     >>> dataset.name
@@ -26,3 +26,8 @@ def __getattr__(self, key):
             return self[key]
         except KeyError:
             raise AttributeError(key)
+
+
+# alias for Dataset
+Bunch = Dataset
+

sknetwork/data/load.py

@@ -19,15 +19,12 @@
 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('.')
@@ -340,21 +337,21 @@ 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.
 
     Parameters
     ----------
     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)