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

sknetwork/classification/propagation.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 # coding: utf-8
 """
-Created on April 2020
+Created in April 2020
 @author: Thomas Bonald <tbonald@enst.fr>
 """
 
@@ -12,7 +12,7 @@ from scipy import sparse
 
 from sknetwork.classification.base import BaseClassifier
 from sknetwork.classification.vote import vote_update
-from sknetwork.linalg.normalization import normalize
+from sknetwork.linalg.normalizer import normalize
 from sknetwork.utils.format import get_adjacency_values
 from sknetwork.utils.membership import get_membership
 
@@ -25,9 +25,9 @@ class Propagation(BaseClassifier):
     n_iter : float
         Maximum number of iterations (-1 for infinity).
     node_order : str
-        * `'random'`: node labels are updated in random order.
-        * `'increasing'`: node labels are updated by increasing order of (in-)weight.
-        * `'decreasing'`: node labels are updated by decreasing order of (in-)weight.
+        * ``'random'``: node labels are updated in random order.
+        * ``'increasing'``: node labels are updated by increasing order of (in-) weight.
+        * ``'decreasing'``: node labels are updated by decreasing order of (in-) weight.
         * Otherwise, node labels are updated by index order.
     weighted : bool
         If ``True``, the vote of each neighbor is proportional to the edge weight.
@@ -36,13 +36,17 @@ class Propagation(BaseClassifier):
     Attributes
     ----------
     labels_ : np.ndarray, shape (n_labels,)
-        Label of each node.
+        Labels of nodes.
     probs_ : sparse.csr_matrix, shape (n_row, n_labels)
         Probability distribution over labels.
-    labels_row_, labels_col_ : np.ndarray
-        Labels of rows and columns, for bipartite graphs.
-    probs_row_, probs_col_ : sparse.csr_matrix, shape (n_row, n_labels)
-        Probability distributions over labels for rows and columns (for bipartite graphs).
+    labels_row_ : np.ndarray
+        Labels of rows, for bipartite graphs.
+    labels_col_ : np.ndarray
+        Labels of columns, for bipartite graphs.
+    probs_row_ : sparse.csr_matrix, shape (n_row, n_labels)
+        Probability distributions over labels of rows, for bipartite graphs.
+    probs_col_ : sparse.csr_matrix, shape (n_col, n_labels)
+        Probability distributions over labels of columns, for bipartite graphs.
 
     Example
     -------
@@ -87,18 +91,22 @@ class Propagation(BaseClassifier):
             labels = labels[index_seed]
         return index_seed.astype(np.int32), index_remain.astype(np.int32), labels.astype(np.int32)
 
-    def fit(self, input_matrix: Union[sparse.csr_matrix, np.ndarray], labels: Union[np.ndarray, dict] = None,
-            labels_row: Union[np.ndarray, dict] = None, labels_col: Union[np.ndarray, dict] = None) -> 'Propagation':
+    def fit(self, input_matrix: Union[sparse.csr_matrix, np.ndarray], labels: Union[np.ndarray, list, dict] = None,
+            labels_row: Union[np.ndarray, list, dict] = None,
+            labels_col: Union[np.ndarray, list, dict] = None) -> 'Propagation':
         """Node classification by label propagation.
 
         Parameters
         ----------
-        input_matrix :
+        input_matrix : sparse.csr_matrix, np.ndarray
             Adjacency matrix or biadjacency matrix of the graph.
-        labels :
-            Known labels (dictionary or array). Negative values ignored.
-        labels_row, labels_col :
-            Known labels of rows and columns (for bipartite graphs).
+        labels : array, list or dict
+            Known labels. Negative values ignored.
+        labels_row : array, list or dict
+            Known labels of rows, for bipartite graphs.
+        labels_col : array, list or dict
+            Known labels of columns, for bipartite graphs.
+
         Returns
         -------
         self: :class:`Propagation`

sknetwork/classification/tests/test_diffusion.py

@@ -36,6 +36,7 @@ class TestDiffusionClassifier(unittest.TestCase):
         algo.fit(biadjacency, labels_row=labels_row, labels_col=labels_col)
         self.assertTrue(len(algo.labels_row_) == n_row)
         self.assertTrue(len(algo.labels_col_) == n_col)
+        self.assertTrue(all(algo.labels_col_ == algo.predict(columns=True)))
 
     def test_predict(self):
         adjacency = test_graph()
@@ -65,3 +66,12 @@ class TestDiffusionClassifier(unittest.TestCase):
         self.assertTrue(membership.shape == (n_row, 2))
         membership = algo.transform(columns=True)
         self.assertTrue(membership.shape == (n_col, 2))
+
+    def test_reindex_label(self):
+        adjacency = test_graph()
+        n_nodes = adjacency.shape[0]
+        labels = {0: 0, 1: 2, 2: 3}
+        algo = DiffusionClassifier()
+        labels_pred = algo.fit_predict(adjacency, labels=labels)
+        self.assertTrue(len(labels_pred) == n_nodes)
+        self.assertTrue(set(list(labels_pred)) == {0, 2, 3})