[Doc] Hidden implementations that may cause confusion to the user. (#2378)

* PPIDataset

* Revert "PPIDataset"

This reverts commit 264bd0c960cfa698a7bb946dad132bf52c2d0c8a.

* data pipeline user guide

* remove chapter numbers

* Update data.rst

* image in dataset userguide

* update links using ref

* modify the link of save_graphs and load_graphs in dataset user guide

* move image to s3 server.

* fix links and ref

* Hide implementations that may cause confusions to the user

docs/source/guide/data-process.rst

@@ -143,7 +143,7 @@ builtin dataset `CitationGraphDataset <https://docs.dgl.ai/en/0.5.x/_modules/dgl
 .. code:: 
 
     from dgl.data import DGLBuiltinDataset
-    from dgl.data.utils import _get_dgl_url, generate_mask_tensor
+    from dgl.data.utils import _get_dgl_url
     
     class CitationGraphDataset(DGLBuiltinDataset):
         _urls = {
@@ -170,9 +170,9 @@ builtin dataset `CitationGraphDataset <https://docs.dgl.ai/en/0.5.x/_modules/dgl
             # build graph
             g = dgl.graph(graph)
             # splitting masks
-            g.ndata['train_mask'] = generate_mask_tensor(train_mask)
-            g.ndata['val_mask'] = generate_mask_tensor(val_mask)
-            g.ndata['test_mask'] = generate_mask_tensor(test_mask)
+            g.ndata['train_mask'] = train_mask
+            g.ndata['val_mask'] = val_mask
+            g.ndata['test_mask'] = test_mask
             # node labels
             g.ndata['label'] = torch.tensor(labels)
             # node features

docs/source/guide_cn/data-process.rst

@@ -126,7 +126,7 @@ DGL建议使用节点掩码来指定数据集的划分。
 .. code::
 
     from dgl.data import DGLBuiltinDataset
-    from dgl.data.utils import _get_dgl_url, generate_mask_tensor
+    from dgl.data.utils import _get_dgl_url
     
     class CitationGraphDataset(DGLBuiltinDataset):
         _urls = {
@@ -154,9 +154,9 @@ DGL建议使用节点掩码来指定数据集的划分。
             g = dgl.graph(graph)
 
             # 划分掩码
-            g.ndata['train_mask'] = generate_mask_tensor(train_mask)
-            g.ndata['val_mask'] = generate_mask_tensor(val_mask)
-            g.ndata['test_mask'] = generate_mask_tensor(test_mask)
+            g.ndata['train_mask'] = train_mask
+            g.ndata['val_mask'] = val_mask
+            g.ndata['test_mask'] = test_mask
 
             # 节点的标签
             g.ndata['label'] = torch.tensor(labels)

python/dgl/data/citation_graph.py

@@ -114,16 +114,16 @@ class CitationGraphDataset(DGLBuiltinDataset):
         idx_train = range(len(y))
         idx_val = range(len(y), len(y)+500)
 
-        train_mask = _sample_mask(idx_train, labels.shape[0])
-        val_mask = _sample_mask(idx_val, labels.shape[0])
-        test_mask = _sample_mask(idx_test, labels.shape[0])
+        train_mask = generate_mask_tensor(_sample_mask(idx_train, labels.shape[0]))
+        val_mask = generate_mask_tensor(_sample_mask(idx_val, labels.shape[0]))
+        test_mask = generate_mask_tensor(_sample_mask(idx_test, labels.shape[0]))
 
         self._graph = graph
         g = from_networkx(graph)
 
-        g.ndata['train_mask'] = generate_mask_tensor(train_mask)
-        g.ndata['val_mask'] = generate_mask_tensor(val_mask)
-        g.ndata['test_mask'] = generate_mask_tensor(test_mask)
+        g.ndata['train_mask'] = train_mask
+        g.ndata['val_mask'] = val_mask
+        g.ndata['test_mask'] = test_mask
         g.ndata['label'] = F.tensor(labels)
         g.ndata['feat'] = F.tensor(_preprocess_features(features), dtype=F.data_type_dict['float32'])
         self._num_classes = onehot_labels.shape[1]