[Dataset & Transform] Synthetic Datasets for Explainability and SIGND…

…iffusion Transform (dmlc#3982) * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Update * Fix * Update * Update * Update
anirband · May 16, 2022 · 65b0b9e · 65b0b9e
1 parent 03024f9
commit 65b0b9e
Show file tree

Hide file tree

Showing 8 changed files with 1,088 additions and 9 deletions.
diff --git a/docs/source/api/python/dgl.data.rst b/docs/source/api/python/dgl.data.rst
@@ -47,6 +47,11 @@ Datasets for node classification/regression tasks
     FraudDataset
     FraudYelpDataset
     FraudAmazonDataset
+    BAShapeDataset
+    BACommunityDataset
+    TreeCycleDataset
+    TreeGridDataset
+    BA2MotifDataset
 
 Edge Prediction Datasets
 ---------------------------------------

diff --git a/docs/source/api/python/transforms.rst b/docs/source/api/python/transforms.rst
@@ -32,3 +32,4 @@ dgl.transforms
     LaplacianPE
     FeatMask
     RowFeatNormalizer
+    SIGNDiffusion
diff --git a/python/dgl/data/__init__.py b/python/dgl/data/__init__.py
@@ -31,6 +31,7 @@
 from .fakenews import FakeNewsDataset
 from .csv_dataset import CSVDataset
 from .adapter import AsNodePredDataset, AsLinkPredDataset
+from .synthetic import BAShapeDataset, BACommunityDataset, TreeCycleDataset, TreeGridDataset, BA2MotifDataset
 
 def register_data_args(parser):
     parser.add_argument(

diff --git a/python/dgl/data/dgl_dataset.py b/python/dgl/data/dgl_dataset.py
@@ -17,7 +17,7 @@ class DGLDataset(object):
       1. Check whether there is a dataset cache on disk
          (already processed and stored on the disk) by
          invoking ``has_cache()``. If true, goto 5.
-      2. Call ``download()`` to download the data.
+      2. Call ``download()`` to download the data if ``url`` is not None.
       3. Call ``process()`` to process the data.
       4. Call ``save()`` to save the processed dataset on disk and goto 6.
       5. Call ``load()`` to load the processed dataset from disk.
@@ -31,7 +31,7 @@ class DGLDataset(object):
     name : str
         Name of the dataset
     url : str
-        Url to download the raw dataset
+        Url to download the raw dataset. Default: None
     raw_dir : str
         Specifying the directory that will store the
         downloaded data or the directory that
@@ -313,6 +313,7 @@ def __init__(self, name, url, raw_dir=None, hash_key=(),
     def download(self):
         r""" Automatically download data and extract it.
         """
-        zip_file_path = os.path.join(self.raw_dir, self.name + '.zip')
-        download(self.url, path=zip_file_path)
-        extract_archive(zip_file_path, self.raw_path)
+        if self.url is not None:
+            zip_file_path = os.path.join(self.raw_dir, self.name + '.zip')
+            download(self.url, path=zip_file_path)
+            extract_archive(zip_file_path, self.raw_path)