add flickr and blog datasets, add dataset split functions

Author: yifanfeng97

dhg/data/__init__.py

@@ -7,12 +7,16 @@
 from .amazon import AmazonBook
 from .coauthorship import CoauthorshipCora, CoauthorshipDBLP
 from .cocitation import CocitationCora, CocitationCiteseer, CocitationPubmed
+from .blogcatalog import BlogCatalog
+from .flickr import Flickr
 
 __all__ = [
     "BaseData",
     "Cora",
     "Citeseer",
     "Pubmed",
+    "BlogCatalog",
+    "Flickr",
     "Cooking200",
     "MovieLens1M",
     "Yelp2018",

dhg/data/amazon.py

@@ -21,7 +21,7 @@ class AmazonBook(BaseData):
         The first item of each line in the ``adj_list`` is the user id, and the rest is the item id.
 
     Args:
-        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to None.
+        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to ``None``.
     """
 
     def __init__(self, data_root: Optional[str] = None) -> None:

dhg/data/blogcatalog.py

@@ -0,0 +1,53 @@
+from typing import Optional
+from functools import partial
+
+from dhg.datapipe import load_from_pickle, norm_ft, to_tensor, to_long_tensor, to_bool_tensor
+
+from .base import BaseData
+
+
+class BlogCatalog(BaseData):
+    r"""The BlogCatalog dataset is a social network dataset for vertex classification task. 
+    This is a network of social relationships of bloggers from the BlogCatalog website, 
+    where nodes' attributes are constructed by keywords, which are generated by users as a short description of their blogs. 
+    The labels represent the topic categories provided by the authors.
+    
+    .. note:: 
+        The L1-normalization for the feature is not recommended for this dataset.
+
+    The content of the BlogCatalog dataset includes the following:
+
+    - ``num_classes``: The number of classes: :math:`6`.
+    - ``num_vertices``: The number of vertices: :math:`5,196`.
+    - ``num_edges``: The number of edges: :math:`343,486`.
+    - ``dim_features``: The dimension of features: :math:`8,189`.
+    - ``features``: The vertex feature matrix. ``torch.Tensor`` with size :math:`(5,196 \times 8,189)`.
+    - ``edge_list``: The edge list. ``List`` with length :math:`(343,486 \times 2)`.
+    - ``labels``: The label list. ``torch.LongTensor`` with size :math:`(5,196, )`.
+
+    Args:
+        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to ``None``.
+    """
+
+    def __init__(self, data_root: Optional[str] = None) -> None:
+        super().__init__("BlogCatalog", data_root)
+        self._content = {
+            "num_classes": 6,
+            "num_vertices": 5196,
+            "num_edges": 171743,
+            "dim_features": 8189,
+            "features": {
+                "upon": [{"filename": "features.pkl", "md5": "ecdd26c63f483c4d919a156f9c8e92fc"}],
+                "loader": load_from_pickle,
+                "preprocess": [to_tensor],  # partial(norm_ft, ord=1)
+            },
+            "edge_list": {
+                "upon": [{"filename": "edge_list.pkl", "md5": "03ffbc8c9a4d9abeab0f127c717888f0"}],
+                "loader": load_from_pickle,
+            },
+            "labels": {
+                "upon": [{"filename": "labels.pkl", "md5": "246e7096dd834a631c33fe0c7afb89b4"}],
+                "loader": load_from_pickle,
+                "preprocess": [to_long_tensor],
+            },
+        }

dhg/data/coauthorship.py

@@ -24,7 +24,7 @@ class CoauthorshipCora(BaseData):
     - ``test_mask``: The test mask. ``torch.BoolTensor`` with size :math:`(2,708, )`.
 
     Args:
-        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to None.
+        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to ``None``.
     """
     def __init__(self, data_root: Optional[str] = None) -> None:
         super().__init__("coauthorship_cora", data_root)

dhg/data/cocitation.py

@@ -24,7 +24,7 @@ class CocitationCora(BaseData):
     - ``test_mask``: The test mask. ``torch.BoolTensor`` with size :math:`(2,708, )`.
 
     Args:
-        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to None.
+        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to ``None``.
     """
 
     def __init__(self, data_root: Optional[str] = None) -> None:
@@ -84,7 +84,7 @@ class CocitationCiteseer(BaseData):
     - ``test_mask``: The test mask. ``torch.BoolTensor`` with size :math:`(3,327, )`.
 
     Args:
-        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to None.
+        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to ``None``.
     """
 
     def __init__(self, data_root: Optional[str] = None) -> None:
@@ -144,7 +144,7 @@ class CocitationPubmed(BaseData):
     - ``test_mask``: The test mask. ``torch.BoolTensor`` with size :math:`(19,717, )`.
 
     Args:
-        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to None.
+        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to ``None``.
     """
 
     def __init__(self, data_root: Optional[str] = None) -> None:

dhg/data/cooking_200.py

@@ -26,7 +26,7 @@ class Cooking200(BaseData):
     - ``test_mask``: The test mask. ``torch.BoolTensor`` with size :math:`(7,403)`.
 
     Args:
-        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to None.
+        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to ``None``.
     """
 
     def __init__(self, data_root: Optional[str] = None) -> None:

dhg/data/flickr.py

@@ -0,0 +1,52 @@
+from typing import Optional
+from functools import partial
+
+from dhg.datapipe import load_from_pickle, norm_ft, to_tensor, to_long_tensor, to_bool_tensor
+
+from .base import BaseData
+
+
+class Flickr(BaseData):
+    r"""The Flickr dataset is a social network dataset for vertex classification task. 
+    It is a social network where nodes represent users and edges correspond to friendships among users. 
+    The labels represent the interest groups of the users.
+    
+    .. note:: 
+        The L1-normalization for the feature is not recommended for this dataset.
+
+    The content of the Flickr dataset includes the following:
+
+    - ``num_classes``: The number of classes: :math:`9`.
+    - ``num_vertices``: The number of vertices: :math:`7,575`.
+    - ``num_edges``: The number of edges: :math:`479,476`.
+    - ``dim_features``: The dimension of features: :math:`12,047`.
+    - ``features``: The vertex feature matrix. ``torch.Tensor`` with size :math:`(7,575 \times 12,047)`.
+    - ``edge_list``: The edge list. ``List`` with length :math:`(479,476 \times 2)`.
+    - ``labels``: The label list. ``torch.LongTensor`` with size :math:`(7,575, )`.
+
+    Args:
+        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to ``None``.
+    """
+
+    def __init__(self, data_root: Optional[str] = None) -> None:
+        super().__init__("Flickr", data_root)
+        self._content = {
+            "num_classes": 9,
+            "num_vertices": 7575,
+            "num_edges": 239738,
+            "dim_features": 12047,
+            "features": {
+                "upon": [{"filename": "features.pkl", "md5": "8e889c8532a91ddcb29d6a9c377b5528"}],
+                "loader": load_from_pickle,
+                "preprocess": [to_tensor],  # partial(norm_ft, ord=1)
+            },
+            "edge_list": {
+                "upon": [{"filename": "edge_list.pkl", "md5": "ea7412a30539fbc95f76ee3712a07017"}],
+                "loader": load_from_pickle,
+            },
+            "labels": {
+                "upon": [{"filename": "labels.pkl", "md5": "9603c29e31b863a34fc707b606c02880"}],
+                "loader": load_from_pickle,
+                "preprocess": [to_long_tensor],
+            },
+        }

dhg/data/gowalla.py

@@ -22,7 +22,7 @@ class Gowalla(BaseData):
         The first item of each line in the ``adj_list`` is the user id, and the rest is the item id.
 
     Args:
-        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to None.
+        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to ``None``.
     """
     def __init__(self, data_root: Optional[str] = None) -> None:
         super().__init__("gowalla", data_root)

dhg/data/movielens.py

@@ -22,7 +22,7 @@ class MovieLens1M(BaseData):
         The first item of each line in the ``adj_list`` is the user id, and the rest is the item id.
 
     Args:
-        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to None.
+        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to ``None``.
     """
     def __init__(self, data_root: Optional[str] = None) -> None:
         super().__init__("movielens_1m", data_root)

dhg/data/planetoid.py

@@ -23,7 +23,7 @@ class Cora(BaseData):
     - ``test_mask``: The test mask. ``torch.BoolTensor`` with size :math:`(2,708, )`.
 
     Args:
-        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to None.
+        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to ``None``.
     """
     def __init__(self, data_root: Optional[str] = None) -> None:
         super().__init__('cora', data_root)
@@ -79,7 +79,7 @@ class Citeseer(BaseData):
     - ``test_mask``: The test mask. ``torch.BoolTensor`` with size :math:`(3,327, )`.
 
     Args:
-        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to None.
+        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to ``None``.
     """
     def __init__(self, data_root: Optional[str] = None) -> None:
         super().__init__('citeseer', data_root)
@@ -135,7 +135,7 @@ class Pubmed(BaseData):
     - ``test_mask``: The test mask. ``torch.BoolTensor`` with size :math:`(19,717, )`.
 
     Args:
-        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to None.
+        ``data_root`` (``str``, optional): The ``data_root`` has stored the data. If set to ``None``, this function will auto-download from server and save into the default direction ``~/.dhg/datasets/``. Defaults to ``None``.
     """
     def __init__(self, data_root: Optional[str] = None) -> None:
         super().__init__('pubmed', data_root)