21 Sep 13:57

c95e749

GraphGallery 1.0.0 Latest

Latest

GraphGallery 1.0.0

GraphGallery is a gallery for benchmarking Graph Neural Networks (GNNs) and Graph Adversarial Learning with TensorFlow 2.x and PyTorch backend. Besides, Pytorch Geometric (PyG) backend and Deep Graph Library (DGL) backend now are available in GraphGallery.

Usages

read a graph dataset

import graphgallery as gg
data = gg.datasets.Planetoid('cora', root="~/GraphData/datasets", verbose=None)
graph = data.graph
splits = data.split_nodes()

run a simple GCN model for node classification task

from graphgallery.gallery.nodeclas import GCN
trainer = GCN()
trainer.setup_graph(graph)
trainer.build()
history = trainer.fit(train_nodes, val_nodes, epochs=100, verbose=1)
results = trainer.evaluate(test_nodes)
print(f'Test loss {results.loss:.5}, Test accuracy {results.accuracy:.2%}')

If you have any troubles, you can simply run trainer.help() for more messages, and it would print


**************************************Help Message for GCN******************************************
|First, initialize a trainer object, run `trainer=GCN(device='cpu', seed=42)                  |
------------------------------------------------------------------------------------------------------------
|Second, setup a graph, run `trainer.setup_graph()`, the reqiured argument are:                      |
(1) `graph`, UNSPECIDIED position argument
(2) `graph_transform`, Default is `None` 
(3) `device`, Default is `None` 
(4) `adj_transform`, Default is `normalize_adj` 
(5) `attr_transform`, Default is `None` 

------------------------------------------------------------------------------------------------------------
|Third, build your model, run `trainer.build()`, the reqiured argument are:                          |
(1) `hids`, Default is `[16]` 
(2) `acts`, Default is `['relu']` 
(3) `dropout`, Default is `0.5` 
(4) `weight_decay`, Default is `0.0005` 
(5) `lr`, Default is `0.01` 
(6) `bias`, Default is `False` 
 
------------------------------------------------------------------------------------------------------------
|Fourth, train your model, run `trainer.fit()`, the reqiured argument are:                           |
(1) `train_data`, UNSPECIDIED position argument
(2) `val_data`, Default is `None` 
 
------------------------------------------------------------------------------------------------------------
|Finally and optionally, evaluate your model, run `trainer.evaluate()`, the reqiured argument are:   |
(1) `test_data`, UNSPECIDIED position argument
 
------------------------------------------------------------------------------------------------------------

The default backend module is PyTorch, you can switch to others:

>>> import graphgallery
# Default: PyTorch backend
>>> graphgallery.backend()
PyTorch 1.7.0cu101 Backend
# Switch to TensorFlow backend
>>> graphgallery.set_backend("tf")
# Switch to PyTorch backend
>>> graphgallery.set_backend("th")
# Switch to PyTorch Geometric backend
>>> graphgallery.set_backend("pyg")
# Switch to DGL PyTorch backend
>>> graphgallery.set_backend("dgl")

But your codes don't even need to change, for example:

from graphgallery.gallery.nodeclas import GCN
# this line of code imports GCN written by PyTorch by default
# but if you switch to other backend such as tensorflow, it imports GCN written by TensorFlow as well
# and the following codes for training or testing don't even need to change.

Note, not all models are implemented by four backends (PyTorch, TensorFlow, PyG and DGL),
just run

>>> from graphgallery.gallery.nodeclas import models
>>> models()
# you will get a dict of implanted models here

For more examples, please refer to examples

Assets 2

20 Jan 16:42

EdisonLeeeee

0.7.2

6d88146

GraphGallery 0.7.2

V0.7.2

Assets 2

15 Dec 01:35

EdisonLeeeee

0.6.0

4583af1

GraphGallery 0.6.0

update README

Assets 2

06 Nov 10:44

EdisonLeeeee

0.5.0

236e4ac

GraphGallery 0.5.0

update

Assets 2

22 Oct 08:12

EdisonLeeeee

0.4.2

72cd50d

GraphGallery 0.4.2

New features

Strided (dense) Tensor

>>> backend()
TensorFlow 2.1.2 Backend

>>> from graphgallery import transforms as T
>>> arr = [1, 2, 3]
>>> T.astensor(arr)
<tf.Tensor: shape=(3,), dtype=int32, numpy=array([1, 2, 3], dtype=int32)>

Sparse Tensor

>>> import scipy.sparse as sp
>>> sp_matrix = sp.eye(3)
>>> T.astensor(sp_matrix)
<tensorflow.python.framework.sparse_tensor.SparseTensor at 0x7f1bbc205dd8>

also works for PyTorch, just like

>>> from graphgallery import set_backend
>>> set_backend('torch') # torch, pytorch or th
PyTorch 1.6.0+cu101 Backend

>>> T.astensor(arr)
tensor([1, 2, 3])

>>> T.astensor(sp_matrix)
tensor(indices=tensor([[0, 1, 2],
                       [0, 1, 2]]),
       values=tensor([1., 1., 1.]),
       size=(3, 3), nnz=3, layout=torch.sparse_coo)

To Numpy or Scipy sparse matrix

>>> tensor = T.astensor(arr)
>>> T.tensoras(tensor)
array([1, 2, 3])

>>> sp_tensor = T.astensor(sp_matrix)
>>> T.tensoras(sp_tensor)
<3x3 sparse matrix of type '<class 'numpy.float32'>'
    with 3 stored elements in Compressed Sparse Row format>

Or even convert one Tensor to another one

>>> tensor = T.astensor(arr, kind="T")
>>> tensor
<tf.Tensor: shape=(3,), dtype=int64, numpy=array([1, 2, 3])>
>>> T.tensor2tensor(tensor)
tensor([1, 2, 3])

>>> sp_tensor = T.astensor(sp_matrix, kind="T") # set kind="T" to convert to tensorflow tensor
>>> sp_tensor
<tensorflow.python.framework.sparse_tensor.SparseTensor at 0x7efb6836a898>
>>> T.tensor2tensor(sp_tensor)
tensor(indices=tensor([[0, 1, 2],
                       [0, 1, 2]]),
       values=tensor([1., 1., 1.]),
       size=(3, 3), nnz=3, layout=torch.sparse_coo)

Assets 2

07 Oct 07:36

EdisonLeeeee

0.4.1

5f628bf

GraphGallery 0.4.1

New features

Strided (dense) Tensor

>>> backend()
TensorFlow 2.1.2 Backend

>>> from graphgallery import transforms as T
>>> arr = [1, 2, 3]
>>> T.astensor(arr)
<tf.Tensor: shape=(3,), dtype=int32, numpy=array([1, 2, 3], dtype=int32)>

Sparse Tensor

>>> import scipy.sparse as sp
>>> sp_matrix = sp.eye(3)
>>> T.astensor(sp_matrix)
<tensorflow.python.framework.sparse_tensor.SparseTensor at 0x7f1bbc205dd8>

also works for PyTorch, just like

>>> from graphgallery import set_backend
>>> set_backend('torch') # torch, pytorch or th
PyTorch 1.6.0+cu101 Backend

>>> T.astensor(arr)
tensor([1, 2, 3])

>>> T.astensor(sp_matrix)
tensor(indices=tensor([[0, 1, 2],
                       [0, 1, 2]]),
       values=tensor([1., 1., 1.]),
       size=(3, 3), nnz=3, layout=torch.sparse_coo)

To Numpy or Scipy sparse matrix

>>> tensor = T.astensor(arr)
>>> T.tensoras(tensor)
array([1, 2, 3])

>>> sp_tensor = T.astensor(sp_matrix)
>>> T.tensoras(sp_tensor)
<3x3 sparse matrix of type '<class 'numpy.float32'>'
    with 3 stored elements in Compressed Sparse Row format>

Or even convert one Tensor to another one

>>> tensor = T.astensor(arr, kind="T")
>>> tensor
<tf.Tensor: shape=(3,), dtype=int64, numpy=array([1, 2, 3])>
>>> T.tensor2tensor(tensor)
tensor([1, 2, 3])

>>> sp_tensor = T.astensor(sp_matrix, kind="T") # set kind="T" to convert to tensorflow tensor
>>> sp_tensor
<tensorflow.python.framework.sparse_tensor.SparseTensor at 0x7efb6836a898>
>>> T.tensor2tensor(sp_tensor)
tensor(indices=tensor([[0, 1, 2],
                       [0, 1, 2]]),
       values=tensor([1., 1., 1.]),
       size=(3, 3), nnz=3, layout=torch.sparse_coo)

Assets 2

03 Oct 06:34

EdisonLeeeee

0.4.0

de79b65

GraphGallery 0.4.0

update README

Assets 2

24 Sep 07:23

EdisonLeeeee

0.3.0

598c923

GraphGallery 0.3.0

read the dataset

from graphgallery.data import Planetoid, NPZDataset;
data = Planetoid('cora', root="~/GraphData/datasets/", verbose=False);
graph = data.graph
idx_train, idx_val, idx_test = data.split()

>>> graph
Graph(adj_matrix(2708, 2708), attr_matrix(2708, 2708), labels(2708,))

Add TensorFlow and PyTorch support

Using TensorFlow

graphgallery.set_backend("tensorflow")

from graphgallery.nn.models import GCN
model = GCN(graph, attr_transformer="normalize_attr", device="GPU", seed=123);
model.build()
his = model.train(idx_train, idx_val, verbose=1, epochs=100)
loss, accuracy = model.test(idx_test)
print(f'Test loss {loss:.5}, Test accuracy {accuracy:.2%}')

Using PyTorch

graphgallery.set_backend("pytorch")

# the following codes are the same!
from graphgallery.nn.models import GCN
model = GCN(graph, attr_transformer="normalize_attr", device="GPU", seed=123);
model.build()
his = model.train(idx_train, idx_val, verbose=1, epochs=100)
loss, accuracy = model.test(idx_test)
print(f'Test loss {loss:.5}, Test accuracy {accuracy:.2%}')

Assets 2

26 Aug 12:54

EdisonLeeeee

0.2.0

4803b5a

GraphGallery 0.2.0

Changelogs

update docstrings
rewrite dataset API
you can load the dataset like

from graphgallery.data import Planetoid, NPZDataset
data = Planetoid('cora',, verbose=True)
# data = NPZDataset('cora', verbose=True)
adj, x, labels = data.graph.unpack()
idx_train, idx_val, idx_test = data.split()

Assets 2

26 Aug 11:09

EdisonLeeeee

0.1.12

12c5e04

GraphGallery 0.1.12

Changelogs

update docstrings
rewrite dataset API
you can load the dataset like

from graphgallery.data import Planetoid, NPZDataset
data = Planetoid('cora',, verbose=True)
# data = NPZDataset('cora', verbose=True)
adj, x, labels = data.graph.unpack()
idx_train, idx_val, idx_test = data.split()

Assets 2

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

GraphGallery 1.0.0

Usages

New features

New features

GraphGallery 0.3.0

read the dataset

Add TensorFlow and PyTorch support

Using TensorFlow

Using PyTorch

Releases: EdisonLeeeee/GraphGallery