CoauthorCSDataset(raw_dir=None, force_reload=False, verbose=False, transform=None)[source]¶
‘Computer Science (CS)’ part of the Coauthor dataset for node classification task.
Coauthor CS and Coauthor Physics are co-authorship graphs based on the Microsoft Academic Graph from the KDD Cup 2016 challenge. Here, nodes are authors, that are connected by an edge if they co-authored a paper; node features represent paper keywords for each author’s papers, and class labels indicate most active fields of study for each author.
Edges: 163,788 (note that the original dataset has 81,894 edges but DGL adds the reverse edges and remove the duplicates, hence with a different number)
Number of classes: 15
Node feature size: 6,805
raw_dir (str) – Raw file directory to download/contains the input data directory. Default: ~/.dgl/
force_reload (bool) – Whether to reload the dataset. Default: False
verbose (bool) – Whether to print out progress information. Default: True.
transform (callable, optional) – A transform that takes in a
DGLGraphobject and returns a transformed version. The
DGLGraphobject will be transformed before every access.
>>> data = CoauthorCSDataset() >>> g = data >>> num_class = data.num_classes >>> feat = g.ndata['feat'] # get node feature >>> label = g.ndata['label'] # get node labels
Get graph by index
idx (int) – Item index
The graph contains:
ndata['feat']: node features
ndata['label']: node labels
- Return type
Number of graphs in the dataset