AMDataset

class dgl.data.AMDataset(print_every=10000, insert_reverse=True, raw_dir=None, force_reload=False, verbose=True, transform=None)[source]

Bases: RDFGraphDataset

AM数据集。用于节点分类任务

命名空间约定：

  • 实例: http://purl.org/collections/nl/am/-

  • 关系: http://purl.org/collections/nl/am/

我们在输出图中忽略了所有字面节点以及连接它们的关系。

AM 数据集统计：

  • 节点数：881680

  • 边数：5668682（包括反向边）

  • 目标类别：代理

  • 班级数量：11

  • 标签分割：

    • 列车：802

    • 测试: 198

Parameters:

  • print_every (int) – Preprocessing log for every X tuples. Default: 10000.

  • insert_reverse (bool) – If true, add reverse edge and reverse relations to the final graph. Default: True.

  • 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 DGLGraph object and returns a transformed version. The DGLGraph object will be transformed before every access.

num_classes

预测的类别数量

Type:

int

predict_category

具有预测标签的实体类别（节点类型）

Type:

str

示例

>>> dataset = dgl.data.rdf.AMDataset()
>>> graph = dataset[0]
>>> category = dataset.predict_category
>>> num_classes = dataset.num_classes
>>>
>>> train_mask = g.nodes[category].data['train_mask']
>>> test_mask = g.nodes[category].data['test_mask']
>>> label = g.nodes[category].data['label']
__getitem__(idx)[source]

获取图形对象

Parameters:

idx (int) – 项目索引，AMDataset 只有一个图对象

Returns:

The graph contains:

  • ndata['train_mask']: mask for training node set

  • ndata['test_mask']: mask for testing node set

  • ndata['label']: node labels

Return type:

dgl.DGLGraph

__len__()[source]

数据集中图的数量。

Return type:

int