# DataScience2019#HW5 — Data

来源：https://www.kaggle.com/competitions/datasciencefall2019hw5/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<h2>File descriptions</h2>
<ul>
<li><strong>train_graph.json</strong> - the training graph, contains nodes and links</li>
<li><strong>train_graph_id.npy</strong> - the index of group for every nodes</li>
<li><strong>train_feats.npy</strong> - the features for every nodes</li>
<li><strong>train_labels.npy</strong> - the class information for every nodes</li>

<li><strong>test_graph.json</strong> - the testing graph, contains nodes and links</li>
<li><strong>test_graph_id.npy</strong> - the index of group for every nodes</li>
<li><strong>test_feats.npy</strong> - the features for every nodes</li>
<li><strong>submission_sample.csv</strong> - the submission sample for testing data</li>

</ul>
<h2>Keys for the json files</h2>
<ul>
<li><strong>directed</strong> - True, indicating that this is a graph with directed link</li>
<li><strong>nodes</strong> - indicating the index for every node</li>
<li><strong>links</strong> - indicating the source and target of link, i.e. {'source':0, 'target':3} means that there is a directed link from node 0 to node 3</li>
</ul>