Risk Commodity Dataset (RCDD) from Alibaba's e-commerce platform

This is a risk commodity detection dataset (RCDD) that is based on a real risk detection scenario from Alibaba's e-commerce platform. All the .csv files are the initial data which consists of edges, node features, supervised information as well as IDs of candidate items. More details can see in README.md, we list the type of each column in each file as follows:

1. RCDD_edges.csv (edge file): 
    source_node_id int, target_node_id int, source_node_type string, target_node_type string, edge_type string
2. RCDD_nodes.csv (node file):
    node_id int, node_type string, node_atts string (notice that node_atts are 256-dimensional feature vector strings with delimiter ":")
3. RCDD_train_labels.csv (training labels):
    item_id int, label int
4. RCDD_test_ids.csv (testing ids):
    item_id int
5. RCDD_test_labels.csv (testing labels):
    item_id int, label int    

Besides that, graph.bin is the format in DGL which is constructed by  all *.csv files, and a general method to load this graph as follows:

from dgl import load_graphs #should install dgl
ds,_ = load_graphs("./graph.bin")
g = ds[0]
print(g)

And then you can easily get a large-scale heterogeneous graph with 157,814,864 edges and 13,806,619 nodes, our graph task is node classification: detect risk product.