Cascade Dataset and Code
收藏资源简介:
This dataset contains two parts: 1. Data (APS and Weibo) (1) APS: It comprises the papers published in all journals in American Physical Society from 1893 to 2009, consisting of 245,365 authors, 463,344 papers, and 4,692,026 citations. (2) Weibo: It consists of all the original microblogs that were submitted on June 1, 2016, and for each microblog, we collect its retweets within the next 24 hours. 2. Code (1) split the data to train set, validation set and test set (2) trainsform the datasets to the format of ".pkl" (3) train CST-Net
本数据集包含两个组成部分: 1. 数据(APS与微博(Weibo)) (1) APS数据集:涵盖1893年至2009年间美国物理学会(American Physical Society)全期刊刊载的全部学术论文,共计包含245,365位作者、463,344篇论文以及4,692,026次引用。 (2) 微博(Weibo)数据集:包含2016年6月1日发布的全部原始微博,且针对每条微博,我们采集了其发布后24小时内的转发数据。 2. 代码 (1) 将数据集划分为训练集、验证集与测试集 (2) 将数据集转换为".pkl"格式 (3) 训练CST-Net模型



