fangqiyu's repositories
TextClassification
基于scikit-learn实现对新浪新闻的文本分类，数据集为100w篇文档，总计10类，测试集与训练集1:1划分。分类算法采用SVM和Bayes，其中Bayes作为baseline。
GoogleScholarSpider
A spider to crawl references from Google Scholar
KnowledgeGraph
A system with reference spider and knowledge graph
ReferenceManagementSystem
A reference management system with social networking approach and visualization.