Get to know How deepwalk works by this project.
Two steps: 1. gen the graph, and gen the corpus on the graph via random walk. 2. use the corpus generated by step1 to fit the Word2vec model and calculate the similarity of two nodes.
Project link: https://gitee.com/sonica/basic-deepwalk
Read more about develop word2vec model with python: https://machinelearningmastery.com/develop-word-embeddings-python-gensim/ This blog will tell you:
- How to train your own word2vec word embedding model on text data.
- How to visualize a trained word embedding model using Principal Component Analysis.
- How to load pre-trained word2vec and GloVe word embedding models from Google and Stanford.