Uri Alon

Can you try running the java process directly, e.g.,: ``` java -cp JavaExtractor/JPredict/target/JavaExtractor-0.0.1-SNAPSHOT.jar JavaExtractor.App --max_path_length 8 --max_path_width 2 --dir JavaExtractor/JPredict/src/main ``` ?

OK so the base java process is running fine, it looks like the problem is in some input/output redirection because of Windows. Can you try running that on a linux...

Hi @DJjjjhao , Sorry for the late response. The output is split by space where: 1. The first "word" is the target label (`assign|message|group`) 2. Every following "word" is a...

Hi @anon721702 , Thank you for your interest in code2vec, and sorry for the delayed response. You can reproduce the way that our code opens this file: [https://github.com/tech-srl/code2vec/blob/master/vocabularies.py#L75](https://github.com/tech-srl/code2vec/blob/master/vocabularies.py#L75) to see...

By the way, See our newer [code2seq](https://code2seq.org/) model's demo and [code](https://github.com/tech-srl/code2seq).

Hi @brcsnt , Of course, You can just move each file into a separate directory and point the `preprocess.sh` script to each individual directory. You can also modify the `JavaExtractor`...

Not necessarily. But you do need to build the `*.jar*` file of the `JavaExtractor` by running `mvn package` from the directory `JavaExtractor/JPredict` for your changes to take effect. Best, Uri...

Hi @WQR53 , Thank you for your interest in our work! I don't know the reason, since astminer and neuro-vectorizer are not mine. However, please check out this **PolyCoder** paper:...

Hi @abitrolly , Thank you for your interest in our work! Every unique token and unique path in the training data is allocated with a randomly initialized vector, and we...

Hi @abitrolly , Sorry for the delayed response. I am not sure where to begin. Do you have any concrete questions? Did you have a chance to look at [the...