Comments (5)
Hi @rishab-32 ,
Thank you for your interest in code2seq.
By default, our preprocessing takes Java method names as the code sequences. Getting the sequences from a separate text file will require some modifications. For example, you can change the method names to unique IDs in the Java file, and then use these IDs to look up the code sequence in the text file and join them.
Please see: https://github.com/tech-srl/code2seq#creating-and-preprocessing-a-new-java-dataset
and follow the execution of preprocess.sh
on a small code directory, to see the outcomes of every step.
Best,
Uri
from code2seq.
Hi thanks for the prompt reply, In the paper, you have talked about an additional comparison to Hu et al. (2018) dataset. I am also working with the Hu dataset, do you have any implementation of code2seq available on this dataset? That would be really helpful.
from code2seq.
The comparison to Hu et al was rush, because one of the reviewers asked for it throughout the rebuttal. Since we found out that the BLEU scores reported by Hu et al were totally erroneous, we did not release official repro scripts (if I remember correctly, they reported exceptional BLEU score of about 40, while in fact, when I measured BLEU score on their logs - it was about 9).
However, I do have the scripts that I used to convert their dataset to our format.
If I remember correctly, you need to use the first script to convert their dataset from one-large-json into a directory of many files (for each of training/validation/test):
https://gist.github.com/urialon/6ce2ffab7b675d9437b730246dc07827
Then, run our preprocess.sh
script on the resulting directories.
Finally, you need to "insert" the code sequences into the produced files, using this script:
https://gist.github.com/urialon/7c4d129f6cb45c2cdba669a15f132fb4
from code2seq.
But note that I haven't touched these scripts for almost two years, so it is very likely that I am forgetting some details. Follow these scripts carefully to verify that I did not mislead you.
from code2seq.
Thanks a lot for sharing the scripts. I understand that you do not have any intention of misleading me in any way.
from code2seq.
Related Issues (20)
- Generating embeddings for Python and Java HOT 5
- Help with implementing local service with JavaExtractor HOT 10
- I can not preprocess Python dataset
- Error running prediction on Code2seq released model
- I got Out of Memory Error during Training
- Unable to get embeddings from the trained model for Java
- Extract Path Contexts Only HOT 5
- InvalidArgumentError in sess.run() HOT 3
- Visualize Python AST HOT 2
- Extract java files HOT 2
- Getting "was not completed in time" error when preprocessing dataset HOT 11
- code2seq for Python HOT 3
- Error processing property '_dropout_mask_cache' of <ContextValueCache> HOT 6
- Sampling k paths from AST tree HOT 11
- I am getting TimeError while using code2seq to predict long method HOT 2
- Generating code documentation with code2seq HOT 8
- Tensorflow out-of-bound error while trying to train the Code2Seq model on our own python dataset HOT 6
- Model is predicting empty string for custom python dataset HOT 8
- Exporting code vectors HOT 6
- Encountered error of preprocess data HOT 8
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from code2seq.