Comments (7)
I updated the data and outputs by different RQs. I think it would be more convenient for comparison.
from emse-deepcom.
I updated the data and outputs by different RQs. I think it would be more convenient for comparison.
Thank you for your answer, and by the way, can the previous dataset be used?
I see that although the size of the data set has not changed, the content of the data set is different. I have further processed your data set and it would be cumbersome to reprocess. Also, train.token.ast in your current training set is one line less than train.token.code
from emse-deepcom.
The difference between the two version dataset is the index of samples. In theory, it wouldn't affect the performance of your model. If you want to compare directly, I recommend this version as I provided the output of my model in the folder "output".
Thanks for pointing the issue in train.token.ast, I will check it.
from emse-deepcom.
I compared the old and new data sets, and found that some samples of the new data set are not on the old data set. Shouldn't you just disrupt the order, should you change some data samples? If so, I may still need to update the dataset for comparison.
from emse-deepcom.
Some samples may change when shuffled from the large codebase.
I update the train.token.ast and hope the new one is more convenient for comparison.
from emse-deepcom.
I also reopen the old version dataset and the output on it. I hope both datasets can help your research.
from emse-deepcom.
Hello, I have been able to run this code successfully using the data set given by the author,but the complete data processing code does not seem to be given, because I can't use the existing data processing code to generate the files provided by the author.
Can you successfully preprocess the data?If you can run it successfully, could you share me your code?
from emse-deepcom.
Related Issues (20)
- tensorflow.python.framework.errors_impl.AlreadyExistsError:
- could you tell me how the hybrid.out file is generated?
- Why the corpus_bleu is 0.0000? HOT 2
- I had stop the training the model at 28 epoch and at a learning rate of 0.13 but I am not able to run the prediction could you kindly tell me is it necessary for us to train full 50 epoch before we train the model ? The reason is training 28 epoch it already cost my small budget and I like to see it working. Could you kindly explain this to me. Thank you
- The data process code is incomplete HOT 2
- FileNotFoundError: [Errno 2] No such file or directory: '../emse-data/vocab.code' HOT 3
- DeepCom and DFS analysis
- The file get_ast.py is confusing and imcomplete HOT 5
- Version problem about NLTK
- How to get the vocab.nl with a new dataset?
- File get_ast.py returns too big a string. HOT 1
- Why the corpus_bleu is 0.0001? I have trained the model. HOT 5
- Generate strange AST
- The link of the dataset has broken HOT 3
- 链接无效 HOT 3
- I found the .code and .nl files, but I did not find the .sbt file. How do I get the .sbt file? Thank you very much for answering my question
- Whether there are more duplicate data in the test set and training set?
- FileNotFoundError: [Errno 2] No such file or directory: '../emse-data/vocab.sbt' HOT 11
- 您好,在get_ast时,遇到javalang.parser.JavaSyntaxError应该如何处理 HOT 1
- Prediction (Output) file not getting generated
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 emse-deepcom.