jilljenn / ktm Goto Github PK
View Code? Open in Web Editor NEWKnowledge Tracing Machines: Factorization Machines for Knowledge Tracing
Home Page: https://arxiv.org/abs/1811.03388
License: MIT License
Knowledge Tracing Machines: Factorization Machines for Knowledge Tracing
Home Page: https://arxiv.org/abs/1811.03388
License: MIT License
When I loaded your notebook, I found that you tried to read the duck/DUCKgt.txt file, but I don't have it now and you haven't provided it either. Where should I download it?
Hello, I am interested in your research, especially the part of embedding visualizing. It will be helpful for analyzing the student's performance. Can you offer the code for this part? I am not good at this (T_T). Thanks a lot~
Hello jilljenn
I am learning this field. I try to reproduce your results, following the instructions in the readme to execute python encode.py --users --items, but the program reports an error and returns KeyError: 'tutor'. This seems to be due to the first in the encode.py file 73 lines
X['tutor'] = onehotize(df['tutor'], len(df['tutor'].unique()))
There is no tutor column in the sample data, so it shall be a bug right?May i have any suggestions?Thank you very much
best wishes
MA Jinghao
Hi Jill-Jênn,
Are you considering add a predict function to the code to get predictions once the model is trained?. Thanks for sharing this project
There is already knowledge tracing however this is the wrong version of the dataset, with duplicate rows 😞
https://paperswithcode.com/sota/knowledge-tracing-on-assistments
We should provide our reproducible benchmark there.
you project didn't have the information of TIMSS and Caster dataset used in your paper, Could you give me the download links of these dataset? Thank you!!!
When running your codes and reading your details about the repository,I find some errors below:
1: The file doc/tuto.md
render with some error,maybe syntax incompatible?
2: On Assistments 2009 dataset. I download the dataset from https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/8SWHNO,is it the same data you used?
I check the data with the data/dummy/data.csv,but their formats are different.
Thanks al lot!
Maybe not.
Hello, I don’t quite understand the part of embedding visualizing. In your paper, what‘s does the item 5(4 3/5−3 4/10) mean?
Hi there! Thanks for your implementation.
After running the following commands:
python encode.py --dataset assistments09 --skills --wins --fails
python lr.py data/dummy/X-swf.npz
The following output error reveals:
TypeError: load_folds() missing 2 required positional arguments: 'options' and 'df'
Am I doing something wrong?
Thanks in advance.
Hello, I enjoyed the great code
If you are training fm.py on data such as assistance09 and multiple skills are associated in one problem, you follow these steps? PREPARE_assist09.py --> encode.py --tw --> fm.py training
After training like this, I want to do Inference using the stored W,V, but if there is no data in the columns corresponding to 'correct' in the information data (if there is a given problem and user as in the actual case, but we don't know whether the user will answer or not)
In this case, I can't make attempts, wins without correct value, how did you solve it in this case?
Hello, I found that the model was trained and used for prediction in a single function FM.run()
, but how can I save or load a trained model? I would appreciate it if the problem could be addressed.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.