jilljenn / ktm Goto Github PK

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.

scikit-learn/scikit-learn#28026

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.

https://contrib.scikit-learn.org/polylearn/generated/polylearn.FactorizationMachineClassifier.html

I guess MCMC wins.

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.