https://github.com/s1998/dsc291-linearalgebra
https://github.com/s1998/dsc291-linearalgebra
Last synced: over 1 year ago
JSON representation
- Host: GitHub
- URL: https://github.com/s1998/dsc291-linearalgebra
- Owner: s1998
- Created: 2022-06-07T07:02:16.000Z (about 4 years ago)
- Default Branch: main
- Last Pushed: 2022-06-09T04:25:56.000Z (about 4 years ago)
- Last Synced: 2025-02-01T18:27:26.344Z (over 1 year ago)
- Language: Jupyter Notebook
- Size: 8.54 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# dsc291-linearAlgebra
To run the baselines related to linear algebra, use the notebook `matrixfactorization_notebook.ipynb`
The notebook has been properly commented and divided into sections for explaining everything.
To run the transformers based models, use the file `transformersTrain.py`.
It runs the code on the given datasets. The file has been commented to provide appropriate pointers.
Also, the logs for the same are present oin twitterCovidKaggleLogs.
Experiemtal results obtained :
| Method name | Micro-F1 | Macro-F1 | Weighted-F1 |
|:--------------:|:--------:|:--------:|:-----------:|
| Sparse Vectors | 0.547 | 0.557 | 0.547 |
| LSA | 0.376 | 0.369 | 0.369 |
| NNMF | 0.350 | 0.334 | 0.339 |
| BERT | 0.858 | 0.853 | 0.858 |
Environment assumes the following:
sentence-transformers==1.2.0
transformers==3.5.1
scikit-image==0.17.2
scikit-learn==0.23.2
numpy==1.19.5
pandas==1.1.5