Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
â—‹DOI references
-
â—‹Academic publication links
-
â—‹Committers with academic emails
-
â—‹Institutional organization owner
-
â—‹JOSS paper metadata
-
â—‹Scientific vocabulary similarity
Low similarity (17.0%) to scientific vocabulary
Keywords
Repository
🧌 Upload a CSV file and get an ML model
Basic Info
Statistics
- Stars: 2
- Watchers: 2
- Forks: 0
- Open Issues: 0
- Releases: 0
Topics
Metadata Files
README.md
🧌 csv-to-ml
Upload a CSV file and get an ML model
Setup
- Get an OpenAI API Key
- Create an assistant and copy its id
2.1 Name: csvtoml
2.2 Instructions:
"Create a ML model based on csv I provided to predict data. Please do data preprocessing and cleaning, feature engineering and all possible improvements that will contribute to better model's quality and then repeat your experiments using the new, cleared data. Shuffle train/test data split, make it 70% train, 20% test and 10% validation and repeat experiments using cleared data. Save the weights and biases in a Pickle format that makes it super easy to just load them on my computer and run inference on this model. Return the Pickle file so I can download it. In a single separate file, return all the source code of your machine learning model architecture, which allows to just take the Pickle file you provided and start doing inference without any further changes. Don't ask any additional questions, just go straight to training the model, returning the valid Pickle file with weights and biases and fully correct Python file with source code of our machine learning model, which allows to load a pickle file and do the predictions right away. If you get a csv file as an input, it probably contains either tabular data or timeseries data. Make sure to choose simple yet most accurate and powerful model for this purpose. If accuracy is less than 50%, then pick another model architecture and reevaluate. Calculate final accuracy and loss on validation set and put it as JSON to file metrics.json. This is very important: as an final output, you must return ONLY three files: "parameters.pkl", which is a Pickle file with weights and biases, "model.py", which contains source code of our model and "metrics.json" which contains final accuracy as "accuracy" property and loss as "loss" property for the trained model. In Python file, make sure you add code that allows to just run the file using python model.py - so the code needs if name == "main" and then relevant call for prediction."
2.3 Model: gpt-4-turbo-preview
2.4 Tools: Code Interpreter
Create .env file and fill it with values:
OPENAI_API_KEY=
OPENAI_ASSISTANT_ID=
Build
sh
npm install
npm run build
Run dev
npm run dev
Run prod
npm run start
Cite
If you use this software in your research, please use the following citation:
bibtex
@misc{Maczan_csvtoml_2024,
title = "csv-to-ml: Upload a CSV file and get an ML model",
author = "{Maczan, Jędrzej Paweł}",
howpublished = "\url{https://github.com/jmaczan/csv-to-ml}",
year = 2024,
publisher = {GitHub}
}
License
GPLv3
Author
UI comes from Vercel templates
Jędrzej Paweł Maczan, Poland, 2024
Owner
- Name: Jędrzej Maczan
- Login: jmaczan
- Kind: user
- Website: https://maczan.pl
- Twitter: jedmaczan
- Repositories: 30
- Profile: https://github.com/jmaczan
Citation (CITATION.cff)
cff-version: 1.2.0 message: "If you use this software, please cite it as below." authors: - family-names: "Maczan" given-names: "Jędrzej Paweł" orcid: "https://orcid.org/0000-0003-1741-6064" title: "csv-to-ml: Upload a CSV file and get an ML model" date-released: 2024-04-04 url: "https://github.com/jmaczan/csv-to-ml"
GitHub Events
Total
- Watch event: 1
Last Year
- Watch event: 1
Committers
Last synced: 9 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| jmaczan | j****l@m****l | 7 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 9 months ago
All Time
- Total issues: 0
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 0
- Total pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels
Dependencies
- 430 dependencies
- @types/ms ^0.7.34 development
- turbo ^1.12.3 development
- @auth0/nextjs-auth0 ^3.5.0
- @tmlc/openai-polling ^0.0.5
- @types/node 20.11.16
- @types/react 18.2.55
- @types/react-dom 18.2.18
- @vercel/blob ^0.21.0
- @vercel/kv ^1.0.1
- auth0 ^4.3.1
- autoprefixer 10.4.17
- eslint 8.56.0
- eslint-config-next 14.1.0
- jwt-decode ^4.0.0
- nanoid ^5.0.5
- next 14.1.0
- openai ^4.28.0
- postcss 8.4.34
- react 18.2.0
- react-dom 18.2.0
- react-hot-toast ^2.4.1
- stripe ^14.19.0
- tailwindcss 3.4.1
- typescript 5.3.3