LLM-powered modular data science pipeline
Project description
data_science_pro
A modular, LLM-powered data science pipeline for automated EDA, preprocessing, model selection, training, and testing.
Installation
pip install .
Usage
data-science-pro --help
Or run the pipeline interactively:
python pipeline.py
Features
- Automated EDA and preprocessing
- LLM-powered suggestions and cyclic workflow
- Model selection, training, evaluation, and saving
- CLI entrypoint for easy usage
Requirements
See requirements.txt for dependencies.
Project Structure
api/- LLM connectorcycle/- Suggestion and control logicdata/- Data loading, analysis, operationsmodeling/- Model training, evaluation, registryutils/- Utility filespipeline.py- Main pipeline classtest.py- Example/test script
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file data_science_pro-0.1.0.tar.gz.
File metadata
- Download URL: data_science_pro-0.1.0.tar.gz
- Upload date:
- Size: 8.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e3b82debe45cc68b1c70b841cba3811b38f04f905a47306a2d0b95b5da69c38d
|
|
| MD5 |
a4efb98d83de7186484ebc2ee373daff
|
|
| BLAKE2b-256 |
9dd029d708544dec26ee7510fe0e4b68cc647337c9a62bf1d493ca691cc8e855
|
File details
Details for the file data_science_pro-0.1.0-py3-none-any.whl.
File metadata
- Download URL: data_science_pro-0.1.0-py3-none-any.whl
- Upload date:
- Size: 10.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
db6891df547b9077e0ec2a1767e1ddad2b1eb3266a430595e217b2d38c4d15d0
|
|
| MD5 |
d712a0eae4f94d59cce5b03007ff8849
|
|
| BLAKE2b-256 |
2b15043e6042f5d6ecb2146d3b27ce91b15071ef755de318b2b601806ecf68fa
|
