A minimal ML/DL framework written in pure Python and NumPy.
Project description
pytaught
pytaught is a minimal Machine Learning / Deep Learning framework built from scratch using pure Python and NumPy.
Installation
pip install pytaught
Or build locally:
python -m build
python -m twine upload dist/*
Usage
pytaught --csv data.csv --target price --model mlp --hidden-sizes 64 32 --epochs 100
If no CSV is given, the framework generates synthetic data automatically.
Features
- Linear regression and MLP models
- Pure NumPy training loops
- Early stopping and model checkpointing
- CLI interface for flexible training
License
MIT License © 2025 Sathsara Wijekulasuriya
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
pytaught-1.0.0.tar.gz
(7.5 kB
view details)
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 pytaught-1.0.0.tar.gz.
File metadata
- Download URL: pytaught-1.0.0.tar.gz
- Upload date:
- Size: 7.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a8fc9d300c11381ce5ae6345f45d7c3f1eae155d66e211d5bac5a13510299ee4
|
|
| MD5 |
46a6824fe1014eb00b42f15fb983107a
|
|
| BLAKE2b-256 |
42490008f11cd645749610cf4db45d1e09f6a81013dbf30e0219a34897d2db47
|
File details
Details for the file pytaught-1.0.0-py3-none-any.whl.
File metadata
- Download URL: pytaught-1.0.0-py3-none-any.whl
- Upload date:
- Size: 8.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4c3b7644d948b3693ea88b4a099a4695bdda687e83bb96a901efe85180d80b58
|
|
| MD5 |
f49ecb5652de1c6951ddfd7f5ccf17b9
|
|
| BLAKE2b-256 |
84fd73f47e958058e8f6dcdcd3cc80700a31f745b55f7bd1e09243bde02c9914
|
