Topic modeling via sum-to-one constrained Poisson non-negative matrix factorization
Project description
tinytopics
Topic modeling via sum-to-one constrained Poisson non-negative matrix factorization, built with PyTorch, runs on both CPUs and GPUs.
Installation
You can install tinytopics from PyPI:
pip3 install tinytopics
Or install the development version from GitHub:
git clone https://github.com/nanxstats/tinytopics.git
cd tinytopics
python3 -m pip install -e .
GPU support
The above will install the CPU version of PyTorch by default. To enable GPU support, follow the PyTorch official guide to install the appropriate PyTorch version.
For example, to install PyTorch for Windows with CUDA 12.4:
pip3 uninstall torch
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124
To manage the PyTorch dependency under a project context using virtual environments, you might want to set up manual sources. For example, using Rye.
Get started
After tinytopics is installed, try the example from the getting started guide or see the speed benchmark.
License
MIT
Project details
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
Hashes for tinytopics-0.1.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 41828f7f0427e85c9339b3ebaacbd9c99d2d6374bff68c3185034d5dbb0cf32d |
|
MD5 | 32c38d39afc41ee9994bf5a86992a9e8 |
|
BLAKE2b-256 | 9579f08e67edb26cc3c692c0df15ce316ca568eacd9ac23288e5e369081c3bd2 |