Install

theoryminer needs Python 3.10 or newer.

From PyPI

pip install theoryminer

The install includes UMAP (for clusterer(..., umap={...})) and tmsr-doi-downloader, an extra download source. On Python 3.10, pip leaves out tmsr-doi-downloader. The default download sources work on every version.

The newest code

To get the code on GitHub before the next release:

pip install "theoryminer @ git+https://github.com/rasoulnorouzi/theoryminer.git"

In a notebook

In Google Colab or Jupyter, put this line at the start of the first cell:

%pip install theoryminer

The tutorial notebook does this for you.

The models

The package downloads two models on first use. It keeps them in the Hugging Face cache, so later runs use the local copy.

Model	First used by	Size
`rasoultilburg/SocioCausaNet`	`causenet()`	about 430 MB
`sentence-transformers/all-mpnet-base-v2`	the grouping and naming functions	about 420 MB

Without a network, set the environment variable HF_HUB_OFFLINE=1. The models must already be in the cache.

The GPU

You do not need to set anything. causenet() uses device="auto": an NVIDIA GPU when PyTorch sees one, else the GPU of an Apple Silicon Mac, else the CPU.

System	What to do
Google Colab	Choose a GPU runtime: Runtime → Change runtime type → T4 GPU.
Linux with an NVIDIA GPU	Nothing. The PyTorch from pip supports the GPU.
Windows with an NVIDIA GPU	Install PyTorch from pytorch.org first, then `theoryminer`. The PyTorch from pip uses only the CPU on Windows.
Apple Silicon Mac	Nothing. When the model fails on the Apple GPU, the run moves to the CPU.

The caches

What	Where	Change it with
The text of each PDF page	`<pdf>.pages.json` beside each PDF	`harvest(..., cache=False)`
The thesaurus vectors	`~/.cache/theoryminer/taxonomy`	the environment variable `THEORYMINER_CACHE_DIR`
The models	the Hugging Face cache	the environment variable `HF_HOME`

When the package cannot write a cache folder, the functions still work. They compute the vectors again in the next session.

Keyboard shortcuts