Skip to main content

Sumerian Named Entity Recognition

Project description

Build Status Documentation Status

Installation

$ pip3 install sumerian-ner

If you are not in a virtualenv you may need to use pip3 with sudo or --user.

If you’d rather clone the repository.

$ git clone https://github.com/wwunlp/sner.git
$ cd sner/
$ pip3 install .

Usage

If you used pip3 to install sner, you can call sner from the command line. If you cloned the repo, you can run python3 -m sner from within the repo.

Options and Arguments

  • -r or --run: Run one of the following models: dec, nbc, ner, rdf, sgd, or svc. Or one of the following routines: analysis, export, export-atf, formatting, over-fit, or testing.

  • -cf or --config: Configuration file to use.

  • -p or --path: Path to data directory.

  • -c or --corpus: File name of the corpus.

  • -a or --attestations: File name of the attestations.

  • -sr or --seed-rules: File name of the seed rules.

  • -i or --iterations: Number of iterations.

  • -mr or --max-rules: Max number of rules per iterations.

  • -al or --alpha: Alpha value.

  • -k or --k: K value.

  • -nd or --norm-date: Enable date normalization.

  • -ng or --norm-geo: Enable geographical name normalization.

  • -nn or --norm-num: Enable number normalization.

  • -np or --norm-prof: Enable profession normalization.

sner will check sner.conf before using default value. The sner.conf uses JSON syntax. i.e. --corpus corpus.csv would be "corpus": "corpus.csv". If you want to change the hyperparameters used, you can define them in sner.conf. If your sner.conf is not in the root of the repository, you can set the environment variable SNER_CONF to the path of sner.conf.

Corgi playing in snow, with text 'ERMAHGERD SNER'

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

sumerian-ner-0.1.1.tar.gz (31.8 kB view hashes)

Uploaded Source

Built Distribution

sumerian_ner-0.1.1-py3-none-any.whl (43.6 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page