Skip to main content

A Python library for NLP experiments.

Project description

NLPE

Nural Language Process Experiments (NLPE) is a python package supporting you setup NLP experiments fastly.

Its mission is tio reduce the duplicate labors when we set up and NLP models or framework in current popular deep learning framework or methodology.

Installation

Install from Source

git clone https://github.com/codesedoc/nlpe.git
cd nlpe
pip install -e .

Install from PyPi

pip install nlpe

Install from Docker Hub

docker run -it codedocx/nlpe

Experiment

There are examples of conducting expeirments by using nlpe at experiment dir. The experiment/semantic_similarity is an example to calculate semantic similarity of two texts by fine-tuned the uncased BERT on STSB dataset.

cd experiment/semantic_similarity
pip install -r requrements.txt
python main.py -t sematic_similarity -d glue -a bert --eval_strategy epoch --output_dir tmp_trainer

Version: 0.0.5

E-mail: gocodedoc@gmail.com

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

nlpe-0.0.5.tar.gz (14.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nlpe-0.0.5-py3-none-any.whl (14.6 kB view details)

Uploaded Python 3

File details

Details for the file nlpe-0.0.5.tar.gz.

File metadata

  • Download URL: nlpe-0.0.5.tar.gz
  • Upload date:
  • Size: 14.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.9

File hashes

Hashes for nlpe-0.0.5.tar.gz
Algorithm Hash digest
SHA256 6e45e2abb7aa8af4a448ae5d07444368d8726bb7b9849351365d9d8c6fc2c564
MD5 7b28090fe8ebe042370f20fb56635787
BLAKE2b-256 744d49334bd3a9fcbf1867ed7affaf19226fc3b61a6baed70cc7cdc73cadeefa

See more details on using hashes here.

File details

Details for the file nlpe-0.0.5-py3-none-any.whl.

File metadata

  • Download URL: nlpe-0.0.5-py3-none-any.whl
  • Upload date:
  • Size: 14.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.9

File hashes

Hashes for nlpe-0.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 333103acad0c30f822566fafdbf04644640bb5477ab47056890fcce173c823d4
MD5 799c4fd0a6d1175c191a43434c18cd70
BLAKE2b-256 21d34999605603e65b5fe03067ae470092f83fd2959ca2dee76bb043760789d3

See more details on using hashes here.

Supported by

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