Skip to main content

A part of speech tagger based on Hidden Markov models

Project description

PyPOS - Python Part-of-Speech tagger

This is  a  project, which allows its  users to assign part of speech tags to words in a  sentence .
dt   vbz dt nn     , wdt   vbz    prp$ nns   to vb     nn   in nn     nns  to nns   in dt nn       .

PyPOS uses Hidden Markov Models and Viterbi decoding to determine the most likely sequence of POS tags for a given sequence of words.

Usage

Installation

Requires Python 3.6 or higher

pip3 install pypos

Training

from pypos import PartOfSpeechTagger, PartOfSpeechDataset
tagger = PartOfSpeechTagger()
ds = PartOfSpeechDataset.load('train.txt')
tagger.fit(ds).save('tagger.p')

Tagging

from pypos import PartOfSpeechTagger
tagger = PartOfSpeechTagger.load('tagger.p')

# Reproducing the results shown above:
sentence = 'This is a project, which allows its users to assign part of speech tags to words in a sentence.'
tokens = tagger.tokenize(sentence)
tags = tagger.tag(sentence, human_readable=False)

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

pypos-0.1.2.tar.gz (3.7 kB view details)

Uploaded Source

Built Distribution

pypos-0.1.2-py3-none-any.whl (5.1 kB view details)

Uploaded Python 3

File details

Details for the file pypos-0.1.2.tar.gz.

File metadata

  • Download URL: pypos-0.1.2.tar.gz
  • Upload date:
  • Size: 3.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.12.1 pkginfo/1.5.0.1 requests/2.18.4 setuptools/40.8.0 requests-toolbelt/0.9.1 tqdm/4.23.3 CPython/3.6.5

File hashes

Hashes for pypos-0.1.2.tar.gz
Algorithm Hash digest
SHA256 d5acb4f4968f88877a8626b8cee877d2b3a56fca57987cf08da1346cc540a1cd
MD5 6e39ef0e2c2581e3ff9af5c344814b0f
BLAKE2b-256 9fda9b94d9e0926dc960107492cc29c023a7aeebba326a574aa4816e351ce183

See more details on using hashes here.

File details

Details for the file pypos-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: pypos-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 5.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.12.1 pkginfo/1.5.0.1 requests/2.18.4 setuptools/40.8.0 requests-toolbelt/0.9.1 tqdm/4.23.3 CPython/3.6.5

File hashes

Hashes for pypos-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 062344d6354f88fe2f3e3301803e6eb6402482205efc46783752b597f24f6b75
MD5 d2e09b7f25c554d9241392b7613bf431
BLAKE2b-256 dac224a8f9e47d0f2e03a1e68afb75b3660dcc58622e1bb9069d3c8bad1b32bd

See more details on using hashes here.

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