You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
79 lines
2.0 KiB
Plaintext
79 lines
2.0 KiB
Plaintext
5 years ago
|
.. Copyright (C) 2001-2019 NLTK Project
|
||
|
|
.. For license information, see LICENSE.TXT
|
||
|
|
|
||
|
|
==========
|
||
|
|
Stemmers
|
||
|
|
==========
|
||
|
|
|
||
|
|
Overview
|
||
|
|
~~~~~~~~
|
||
|
|
|
||
|
|
Stemmers remove morphological affixes from words, leaving only the
|
||
|
|
word stem.
|
||
|
|
|
||
|
|
>>> from __future__ import print_function
|
||
|
|
>>> from nltk.stem import *
|
||
|
|
|
||
|
|
Unit tests for the Porter stemmer
|
||
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||
|
|
|
||
|
|
>>> from nltk.stem.porter import *
|
||
|
|
|
||
|
|
Create a new Porter stemmer.
|
||
|
|
|
||
|
|
>>> stemmer = PorterStemmer()
|
||
|
|
|
||
|
|
Test the stemmer on various pluralised words.
|
||
|
|
|
||
|
|
>>> plurals = ['caresses', 'flies', 'dies', 'mules', 'denied',
|
||
|
|
... 'died', 'agreed', 'owned', 'humbled', 'sized',
|
||
|
|
... 'meeting', 'stating', 'siezing', 'itemization',
|
||
|
|
... 'sensational', 'traditional', 'reference', 'colonizer',
|
||
|
|
... 'plotted']
|
||
|
|
|
||
|
|
>>> singles = [stemmer.stem(plural) for plural in plurals]
|
||
|
|
|
||
|
|
>>> print(' '.join(singles)) # doctest: +NORMALIZE_WHITESPACE
|
||
|
|
caress fli die mule deni die agre own humbl size meet
|
||
|
|
state siez item sensat tradit refer colon plot
|
||
|
|
|
||
|
|
|
||
|
|
Unit tests for Snowball stemmer
|
||
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||
|
|
|
||
|
|
>>> from nltk.stem.snowball import SnowballStemmer
|
||
|
|
|
||
|
|
See which languages are supported.
|
||
|
|
|
||
|
|
>>> print(" ".join(SnowballStemmer.languages))
|
||
|
|
arabic danish dutch english finnish french german hungarian italian
|
||
|
|
norwegian porter portuguese romanian russian spanish swedish
|
||
|
|
|
||
|
|
Create a new instance of a language specific subclass.
|
||
|
|
|
||
|
|
>>> stemmer = SnowballStemmer("english")
|
||
|
|
|
||
|
|
Stem a word.
|
||
|
|
|
||
|
|
>>> print(stemmer.stem("running"))
|
||
|
|
run
|
||
|
|
|
||
|
|
Decide not to stem stopwords.
|
||
|
|
|
||
|
|
>>> stemmer2 = SnowballStemmer("english", ignore_stopwords=True)
|
||
|
|
>>> print(stemmer.stem("having"))
|
||
|
|
have
|
||
|
|
>>> print(stemmer2.stem("having"))
|
||
|
|
having
|
||
|
|
|
||
|
|
The 'english' stemmer is better than the original 'porter' stemmer.
|
||
|
|
|
||
|
|
>>> print(SnowballStemmer("english").stem("generously"))
|
||
|
|
generous
|
||
|
|
>>> print(SnowballStemmer("porter").stem("generously"))
|
||
|
|
gener
|
||
|
|
|
||
|
|
.. note::
|
||
|
|
|
||
|
|
Extra stemmer tests can be found in `nltk.test.unit.test_stem`.
|