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.

86 lines
2.3 KiB
Plaintext

.. Copyright (C) 2001-2019 NLTK Project
.. For license information, see LICENSE.TXT
=================
EasyInstall Tests
=================
This file contains some simple tests that will be run by EasyInstall in
order to test the installation when NLTK-Data is absent.
>>> from __future__ import print_function
------------
Tokenization
------------
>>> from nltk.tokenize import wordpunct_tokenize
>>> s = ("Good muffins cost $3.88\nin New York. Please buy me\n"
... "two of them.\n\nThanks.")
>>> wordpunct_tokenize(s) # doctest: +NORMALIZE_WHITESPACE
['Good', 'muffins', 'cost', '$', '3', '.', '88', 'in', 'New', 'York', '.',
'Please', 'buy', 'me', 'two', 'of', 'them', '.', 'Thanks', '.']
-------
Metrics
-------
>>> from nltk.metrics import precision, recall, f_measure
>>> reference = 'DET NN VB DET JJ NN NN IN DET NN'.split()
>>> test = 'DET VB VB DET NN NN NN IN DET NN'.split()
>>> reference_set = set(reference)
>>> test_set = set(test)
>>> precision(reference_set, test_set)
1.0
>>> print(recall(reference_set, test_set))
0.8
>>> print(f_measure(reference_set, test_set))
0.88888888888...
------------------
Feature Structures
------------------
>>> from nltk import FeatStruct
>>> fs1 = FeatStruct(PER=3, NUM='pl', GND='fem')
>>> fs2 = FeatStruct(POS='N', AGR=fs1)
>>> print(fs2)
[ [ GND = 'fem' ] ]
[ AGR = [ NUM = 'pl' ] ]
[ [ PER = 3 ] ]
[ ]
[ POS = 'N' ]
>>> print(fs2['AGR'])
[ GND = 'fem' ]
[ NUM = 'pl' ]
[ PER = 3 ]
>>> print(fs2['AGR']['PER'])
3
-------
Parsing
-------
>>> from nltk.parse.recursivedescent import RecursiveDescentParser
>>> from nltk.grammar import CFG
>>> grammar = CFG.fromstring("""
... S -> NP VP
... PP -> P NP
... NP -> 'the' N | N PP | 'the' N PP
... VP -> V NP | V PP | V NP PP
... N -> 'cat' | 'dog' | 'rug'
... V -> 'chased'
... P -> 'on'
... """)
>>> rd = RecursiveDescentParser(grammar)
>>> sent = 'the cat chased the dog on the rug'.split()
>>> for t in rd.parse(sent):
... print(t)
(S
(NP the (N cat))
(VP (V chased) (NP the (N dog) (PP (P on) (NP the (N rug))))))
(S
(NP the (N cat))
(VP (V chased) (NP the (N dog)) (PP (P on) (NP the (N rug)))))