def lemma_via_patternlib(token, pos):
if pos == 'NP': # singularize noun
return singularize(token)
elif pos.startswith('V'): # get infinitive of verb
return conjugate(token)
elif pos.startswith('ADJ') or pos.startswith('ADV'): # get baseform of adjective or adverb
return predicative(token)
return token
def test_predicative(self):
# Assert the accuracy of the predicative algorithm ("großer" => "groß").
from pattern.db import Datasheet
i, n = 0, 0
for tag, pred, attr in Datasheet.load(os.path.join(PATH, "corpora", "wordforms-de-celex.csv")):
if tag == "a":
if de.predicative(attr) == pred:
i +=1
n += 1
self.assertTrue(float(i) / n > 0.98)
print("pattern.de.predicative()")
def test_predicative(self):
# Assert the accuracy of the predicative algorithm ("großer" => "groß").
from pattern.db import Datasheet
i, n = 0, 0
for tag, pred, attr in Datasheet.load(os.path.join(PATH, "corpora", "celex-wordforms-de.csv")):
if tag == "a":
if de.predicative(attr) == pred:
i +=1
n += 1
self.assertTrue(float(i) / n > 0.98)
print "pattern.de.predicative()"
# pprint(tt_en.tag('Does this thing work?'))
tagger = ttw.TreeTagger(TAGLANG='de', TAGDIR='/home/niklas/treetagger/')
# satz = u'Dies ist ein Testsatz.'
# print type(satz)
# satzu = satz.decode('utf-8')
# tags = tagger.tag_text(satz)
# pprint.pprint(tags)
datei = open('196.txt', 'r')
dat = datei.read()
s = parse(dat, tagset='STTS')
s = split(s)
print s.sentences[0]
print predicative('neugierige')
with open('196.txt', 'r') as openfile:
for line in openfile:
nltk.tag.brill.BrillTagger(line)
# datu = dat.decode('utf-8')
# print tagger.tag_text(dat)
# print datu
# tags = tagger.TagText(datu)
# # for tag in tags:
# # print tag
datei.close()
# for dirpath, dirs, files in os.walk('../temp'):
# for filename in fnmatch.filter(files, '*.txt'):
# run with PYTHONIOENCODING=utf-8
import sys
import re
import codecs
# not used, but possibly interesting http://www.nltk.org/
# http://www.clips.ua.ac.be/pages/pattern-de
from pattern.de import lemma, tag, predicative, singularize
# possible parts of speech:
# PRP$, FW, VBN, WDT, JJ, WP, DT, RP, NN, TO, PRP,
# RB, NNS, NNP, VB, WRB, CC, LS, CD, IN, MD, UH
part_of_speech_command = {
'PRP$': lambda word: predicative(word), # pronomina
'VBN': lambda word: lemma(word), # verba
'DT': lambda word: predicative(word), # pronomina
'VB': lambda word: lemma(word), # verba
'NN': lambda word: singularize(word), # nomina
'JJ': lambda word: predicative(word) # preposice
}
pattern_word = re.compile('[a-zA-Z]')
pattern_punctuation = re.compile(ur'[—\-|«»…–<>]')
def transform(tagword):
word = tagword[0]
part = tagword[1]
# if part == 'VBN':
