f44cb644187ca69159fd79fb917077520c3ea031,estnltk/examples/ex01.py,,,#,18

Before Change

corp_path = os.path.join(AA_PATH, "tea_AA_03_1.tasak.xml")

corp = json.loads(json.dumps(parse_tei_corpus(corp_path)))

from estnltk.corpus import Corpus
from estnltk.morf import PyVabamorfAnalyzer
from estnltk.ner import NerTagger

analyzer = PyVabamorfAnalyzer()
tagger = NerTagger()

analyzer(corp, inplace=True)
corp = tagger(corp, inplace=False)

corp = Corpus.construct(corp)
pprint (zip(corp.lemmas, corp.labels))

After Change

// tokenize it using default tokenizer
from estnltk import Tokenizer
tokenizer = Tokenizer()
document = tokenizer.tokenize(text)

// tokenized results
print (document.word_texts)
print (document.sentence_texts)
print (document.paragraph_texts)
print (document.text)

// start and end positions of words, sentences and paragraphs
from pprint import pprint
pprint (list(zip(document.word_texts, document.word_spans)))

Instances