def readCorpusList(self):
reader = ChunkedCorpusReader('C:/nltk_data/corpora/cookbook',
r'.*\.chunk')
for chunk in reader.chunked_words():
try:
print(chunk.leaves())
except:
print(chunk)
tagset='en-brown')
reader1 = TaggedCorpusReader('/Users/atul/nltk_data',
r'brown.pos',
word_tokenizer=SpaceTokenizer())
print(reader.words())
print(reader.sents())
print(reader.tagged_words())
print(reader.tagged_sents())
print(
reader.tagged_words(tagset='universal')
) ## Mapping tags to universal format, if tagset is not correct every TAG will have UNK
## Reading chunk corpora #######
reader = ChunkedCorpusReader('/Users/atul/nltk_data',
r'treebank.chunk',
tagset='en-brown')
print(reader.chunked_words()) ## Word level structure
print(reader.chunked_sents()) ## Sentence level structure
print(reader.chunked_paras()) ## Paragraph level structure
## Reading classifed corpora ##################
## classification extracted using cat_pattern (from file name), or cat_dict or cat_file ######
from nltk.corpus.reader import CategorizedPlaintextCorpusReader
reader = CategorizedPlaintextCorpusReader(
'/Users/atul/nltk_data', r'movie_.*\.txt', cat_pattern=r'movie_(\w+)\.txt'
) ## Easiest is to read files for different category
reader.categories()
reader.fileids(categories=['neg'])
reader.fileids(categories=['pos'])
from nltk.corpus.reader import ChunkedCorpusReader
from nltk.tokenize import SpaceTokenizer
import nltk
d = nltk.data.find('corpora/cookbook')
reader = ChunkedCorpusReader(d, r'.*\.chunk')
print(reader.chunked_words())
print(reader.chunked_sents())
print(reader.chunked_paras())
# reader.chunked_sents()[0].draw()
print(reader.chunked_sents()[0].leaves())
