''' draw tree '''
reader.chunked_sents()[0].draw()
''' get leaves '''
reader.chunked_words()[0].leaves()
reader.chunked_sents()[0].leaves()
reader.chunked_paras()[0][0].leaves()
''' categorized corpus '''
from nltk.corpus import brown
brown.categories()
from nltk.corpus.reader import CategorizedPlaintextCorpusReader
reader = CategorizedPlaintextCorpusReader(path + '/corpora/cookbook/', r'movie_.*\.txt', cat_pattern=r'movie_(\w+)\.txt')
reader.categories()
reader.fileids(categories=['neg'])
reader.fileids(categories=['pos'])
''' using a categorized chunked corpus reader '''
#import nltk.data
from catchunked import CategorizedChunkedCorpusReader
path = nltk.data.find('corpora/treebank/tagged')
reader = CategorizedChunkedCorpusReader(path, r'wsj_.*\.pos',cat_pattern=r'wsj_(.*)\.pos')
#len(reader.categories()) == len(reader.fileids())
len(reader.chunked_sents(categories=['0001']))
''' Lazy corpus loader '''
from nltk.corpus.util import LazyCorpusLoader
#from nltk.corpus.reader import WordListCorpusReader
