''' load a sample wordlist '''
#import nltk.data
nltk.data.load('corpora/cookbook/GL_Sequent.txt', format='raw')
'nltk\n'
from nltk.corpus.reader import WordListCorpusReader
reader = WordListCorpusReader(path + '/corpora/cookbook/', ['GL_Sequent.txt'])
reader.words()
''' reading a tagged corpus '''
from nltk.corpus.reader import TaggedCorpusReader
reader = TaggedCorpusReader(path + '/corpora/cookbook/', r'.*\.pos')
reader.words()
reader.tagged_words()
reader.sents()
reader.tagged_sents()
reader.paras()
reader.tagged_paras()
''' different Tokenizer - works? '''
from nltk.tokenize import SpaceTokenizer
reader = TaggedCorpusReader(path + '/corpora/cookbook/', r'.*\.pos',word_tokenizer=SpaceTokenizer())
reader.words()
''' different Sentence Tokenizer '''
from nltk.tokenize import LineTokenizer
reader = TaggedCorpusReader(path + '/corpora/cookbook/', r'.*\.pos', sent_tokenizer=LineTokenizer())
reader.sents()
''' chunked Corpus Reader '''
