from nltk.corpus.reader import WordListCorpusReader
import nltk
# print(nltk.data.find('corpora/cookbook'))
# print(nltk.data.find('corpora/cookbook/wordlist.txt'))
d = nltk.data.find('corpora/cookbook')
reader = WordListCorpusReader(d, ['wordlist.txt'])
print(reader.words())
print(reader.fileids())
def read_emails(self, path):
# Get all files
files = [f for f in listdir(path) if isfile(join(path, f))]
try:
del (files[files.index('DS_Store')])
except:
pass
reader = WordListCorpusReader(path, files)
cleaner = Cleaner()
emails = list()
# Creates the Email Object out of each email file and appends to list
for file_id in reader.fileids():
with open(path + file_id, 'r') as current_file:
cleaned_contents = cleaner.clean_file(current_file.read())
split_email_header, split_email_body, split_email_file_id = self.divide(
cleaned_contents, file_id)
emails.append(
Email(split_email_header, split_email_body,
split_email_file_id))
# Return list of Email objects
return emails
def read_emails(path):
files = [f for f in listdir(path) if isfile(join(path, f))]
try:
del (files[files.index('.DS_Store')])
except:
pass
reader = WordListCorpusReader(path, files)
text = clean(reader.raw())
emails = split_emails(text, reader.fileids())
return emails
import nltk.data
from nltk.corpus.reader import WordListCorpusReader
from nltk.corpus import names
from nltk.corpus.reader import TaggedCorpusReader
from nltk.tokenize import SpaceTokenizer
from nltk.corpus import treebank
wordlist = WordListCorpusReader("C:/nltk_data/corpora/cookbook", ['wordlist'])
print(wordlist.words())
print(wordlist.fileids())
print(names.fileids())
print(len(names.words('male.txt')))
reader = TaggedCorpusReader("C:/nltk_data/corpora/treebank/tagged",
r'.*\.pos',
word_tokenizer=SpaceTokenizer(),
tagset='en-brown')
print(reader.words('wsj_0001.pos'))
print(reader.tagged_words('wsj_0001.pos'))
print(reader.tagged_sents('wsj_0001.pos'))
print(reader.tagged_paras('wsj_0001.pos'))
print(reader.fileids())
print("\n")
print(reader.tagged_words('wsj_0001.pos', tagset='universal'))
print(treebank.tagged_words())
''' 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
reader = LazyCorpusLoader('cookbook', WordListCorpusReader,['wordlist'])
########## WORDLIST CORPUS READER ###############
#Basic Corpus Reader
from nltk.corpus.reader import WordListCorpusReader
#List of a few thousand names organized by gender
from nltk.corpus import names
#List of english words
from nltk.corpus import words
nltkDir="C:\\Users\\Matrix\\AppData\\Roaming\\nltk_data\\corpora\\cookbook\\"
#nltkFile="mywords.txt"
#source=nltkDir+nltkFile
### One File WordListCorpusReader
reader=WordListCorpusReader(nltkDir,['wordlist.txt'])
print reader.words()
print reader.fileids()
### MultiFile WordListCorpusReader
#To get the names of the files in the corpus use the "fileids" command
names.fileids()
print len(names.words('female.txt'))
print len(names.words('female.txt'))
words.fileids()
print len(words.words('en-basic'))
print len(words.words('en'))
###Chunked Corpus Reader
