def test_categories(self):
self.assertEqual(
ptb.categories(),
[
'adventure',
'belles_lettres',
'fiction',
'humor',
'lore',
'mystery',
'news',
'romance',
'science_fiction',
],
)
def test_categories(self):
self.assertEqual(
ptb.categories(),
[
"adventure",
"belles_lettres",
"fiction",
"humor",
"lore",
"mystery",
"news",
"romance",
"science_fiction",
],
)
def test_categories(self):
self.assertEqual(
ptb.categories(),
[
"adventure",
"belles_lettres",
"fiction",
"humor",
"lore",
"mystery",
"news",
"romance",
"science_fiction",
],
)
def verify_ptb_install():
# Download PTB metadata
assert (nltk.download('ptb'))
import hashlib
from nltk.corpus import ptb
# Be sure we have the category list
assert ('news' in ptb.categories())
m = hashlib.md5() # NOT SECURE!
m.update(','.join(ptb.fileids()).encode('utf8'))
if m.hexdigest() == 'e3b49c6df5529560b2945e6a4715f9b0':
print('Penn Treebank succesfully installed!')
return True
else:
print('Error installing Penn Treebank (hash mismatch).')
print('It may still work - try loading it in NLTK.')
return False
def verify_ptb_install():
# Download PTB metadata
assert(nltk.download('ptb'))
import hashlib
from nltk.corpus import ptb
# Be sure we have the category list
assert('news' in ptb.categories())
m = hashlib.md5() # NOT SECURE!
m.update(','.join(ptb.fileids()).encode('utf8'))
if m.hexdigest() == 'e3b49c6df5529560b2945e6a4715f9b0':
print('Penn Treebank succesfully installed!')
return True
else:
print('Error installing Penn Treebank (hash mismatch).')
print('It may still work - try loading it in NLTK.')
return False
def test_categories(self):
self.assertEqual(
ptb.categories(),
['adventure', 'belles_lettres', 'fiction', 'humor', 'lore', 'mystery', 'news', 'romance', 'science_fiction']
)