def test_parsed_sents(self):
parsed_sents = conll2007.parsed_sents("esp.train")[0]
self.assertEqual(
parsed_sents.tree(),
Tree(
"fortaleció",
[
Tree(
"aumento",
["El", Tree("del", [Tree("índice", [Tree("de", [Tree("desempleo", ["estadounidense"])])])])],
),
"hoy",
"considerablemente",
Tree(
"al",
[
Tree(
"euro",
[
Tree(
"cotizaba",
[
",",
"que",
Tree("a", [Tree("15.35", ["las", "GMT"])]),
"se",
Tree(
"en",
[
Tree(
"mercado",
["el", Tree("de", ["divisas"]), Tree("de", ["Fráncfort"])],
)
],
),
Tree("a", ["0,9452_dólares"]),
Tree(
"frente_a",
[
",",
Tree(
"0,9349_dólares",
["los", Tree("de", [Tree("mañana", ["esta"])])],
),
],
),
],
)
],
)
],
),
".",
],
),
)
def test_parsed_sents(self):
parsed_sents = conll2007.parsed_sents('esp.train')[0]
self.assertEqual(parsed_sents.tree(),
Tree('fortaleció', [
Tree('aumento', [
'El',
Tree('del', [
Tree('índice', [
Tree('de', [
Tree('desempleo', ['estadounidense'])
])
])
])
]),
'hoy',
'considerablemente',
Tree('al', [
Tree('euro', [
Tree('cotizaba', [
',',
'que',
Tree('a', [
Tree('15.35', ['las', 'GMT'])
]),
'se',
Tree('en', [
Tree('mercado', [
'el',
Tree('de', ['divisas']),
Tree('de', ['Fráncfort'])
])
]),
Tree('a', ['0,9452_dólares']),
Tree('frente_a', [
',',
Tree('0,9349_dólares', [
'los',
Tree('de', [
Tree('mañana', ['esta'])
])
])
])
])
])
]),
'.'
])
)
def test_parsed_sents(self):
parsed_sents = conll2007.parsed_sents('esp.train')[0]
self.assertEqual(parsed_sents.tree(),
Tree('fortaleció', [
Tree('aumento', [
'El',
Tree('del', [
Tree('índice', [
Tree('de', [
Tree('desempleo', ['estadounidense'])
])
])
])
]),
'hoy',
'considerablemente',
Tree('al', [
Tree('euro', [
Tree('cotizaba', [
',',
'que',
Tree('a', [
Tree('15.35', ['las', 'GMT'])
]),
'se',
Tree('en', [
Tree('mercado', [
'el',
Tree('de', ['divisas']),
Tree('de', ['Fráncfort'])
])
]),
Tree('a', ['0,9452_dólares']),
Tree('frente_a', [
',',
Tree('0,9349_dólares', [
'los',
Tree('de', [
Tree('mañana', ['esta'])
])
])
])
])
])
]),
'.'
])
)
def test_parsed_sents(self):
parsed_sents = conll2007.parsed_sents("esp.train")[0]
self.assertEqual(
parsed_sents.tree(),
Tree(
"fortaleció",
[
Tree(
"aumento",
[
"El",
Tree(
"del",
[
Tree(
"índice",
[
Tree(
"de",
[
Tree(
"desempleo",
["estadounidense"])
],
)
],
)
],
),
],
),
"hoy",
"considerablemente",
Tree(
"al",
[
Tree(
"euro",
[
Tree(
"cotizaba",
[
",",
"que",
Tree("a", [
Tree("15.35", ["las", "GMT"])
]),
"se",
Tree(
"en",
[
Tree(
"mercado",
[
"el",
Tree(
"de",
["divisas"]),
Tree(
"de",
["Fráncfort"]),
],
)
],
),
Tree("a", ["0,9452_dólares"]),
Tree(
"frente_a",
[
",",
Tree(
"0,9349_dólares",
[
"los",
Tree(
"de",
[
Tree(
"mañana",
[
"esta"
],
)
],
),
],
),
],
),
],
)
],
)
],
),
".",
],
),
)
[0]) # doctest: +ELLIPSIS +NORMALIZE_WHITESPACE
# nltk.download('ptb')
print(ptb.fileids()) # doctest: +SKIP
# download the corpus from here: https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/treebank.zip
# then extract and place to the following location: .../nltk_data/corpora/ptb/
print(ptb.words('treebank/combined/wsj_0003.mrg')) # doctest: +SKIP
print(ptb.tagged_words('treebank/combined/wsj_0003.mrg')) # doctest: +SKIP
# print(ptb.categories()) # doctest: +SKIP
# print(ptb.fileids('news')) # doctest: +SKIP
# print(ptb.words(categories=['humor', 'fiction'])) # doctest: +SKIP
# nltk.download('sinica_treebank')
print(sinica_treebank.sents()) # doctest: +SKIP
print(sinica_treebank.parsed_sents()[25]) # doctest: +SKIP
# nltk.download('conll2007')
print(conll2007.sents('esp.train')[0]) # doctest: +SKIP
print(conll2007.parsed_sents('esp.train')[0]) # doctest: +SKIP
print(conll2007.parsed_sents('esp.train')[0].tree()) # doctest: +SKIP
# for tree in ycoe.parsed_sents('cocuraC')[:4]:
# print(tree) # doctest: +SKIP
# word lists and lexicons
print(words.fileids())
print(words.words('en')) # doctest: +ELLIPSIS
print(stopwords.fileids()) # doctest: +ELLIPSIS
print(stopwords.words('portuguese')) # doctest: +ELLIPSIS
# nltk.download('names')
print(names.fileids())
print(names.words('male.txt')) # doctest: +ELLIPSIS
print(names.words('female.txt')) # doctest: +ELLIPSIS
# nltk.download('cmudict')
print(cmudict.entries()[653:659]) # doctest: +ELLIPSIS +NORMALIZE_WHITESPACE
# Load the entire cmudict corpus into a Python dictionary:
