def test_parse(self):
# Assert parsed output with Penn Treebank II tags (slash-formatted).
# 1) "de zwarte kat" is a noun phrase, "op de mat" is a prepositional
# noun phrase.
v = nl.parser.parse("De zwarte kat zat op de mat.")
self.assertEqual(v,
"De/DT/B-NP/O zwarte/JJ/I-NP/O kat/NN/I-NP/O " +
"zat/VBD/B-VP/O " +
"op/IN/B-PP/B-PNP de/DT/B-NP/I-PNP mat/NN/I-NP/I-PNP ././O/O"
)
# 2) "jaagt" and "vogels" lemmata are "jagen" and "vogel".
v = nl.parser.parse("De zwarte kat jaagt op vogels.", lemmata=True)
self.assertEqual(v,
"De/DT/B-NP/O/de zwarte/JJ/I-NP/O/zwart kat/NN/I-NP/O/kat " +
"jaagt/VBZ/B-VP/O/jagen " +
"op/IN/B-PP/B-PNP/op vogels/NNS/B-NP/I-PNP/vogel ././O/O/."
)
# Assert the accuracy of the Dutch tagger.
i, n = 0, 0
for sentence in open(os.path.join(PATH, "corpora", "tagged-nl-twnc.txt")).readlines():
sentence = sentence.decode("utf-8").strip()
s1 = [w.split("/") for w in sentence.split(" ")]
s1 = [nl.wotan2penntreebank(w, tag) for w, tag in s1]
s2 = [[w for w, pos in s1]]
s2 = nl.parse(s2, tokenize=False)
s2 = [w.split("/") for w in s2.split(" ")]
for j in range(len(s1)):
if s1[j][1] == s2[j][1]:
i += 1
n += 1
self.assertTrue(float(i) / n > 0.90)
print("pattern.nl.parser.parse()")
def test_parse(self):
# Assert parsed output with Penn Treebank II tags (slash-formatted).
# 1) "de zwarte kat" is a noun phrase, "op de mat" is a prepositional
# noun phrase.
v = nl.parser.parse("De zwarte kat zat op de mat.")
self.assertEqual(
v, "De/DT/B-NP/O zwarte/JJ/I-NP/O kat/NN/I-NP/O " +
"zat/VBD/B-VP/O " +
"op/IN/B-PP/B-PNP de/DT/B-NP/I-PNP mat/NN/I-NP/I-PNP ././O/O")
# 2) "jaagt" and "vogels" lemmata are "jagen" and "vogel".
v = nl.parser.parse("De zwarte kat jaagt op vogels.", lemmata=True)
self.assertEqual(
v, "De/DT/B-NP/O/de zwarte/JJ/I-NP/O/zwart kat/NN/I-NP/O/kat " +
"jaagt/VBZ/B-VP/O/jagen " +
"op/IN/B-PP/B-PNP/op vogels/NNS/B-NP/I-PNP/vogel ././O/O/.")
# Assert the accuracy of the Dutch tagger.
i, n = 0, 0
for sentence in open(
os.path.join(PATH, "corpora",
"tagged-nl-twnc.txt")).readlines():
sentence = sentence.strip()
s1 = [w.split("/") for w in sentence.split(" ")]
s1 = [nl.wotan2penntreebank(w, tag) for w, tag in s1]
s2 = [[w for w, pos in s1]]
s2 = nl.parse(s2, tokenize=False)
s2 = [w.split("/") for w in s2.split(" ")]
for j in range(len(s1)):
if s1[j][1] == s2[j][1]:
i += 1
n += 1
self.assertTrue(float(i) / n > 0.90)
print("pattern.nl.parser.parse()")
def test_wotan2penntreebank(self):
# Assert tag translation.
for penntreebank, wotan in (
("NNP", "N(eigen,ev,neut)"),
("NNPS", "N(eigen,mv,neut)"),
("NN", "N(soort,ev,neut)"),
("NNS", "N(soort,mv,neut)"),
("VBZ", "V(refl,ott,3,ev)"),
("VBP", "V(intrans,ott,1_of_2_of_3,mv)"),
("VBD", "V(trans,ovt,1_of_2_of_3,mv)"),
("VBN", "V(trans,verl_dw,onverv)"),
("VBG", "V(intrans,teg_dw,onverv)"),
("VB", "V(intrans,inf)"),
("MD", "V(hulp_of_kopp,ott,3,ev)"),
("JJ", "Adj(attr,stell,onverv)"),
("JJR", "Adj(adv,vergr,onverv)"),
("JJS", "Adj(attr,overtr,verv_neut)"),
("RP", "Adv(deel_v)"),
("RB", "Adv(gew,geen_func,stell,onverv)"),
("DT", "Art(bep,zijd_of_mv,neut)"),
("CC", "Conj(neven)"),
("CD", "Num(hoofd,bep,zelfst,onverv)"),
("TO", "Prep(voor_inf)"),
("IN", "Prep(voor)"),
("PRP", "Pron(onbep,neut,attr)"),
("PRP$", "Pron(bez,2,ev,neut,attr)"),
(",", "Punc(komma)"),
("(", "Punc(haak_open)"),
(")", "Punc(haak_sluit)"),
(".", "Punc(punt)"),
("UH", "Int"),
("SYM", "Misc(symbool)")):
self.assertEqual(nl.wotan2penntreebank("", wotan)[1], penntreebank)
print("pattern.nl.wotan2penntreebank()")
def test_wotan2penntreebank(self):
# Assert tag translation.
for penntreebank, wotan in (
("NNP", "N(eigen,ev,neut)"),
("NNPS", "N(eigen,mv,neut)"),
("NN", "N(soort,ev,neut)"),
("NNS", "N(soort,mv,neut)"),
("VBZ", "V(refl,ott,3,ev)"),
("VBP", "V(intrans,ott,1_of_2_of_3,mv)"),
("VBD", "V(trans,ovt,1_of_2_of_3,mv)"),
("VBN", "V(trans,verl_dw,onverv)"),
("VBG", "V(intrans,teg_dw,onverv)"),
("VB", "V(intrans,inf)"),
("MD", "V(hulp_of_kopp,ott,3,ev)"),
("JJ", "Adj(attr,stell,onverv)"),
("JJR", "Adj(adv,vergr,onverv)"),
("JJS", "Adj(attr,overtr,verv_neut)"),
("RP", "Adv(deel_v)"),
("RB", "Adv(gew,geen_func,stell,onverv)"),
("DT", "Art(bep,zijd_of_mv,neut)"),
("CC", "Conj(neven)"),
("CD", "Num(hoofd,bep,zelfst,onverv)"),
("TO", "Prep(voor_inf)"),
("IN", "Prep(voor)"),
("PRP", "Pron(onbep,neut,attr)"),
("PRP$", "Pron(bez,2,ev,neut,attr)"),
(",", "Punc(komma)"),
("(", "Punc(haak_open)"),
(")", "Punc(haak_sluit)"),
(".", "Punc(punt)"),
("UH", "Int"),
("SYM", "Misc(symbool)")):
self.assertEqual(nl.wotan2penntreebank("", wotan)[1], penntreebank)
print "pattern.nl.wotan2penntreebank()"