Browse Source

add data and test codes for testing OntoNotes and Conll2003 tasks

tags/v0.4.10
Yige Xu 5 years ago
parent
commit
d677ea879a
9 changed files with 240 additions and 3 deletions
  1. +10
    -0
      test/data_for_tests/io/OntoNotes/dev.txt
  2. +10
    -0
      test/data_for_tests/io/OntoNotes/test.txt
  3. +50
    -0
      test/data_for_tests/io/OntoNotes/train.txt
  4. +49
    -0
      test/data_for_tests/io/conll2003/dev.txt
  5. +51
    -0
      test/data_for_tests/io/conll2003/test.txt
  6. +48
    -0
      test/data_for_tests/io/conll2003/train.txt
  7. +7
    -1
      test/io/loader/test_conll_loader.py
  8. +13
    -1
      test/io/pipe/test_conll.py
  9. +2
    -1
      test/io/pipe/test_cws.py

+ 10
- 0
test/data_for_tests/io/OntoNotes/dev.txt View File

@@ -0,0 +1,10 @@

bc/msnbc/00/msnbc_0000 0 0 Hi UH (TOP(FRAG(INTJ*) - - - Dan_Abrams * -
bc/msnbc/00/msnbc_0000 0 1 everyone NN (NP*) - - - Dan_Abrams * -
bc/msnbc/00/msnbc_0000 0 2 /. . *)) - - - Dan_Abrams * -

bc/msnbc/00/msnbc_0000 0 0 first RB (TOP(S(ADVP* - - - Dan_Abrams * (ARGM-TMP* * * * -
bc/msnbc/00/msnbc_0000 0 1 up RB * - - - Dan_Abrams * * * * * -
bc/msnbc/00/msnbc_0000 0 2 on IN (PP* - - - Dan_Abrams * * * * * -
bc/msnbc/00/msnbc_0000 0 3 the DT (NP* - - - Dan_Abrams * * * * * -
bc/msnbc/00/msnbc_0000 0 4 docket NN *)) docket - - Dan_Abrams * * * * * -

+ 10
- 0
test/data_for_tests/io/OntoNotes/test.txt View File

@@ -0,0 +1,10 @@

bc/msnbc/00/msnbc_0007 0 0 Dealing VBG (TOP(VP* deal 01 - speaker_1 * (V*) -
bc/msnbc/00/msnbc_0007 0 1 with IN (PP* - - - speaker_1 * (ARG1* -
bc/msnbc/00/msnbc_0007 0 2 serial JJ (NP(NP* - - - speaker_1 * * (156
bc/msnbc/00/msnbc_0007 0 3 crimes NNS *) crime - 1 speaker_1 * * 156)
bc/msnbc/00/msnbc_0007 0 4 per FW (ADVP* - - - speaker_1 * * -
bc/msnbc/00/msnbc_0007 0 5 se FW *))) - - - speaker_1 * *) -
bc/msnbc/00/msnbc_0007 0 6 /. . *)) - - - speaker_1 * * -

bc/msnbc/00/msnbc_0007 0 0 We PRP (TOP(S(NP*) - - - speaker_1 * (ARG0*) * (90)

+ 50
- 0
test/data_for_tests/io/OntoNotes/train.txt View File

@@ -0,0 +1,50 @@

bc/msnbc/00/msnbc_0003 0 0 The DT (TOP(S(NP* - - - Chris_Matthews * * (ARG1* * * * * -
bc/msnbc/00/msnbc_0003 0 1 move NN *) move 02 2 Chris_Matthews * (V*) *) * * * * -
bc/msnbc/00/msnbc_0003 0 2 comes VBZ (VP* come 03 2 Chris_Matthews * * (V*) * * * * -
bc/msnbc/00/msnbc_0003 0 3 a DT (SBAR(NP* - - - Chris_Matthews (DATE* * (ARGM-TMP* * * * * -
bc/msnbc/00/msnbc_0003 0 4 month NN *) month - 2 Chris_Matthews *) * * * * * * -
bc/msnbc/00/msnbc_0003 0 5 before IN * - - - Chris_Matthews * * * * * * * -
bc/msnbc/00/msnbc_0003 0 6 the DT (S(NP* - - - Chris_Matthews * * * * (ARG1* (ARG0* * -
bc/msnbc/00/msnbc_0003 0 7 Senate NNP *) - - - Chris_Matthews (ORG) * * * *) *) * -
bc/msnbc/00/msnbc_0003 0 8 is VBZ (VP* be 03 - Chris_Matthews * * * (V*) * * * -
bc/msnbc/00/msnbc_0003 0 9 scheduled VBN (VP* schedule 01 - Chris_Matthews * * * * (V*) * * -
bc/msnbc/00/msnbc_0003 0 10 to TO (S(VP* - - - Chris_Matthews * * * * (ARG2* * * -
bc/msnbc/00/msnbc_0003 0 11 hold VB (VP* hold 04 8 Chris_Matthews * * * * * (V*) * -
bc/msnbc/00/msnbc_0003 0 12 confirmation NN (NP(NP* - - - Chris_Matthews * * * * * (ARG1* (ARG2*) -
bc/msnbc/00/msnbc_0003 0 13 hearings NNS *) hearing 01 1 Chris_Matthews * * * * * * (V*) -
bc/msnbc/00/msnbc_0003 0 14 on IN (PP* - - - Chris_Matthews * * * * * * (ARG1* -
bc/msnbc/00/msnbc_0003 0 15 President NNP (NP(NP(NP* - - - Chris_Matthews * * * * * * * (194
bc/msnbc/00/msnbc_0003 0 16 Bush NNP * - - - Chris_Matthews (PERSON) * * * * * * -
bc/msnbc/00/msnbc_0003 0 17 's POS *) - - - Chris_Matthews * * * * * * * 194)
bc/msnbc/00/msnbc_0003 0 18 Supreme NNP (NML* - - - Chris_Matthews (ORG* * * * * * * -
bc/msnbc/00/msnbc_0003 0 19 Court NNP *) - - - Chris_Matthews *) * * * * * * -
bc/msnbc/00/msnbc_0003 0 20 nominee NN *) - - - Chris_Matthews * * * * * * * -
bc/msnbc/00/msnbc_0003 0 21 John NNP (NP* - - - Chris_Matthews (PERSON* * * * * * * -
bc/msnbc/00/msnbc_0003 0 22 Roberts NNP *)))))))))))) - - - Chris_Matthews *) * *) * *) *) *) -
bc/msnbc/00/msnbc_0003 0 23 /. . *)) - - - Chris_Matthews * * * * * * * -

bc/msnbc/00/msnbc_0003 0 0 Senator NNP (TOP(S(NP(NP* - - - Chris_Matthews * (ARG1* * * (162
bc/msnbc/00/msnbc_0003 0 1 Chris NNP * - - - Chris_Matthews (PERSON* * * * -
bc/msnbc/00/msnbc_0003 0 2 Dodd NNP *) - - - Chris_Matthews *) * * * -
bc/msnbc/00/msnbc_0003 0 3 of IN (PP* - - - Chris_Matthews * * * * -
bc/msnbc/00/msnbc_0003 0 4 Connecticut NNP (NP*))) - - - Chris_Matthews (GPE) *) * * 162)
bc/msnbc/00/msnbc_0003 0 5 was VBD (VP* be 01 1 Chris_Matthews * (V*) * * -
bc/msnbc/00/msnbc_0003 0 6 among IN (PP* - - - Chris_Matthews * (ARG2* * * -
bc/msnbc/00/msnbc_0003 0 7 those DT (NP(NP* - - - Chris_Matthews * * (ARG0* * -
bc/msnbc/00/msnbc_0003 0 8 Democrats NNPS *) - - - Chris_Matthews (NORP) * *) * -
bc/msnbc/00/msnbc_0003 0 9 who WP (SBAR(WHNP*) - - - Chris_Matthews * * (R-ARG0*) * -
bc/msnbc/00/msnbc_0003 0 10 spoke VBD (S(VP* speak 03 5 Chris_Matthews * * (V*) * -
bc/msnbc/00/msnbc_0003 0 11 out RP (PRT*) - - - Chris_Matthews * * * * -
bc/msnbc/00/msnbc_0003 0 12 against IN (PP* - - - Chris_Matthews * * (ARG1* * -
bc/msnbc/00/msnbc_0003 0 13 Bolton NNP (NP(NP* - - - Chris_Matthews (PERSON) * * (ARG1* (31|(130
bc/msnbc/00/msnbc_0003 0 14 's POS *) - - - Chris_Matthews * * * *) 31)
bc/msnbc/00/msnbc_0003 0 15 appointment NN *)) appointment 01 1 Chris_Matthews * * *) (V*) 130)
bc/msnbc/00/msnbc_0003 0 16 today NN (NP*))))))) today - 2 Chris_Matthews (DATE) *) (ARGM-TMP*) * (121)
bc/msnbc/00/msnbc_0003 0 17 /. . *)) - - - Chris_Matthews * * * * -

bc/msnbc/00/msnbc_0003 0 0 I PRP (TOP(S(NP*) - - - Christopher_Dodd * * (ARG0*) * (162)
bc/msnbc/00/msnbc_0003 0 1 just RB (ADVP*) - - - Christopher_Dodd * * (ARGM-ADV*) * -
bc/msnbc/00/msnbc_0003 0 2 do VBP (VP* do 01 - Christopher_Dodd * (V*) * * -
bc/msnbc/00/msnbc_0003 0 3 n't RB * - - - Christopher_Dodd * * (ARGM-NEG*) * -
bc/msnbc/00/msnbc_0003 0 4 think VB (VP* think 01 1 Christopher_Dodd * * (V*) * -

+ 49
- 0
test/data_for_tests/io/conll2003/dev.txt View File

@@ -0,0 +1,49 @@
-DOCSTART- -X- -X- O

CRICKET NNP B-NP O
- : O O
LEICESTERSHIRE NNP B-NP B-ORG
TAKE NNP I-NP O
OVER IN B-PP O
AT NNP B-NP O
TOP NNP I-NP O
AFTER NNP I-NP O
INNINGS NNP I-NP O
VICTORY NN I-NP O
. . O O

LONDON NNP B-NP B-LOC
1996-08-30 CD I-NP O

Phil NNP B-NP B-PER
Simmons NNP I-NP I-PER
took VBD B-VP O
four CD B-NP O
for IN B-PP O
38 CD B-NP O
on IN B-PP O
Friday NNP B-NP O
as IN B-PP O
Leicestershire NNP B-NP B-ORG
beat VBD B-VP O
Somerset NNP B-NP B-ORG
by IN B-PP O
an DT B-NP O
innings NN I-NP O
and CC O O
39 CD B-NP O
runs NNS I-NP O
in IN B-PP O
two CD B-NP O
days NNS I-NP O
to TO B-VP O
take VB I-VP O
over IN B-PP O
at IN B-PP O
the DT B-NP O
head NN I-NP O
of IN B-PP O
the DT B-NP O
county NN I-NP O
championship NN I-NP O
. . O O

+ 51
- 0
test/data_for_tests/io/conll2003/test.txt View File

@@ -0,0 +1,51 @@
-DOCSTART- -X- -X- O

SOCCER NN B-NP O
- : O O
JAPAN NNP B-NP B-LOC
GET VB B-VP O
LUCKY NNP B-NP O
WIN NNP I-NP O
, , O O
THE NP B-NP B-PER
CHINA NNP I-NP I-PER
IN IN B-PP O
SURPRISE DT B-NP O
DEFEAT NN I-NP O
. . O O

Nadim NNP B-NP B-PER
Ladki NNP I-NP I-PER

AL-AIN NNP B-NP B-LOC
, , O O
United NNP B-NP B-LOC
Arab NNP I-NP I-LOC
Emirates NNPS I-NP I-LOC
1996-12-06 CD I-NP O

Japan NNP B-NP B-LOC
began VBD B-VP O
the DT B-NP O
defence NN I-NP O
of IN B-PP O
their PRP$ B-NP O
Asian JJ I-NP B-MISC
Cup NNP I-NP I-MISC
title NN I-NP O
with IN B-PP O
a DT B-NP O
lucky JJ I-NP O
2-1 CD I-NP O
win VBP B-VP O
against IN B-PP O
Syria NNP B-NP B-LOC
in IN B-PP O
a DT B-NP O
Group NNP I-NP O
C NNP I-NP O
championship NN I-NP O
match NN I-NP O
on IN B-PP O
Friday NNP B-NP O
. . O O

+ 48
- 0
test/data_for_tests/io/conll2003/train.txt View File

@@ -0,0 +1,48 @@
-DOCSTART- -X- -X- O

EU NNP B-NP B-ORG
rejects VBZ B-VP O
German JJ B-NP B-MISC
call NN I-NP O
to TO B-VP O
boycott VB I-VP O
British JJ B-NP B-MISC
lamb NN I-NP O
. . O O

Peter NNP B-NP B-PER
Blackburn NNP I-NP I-PER

BRUSSELS NNP B-NP B-LOC
1996-08-22 CD I-NP O

The DT B-NP O
European NNP I-NP B-ORG
Commission NNP I-NP I-ORG
said VBD B-VP O
on IN B-PP O
Thursday NNP B-NP O
it PRP B-NP O
disagreed VBD B-VP O
with IN B-PP O
German JJ B-NP B-MISC
advice NN I-NP O
to TO B-PP O
consumers NNS B-NP O
to TO B-VP O
shun VB I-VP O
British JJ B-NP B-MISC
lamb NN I-NP O
until IN B-SBAR O
scientists NNS B-NP O
determine VBP B-VP O
whether IN B-SBAR O
mad JJ B-NP O
cow NN I-NP O
disease NN I-NP O
can MD B-VP O
be VB I-VP O
transmitted VBN I-VP O
to TO B-PP O
sheep NN B-NP O
. . O O

+ 7
- 1
test/io/loader/test_conll_loader.py View File

@@ -26,6 +26,12 @@ class TestWeiboNER(unittest.TestCase):


class TestConll2003Loader(unittest.TestCase):
def test__load(self):
def test_load(self):
Conll2003Loader()._load('test/data_for_tests/conll_2003_example.txt')


class TestConllLoader(unittest.TestCase):
def test_conll(self):
db = Conll2003Loader().load('test/data_for_tests/io/conll2003')
print(db)


+ 13
- 1
test/io/pipe/test_conll.py View File

@@ -1,6 +1,7 @@
import unittest
import os
from fastNLP.io import MsraNERPipe, PeopleDailyPipe, WeiboNERPipe, Conll2003Pipe, Conll2003NERPipe
from fastNLP.io import MsraNERPipe, PeopleDailyPipe, WeiboNERPipe, Conll2003Pipe, Conll2003NERPipe, \
OntoNotesNERPipe


@unittest.skipIf('TRAVIS' in os.environ, "Skip in travis")
@@ -38,3 +39,14 @@ class TestNERPipe(unittest.TestCase):
print(data_bundle)
data_bundle = pipe(encoding_type='bioes').process_from_file(f'test/data_for_tests/io/{k}')
print(data_bundle)


class TestConll2003Pipe(unittest.TestCase):
def test_conll(self):
with self.assertWarns(Warning):
data_bundle = Conll2003Pipe().process_from_file('test/data_for_tests/io/conll2003')
print(data_bundle)

def test_OntoNotes(self):
data_bundle = OntoNotesNERPipe().process_from_file('test/data_for_tests/io/OntoNotes')
print(data_bundle)

+ 2
- 1
test/io/pipe/test_cws.py View File

@@ -19,5 +19,6 @@ class TestRunCWSPipe(unittest.TestCase):
dataset_names = ['msra', 'cityu', 'as', 'pku']
for dataset_name in dataset_names:
with self.subTest(dataset_name=dataset_name):
data_bundle = CWSPipe().process_from_file(f'test/data_for_tests/io/cws_{dataset_name}')
data_bundle = CWSPipe(bigrams=True, trigrams=True).\
process_from_file(f'test/data_for_tests/io/cws_{dataset_name}')
print(data_bundle)

Loading…
Cancel
Save