brill-postagger 0.1.1__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- brill_postagger-0.1.1.dist-info/METADATA +13 -0
- brill_postagger-0.1.1.dist-info/RECORD +17 -0
- brill_postagger-0.1.1.dist-info/WHEEL +5 -0
- brill_postagger-0.1.1.dist-info/top_level.txt +1 -0
- brill_postaggers/__init__.py +37 -0
- brill_postaggers/ca_ancora-ud-brill.pkl +0 -0
- brill_postaggers/da_ddt-ud-brill.pkl +0 -0
- brill_postaggers/de_gsd-ud-brill.pkl +0 -0
- brill_postaggers/en_ewt-ud-brill.pkl +0 -0
- brill_postaggers/es_ancora-ud-brill.pkl +0 -0
- brill_postaggers/eu_bdt-ud-brill.pkl +0 -0
- brill_postaggers/fr_gsd-ud-brill.pkl +0 -0
- brill_postaggers/gl_ctg-ud-brill.pkl +0 -0
- brill_postaggers/it_vit-ud-brill.pkl +0 -0
- brill_postaggers/nl_alpino-ud-brill.pkl +0 -0
- brill_postaggers/pt_bosque-ud-brill.pkl +0 -0
- brill_postaggers/version.py +6 -0
|
@@ -0,0 +1,13 @@
|
|
|
1
|
+
Metadata-Version: 2.1
|
|
2
|
+
Name: brill-postagger
|
|
3
|
+
Version: 0.1.1
|
|
4
|
+
Summary: Brill Postagger for various languages using NLTK
|
|
5
|
+
Home-page: https://github.com/TigreGotico/brill_postaggers
|
|
6
|
+
Author: JarbasAi
|
|
7
|
+
Author-email: jarbasai@mailfence.com
|
|
8
|
+
Classifier: Programming Language :: Python :: 3
|
|
9
|
+
Classifier: License :: OSI Approved :: MIT License
|
|
10
|
+
Classifier: Operating System :: OS Independent
|
|
11
|
+
Requires-Python: >=3.9
|
|
12
|
+
Requires-Dist: nltk
|
|
13
|
+
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
brill_postaggers/__init__.py,sha256=0ZyNcYNYnD52ND53Mw266eNbH5D6RLuanh34MhVznRU,1041
|
|
2
|
+
brill_postaggers/ca_ancora-ud-brill.pkl,sha256=bNIvxc5qGwGbtKaC2h9KvlY7YJvlCmqesLHXKruRpVE,455670
|
|
3
|
+
brill_postaggers/da_ddt-ud-brill.pkl,sha256=jfBHIQ9HPZcOX3SBjMxPdC6Lky7E-Psu0EnDz_J__Js,199618
|
|
4
|
+
brill_postaggers/de_gsd-ud-brill.pkl,sha256=OrvzjQUCxJabiaoMImiTDJ9iKUL_yQbBpwEgDE1kIow,617411
|
|
5
|
+
brill_postaggers/en_ewt-ud-brill.pkl,sha256=w77qqvBO5ikmq4FyXZiuOFfUkjY_dm3IkyLnj3m7FCU,351010
|
|
6
|
+
brill_postaggers/es_ancora-ud-brill.pkl,sha256=Tq-u1KAYSb4FjXxcTO0ipRajmdoISPcV6lb_k-6LsBM,487110
|
|
7
|
+
brill_postaggers/eu_bdt-ud-brill.pkl,sha256=o4nz80P2avs9PqTCBxVSWZMPseihr2ay6W8bemdcQV4,210031
|
|
8
|
+
brill_postaggers/fr_gsd-ud-brill.pkl,sha256=7chlLTquLp3u81FXirmt9411jvgIMChW1a8SiCVuJNU,524861
|
|
9
|
+
brill_postaggers/gl_ctg-ud-brill.pkl,sha256=o2EaBNpNGk6TKSwBHExxvZQQOaIzh8e9RrwiVwAqBE4,110388
|
|
10
|
+
brill_postaggers/it_vit-ud-brill.pkl,sha256=LhIjvOTbBCk5R0AzJZv9cmStJ3bH9EO9NoAl6V94Ep0,334131
|
|
11
|
+
brill_postaggers/nl_alpino-ud-brill.pkl,sha256=rYGDVc3fRLO2qPdJ3zU_EWHryuYl715p0yuYqybnzGA,321092
|
|
12
|
+
brill_postaggers/pt_bosque-ud-brill.pkl,sha256=g1aND1pmE16mHrIxWlFyLaBzMq-8_rjP-pWmWfoHH20,332838
|
|
13
|
+
brill_postaggers/version.py,sha256=YO17Z54RmHA5oRw9Kj8GqtARGSultBm53Tz4k26JgYE,114
|
|
14
|
+
brill_postagger-0.1.1.dist-info/METADATA,sha256=UL35jXLlRDIhNMRv17V5OcU3619EAehT9pVmcp-mko0,420
|
|
15
|
+
brill_postagger-0.1.1.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
|
|
16
|
+
brill_postagger-0.1.1.dist-info/top_level.txt,sha256=AxlyH2Mx_X0YODSowoeZ7aAIMNt8d4p44jY7XKTnoh4,17
|
|
17
|
+
brill_postagger-0.1.1.dist-info/RECORD,,
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
brill_postaggers
|
|
@@ -0,0 +1,37 @@
|
|
|
1
|
+
import os.path
|
|
2
|
+
import pickle
|
|
3
|
+
|
|
4
|
+
import nltk
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
class BrillPostagger:
|
|
8
|
+
MODELS = {
|
|
9
|
+
"ca": "ca_ancora-ud-brill",
|
|
10
|
+
"da": "da_ddt-ud-brill",
|
|
11
|
+
"de": "de_gsd-ud-brill",
|
|
12
|
+
"en": "en_ewt-ud-brill",
|
|
13
|
+
"es": "es_ancora-ud-brill",
|
|
14
|
+
"eu": "eu_bdt-ud-brill",
|
|
15
|
+
"fr": "fr_gsd-ud-brill",
|
|
16
|
+
"gl": "gl_ctg-ud-brill",
|
|
17
|
+
"it": "it_vit-ud-brill",
|
|
18
|
+
"nl": "nl_alpino-ud-brill",
|
|
19
|
+
"pt": "pt_bosque-ud-brill"
|
|
20
|
+
}
|
|
21
|
+
def __init__(self, model: str):
|
|
22
|
+
with open(model, "rb") as f:
|
|
23
|
+
self.tagger = pickle.load(f)
|
|
24
|
+
|
|
25
|
+
@staticmethod
|
|
26
|
+
def from_pretrained(lang: str):
|
|
27
|
+
lang = lang.split("-")[0].lower()
|
|
28
|
+
model = BrillPostagger.MODELS[lang]
|
|
29
|
+
return BrillPostagger(f"{os.path.dirname(__file__)}/{model}.pkl")
|
|
30
|
+
|
|
31
|
+
def tag(self, sentence: str):
|
|
32
|
+
tokens = nltk.word_tokenize(sentence)
|
|
33
|
+
return self.tagger.tag(tokens)
|
|
34
|
+
|
|
35
|
+
if __name__ == "__main__":
|
|
36
|
+
tagger = BrillPostagger.from_pretrained("pt")
|
|
37
|
+
print(tagger.tag("como está o tempo lá fora?"))
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|