Skip to content

refactor code and add test cases #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 14, 2023
Merged

refactor code and add test cases #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 22 additions & 14 deletions pythainlp/tag/pos_tag.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,7 +180,9 @@ def pos_tag_sents(


def pos_tag_transformers(
words: str, engine: str = "bert-base-th-cased-blackboard"
words: str,
engine: str = "bert",
corpus: str = "blackboard",
):
"""
"wangchanberta-ud-thai-pud-upos",
Expand All @@ -199,21 +201,27 @@ def pos_tag_transformers(
if not words:
return []

if engine == "wangchanberta-ud-thai-pud-upos":
model = AutoModelForTokenClassification.from_pretrained(
"Pavarissy/wangchanberta-ud-thai-pud-upos")
tokenizer = AutoTokenizer.from_pretrained("Pavarissy/wangchanberta-ud-thai-pud-upos")
elif engine == "mdeberta-v3-ud-thai-pud-upos":
model = AutoModelForTokenClassification.from_pretrained(
"Pavarissy/mdeberta-v3-ud-thai-pud-upos")
tokenizer = AutoTokenizer.from_pretrained("Pavarissy/mdeberta-v3-ud-thai-pud-upos")
elif engine == "bert-base-th-cased-blackboard":
model = AutoModelForTokenClassification.from_pretrained("lunarlist/pos_thai")
tokenizer = AutoTokenizer.from_pretrained("lunarlist/pos_thai")
_blackboard_support_engine = {
"bert" : "lunarlist/pos_thai",
}

_pud_support_engine = {
"wangchanberta" : "Pavarissy/wangchanberta-ud-thai-pud-upos",
"mdeberta" : "Pavarissy/mdeberta-v3-ud-thai-pud-upos",
}

if corpus == 'blackboard' and engine in _blackboard_support_engine.keys():
base_model = _blackboard_support_engine.get(engine)
model = AutoModelForTokenClassification.from_pretrained(base_model)
tokenizer = AutoTokenizer.from_pretrained(base_model)
elif corpus == 'pud' and engine in _pud_support_engine.keys():
base_model = _pud_support_engine.get(engine)
model = AutoModelForTokenClassification.from_pretrained(base_model)
tokenizer = AutoTokenizer.from_pretrained(base_model)
else:
raise ValueError(
"pos_tag_transformers not support {0} engine.".format(
engine
"pos_tag_transformers not support {0} engine or {1} corpus.".format(
engine, corpus
)
)

Expand Down
11 changes: 7 additions & 4 deletions tests/test_tag.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -367,10 +367,13 @@ def test_NNER_class(self):

def test_pos_tag_transformers(self):
self.assertIsNotNone(pos_tag_transformers(
words="แมวทำอะไรตอนห้าโมงเช้า", engine="bert-base-th-cased-blackboard"))
words="แมวทำอะไรตอนห้าโมงเช้า", engine="bert", corpus="blackboard"))
self.assertIsNotNone(pos_tag_transformers(
words="แมวทำอะไรตอนห้าโมงเช้า", engine="mdeberta-v3-ud-thai-pud-upos"))
words="แมวทำอะไรตอนห้าโมงเช้า", engine="mdeberta", corpus="pud"))
self.assertIsNotNone(pos_tag_transformers(
words="แมวทำอะไรตอนห้าโมงเช้า", engine="wangchanberta-ud-thai-pud-upos"))
words="แมวทำอะไรตอนห้าโมงเช้า", engine="wangchanberta", corpus="pud"))
with self.assertRaises(ValueError):
pos_tag_transformers(words="แมวทำอะไรตอนห้าโมงเช้า", engine="non-existing-engine")
pos_tag_transformers(words="แมวทำอะไรตอนห้าโมงเช้า", engine="non-existing-engine")
with self.assertRaises(ValueError):
pos_tag_transformers(words="แมวทำอะไรตอนห้าโมงเช้า", engine="bert",
corpus="non-existing corpus")