7218641444

Committed 15 Dec 2023 06:09AM UTC coverage: 84.897% (-0.6%) from 85.496%

Build # 7218641444

Build Type

push

github

Committed by

wannaphong

Commit Message

Fix code block

Run Details

6234 of 7343 relevant lines covered (84.9%)

0.85 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

35.0

/pythainlp/parse/core.py

# -*- coding: utf-8 -*-
# SPDX-FileCopyrightText: Copyright 2016-2023 PyThaiNLP Project
# SPDX-License-Identifier: Apache-2.0

from typing import List, Union


_tagger = None
_tagger_name = ""


def dependency_parsing(
    text: str,
    model: Union[str, None] = None,
    tag: str = "str",
    engine: str = "esupar",
) -> Union[List[List[str]], str]:
    """
    Dependency Parsing

    :param str text: text to apply dependency parsing to
    :param str model: model for using with engine \
        (for esupar and transformers_ud)
    :param str tag: output type (str or list)
    :param str engine: the name of dependency parser
    :return: str (conllu) or List
    :rtype: Union[List[List[str]], str]

    **Options for engine**
        * *esupar* (default) - Tokenizer, POS tagger and Dependency parser \
            using BERT/RoBERTa/DeBERTa models. `GitHub \
                <https://github.com/KoichiYasuoka/esupar>`_
        * *spacy_thai* - Tokenizer, POS tagger, and dependency parser \
            for the Thai language, using Universal Dependencies. \
            `GitHub <https://github.com/KoichiYasuoka/spacy-thai>`_
        * *transformers_ud* - TransformersUD \
            `GitHub <https://github.com/KoichiYasuoka/>`_
        * *ud_goeswith* - POS tagging and dependency parsing \
            using `goeswith` for subwords

    **Options for model (esupar engine)**
        * *th* (default) - KoichiYasuoka/roberta-base-thai-spm-upos model \
            `Huggingface \
            <https://huggingface.co/KoichiYasuoka/roberta-base-thai-spm-upos>`_
        * *KoichiYasuoka/deberta-base-thai-upos* - DeBERTa(V2) model \
            pre-trained on Thai Wikipedia texts for POS tagging and \
            dependency parsing `Huggingface \
            <https://huggingface.co/KoichiYasuoka/deberta-base-thai-upos>`_
        * *KoichiYasuoka/roberta-base-thai-syllable-upos* - RoBERTa model \
            pre-trained on Thai Wikipedia texts for POS tagging and \
            dependency parsing. (syllable level) `Huggingface \
            <https://huggingface.co/KoichiYasuoka/roberta-base-thai-syllable-upos>`_
        * *KoichiYasuoka/roberta-base-thai-char-upos* - RoBERTa model \
            pre-trained on Thai Wikipedia texts for POS tagging \
            and dependency parsing. (char level) `Huggingface \
            <https://huggingface.co/KoichiYasuoka/roberta-base-thai-char-upos>`_

    If you want to train models for esupar, you can read \
    `Huggingface <https://github.com/KoichiYasuoka/esupar>`_

    **Options for model (transformers_ud engine)**
        * *KoichiYasuoka/deberta-base-thai-ud-head* (default) - \
            DeBERTa(V2) model pretrained on Thai Wikipedia texts \
            for dependency parsing (head-detection using Universal \
            Dependencies) and question-answering, derived from \
            deberta-base-thai. \
            trained by th_blackboard.conll. `Huggingface \
            <https://huggingface.co/KoichiYasuoka/deberta-base-thai-ud-head>`_
        * *KoichiYasuoka/roberta-base-thai-spm-ud-head* - \
            roberta model pretrained on Thai Wikipedia texts \
            for dependency parsing. `Huggingface \
            <https://huggingface.co/KoichiYasuoka/roberta-base-thai-spm-ud-head>`_

    **Options for model (ud_goeswith engine)**
        * *KoichiYasuoka/deberta-base-thai-ud-goeswith* (default) - \
            This is a DeBERTa(V2) model pre-trained on Thai Wikipedia \
            texts for POS tagging and dependency parsing (using goeswith for subwords) \
            `Huggingface <https://huggingface.co/KoichiYasuoka/deberta-base-thai-ud-goeswith>`_

    :Example:
    ::

        from pythainlp.parse import dependency_parsing

        print(dependency_parsing("ผมเป็นคนดี", engine="esupar"))
        # output:
        # 1       ผม      _       PRON    _       _       3       nsubj   _       SpaceAfter=No
        # 2       เป็น     _       VERB    _       _       3       cop     _       SpaceAfter=No
        # 3       คน      _       NOUN    _       _       0       root    _       SpaceAfter=No
        # 4       ดี       _       VERB    _       _       3       acl     _       SpaceAfter=No

        print(dependency_parsing("ผมเป็นคนดี", engine="spacy_thai"))
        # output:
        # 1       ผม              PRON    PPRS    _       2       nsubj   _       SpaceAfter=No
        # 2       เป็น             VERB    VSTA    _       0       ROOT    _       SpaceAfter=No
        # 3       คนดี             NOUN    NCMN    _       2       obj     _       SpaceAfter=No
    """
    global _tagger, _tagger_name

    if _tagger_name != engine:
        if engine == "esupar":
            from pythainlp.parse.esupar_engine import Parse

            _tagger = Parse(model=model)
        elif engine == "transformers_ud":
            from pythainlp.parse.transformers_ud import Parse

            _tagger = Parse(model=model)
        elif engine == "spacy_thai":
            from pythainlp.parse.spacy_thai_engine import Parse

            _tagger = Parse()
        elif engine == "ud_goeswith":
            from pythainlp.parse.ud_goeswith import Parse

            _tagger = Parse(model=model)
        else:
            raise NotImplementedError("The engine doesn't support.")

    _tagger_name = engine

    return _tagger(text, tag=tag)

1	# -- coding: utf-8 --
2	# SPDX-FileCopyrightText: Copyright 2016-2023 PyThaiNLP Project
3	# SPDX-License-Identifier: Apache-2.0
4
5	from typing import List, Union	1✔
6
7
8	_tagger = None	1✔
9	_tagger_name = ""	1✔
10
11
12	def dependency_parsing(	1✔
13	text: str,
14	model: Union[str, None] = None,
15	tag: str = "str",
16	engine: str = "esupar",
17	) -> Union[List[List[str]], str]:
18	"""
19	Dependency Parsing
20
21	:param str text: text to apply dependency parsing to
22	:param str model: model for using with engine \
23	(for esupar and transformers_ud)
24	:param str tag: output type (str or list)
25	:param str engine: the name of dependency parser
26	:return: str (conllu) or List
27	:rtype: Union[List[List[str]], str]
28
29	Options for engine
30	* esupar (default) - Tokenizer, POS tagger and Dependency parser \
31	using BERT/RoBERTa/DeBERTa models. `GitHub \
32	<https://github.com/KoichiYasuoka/esupar>`_
33	* spacy_thai - Tokenizer, POS tagger, and dependency parser \
34	for the Thai language, using Universal Dependencies. \
35	`GitHub <https://github.com/KoichiYasuoka/spacy-thai>`_
36	* transformers_ud - TransformersUD \
37	`GitHub <https://github.com/KoichiYasuoka/>`_
38	* ud_goeswith - POS tagging and dependency parsing \
39	using `goeswith` for subwords
40
41	Options for model (esupar engine)
42	* th (default) - KoichiYasuoka/roberta-base-thai-spm-upos model \
43	`Huggingface \
44	<https://huggingface.co/KoichiYasuoka/roberta-base-thai-spm-upos>`_
45	* KoichiYasuoka/deberta-base-thai-upos - DeBERTa(V2) model \
46	pre-trained on Thai Wikipedia texts for POS tagging and \
47	dependency parsing `Huggingface \
48	<https://huggingface.co/KoichiYasuoka/deberta-base-thai-upos>`_
49	* KoichiYasuoka/roberta-base-thai-syllable-upos - RoBERTa model \
50	pre-trained on Thai Wikipedia texts for POS tagging and \
51	dependency parsing. (syllable level) `Huggingface \
52	<https://huggingface.co/KoichiYasuoka/roberta-base-thai-syllable-upos>`_
53	* KoichiYasuoka/roberta-base-thai-char-upos - RoBERTa model \
54	pre-trained on Thai Wikipedia texts for POS tagging \
55	and dependency parsing. (char level) `Huggingface \
56	<https://huggingface.co/KoichiYasuoka/roberta-base-thai-char-upos>`_
57
58	If you want to train models for esupar, you can read \
59	`Huggingface <https://github.com/KoichiYasuoka/esupar>`_
60
61	Options for model (transformers_ud engine)
62	* KoichiYasuoka/deberta-base-thai-ud-head (default) - \
63	DeBERTa(V2) model pretrained on Thai Wikipedia texts \
64	for dependency parsing (head-detection using Universal \
65	Dependencies) and question-answering, derived from \
66	deberta-base-thai. \
67	trained by th_blackboard.conll. `Huggingface \
68	<https://huggingface.co/KoichiYasuoka/deberta-base-thai-ud-head>`_
69	* KoichiYasuoka/roberta-base-thai-spm-ud-head - \
70	roberta model pretrained on Thai Wikipedia texts \
71	for dependency parsing. `Huggingface \
72	<https://huggingface.co/KoichiYasuoka/roberta-base-thai-spm-ud-head>`_
73
74	Options for model (ud_goeswith engine)
75	* KoichiYasuoka/deberta-base-thai-ud-goeswith (default) - \
76	This is a DeBERTa(V2) model pre-trained on Thai Wikipedia \
77	texts for POS tagging and dependency parsing (using goeswith for subwords) \
78	`Huggingface <https://huggingface.co/KoichiYasuoka/deberta-base-thai-ud-goeswith>`_
79
80	:Example:
81	::
82
83	from pythainlp.parse import dependency_parsing
84
85	print(dependency_parsing("ผมเป็นคนดี", engine="esupar"))
86	# output:
87	# 1 ผม _ PRON _ _ 3 nsubj _ SpaceAfter=No
88	# 2 เป็น _ VERB _ _ 3 cop _ SpaceAfter=No
89	# 3 คน _ NOUN _ _ 0 root _ SpaceAfter=No
90	# 4 ดี _ VERB _ _ 3 acl _ SpaceAfter=No
91
92	print(dependency_parsing("ผมเป็นคนดี", engine="spacy_thai"))
93	# output:
94	# 1 ผม PRON PPRS _ 2 nsubj _ SpaceAfter=No
95	# 2 เป็น VERB VSTA _ 0 ROOT _ SpaceAfter=No
96	# 3 คนดี NOUN NCMN _ 2 obj _ SpaceAfter=No
97	"""
98	global _tagger, _tagger_name
99
100	if _tagger_name != engine:	1✔
101	if engine == "esupar":	1✔
102	from pythainlp.parse.esupar_engine import Parse	1✔
103
104	_tagger = Parse(model=model)	×
105	elif engine == "transformers_ud":	×
106	from pythainlp.parse.transformers_ud import Parse	×
107
108	_tagger = Parse(model=model)	×
109	elif engine == "spacy_thai":	×
110	from pythainlp.parse.spacy_thai_engine import Parse	×
111
112	_tagger = Parse()	×
113	elif engine == "ud_goeswith":	×
114	from pythainlp.parse.ud_goeswith import Parse	×
115
116	_tagger = Parse(model=model)	×
117	else:
118	raise NotImplementedError("The engine doesn't support.")	×
119
120	_tagger_name = engine	×
121
122	return _tagger(text, tag=tag)	×

PyThaiNLP / pythainlp / 7218641444

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous