move pos_tag from pythainlp.tag to pythainlp.tag.pos_tag (build and deploy docs)

Author: wannaphong

pythainlp/tag/__init__.py

@@ -6,251 +6,7 @@
 such as its Part-of-Speech (POS) tag, and Named Entity Recognition (NER) tag.
 """
 
-from typing import List, Tuple
-
 __all__ = ["pos_tag", "pos_tag_sents", "tag_provinces"]
 from .locations import tag_provinces
-
-# tag map for orchid to Universal Dependencies
-# from Korakot Chaovavanich
-_TAG_MAP_UD = {
-    # NOUN
-    "NOUN": "NOUN",
-    "NCMN": "NOUN",
-    "NTTL": "NOUN",
-    "CNIT": "NOUN",
-    "CLTV": "NOUN",
-    "CMTR": "NOUN",
-    "CFQC": "NOUN",
-    "CVBL": "NOUN",
-    # VERB
-    "VACT": "VERB",
-    "VSTA": "VERB",
-    # PROPN
-    "PROPN": "PROPN",
-    "NPRP": "PROPN",
-    # ADJ
-    "ADJ": "ADJ",
-    "NONM": "ADJ",
-    "VATT": "ADJ",
-    "DONM": "ADJ",
-    # ADV
-    "ADV": "ADV",
-    "ADVN": "ADV",
-    "ADVI": "ADV",
-    "ADVP": "ADV",
-    "ADVS": "ADV",
-    # INT
-    "INT": "INTJ",
-    # PRON
-    "PRON": "PRON",
-    "PPRS": "PRON",
-    "PDMN": "PRON",
-    "PNTR": "PRON",
-    # DET
-    "DET": "DET",
-    "DDAN": "DET",
-    "DDAC": "DET",
-    "DDBQ": "DET",
-    "DDAQ": "DET",
-    "DIAC": "DET",
-    "DIBQ": "DET",
-    "DIAQ": "DET",
-    # NUM
-    "NUM": "NUM",
-    "NCNM": "NUM",
-    "NLBL": "NUM",
-    "DCNM": "NUM",
-    # AUX
-    "AUX": "AUX",
-    "XVBM": "AUX",
-    "XVAM": "AUX",
-    "XVMM": "AUX",
-    "XVBB": "AUX",
-    "XVAE": "AUX",
-    # ADP
-    "ADP": "ADP",
-    "RPRE": "ADP",
-    # CCONJ
-    "CCONJ": "CCONJ",
-    "JCRG": "CCONJ",
-    # SCONJ
-    "SCONJ": "SCONJ",
-    "PREL": "SCONJ",
-    "JSBR": "SCONJ",
-    "JCMP": "SCONJ",
-    # PART
-    "PART": "PART",
-    "FIXN": "PART",
-    "FIXV": "PART",
-    "EAFF": "PART",
-    "EITT": "PART",
-    "AITT": "PART",
-    "NEG": "PART",
-    # PUNCT
-    "PUNCT": "PUNCT",
-    "PUNC": "PUNCT",
-}
-
-
-def _UD_Exception(w: str, tag: str) -> str:
-    if w == "การ" or w == "ความ":
-        return "NOUN"
-
-    return tag
-
-
-def _orchid_to_ud(tag) -> List[Tuple[str, str]]:
-    _i = 0
-    temp = []
-    while _i < len(tag):
-        temp.append(
-            (tag[_i][0], _UD_Exception(tag[_i][0], _TAG_MAP_UD[tag[_i][1]]))
-        )
-        _i += 1
-
-    return temp
-
-
-def pos_tag(
-    words: List[str], engine: str = "perceptron", corpus: str = "orchid"
-) -> List[Tuple[str, str]]:
-    """
-    The function tag a list of tokenized words into Part-of-Speech (POS) tags
-    such as 'NOUN', 'VERB', 'ADJ', and 'DET'.
-
-    :param list words: a list of tokenized words
-    :param str engine:
-        * *perceptron* - perceptron tagger (default)
-        * *unigram* - unigram tagger
-    :param str corpus:
-        * *orchid* - annotated Thai academic articles namedly
-          `Orchid <https://www.academia.edu/9127599/Thai_Treebank>`_ (default)
-        * *orchid_ud* - annotated Thai academic articles *Orchid* but the
-          POS tags are mapped to comply with
-          `Universal Dependencies <https://universaldependencies.org/u/pos>`_
-          POS  Tags
-        * *pud* - `Parallel Universal Dependencies (PUD)
-          <https://github.com/UniversalDependencies/UD_Thai-PUD>`_ treebanks
-    :return: returns a list of labels regarding which part of speech it is
-    :rtype: list[tuple[str, str]]
-
-    :Example:
-
-    Tag words with corpus `orchid` (default)::
-
-        from pythainlp.tag import pos_tag
-
-        words = ['ฉัน','มี','ชีวิต','รอด','ใน','อาคาร','หลบภัย','ของ', \\
-            'นายก', 'เชอร์ชิล']
-        pos_tag(words)
-        # output:
-        # [('ฉัน', 'PPRS'), ('มี', 'VSTA'), ('ชีวิต', 'NCMN'), ('รอด', 'NCMN'),
-        #   ('ใน', 'RPRE'), ('อาคาร', 'NCMN'), ('หลบภัย', 'NCMN'),
-        #   ('ของ', 'RPRE'), ('นายก', 'NCMN'), ('เชอร์ชิล', 'NCMN')]
-
-    Tag words with corpus `orchid_ud`::
-
-        from pythainlp.tag import pos_tag
-
-        words = ['ฉัน','มี','ชีวิต','รอด','ใน','อาคาร','หลบภัย','ของ', \\
-            'นายก', 'เชอร์ชิล']
-        pos_tag(words, corpus='orchid_ud')
-        # output:
-        # [('ฉัน', 'PROPN'), ('มี', 'VERB'), ('ชีวิต', 'NOUN'),
-        #   ('รอด', 'NOUN'), ('ใน', 'ADP'),  ('อาคาร', 'NOUN'),
-        #   ('หลบภัย', 'NOUN'), ('ของ', 'ADP'), ('นายก', 'NOUN'),
-        #   ('เชอร์ชิล', 'NOUN')]
-
-    Tag words with corpus `pud`::
-
-        from pythainlp.tag import pos_tag
-
-        words = ['ฉัน','มี','ชีวิต','รอด','ใน','อาคาร','หลบภัย','ของ', \\
-            'นายก', 'เชอร์ชิล']
-        pos_tag(words, corpus='pud')
-        # [('ฉัน', 'PRON'), ('มี', 'VERB'), ('ชีวิต', 'NOUN'), ('รอด', 'VERB'),
-        #   ('ใน', 'ADP'), ('อาคาร', 'NOUN'), ('หลบภัย', 'NOUN'),
-        #   ('ของ', 'ADP'), ('นายก', 'NOUN'), ('เชอร์ชิล', 'PROPN')]
-
-    Tag words with different engines including *perceptron* and *unigram*::
-
-        from pythainlp.tag import pos_tag
-
-        words = ['เก้าอี้','มี','จำนวน','ขา', ' ', '=', '3']
-
-        pos_tag(words, engine='perceptron', corpus='orchid')
-        # output:
-        # [('เก้าอี้', 'NCMN'), ('มี', 'VSTA'), ('จำนวน', 'NCMN'),
-        #   ('ขา', 'NCMN'), (' ', 'PUNC'),
-        #   ('=', 'PUNC'), ('3', 'NCNM')]
-
-        pos_tag(words, engine='unigram', corpus='pud')
-        # output:
-        # [('เก้าอี้', None), ('มี', 'VERB'), ('จำนวน', 'NOUN'), ('ขา', None),
-        #   ('<space>', None), ('<equal>', None), ('3', 'NUM')]
-    """
-
-    # NOTE:
-    _corpus = corpus
-    _tag = []
-    if corpus == "orchid_ud":
-        corpus = "orchid"
-    if not words:
-        return []
-
-    if engine == "perceptron":
-        from .perceptron import tag as tag_
-    else:  # default, use "unigram" ("old") engine
-        from .unigram import tag as tag_
-    _tag = tag_(words, corpus=corpus)
-
-    if _corpus == "orchid_ud":
-        _tag = _orchid_to_ud(_tag)
-
-    return _tag
-
-
-def pos_tag_sents(
-    sentences: List[List[str]],
-    engine: str = "perceptron",
-    corpus: str = "orchid",
-) -> List[List[Tuple[str, str]]]:
-    """
-    The function tag multiple list of tokenized words into Part-of-Speech
-    (POS) tags.
-
-    :param list sentences: a list of lists of tokenized words
-    :param str engine:
-        * *perceptron* - perceptron tagger (default)
-        * *unigram* - unigram tagger
-    :param str corpus:
-        * *orchid* - annotated Thai academic articles namedly\
-            `Orchid <https://www.academia.edu/9127599/Thai_Treebank>`_\
-            (default)
-        * *orchid_ud* - annotated Thai academic articles using\
-            `Universal Dependencies <https://universaldependencies.org/>`_ Tags
-        * *pud* - `Parallel Universal Dependencies (PUD)\
-            <https://github.com/UniversalDependencies/UD_Thai-PUD>`_ treebanks
-    :return: returns a list of labels regarding which part of speech it is
-             for each sentence given.
-    :rtype: list[list[tuple[str, str]]]
-
-    :Example:
-
-    Labels POS for two sentences::
-
-        from pythainlp.tag import pos_tag_sents
-
-        sentences = [['เก้าอี้','มี','3','ขา'], \\
-                            ['นก', 'บิน', 'กลับ', 'รัง']]
-        pos_tag_sents(sentences, corpus='pud)
-        # output:
-        # [[('เก้าอี้', 'PROPN'), ('มี', 'VERB'), ('3', 'NUM'),
-        #   ('ขา', 'NOUN')], [('นก', 'NOUN'), ('บิน', 'VERB'),
-        #   ('กลับ', 'VERB'), ('รัง', 'NOUN')]]
-    """
-    if not sentences:
-        return []
-
-    return [pos_tag(sent, engine=engine, corpus=corpus) for sent in sentences]
+from .pos_tag import pos_tag
+from .pos_tag import pos_tag_sents