4699361508

Build Type

push

github

Committed by GitHub

Commit Message

Merge pull request #789 from PyThaiNLP/4.0

Run Details

22 of 22 new or added lines in 6 files covered. (100.0%)

5749 of 6246 relevant lines covered (92.04%)

0.92 hits per line

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

31.25

/pythainlp/augment/lm/fasttext.py

# -*- coding: utf-8 -*-
# Copyright (C) 2016-2023 PyThaiNLP Project
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import List, Tuple
from gensim.models.fasttext import FastText as FastText_gensim
from pythainlp.tokenize import word_tokenize
from gensim.models.keyedvectors import KeyedVectors
import itertools


class FastTextAug:
    """
    Text Augment from FastText

    :param str model_path: path of model file
    """

    def __init__(self, model_path: str):
        """
        :param str model_path: path of model file
        """
        if model_path.endswith(".bin"):
            self.model = FastText_gensim.load_facebook_vectors(model_path)
        elif model_path.endswith(".vec"):
            self.model = KeyedVectors.load_word2vec_format(model_path)
        else:
            self.model = FastText_gensim.load(model_path)
        self.dict_wv = list(self.model.key_to_index.keys())

    def tokenize(self, text: str) -> List[str]:
        """
        Thai text tokenize for fasttext

        :param str text: thai text

        :return: list of word
        :rtype: List[str]
        """
        return word_tokenize(text, engine="icu")

    def modify_sent(self, sent: str, p: float = 0.7) -> List[List[str]]:
        """
        :param str sent: text sentence
        :param float p: probability
        :rtype: List[List[str]]
        """
        list_sent_new = []
        for i in sent:
            if i in self.dict_wv:
                w = [j for j, v in self.model.most_similar(i) if v >= p]
                if w == []:
                    list_sent_new.append([i])
                else:
                    list_sent_new.append(w)
            else:
                list_sent_new.append([i])
        return list_sent_new

    def augment(
        self, sentence: str, n_sent: int = 1, p: float = 0.7
    ) -> List[Tuple[str]]:
        """
        Text Augment from FastText

        You wants to download thai model
        from https://fasttext.cc/docs/en/crawl-vectors.html.

        :param str sentence: thai sentence
        :param int n_sent: number sentence
        :param float p: Probability of word

        :return: list of synonyms
        :rtype: List[Tuple[str]]
        """
        self.sentence = self.tokenize(sentence)
        self.list_synonym = self.modify_sent(self.sentence, p=p)
        new_sentences = []
        for x in list(itertools.product(*self.list_synonym))[0:n_sent]:
            new_sentences.append(x)
        return new_sentences

1	# -- coding: utf-8 --
2	# Copyright (C) 2016-2023 PyThaiNLP Project
3	#
4	# Licensed under the Apache License, Version 2.0 (the "License");
5	# you may not use this file except in compliance with the License.
6	# You may obtain a copy of the License at
7	#
8	# http://www.apache.org/licenses/LICENSE-2.0
9	#
10	# Unless required by applicable law or agreed to in writing, software
11	# distributed under the License is distributed on an "AS IS" BASIS,
12	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13	# See the License for the specific language governing permissions and
14	# limitations under the License.
15	from typing import List, Tuple	1✔
16	from gensim.models.fasttext import FastText as FastText_gensim	1✔
17	from pythainlp.tokenize import word_tokenize	1✔
18	from gensim.models.keyedvectors import KeyedVectors	1✔
19	import itertools	1✔
20
21
22	class FastTextAug:	1✔
23	"""
24	Text Augment from FastText
25
26	:param str model_path: path of model file
27	"""
28
29	def __init__(self, model_path: str):	1✔
30	"""
31	:param str model_path: path of model file
32	"""
33	if model_path.endswith(".bin"):	×
34	self.model = FastText_gensim.load_facebook_vectors(model_path)	×
35	elif model_path.endswith(".vec"):	×
36	self.model = KeyedVectors.load_word2vec_format(model_path)	×
37	else:
38	self.model = FastText_gensim.load(model_path)	×
39	self.dict_wv = list(self.model.key_to_index.keys())	×
40
41	def tokenize(self, text: str) -> List[str]:	1✔
42	"""
43	Thai text tokenize for fasttext
44
45	:param str text: thai text
46
47	:return: list of word
48	:rtype: List[str]
49	"""
50	return word_tokenize(text, engine="icu")	×
51
52	def modify_sent(self, sent: str, p: float = 0.7) -> List[List[str]]:	1✔
53	"""
54	:param str sent: text sentence
55	:param float p: probability
56	:rtype: List[List[str]]
57	"""
58	list_sent_new = []	×
59	for i in sent:	×
60	if i in self.dict_wv:	×
61	w = [j for j, v in self.model.most_similar(i) if v >= p]	×
62	if w == []:	×
63	list_sent_new.append([i])	×
64	else:
65	list_sent_new.append(w)	×
66	else:
67	list_sent_new.append([i])	×
68	return list_sent_new	×
69
70	def augment(	1✔
71	self, sentence: str, n_sent: int = 1, p: float = 0.7
72	) -> List[Tuple[str]]:
73	"""
74	Text Augment from FastText
75
76	You wants to download thai model
77	from https://fasttext.cc/docs/en/crawl-vectors.html.
78
79	:param str sentence: thai sentence
80	:param int n_sent: number sentence
81	:param float p: Probability of word
82
83	:return: list of synonyms
84	:rtype: List[Tuple[str]]
85	"""
86	self.sentence = self.tokenize(sentence)	×
87	self.list_synonym = self.modify_sent(self.sentence, p=p)	×
88	new_sentences = []	×
89	for x in list(itertools.product(*self.list_synonym))[0:n_sent]:	×
90	new_sentences.append(x)	×
91	return new_sentences	×

PyThaiNLP / pythainlp / 4699361508

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