Spaces:
Running
Running
File size: 13,792 Bytes
2609fac 7c98e23 2609fac 7c98e23 2609fac |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 |
import string
from random import random
from random import sample
from utilities_language_general.esp_constants import nlp
from utilities_language_general.morphology import inflect
from utilities_language_general.esp_utils import check_token
from utilities_language_general.esp_constants import PHRASES
from utilities_language_general.esp_utils import fix_irregular_lemma
from utilities_language_general.esp_constants import BAD_USER_TARGET_WORDS
from utilities_language_general.esp_utils import get_distractors_from_model
class SENTENCE:
def __init__(self, original: str, n_sentence: int, max_num_distractors):
self.original = original
self.n_sentence = n_sentence
self.max_num_distractors = max_num_distractors
self.parsed = nlp(self.original)
self.sentence_lemma_pos = []
self.sentence_phrases = []
self.target_words = []
def lemmatize_sentence(self):
for token in self.parsed:
lemma_pos = f'{token.lemma_}_{token.pos_}'
if token.pos_ in ('AUX', 'VERB', 'ADJ'):
lemma_pos = fix_irregular_lemma(lemma=lemma_pos)
self.sentence_lemma_pos.append((lemma_pos, token))
def bind_phrases(self):
previous_was_phrase = False
for i in range(len(self.sentence_lemma_pos) - 1):
phrase_candidate = f'{self.sentence_lemma_pos[i][0]}_{self.sentence_lemma_pos[i + 1][0]}'
if phrase_candidate in PHRASES and not previous_was_phrase:
# phrase is {phrase: {original_token1: spacy.token, original_token2: spacy.token}}
phrase = [
f'{self.sentence_lemma_pos[i][0]}_{self.sentence_lemma_pos[i + 1][0]}',
{
'original_token1': self.sentence_lemma_pos[i][1],
'original_token2': self.sentence_lemma_pos[i + 1][1]
}
]
self.sentence_phrases.append(phrase)
previous_was_phrase = True
else:
if not previous_was_phrase:
self.sentence_phrases.append(self.sentence_lemma_pos[i][1])
previous_was_phrase = False
def search_target_words_automatically(self, model, target_minimum: set, frequency_dict: dict = None):
for token in self.sentence_phrases:
if isinstance(token, list): # if token is a phrase
original_token1 = token[1]['original_token1']
original_token2 = token[1]['original_token2']
original_token1_tags = original_token1.morph.to_dict()
original_token2_tags = original_token2.morph.to_dict()
tags = dict()
if ('haber_AUX' == f'{original_token1.lemma_}_{original_token1.pos_}'
and original_token2.pos_ in ('VERB', 'ADJ', 'AUX')):
tags['VerbForm'] = 'Compuesto'
tags['Mood'] = original_token1_tags.get('Mood')
tags['Tense'] = original_token1_tags.get('Tense')
tags['Person'] = original_token1_tags.get('Person')
tags['Number'] = original_token1_tags.get('Number')
tags['Gender'] = None
else:
tags = {**original_token1_tags, **original_token2_tags}
not_ner = True if (original_token1.ent_type == 0 and original_token2.ent_type == 0) else False
target_word = {
'sentence_number': self.n_sentence,
'sentence_text': self.original,
'original_text': f'{original_token1.text} {original_token2.text}',
'lemma': token[0],
'pos': 'phrase',
'gender': tags.get('Gender'),
'tags': tags,
'position_in_sentence': self.original.find(original_token1.text),
'not_named_entity': not_ner,
'frequency_in_text': 0
}
self.target_words.append(target_word)
else: # if token is just a spacy.nlp token
if check_token(model=model, token=token, lemma_pos='auto', current_minimum=target_minimum):
tags = token.morph.to_dict()
target_word = {
'sentence_number': self.n_sentence,
'sentence_text': self.original,
'original_text': token.text,
'lemma': token.lemma_,
'pos': token.pos_,
'gender': tags.get('Gender'),
'number_children': len([child for child in token.children]),
'tags': tags,
'position_in_sentence': self.original.find(token.text),
'not_named_entity': True if token.ent_type == 0 else False,
'frequency_in_text': frequency_dict.get(token.lemma_, 1),
}
self.target_words.append(target_word)
def search_user_target_words(self, model, user_target_words: set = None, frequency_dict: dict = None):
for _utw in user_target_words:
if _utw in self.original:
parse_utw = nlp(_utw)
if ' ' in _utw:
tags = dict()
if ('haber_AUX' == f'{parse_utw[0].lemma_}_{parse_utw[0].pos_}'
and parse_utw[1].pos_ in ('VERB', 'ADJ', 'AUX')):
tags['VerbForm'] = 'Compuesto'
tags['Mood'] = parse_utw[0].morph.to_dict().get('Mood')
tags['Tense'] = parse_utw[0].morph.to_dict().get('Tense')
tags['Person'] = parse_utw[0].morph.to_dict().get('Person')
tags['Number'] = parse_utw[0].morph.to_dict().get('Number')
tags['Gender'] = None
else:
tags = {**parse_utw[0].morph.to_dict(), **parse_utw[1].morph.to_dict()}
user_target_word_lemma = '_'.join([f'{token.lemma_}_{token.pos_}' for token in parse_utw])
user_target_word_pos = 'phrase'
user_target_word_tags = tags
not_ner = True if (parse_utw[0].ent_type == 0 and parse_utw[1].ent_type == 0) else False
else:
user_target_word_lemma = f'{parse_utw[0].lemma_}_{parse_utw[0].pos_}'
user_target_word_pos = parse_utw[0].pos_
user_target_word_tags = parse_utw[0].morph.to_dict()
not_ner = parse_utw[0].ent_type == 0
target_word = {
'sentence_number': self.n_sentence,
'sentence_text': self.original,
'original_text': _utw,
'lemma': user_target_word_lemma,
'pos': user_target_word_pos,
'gender': user_target_word_tags.get('Gender'),
'tags': user_target_word_tags,
'position_in_sentence': self.original.find(_utw),
'not_named_entity': not_ner,
'frequency_in_text': frequency_dict.get(user_target_word_lemma, 1)
}
if not (model.has_index_for(user_target_word_lemma)
or model.has_index_for(f'{user_target_word_lemma}_{user_target_word_pos}')):
BAD_USER_TARGET_WORDS.append(_utw)
else:
self.target_words.append(target_word)
def search_target_words(self, model, target_words_automatic_mode: bool, target_minimum,
user_target_words: set = None, frequency_dict: dict = None):
if target_words_automatic_mode:
self.search_target_words_automatically(model=model, target_minimum=target_minimum,
frequency_dict=frequency_dict)
else:
self.search_user_target_words(model=model, user_target_words=user_target_words,
frequency_dict=frequency_dict)
def attach_distractors_to_target_word(self, model, global_distractors, distractor_minimum, level_name,
max_frequency, progress, logs):
n_target_words = len(self.target_words)
bad_target_words = []
for i, target_word in enumerate(self.target_words):
distractors = get_distractors_from_model(model, lemma=target_word['lemma'], pos=target_word['pos'],
gender=target_word['gender'], level_name=level_name,
global_distractors=global_distractors,
distractor_minimum=distractor_minimum,
max_num_distractors=self.max_num_distractors)
if distractors is None or target_word['frequency_in_text'] > max_frequency:
target_word['distractors'] = distractors
bad_target_words.append(target_word)
target_word['distractors'] = distractors
target_word['distractors_number'] = len(distractors) if distractors is not None else 0
progress.progress(i / n_target_words)
logs.success(f'Обработали {i}/{n_target_words} слов в {self.n_sentence + 1}-м предложении')
for btw in bad_target_words:
BAD_USER_TARGET_WORDS.append(btw['original_text'])
self.target_words.remove(btw)
progress.progress(100)
logs.success(
f'Обработали {n_target_words}/{n_target_words} слов в {self.n_sentence + 1}-м предложении')
def inflect_distractors(self):
bad_target_words = []
for target_word in self.target_words:
inflected_distractors = []
for distractor_lemma, distractor_similarity in target_word['distractors']:
if distractor_lemma.count('_') > 1:
if distractor_lemma.startswith('haber_'):
distractor_lemma = distractor_lemma.split('_')[-2]
inflected = inflect(lemma=distractor_lemma, target_pos=target_word['pos'],
target_tags=target_word['tags'])
else:
continue
else:
inflected = inflect(lemma=distractor_lemma, target_pos=target_word['pos'],
target_tags=target_word['tags'])
if inflected is not None:
inflected_distractors.append(inflected)
num_distractors = min(4, self.max_num_distractors) if self.max_num_distractors >= 4 \
else self.max_num_distractors
if len(inflected_distractors) < num_distractors:
bad_target_words.append(target_word)
else:
target_word['inflected_distractors'] = inflected_distractors
for btw in bad_target_words:
BAD_USER_TARGET_WORDS.append(btw['original_text'])
self.target_words.remove(btw)
def filter_target_words(self, target_words_automatic_mode):
c_position = 0
bad_target_words = []
for target_word in self.target_words:
position_difference = 3 if target_words_automatic_mode else 0
if not (target_word['position_in_sentence'] == 0
or abs(target_word['position_in_sentence'] - c_position) >= position_difference):
bad_target_words.append(target_word)
for btw in bad_target_words:
BAD_USER_TARGET_WORDS.append(btw['original_text'])
self.target_words.remove(btw)
def sample_distractors(self, num_distractors):
for target_word in self.target_words:
len_inflected_distractors = len(target_word['inflected_distractors'])
num_distractors = min(len_inflected_distractors, num_distractors) \
if num_distractors >= 4 else num_distractors
target_word['inflected_distractors'] = sample(target_word['inflected_distractors'][:min(
len_inflected_distractors, 10)], num_distractors)
class TASK:
def __init__(self, task_data):
self.task_data = task_data
self.original_text = None
self.sentence_text = None
self.inflected_distractors = None
self.sentence_number = task_data['sentence_number']
self.position_in_sentence = task_data['position_in_sentence']
self.result = ''
self.variants = []
for key, value in task_data.items():
self.__setattr__(key, value)
def __repr__(self):
return '\n'.join([f'{key}\t=\t{value}' for key, value in self.__dict__.items()])
def compile_task(self, max_num_distractors):
len_distractors = len(self.inflected_distractors)
len_variants = min(len_distractors, max_num_distractors) if max_num_distractors > 4 \
else max_num_distractors
letters = (f'({letter})' for letter in string.ascii_lowercase[:len_variants + 1])
try:
distractors = sample(self.inflected_distractors, len_variants) + [self.original_text, ]
except ValueError:
distractors = self.inflected_distractors + [self.original_text, ]
self.variants.append(
(self.original_text, [f'{item[0]} {item[1].replace("_", " ")}'
for item in zip(letters, sorted(distractors, key=lambda _: random()))]))
|