MCPcopy Create free account

hub / github.com/beyondguo/genius / functions

Functions284 in github.com/beyondguo/genius

↓ 1 callersFunctionget_stopwords
()
_backup_scripts/s2t_utils.py:35
↓ 1 callersFunctionget_that_sentence
(text, that)
_backup_scripts/qa_back_trans.py:30
↓ 1 callersFunctionget_that_sentence
(text, that)
_backup_scripts/qa_aug_eda.py:21
↓ 1 callersFunctionget_that_sentence
(text, that)
_backup_scripts/run_qa_aug.py:63
↓ 1 callersFunctionget_that_sentence
(text, that)
augmentation_ner_qa/genius_qa_aug.py:27
↓ 1 callersFunctionget_wllr
WLLR: weighted log likelihood ratio r(w,y) = p(w|y)*log(p(w|y)/p(w|y^)) WLLR reflects the given word's correlation with a class. The
augmentation_clf/STA/keywords_extractor.py:42
↓ 1 callersFunctionglobal_role_kws_extraction
version3:尝试的第三种方案,通过分位数这种大家好接受的标准来划分集合,然后归一化,然后排序。目前来看效果不错。 根据得分的分位数进行划分高低的标准,可选择Q1,Q2,Q3三种分位数。 通用类别指示词(CCW):高lr跟高ls的交集 特殊类别指示词(SCW):
augmentation_clf/STA/keywords_extractor.py:381
↓ 1 callersFunctioninit_model
()
do_clf.py:90
↓ 1 callersFunctioninit_model
()
augmentation_clf/STA/clf.py:89
↓ 1 callersMethodk2t
inputs: text or a list of text
_backup_scripts/ner_aug.py:184
↓ 1 callersFunctionkeynotes_yake
(text, max_ngram=3, topk=20)
_backup_scripts/k2t_new_ner_aug.py:27
↓ 1 callersFunctionkeysents_semantic
(text, candidates=None, aspect_keywords=None, max_ngram=3, topk=20, aspect_only=False)
_backup_scripts/k2t_new_ner_aug.py:39
↓ 1 callersFunctionkeywords
(text_input, input_file, language, ngram_size, verbose=False, dedup_func="seqm", dedup_lim=.9, window_size=1,
yake/cli.py:22
↓ 1 callersFunctionmask_unimportant_parts
kws: List 输出例子: '<mask> Google is acquiring Kaggle <mask> hosts data science and machine learning competitions <mask> Google <mask>
_backup_scripts/k2t_new_ner_aug.py:55
↓ 1 callersFunctionmask_unimportant_parts
kws: List 输出例子: '<mask> Google is acquiring Kaggle <mask> hosts data science and machine learning competitions <mask> Google <mask>
_backup_scripts/k2t_new_sm_aug.py:45
↓ 1 callersFunctionmy_topk
(text)
augmentation_clf/genius_finetune.py:76
↓ 1 callersFunctionmy_topk
(text)
augmentation_clf/genius_clf.py:66
↓ 1 callersFunctionmy_topk
(text)
augmentation_clf/genius_mixup_clf.py:65
↓ 1 callersFunctionmy_topk
(text)
_backup_scripts/sega_yahoo.py:63
↓ 1 callersFunctionpostprocess
(predictions, labels)
_backup_scripts/run_ner.py:224
↓ 1 callersFunctionpostprocess
(predictions, labels)
augmentation_ner_qa/run_ner.py:224
↓ 1 callersFunctionpostprocess_qa_predictions
Post-processes the predictions of a question-answering model to convert them to answers that are substrings of the original contexts. This is
augmentation_ner_qa/utils_qa.py:31
↓ 1 callersMethodpre_filter
(self, text)
yake/datarepresentation.py:118
↓ 1 callersMethodpredict
(self, predict_dataset, predict_examples, ignore_keys=None, metric_key_prefix: str = "test")
augmentation_ner_qa/trainer_qa.py:75
↓ 1 callersMethodrandom_text_augmentation
- text, 直接给一段文本(不用分词), - prob_dict和num_aug_dict的示例如下,给出「修改比例」和「扩增数量」的配置参数: prob_dict = {'r': 0.1, 'i': 0.1, 's': 0.1, 'd':
augmentation_clf/STA/text_augmenter.py:322
↓ 1 callersMethodrandom_text_augmentation
- text, 直接给一段文本(不用分词), - prob_dict和num_aug_dict的示例如下,给出「修改比例」和「扩增数量」的配置参数: prob_dict = {'r': 0.1, 'i': 0.1, 's': 0.1, 'd':
_backup_scripts/easy_text_augmenter.py:298
↓ 1 callersMethodratio
(seq1, seq2)
yake/Levenshtein.py:10
↓ 1 callersFunctionremove_brakets
(text)
genius_utils.py:166
↓ 1 callersFunctionremove_brakets
(text)
_backup_scripts/ner_aug.py:162
↓ 1 callersFunctionremove_brakets
(text)
_backup_scripts/k2t_new_sm_aug.py:97
↓ 1 callersFunctionremove_brakets
(text)
_backup_scripts/s2t_utils.py:18
↓ 1 callersFunctionremove_brakets
(text)
_backup_scripts/prepare_k2t_data_with_mask.py:61
↓ 1 callersFunctionremove_brakets
(text)
_backup_scripts/run_aug.py:208
↓ 1 callersFunctionremove_last_sentence
(text)
_backup_scripts/k2t_new_sm_aug.py:101
↓ 1 callersFunctionremove_last_sentence
(text)
_backup_scripts/s2t_utils.py:22
↓ 1 callersFunctionremove_last_sentence
(text)
_backup_scripts/run_aug.py:213
↓ 1 callersFunctionremove_special_characters
(text)
genius_utils.py:161
↓ 1 callersFunctionremove_special_characters
(text)
_backup_scripts/ner_aug.py:155
↓ 1 callersFunctionremove_special_characters
(text)
_backup_scripts/k2t_new_sm_aug.py:90
↓ 1 callersFunctionremove_special_characters
(text)
_backup_scripts/s2t_utils.py:11
↓ 1 callersFunctionremove_special_characters
(text)
_backup_scripts/prepare_k2t_data_with_mask.py:56
↓ 1 callersFunctionremove_special_characters
(text)
_backup_scripts/run_aug.py:203
↓ 1 callersFunctionrole_kws_extraction_single
通过分位数这种大家好接受的标准来划分集合,然后归一化,然后排序。目前来看效果不错。 根据得分的分位数进行划分高低的标准,可选择Q1,Q2,Q3三种分位数。 通用类别指示词(CCW):高lr跟高ls的交集 特殊类别指示词(SCW):低lr跟高ls的交集 噪音类
augmentation_clf/STA/keywords_extractor.py:328
↓ 1 callersFunctionsetup_seed
(seed)
utils.py:17
↓ 1 callersFunctionshuffle_keywords
(keywords_str)
_backup_scripts/run_aug.py:177
↓ 1 callersMethodtag
(self, sentence)
_backup_scripts/ner_aug.py:215
↓ 1 callersMethodtag
(self, sentence)
_backup_scripts/k2t_new_ner_aug.py:234
↓ 1 callersMethodtokenize
(self, sentence)
_backup_scripts/ner_aug.py:212
↓ 1 callersMethodtokenize
(self, sentence)
_backup_scripts/k2t_new_ner_aug.py:231
↓ 1 callersMethodtokenize
(self, sentence)
augmentation_ner_qa/genius_ner_aug.py:103
↓ 1 callersMethoduptadeCand
(self, cand)
yake/datarepresentation.py:200
MethodPWL
(self)
yake/datarepresentation.py:408
MethodPWR
(self)
yake/datarepresentation.py:393
MethodWDL
(self)
yake/datarepresentation.py:400
MethodWDR
(self)
yake/datarepresentation.py:385
MethodWIL
(self)
yake/datarepresentation.py:404
MethodWIR
(self)
yake/datarepresentation.py:389
Method__getitem__
(self, idx)
utils.py:54
Method__getitem__
(self, i)
genius_utils.py:193
Method__getitem__
(self, idx)
augmentation_clf/mlm_clf.py:70
Method__getitem__
(self, i)
augmentation_clf/conditional_clm_clf.py:62
Method__getitem__
(self, i)
augmentation_clf/backtrans_clf.py:29
Method__getitem__
(self, idx)
augmentation_clf/conditional_mlm_clf.py:82
Method__getitem__
(self, idx)
augmentation_clf/STA/my_dataset.py:36
Method__getitem__
(self, i)
_backup_scripts/k2t_new_ner_aug.py:205
Method__getitem__
(self, i)
_backup_scripts/qa_back_trans.py:50
Method__getitem__
(self, i)
_backup_scripts/k2t_new_sm_aug.py:84
Method__getitem__
(self, i)
_backup_scripts/s2t_utils.py:45
Method__getitem__
(self, i)
_backup_scripts/qa_aug_eda.py:41
Method__getitem__
(self, idx)
_backup_scripts/my_dataset.py:16
Method__init__
(self, model="all-MiniLM-L6-v2")
aspect_keybert.py:21
Method__init__
(self, **kwargs)
utils.py:26
Method__init__
(self, model='yake')
genius_utils.py:27
Method__init__
(self, inputs)
genius_utils.py:187
Method__init__
(self, text, stopword_set, windowsSize, n, tagsToDiscard = set(['u', 'd']), exclude = set(string.punctuation))
yake/datarepresentation.py:16
Method__init__
(self, terms)
yake/datarepresentation.py:185
Method__init__
(self, unique, idx, graph)
yake/datarepresentation.py:339
Method__init__
TextHighlighter constructor. Define highlight text snippets :max_ngram_size - Specifies the maximum ngram size in the keywords.
yake/highlight.py:8
Method__init__
(self, lan="en", n=3, dedupLim=0.9, dedupFunc='seqm', windowsSize=1, top=20, features=None, stopwords=None)
yake/yake.py:14
Method__init__
(self, contents)
augmentation_clf/mlm_clf.py:67
Method__init__
(self, inputs)
augmentation_clf/conditional_clm_clf.py:56
Method__init__
(self, contents)
augmentation_clf/backtrans_clf.py:25
Method__init__
(self, contents, labels)
augmentation_clf/conditional_mlm_clf.py:76
Method__init__
(self, lang, using_wordnet=False)
augmentation_clf/STA/text_augmenter.py:23
Method__init__
(self, lang)
augmentation_clf/STA/keywords_extractor.py:92
Method__init__
(self, **kwargs)
augmentation_clf/STA/utils.py:23
Method__init__
(self, tokenizer, texts, labels, label2idx, maxlen)
augmentation_clf/STA/my_dataset.py:29
Method__init__
(self,train_path, test_path, tokenizer, maxlen, bsz, collate_fn, split_valid_from=None)
augmentation_clf/STA/my_dataset.py:65
Method__init__
(self,model, device)
_backup_scripts/ner_aug.py:182
Method__init__
(self, global_mention_dict)
_backup_scripts/ner_aug.py:198
Method__init__
(self, m_list)
_backup_scripts/k2t_new_ner_aug.py:201
Method__init__
(self, global_mention_dict)
_backup_scripts/k2t_new_ner_aug.py:217
Method__init__
(self, contents)
_backup_scripts/qa_back_trans.py:46
Method__init__
(self, m_list)
_backup_scripts/k2t_new_sm_aug.py:80
Method__init__
(self, inputs)
_backup_scripts/s2t_utils.py:41
Method__init__
(self, contents)
_backup_scripts/qa_aug_eda.py:37
Method__init__
(self, lang, using_wordnet=False)
_backup_scripts/easy_text_augmenter.py:16
Method__init__
(self,model, device)
_backup_scripts/run_qa_aug.py:11
Method__init__
(self, tokenizer, texts, labels, label2idx, maxlen)
_backup_scripts/my_dataset.py:9
Method__init__
(self,train_path, test_path, tokenizer, maxlen, train_bz, eval_bz, collate_fn, split_valid_from=None)
_backup_scripts/my_dataset.py:49
← previousnext →101–200 of 284, ranked by callers