tjoddlZddlZddlmZmZddlZddlmZddl m Z m Z m Z ddl mZmZmZmZe r ddlZddlmZGd d eZGd d e Ze ed dGddeZeZdS)N)Anyoverload)BasicTokenizer) ExplicitEnumadd_end_docstringsis_torch_available)ArgumentHandler ChunkPipelineDatasetbuild_pipeline_init_args),MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING_NAMESc0eZdZdZdeeezfdZdS)"TokenClassificationArgumentHandlerz5 Handles arguments for token classification. inputsc |dd}|d}|Nt|ttfr2t |dkrt|}t |}nft|t r|g}d}nKt t|t st|tjr||d|fStd|d}|rUt|trt|dtr|g}t ||krtd||||fS) Nis_split_into_wordsF delimiterrr zAt least one input is required.offset_mappingz;offset_mapping should have the same batch size as the input) get isinstancelisttuplelenstrr types GeneratorType ValueError)selfrkwargsrr batch_sizers i/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/pipelines/token_classification.py__call__z+TokenClassificationArgumentHandler.__call__sN$jj)>FFJJ{++  *VdE]"C"C F VW&\\FVJJ  $ $ @XFJJ  Z%@%@ JvW\WjDkDk .i? ?>?? ?$455  `.$// 2J~a?PRW4X4X 2"0!1>""j00 !^___*NIEEN)__name__ __module__ __qualname____doc__rrr$r%r#rrsHFsT#YFFFFFFr%rc&eZdZdZdZdZdZdZdZdS)AggregationStrategyzDAll the valid aggregation strategies for TokenClassificationPipelinenonesimplefirstaveragemaxN) r&r'r(r)NONESIMPLEFIRSTAVERAGEMAXr*r%r#r,r,3s-NN D F EG CCCr%r,T) has_tokenizera ignore_labels (`list[str]`, defaults to `["O"]`): A list of labels to ignore. stride (`int`, *optional*): If stride is provided, the pipeline is applied on all the text. The text is split into chunks of size model_max_length. Works only with fast tokenizers and `aggregation_strategy` different from `NONE`. The value of this argument defines the number of overlapping tokens between chunks. In other words, the model will shift forward by `tokenizer.model_max_length - stride` tokens each step. aggregation_strategy (`str`, *optional*, defaults to `"none"`): The strategy to fuse (or not) tokens based on the model prediction. - "none" : Will simply not do any aggregation and simply return raw results from the model - "simple" : Will attempt to group entities following the default schema. (A, B-TAG), (B, I-TAG), (C, I-TAG), (D, B-TAG2) (E, B-TAG2) will end up being [{"word": ABC, "entity": "TAG"}, {"word": "D", "entity": "TAG2"}, {"word": "E", "entity": "TAG2"}] Notice that two consecutive B tags will end up as different entities. On word based languages, we might end up splitting words undesirably : Imagine Microsoft being tagged as [{"word": "Micro", "entity": "ENTERPRISE"}, {"word": "soft", "entity": "NAME"}]. Look for FIRST, MAX, AVERAGE for ways to mitigate that and disambiguate words (on languages that support that meaning, which is basically tokens separated by a space). These mitigations will only work on real words, "New york" might still be tagged with two different entities. - "first" : (works only on word based models) Will use the `SIMPLE` strategy except that words, cannot end up with different tags. Words will simply use the tag of the first token of the word when there is ambiguity. - "average" : (works only on word based models) Will use the `SIMPLE` strategy except that words, cannot end up with different tags. scores will be averaged first across tokens, and then the maximum label is applied. - "max" : (works only on word based models) Will use the `SIMPLE` strategy except that words, cannot end up with different tags. Word entity will simply be the token with the maximum score.creZdZdZdZdZdZdZdZe ffd Z d'de dzde e eefdzd ed edzd edzf d Zed edede eeeffdZed e edede e eeeffdZd ee ezdede eeefe e eeefzffd Zd(dZdZe jdfdZdZ d)dedejdejde e eefdzdejde de edzdzde e eefdzde efdZde ede de efdZd e ede defd!Zd e ede de efd"Z d e edefd#Z!d$ede eeffd%Z"d e ede efd&Z#xZ$S)*TokenClassificationPipelineuv Named Entity Recognition pipeline using any `ModelForTokenClassification`. See the [named entity recognition examples](../task_summary#named-entity-recognition) for more information. Example: ```python >>> from transformers import pipeline >>> token_classifier = pipeline(model="Jean-Baptiste/camembert-ner", aggregation_strategy="simple") >>> sentence = "Je m'appelle jean-baptiste et je vis à montréal" >>> tokens = token_classifier(sentence) >>> tokens [{'entity_group': 'PER', 'score': 0.9931, 'word': 'jean-baptiste', 'start': 12, 'end': 26}, {'entity_group': 'LOC', 'score': 0.998, 'word': 'montréal', 'start': 38, 'end': 47}] >>> token = tokens[0] >>> # Start and end provide an easy way to highlight words in the original text. >>> sentence[token["start"] : token["end"]] ' jean-baptiste' >>> # Some models use the same idea to do part of speech. >>> syntaxer = pipeline(model="vblagoje/bert-english-uncased-finetuned-pos", aggregation_strategy="simple") >>> syntaxer("My name is Sarah and I live in London") [{'entity_group': 'PRON', 'score': 0.999, 'word': 'my', 'start': 0, 'end': 2}, {'entity_group': 'NOUN', 'score': 0.997, 'word': 'name', 'start': 3, 'end': 7}, {'entity_group': 'AUX', 'score': 0.994, 'word': 'is', 'start': 8, 'end': 10}, {'entity_group': 'PROPN', 'score': 0.999, 'word': 'sarah', 'start': 11, 'end': 16}, {'entity_group': 'CCONJ', 'score': 0.999, 'word': 'and', 'start': 17, 'end': 20}, {'entity_group': 'PRON', 'score': 0.999, 'word': 'i', 'start': 21, 'end': 22}, {'entity_group': 'VERB', 'score': 0.998, 'word': 'live', 'start': 23, 'end': 27}, {'entity_group': 'ADP', 'score': 0.999, 'word': 'in', 'start': 28, 'end': 30}, {'entity_group': 'PROPN', 'score': 0.999, 'word': 'london', 'start': 31, 'end': 37}] ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial) This token recognition pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"ner"` (for predicting the classes of tokens in a sequence: person, organisation, location or miscellaneous). The models that this pipeline can use are models that have been fine-tuned on a token classification task. See the up-to-date list of available models on [huggingface.co/models](https://huggingface.co/models?filter=token-classification). sequencesFTc tjdi||tt d|_||_dS)NF) do_lower_caser*)super__init__check_model_typerr_basic_tokenizer _args_parser)r args_parserr! __class__s r#r>z$TokenClassificationPipeline.__init__sV""6""" JKKK .U C C C'r%Naggregation_strategyrrstriderci}||d<|r |dn||d<|||d<i}|yt|trt|}|tjtjtjhvr|jjstd||d<|||d<|i||jj krtd|tj krtd |d |jjr d d |d } | |d <ntd|i|fS)Nr rrz{Slow tokenizers cannot handle subwords. Please set the `aggregation_strategy` option to `"simple"` or use a fast tokenizer.rD ignore_labelszl`stride` must be less than `tokenizer.model_max_length` (or even lower if the tokenizer adds special tokens)zI`stride` was provided to process all the text but `aggregation_strategy="z&"`, please select another one instead.T)return_overflowing_tokenspaddingrEtokenizer_paramszm`stride` was provided to process all the text but you're using a slow tokenizer. Please use a fast tokenizer.) rrr,upperr4r6r5 tokenizeris_fastrmodel_max_lengthr2) r rHrDrrrErpreprocess_paramspostprocess_paramsrKs r#_sanitize_parametersz0TokenClassificationPipeline._sanitize_parameterss3F/0  U4=4ESS9 k *  %2@ . /  +.44 Y':;O;U;U;W;W'X$$'-/B/FH[Hcdee.e!>:N 5 6  $2?  /  888 C$':'??? U,UUU >) 59#'"((($ =M%&899$8!"&888r%rr!returnc dSNr*r rr!s r#r$z$TokenClassificationPipeline.__call__sLOCr%c dSrUr*rVs r#r$z$TokenClassificationPipeline.__call__sX[X[r%c |j|fi|\}}}}||d<||d<|r4td|Dstj|gfi|S|r||d<tj|fi|S)a Classify each token of the text(s) given as inputs. Args: inputs (`str` or `List[str]`): One or several texts (or one list of texts) for token classification. Can be pre-tokenized when `is_split_into_words=True`. Return: A list or a list of list of `dict`: Each result comes as a list of dictionaries (one for each token in the corresponding input, or each entity if this pipeline was instantiated with an aggregation_strategy) with the following keys: - **word** (`str`) -- The token/word classified. This is obtained by decoding the selected tokens. If you want to have the exact string in the original sentence, use `start` and `end`. - **score** (`float`) -- The corresponding probability for `entity`. - **entity** (`str`) -- The entity predicted for that token/word (it is named *entity_group* when *aggregation_strategy* is not `"none"`. - **index** (`int`, only present when `aggregation_strategy="none"`) -- The index of the corresponding token in the sentence. - **start** (`int`, *optional*) -- The index of the start of the corresponding entity in the sentence. Only exists if the offsets are available within the tokenizer - **end** (`int`, *optional*) -- The index of the end of the corresponding entity in the sentence. Only exists if the offsets are available within the tokenizer rrc3@K|]}t|tVdSrU)rr).0inputs r# z7TokenClassificationPipeline.__call__..s,*W*Wu:eT+B+B*W*W*W*W*W*Wr%r)rAallr=r$)r rr!_inputsrrrrCs r#r$z$TokenClassificationPipeline.__call__s6CT$BSTZBeBe^dBeBe?$ni(;$%'{  8s*W*WPV*W*W*W'W'W 8#577#VH7777 7  6'5F# $uww11&111r%c+K|di}|jjo|jjdk}d}|d}|r|d}t|tst d|} || }g}t|} d} | D]>} || | t| zf| t| | zz } ?| } d|d<n&t|tst d|} |j| fd|d|jj d |}|r|jj st d |d dt|d }t|D]efd | D}|||d<dkr|nd|d<|dz k|d<|| |d<||d<|VfdS)NrKrrrzEWhen `is_split_into_words=True`, `sentence` must be a list of tokens.TzKWhen `is_split_into_words=False`, `sentence` must be an untokenized string.pt)return_tensors truncationreturn_special_tokens_maskreturn_offsets_mappingz@is_split_into_words=True is only supported with fast tokenizers.overflow_to_sample_mapping input_idscNi|]!\}}||d"S)r) unsqueeze)rZkvis r# z:TokenClassificationPipeline.preprocess.."s/LLLTQAqt~~a00LLLr%rsentencer is_lastword_idsword_to_chars_map)poprMrOrrrjoinrappendrrNrangeitemsro)r rmrrPrKrbrprrwords delimiter_len char_offsetwordtext_to_tokenizer num_chunks model_inputsrks @r# preprocessz&TokenClassificationPipeline.preprocesssn,001CRHH^4\9X[\9\  /0EF  ()+6Ih-- j !hiiiE ~~e,,H "  NNMK 9 9!((+{SYY7N)OPPPs4yy=88  % 6: 2 3 3h,, p !nooo'   !'+#'>#9        at~'= a_`` ` /666 ,-- z""  ALLLLV\\^^LLLL)1? -.3466xxtL $&':>&9L # ,+1??1+=+= Z(4E 01      r%c|d}|dd}|d}|d}|dd}|dd}|jd i|}t|tr|dn|d} | ||||||d |S) Nspecial_tokens_maskrrmrnrorplogitsr)rrrrmrnrorpr*)rqmodelrdict) r r|rrrmrnrorpoutputrs r#_forwardz$TokenClassificationPipeline._forward.s*../DEE%))*:DAA##J//""9--##J55(,,-@$GG++l++%/%=%=L!!6!9#6,  !2     r%c dgg}|dd}|D]}|ddjtjtjfvr>|ddtj}n |dd}|dd}|dd} |d|ddnd} |dd} |d } tj |d d } tj || z }|| d d z }| || || | || | }| ||}fd|D}||t|}|dkr||}|S)NOrrprrmrfrrroT)axiskeepdims)rorpctg|]4}|ddvr|ddv2|5S)entityN entity_group)r)rZrrHs r# z;TokenClassificationPipeline.postprocess..ksX::h--]BBJJ~t44MIIJIIr%r )rdtypetorchbfloat16float16tofloat32numpynpr1expsumgather_pre_entities aggregateextendraggregate_overlapping_entities)r all_outputsrDrH all_entitiesrp model_outputsrrmrfrrromaxes shifted_expscores pre_entitiesgrouped_entitiesentitiesr{s ` r# postprocessz'TokenClassificationPipeline.postprocessEs   EM (N../BCC($ *$ *MX&q)/ENEM3RRR&x0366u}EEKKMM&x0399;;"1~j1H%k215I6CDT6U6a ./22gk #00E"Fq"I"O"O"Q"Q $((44HF6T:::E&%00K ;??T?#J#JJF33#$!"34  L $~~l>>>|LLLr%ct|dkr|St|d}g}|d}|D]~}|d|dcxkr |dkrFnnC|d|dz }|d|dz }||ks||kr|d|dkr|}g|||}|||S)Nrc|dS)Nstartr*)xs r#zLTokenClassificationPipeline.aggregate_overlapping_entities..zs !G*r%keyrendscore)rsortedrs)r raggregated_entitiesprevious_entityrcurrent_lengthprevious_lengths r#rz:TokenClassificationPipeline.aggregate_overlapping_entitiesws x==A  O((<(<=== "1+ ) )Fw'6'?SSSS_U=SSSSSS!'!@"1%"8?7;S"S"_44%88w/'*BBB&,O#**?;;;"(""?333""r%rmrfrrrorpc g} t|D]\} } || r|jt|| } |K|| \} }|!||| }|||\}}| |z } ||z }t | ts(| } |}|| |}t |jddrAt |jjjddr!t| t|k}nW|tj tj tj hvrtjdt | dkod|| dz | dzv}t|| |jjkr|} d}nd} d}d}| | | || |d }| || S) zTFuse various numpy arrays into dicts with all the information needed for aggregationN _tokenizercontinuing_subword_prefixz?Tokenizer does not support real words, using fallback heuristicrrGr F)ryrrrindex is_subword) enumeraterMconvert_ids_to_tokensintritemgetattrrrrr,r4r5r6warningswarn UserWarning unk_token_idrs)r rmrfrrrrDrorpridx token_scoresry start_indend_ind word_index start_char_word_refr pre_entitys r#rz/TokenClassificationPipeline.gather_pre_entitiess !*6!2!28 ,8 , C"3' >77IcN8K8KLLD)%3C%8" 7',=,I!)#J!-(9*(E A!Z/ :-!)S11- ) 0 0I%llnnG#Ig$564><>>f7N-35PRVDDf "%Tc(mm!;JJ,+1+3+/0 ! ]'"+Q!e3hyST}W`cdWdGd>e3eJy~&&$.*EEE#D!&J " &"( J    + + + +r%rc|tjtjhvr{g}|D]u}|d}|d|}|jjj|||d|d|d|dd}||vn|||}|tjkr|S| |S)Nrrryrr)rrrryrr) r,r2r3argmaxrconfigid2labelrsaggregate_wordsgroup_entities)r rrDrr entity_idxrrs r#rz%TokenClassificationPipeline.aggregates $7$<>Q>X#Y Y YH* ( ( '188:: "8,Z8"j/8D"'0&v.'0%e, '''' (++L:NOOH #6#; ; ;O""8,,,r%rc|jd|D}|tjkrB|dd}|}||}|jjj|}n|tjkrNt|d}|d}|}||}|jjj|}n|tj krhtj d|D}tj |d} | } |jjj| }| | }ntd||||dd |d d d } | S) Ncg|] }|d Sryr*rZrs r#rz>TokenClassificationPipeline.aggregate_word..s7^7^7^6v7^7^7^r%rrc6|dS)Nr)r1)rs r#rz.s&:J:N:N:P:Pr%rcg|] }|d S)rr*rs r#rz>TokenClassificationPipeline.aggregate_word..sGGGFvh/GGGr%)rzInvalid aggregation_strategyrrr)rrryrr)rMconvert_tokens_to_stringr,r4rrrrr6r1r5rstacknanmeanr) r rrDryrrrr max_entityaverage_scoresr new_entitys r#aggregate_wordz*TokenClassificationPipeline.aggregate_words{~667^7^U]7^7^7^__ #6#< < <a[*F--//C3KEZ&/4FF !%8%< < <X+P+PQQQJ)F--//C3KEZ&/4FF !%8%@ @ @XGGhGGGHHFZQ777N'..00JZ&/ ;F":.EE;<< <a[)B<&   r%c`|tjtjhvrtdg}d}|D]R}||g}|dr||&|||||g}S|)|||||S)z Override tokens from a given word that disagree to force agreement on word boundaries. Example: micro|soft| com|pany| B-ENT I-NAME I-ENT I-ENT will be rewritten with first strategy as microsoft| company| B-ENT I-ENT z;NONE and SIMPLE strategies are invalid for word aggregationNr)r,r2r3rrsr)r rrD word_entities word_grouprs r#rz+TokenClassificationPipeline.aggregate_words s  $  &$   Z[[ [   & &F!$X  % &!!&))))$$T%8%8EY%Z%Z[[[$X  !  !4!4ZAU!V!V W W Wr%c>|ddddd}tjd|D}d|D}|tj||j||dd|dd d }|S) z Group together the adjacent tokens with the same entity predicted. Args: entities (`dict`): The entities predicted by the pipeline. rr-r rcg|] }|d S)rr*rs r#rzBTokenClassificationPipeline.group_sub_entities...sDDDVG_DDDr%cg|] }|d Srr*rs r#rzBTokenClassificationPipeline.group_sub_entities../s888V&.888r%rr)rrryrr)splitrrmeanrMr)r rrrtokensrs r#group_sub_entitiesz.TokenClassificationPipeline.group_sub_entities%s!X&,,S!44R8DD8DDDEE88x888#WV__N;;FCCa[)B<&   r% entity_namec|dr d}|dd}n&|dr d}|dd}nd}|}||fS)NzB-BrzI-I) startswith)r rbitags r#get_tagz#TokenClassificationPipeline.get_tag:sk  ! !$ ' ' Babb/CC  # #D ) ) Babb/CCBC3wr%cg}g}|D]}|s||||d\}}||dd\}}||kr|dkr||~||||g}|r(||||S)z Find and group together the adjacent tokens with the same entity predicted. Args: entities (`dict`): The entities predicted by the pipeline. rrr)rsrr) r r entity_groupsentity_group_disaggrrrlast_bilast_tags r#rz*TokenClassificationPipeline.group_entitiesHs   / /F& #**6222 ll6(#344GB $ -@-DX-N O O GXh299#**62222$$T%<%<=P%Q%QRRR'-h##  O  !8!89L!M!M N N Nr%)NNNFNNrU)NN)%r&r'r(r)default_input_names_load_processor_load_image_processor_load_feature_extractor_load_tokenizerrr>r,rrrboolrrRrrrr$r}rr2rrrndarrayrrrrrrr __classcell__)rCs@r#r9r9=s@""H&O!#O#E#E#G#G((((((;?7;$)! $99992D899U38_-4 99 " 99 d 99:99999999vOsOcOd4S>6JOOOXO [tCy[C[Dd3PS8nAUFFF:F F U38_-4 F  Z F2FsTz"T)F c3h047F dFFFFP-d4j-H[-`dei`j----,tDzI\ae<T J]bfgkbl84:$* 3 5c?    #tDz#d4j########r%r9)rrtypingrrrr$models.bert.tokenization_bert_legacyrutilsrrr baser r r rrmodels.auto.modeling_autorrr,r9 NerPipeliner*r%r#rs  AAAAAA TSSSSSSSSSSSYLLLXXXXXXFFFFFFFF:,4000n>OOOOO-OO?>Od* r%