g?iRddlZddlZddlmZmZmZmZddlZddl m Z ddl m Z m Z mZmZddlmZmZmZmZer ddlZddlmZer ddlZdd lmZGd d eZGd d e Ze eddGddeZeZdS)N)ListOptionalTupleUnion)BasicTokenizer) ExplicitEnumadd_end_docstringsis_tf_availableis_torch_available)ArgumentHandler ChunkPipelineDatasetbuild_pipeline_init_args)/TF_MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING_NAMES),MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING_NAMESc:eZdZdZdeeeeffdZdS)"TokenClassificationArgumentHandlerz5 Handles arguments for token classification. inputsc J|Nt|ttfr2t|dkrt|}t|}ndt|tr|g}d}nIt t|t st|t jr|dfStd| d}|rUt|trt|dtr|g}t||krtd||fS)Nrr zAt least one input is required.offset_mappingz;offset_mapping should have the same batch size as the input) isinstancelisttuplelenstrrtypes GeneratorType ValueErrorget)selfrkwargs batch_sizers g/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/pipelines/token_classification.py__call__z+TokenClassificationArgumentHandler.__call__ s  *VdE]"C"C F VW&\\FVJJ  $ $ @XFJJ  Z%@%@ JvW\WjDkDk 4< >?? ?$455  `.$// 2J~a?PRW4X4X 2"0!1>""j00 !^___~%%N)__name__ __module__ __qualname____doc__rrrr&r'r%rrsF&uS$s)^4&&&&&&r'rc&eZdZdZdZdZdZdZdZdS)AggregationStrategyzDAll the valid aggregation strategies for TokenClassificationPipelinenonesimplefirstaveragemaxN) r(r)r*r+NONESIMPLEFIRSTAVERAGEMAXr,r'r%r.r.5s-NN D F EG CCCr'r.T) has_tokenizera ignore_labels (`List[str]`, defaults to `["O"]`): A list of labels to ignore. grouped_entities (`bool`, *optional*, defaults to `False`): DEPRECATED, use `aggregation_strategy` instead. Whether or not to group the tokens corresponding to the same entity together in the predictions or not. 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.cdeZdZdZdZeffd Z d deedeedee dee e e e fd ee f d Z d eee efffd Zd!d ZdZe jdfdZdZdedejdejdee e e e fdejde de efdZde ede de efdZde ede defdZde ede de efdZde edefdZdede eeffdZde ede efdZxZ 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). sequencesctj|i|||jdkrtnt t d|_||_dS)NtfF) do_lower_case) super__init__check_model_type frameworkrrr_basic_tokenizer _args_parser)r" args_parserargsr# __class__s r%rAz$TokenClassificationPipeline.__init__sr$)&))) ~%% < ;=   !/U C C C'r'Ngrouped_entitiesignore_subwordsaggregation_strategyrstrideci}|||d<i}||b|r|r tj}n|r|s tj}n tj}|t jd|d|t jd|d|yt |trt|}|tjtj tj hvr|j j std||d<|||d<|i||j jkrtd|tjkrtd |d |j j r d d |d } | |d <ntd|i|fS)Nrzl`grouped_entities` is deprecated and will be removed in version v5.0.0, defaulted to `aggregation_strategy="z "` instead.zk`ignore_subwords` is deprecated and will be removed in version v5.0.0, defaulted to `aggregation_strategy="z{Slow tokenizers cannot handle subwords. Please set the `aggregation_strategy` option to `"simple"` or use a fast tokenizer.rK 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_tokenspaddingrLtokenizer_paramszm`stride` was provided to process all the text but you're using a slow tokenizer. Please use a fast tokenizer.)r.r6r5r4warningswarnrrupperr8r7 tokenizeris_fastr model_max_length) r"rNrIrJrKrrLpreprocess_paramspostprocess_paramsrQs r%_sanitize_parametersz0TokenClassificationPipeline._sanitize_parameterssE  %2@ . /  '?+F @O @':'@$$! @/ @':'A$$':'?$+ Q/CQQQ* Q/CQQQ +.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'rc h|j|fi|\}}|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. 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 r)rEr@r&)r"rr#_inputsrrHs r%r&z$TokenClassificationPipeline.__call__sV4#4$"3F"E"Ef"E"E  6'5F# $uww11&111r'c+ K|di}|jjr|jjdkrdnd}|j|f|j|d|jjd|}|ddt |d}t |D]r |jdkr! fd |D}n fd |D}|||d < dkr|nd|d < |d z k|d<|VsdS)NrQrTF)return_tensors truncationreturn_special_tokens_maskreturn_offsets_mappingoverflow_to_sample_mapping input_idsr>cNi|]!\}}|tj|d"Sr)r> expand_dims.0kvis r% z:TokenClassificationPipeline.preprocess.. s/VVVtq!2>!A$#:#:VVVr'cNi|]!\}}||d"Sre) unsqueezergs r%rlz:TokenClassificationPipeline.preprocess..s/PPPA1Q4>>!#4#4PPPr'rsentencer is_last)poprUrWrCrVrrangeitems) r"rorrXrQr_r num_chunks model_inputsrks @r% preprocessz&TokenClassificationPipeline.preprocesssc,001CRHH!^<oA`cdAdAdTTjo   >!'+#'>#9        /666 ,-- z""  A~%%VVVVv||~~VVV PPPPPPP )1? -.3466xxtL $&':>&9L #      r'cb|d}|dd}|d}|d}|jdkr|jd i|d}n2|jd i|}t|tr|dn|d}|||||d|S) Nspecial_tokens_maskrrorpr>rlogits)ryrxrrorpr,)rqrCmodelrdict)r"rurxrrorpryoutputs r%_forwardz$TokenClassificationPipeline._forwards*../DEE%))*:DAA##J//""9-- >T ! !TZ//,//2FFTZ//,//F)3FD)A)APVH%%vayF#6,       r'c dgg}|D]}|jdkri|ddjtjtjfvr>|ddtj}n |dd}|dd}|dd}|d|ddnd} |dd} tj |d d } tj || z } | | d d z } |jd kr,|}| | nd} | ||| | | |}| ||}fd |D}||t|}|dkr||}|S)NOptryrrorcrrxT)axiskeepdimsr>ctg|]4}|ddvr|ddv2|5S)entityN entity_group)r!)rhrrNs r% z;TokenClassificationPipeline.postprocess..IsX::h--]BBJJ~t44MIIJIIr'r )rCdtypetorchbfloat16float16tofloat32numpynpr3expsumgather_pre_entities aggregateextendraggregate_overlapping_entities)r" all_outputsrKrN all_entities model_outputsryrorcrrxmaxes shifted_expscores pre_entitiesrIentitiesrts ` r% postprocessz'TokenClassificationPipeline.postprocess+s!   EM ( * *M~%%-*A!*D*Ju~_d_lNm*m*m&x0366u}EEKKMM&x0399;;"1~j1H%k215I6CDT6U6a ./22gk #00E"Fq"I"O"O"Q"Q F6T:::E&%00K ;??T?#J#JJF~%%%OO-- ;I;U!5!5!7!7!7[_33)V^=PRfL $~~l>>>|LLLr'ct|dkr|St|d}g}|d}|D]}|d|dcxkr |dkrInnF|d|dz }|d|dz }||kr|}O||kr|d|dkr|}j|||}|||S)Nrc|dS)Nstartr,)xs r%zLTokenClassificationPipeline.aggregate_overlapping_entities..Xs !G*r'keyrendscore)rsortedappend)r"raggregated_entitiesprevious_entityrcurrent_lengthprevious_lengths r%rz:TokenClassificationPipeline.aggregate_overlapping_entitiesUs x==A  O((<(<=== "1+ ) )Fw'6'?SSSS_U=SSSSSS!'!@"1%"8?7;S"S!O33&,OO#666'?_]dMe;e;e&,O#**?;;;"(""?333""r'rorcrrxreturncXg}t|D]\}} ||r|jt||} |3||\} } t | ts3|jdkr(| } | } || | } t|jddrAt|jjj ddr!t| t| k}nW|tj tj tjhvrtjdt"| dkod|| dz | dzv}t|||jjkr| } d }nd} d} d }| | | | ||d }|||S) zTFuse various numpy arrays into dicts with all the information needed for aggregationNr _tokenizercontinuing_subword_prefixz?Tokenizer does not support real words, using fallback heuristicr r F)wordrrrindex is_subword) enumeraterUconvert_ids_to_tokensintrrCitemgetattrrrzrr.r6r7r8rRrS UserWarning unk_token_idr)r"rorcrrrxrKridx token_scoresr start_indend_indword_refr pre_entitys r%rz/TokenClassificationPipeline.gather_pre_entitiesis !*6!2!20 ,0 , C"3' >77IcN8K8KLLD)%3C%8" 7!)S111~--$-NN$4$4 "),,..#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)Nrrrrr)rrrrrr) r.r4r5argmaxrzconfigid2labelraggregate_wordsgroup_entities)r"rrKrr 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 Srr,rhrs r%rz>TokenClassificationPipeline.aggregate_word..s7^7^7^6v7^7^7^r'rrc6|dS)Nr)r3)rs r%rz.s&:J:N:N:P:Pr'rcg|] }|d S)rr,rs r%rz>TokenClassificationPipeline.aggregate_word..sGGGFvh/GGGr')rzInvalid aggregation_strategyrrr)rrrrr)rUconvert_tokens_to_stringr.r6rrzrrr8r3r7rstacknanmeanr ) r"rrKrrrrr 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.r4r5r rr)r"rrK word_entities word_grouprs r%rz+TokenClassificationPipeline.aggregate_wordss  $  &$   Z[[ [   & &F!$X  % &!!&))))$$T%8%8EY%Z%Z[[[$X  !  !4!4ZAU!V!V W W Wr'c>|ddddd}tjd|D}d|D}|tj||j||dd|dd d }|S) z Group together the adjacent tokens with the same entity predicted. Args: entities (`dict`): The entities predicted by the pipeline. rr-r rcg|] }|d S)rr,rs r%rzBTokenClassificationPipeline.group_sub_entities..sDDDVG_DDDr'cg|] }|d Srr,rs r%rzBTokenClassificationPipeline.group_sub_entities..s888V&.888r'rr)rrrrr)splitrrmeanrUr)r"rrrtokensrs r%group_sub_entitiesz.TokenClassificationPipeline.group_sub_entitiess!X&,,S!44R8DD8DDDEE88x888#WV__N;;FCCa[)B<&   r' entity_namec|dr d}|dd}n&|dr d}|dd}nd}|}||fS)NzB-BrzI-I) startswith)r"rbitags r%get_tagz#TokenClassificationPipeline.get_tag sk  ! !$ ' ' 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)rrr) r"r entity_groupsentity_group_disaggrrrlast_bilast_tags r%rz*TokenClassificationPipeline.group_entitiess   / /F& #**6222 ll6(#344GB $ -@-DX-N O O GXh299#**62222$$T%<%<=P%Q%QRRR'-h##  O  !8!89L!M!M N N Nr')NNNNNN)N)!r(r)r*r+default_input_namesrrArboolr.rrrrZrrr&rvr}r4rrrndarrayr{rrrrrrr __classcell__)rHs@r%r;r;?sF""H&#E#E#G#G ( ( ( ( ( (+/*.>B:> $G9G9#4.G9"$ G9 '':; G9 !eCHo!67 G9 G9G9G9G9R2uS$s)^4222222@4   *=Pmodels.auto.modeling_tf_autorrmodels.auto.modeling_autorrr.r; NerPipeliner,r'r%rs ////////////:::::: TSSSSSSSSSSS?_^^^^^^YLLLXXXXXX&&&&&&&&4,4000n!!D\\\\\-\\E!!D\~* r'