ZjCSSKrSSKrSSKrSSKJr SSKJrJrJ r SSK J r J r J r JrJr \"5(a SSKrSSKJrJr "SS \ 5r\"\"S S 95"S S \ 55rg)N)GenerationConfig)add_end_docstringsis_torch_availablerequires_backends)ArgumentHandlerDatasetPipelinePipelineExceptionbuild_pipeline_init_args),MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING_NAMES0MODEL_FOR_TABLE_QUESTION_ANSWERING_MAPPING_NAMESc"\rSrSrSrSSjrSrg)%TableQuestionAnsweringArgumentHandlerz: Handles arguments for the TableQuestionAnsweringPipeline Nc T[US5 SSKnUc [S5eUGc/[U[5(a(UR S5bUR S5bU/nO[U[ 5(a[U5S:ay[SU55(d[SSU535eUSR S5bUSR S5bUnOz[S USR5S 35e[b[U[5(d[U[R5(aU$[S [U5S 35eXS ./nUHKn[USUR5(aM#USc [S5eURUS5US'MM U$)Npandasrz(Keyword argument `table` cannot be None.querytablec3B# UHn[U[5v M g7fN) isinstancedict.0ds ڀ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/pipelines/table_question_answering.py ATableQuestionAnsweringArgumentHandler.__call__..-s>1:a..sz:Keyword argument `table` should be a list of dict, but is c38# UHn[U5v M g7fr)typers rrr /sUmglbcVZ[\V]V]glszIf keyword argument `table` is a list of dictionaries, each dictionary should have a `table` and `query` key, but only dictionary has keys z `table` and `query` keys.zZInvalid input. Keyword argument `table` should be either of type `dict` or `list`, but is ))rrzTable cannot be None.)rr ValueErrorrrgetlistlenallkeysr types GeneratorTyper" DataFrame)selfrrkwargspdtqa_pipeline_inputstqa_pipeline_inputs r__call__.TableQuestionAnsweringArgumentHandler.__call__s $) =GH H ]%&&599W+=+IeiiX_N`Nl',g#E4((SZ!^>>>>$TUmglUmTno8<<(4qg9N9Z*/'$JJOPQ(--/IZZtv$E7)C)CzRWY^YlYlGmGm  u+a) .3#C"D "5 092<<HH%g.6$%<==.0ll;Mg;V.W"7+ #6#")NN)__name__ __module__ __qualname____firstlineno____doc__r2__static_attributes__r5r4rrrs -#r4rT) has_tokenizerc^\rSrSrSrSrSrSrSrSr Sr \ "SS9r \ "54U4SjjrS rS rU4S jrSS jrSS jrSSjrSrSrU=r$)TableQuestionAnsweringPipelineMah Table Question Answering pipeline using a `ModelForTableQuestionAnswering`. This pipeline is only available in PyTorch. Unless the model you're using explicitly sets these generation parameters in its configuration files (`generation_config.json`), the following default values will be used: - max_new_tokens: 256 Example: ```python >>> from transformers import pipeline >>> oracle = pipeline(model="google/tapas-base-finetuned-wtq") >>> table = { ... "Repository": ["Transformers", "Datasets", "Tokenizers"], ... "Stars": ["36542", "4512", "3934"], ... "Contributors": ["651", "77", "34"], ... "Programming language": ["Python", "Python", "Rust, Python and NodeJS"], ... } >>> oracle(query="How many stars does the transformers repository have?", table=table) {'answer': 'AVERAGE > 36542', 'coordinates': [(0, 1)], 'cells': ['36542'], 'aggregator': 'AVERAGE'} ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial) This tabular question answering pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"table-question-answering"`. The models that this pipeline can use are models that have been fine-tuned on a tabular question answering task. See the up-to-date list of available models on [huggingface.co/models](https://huggingface.co/models?filter=table-question-answering). z table,queryTF)max_new_tokensc >[TU]"S0UD6 Xl[R"5nUR [ 5 URU5 [URRSS5=(a! [URRSS5Ul [URRS5(aSUl gSUl g)Naggregation_labelsnum_aggregation_labelstapasr5)super__init__ _args_parserrcopyupdatercheck_model_typegetattrmodelconfig aggregatehasattrr")r- args_parserr.mapping __class__s rrG'TableQuestionAnsweringPipeline.__init__}s "6"'BGGICD g& !2!24H$O T[ JJ  7U  'tzz'8'8:NOOG UY r4c &UR"S0UD6$)Nr5)rM)r-inputss rbatch_inference.TableQuestionAnsweringPipeline.batch_inferenceszz#F##r4c :/n/nSnUSRSnUSRUR5nUSRUR5nUSRUR5nSn [U5GH=n UGb.U SS2S4n [R "U R 5R55n Xn [U RS5Hn U SS2S4R5U nU SS2S4R5U S- nU SS2S4R5U S- nUS:dM_US:dMgUS:XdMo[XOU45X'M [R"U 5R[R5RUR5U SS2S4'XjnXznXn URURS5URS5U RS5S 9nUR nUR"(aUR%UR&5 UR%U5 [R(R+US 9nUR,UR[R.5RUR,R5-n[0R2"[45n[7UR95R55Hun nU SS2S4R5U nU SS2S4R5U S- nU SS2S4R5U S- nUS:dMbUS:dMjUS:XdMrUUU4R%U5 M UVs0sH.nU[R:"UU5R=5S :_M0 nnGM@ [R>"[AU5S5nUR"(dU4$U[R>"[AU5S54$s snf) z Inference used for models that need to process sequences in a sequential fashion, like the SQA models which handle conversational query related to a table. N input_idsrattention_masktoken_type_idsrr)rZr[r\)logitsg?)!shapetodevicerangenp zeros_likecpunumpytolistinttorch from_numpyr"longrM unsqueezer^rOappendlogits_aggregation distributions Bernoulliprobsfloat32 collections defaultdictr& enumeratesqueezearraymeancattuple)r-rV all_logitsall_aggregations prev_answers batch_sizerZr[r\token_type_ids_exampleindexprev_labels_example model_labelsi segment_idcol_idrow_idinput_ids_exampleattention_mask_exampleoutputsr^dist_per_token probabilitiescoords_to_probspcolrowkey logits_batchs rsequential_inference3TableQuestionAnsweringPipeline.sequential_inferences   K(..q1 ;'**4;;7  0144T[[A 0144T[[A!%:&E'&&|11!45A!71!=!D!D!Fq!IJ3AqD9@@B1EIF3AqD9@@B1EIF{v{zQ*-lF;K.L*M  605/?/? /M/R/RSXS]S]/^/a/abfbmbm/n&q!t, ) 0 %3%: "%3%: "jj+55a85??B5??B!G ^^F~~ ''(B(BC   f %"00::&:IN*003I3N3Nu}}3]3`3`$$++4M*55d;O!-"7"7"9"@"@"BC13AqD9@@B1E ,QT299;A>B,QT299;A>B!8qZ1_#S#J/66q9 DYhhXgQTC/#*>!?!D!D!F!LLXgLhL]'`yyz!2A6 &*nn o<SXYiSjlmIn:oo is5Pcv>UR"U0UD6n[TU]"U40UD6n[U5S:XaUS$U$)a2 Answers queries according to a table. The pipeline accepts several types of inputs which are detailed below: - `pipeline(table, query)` - `pipeline(table, [query])` - `pipeline(table=table, query=query)` - `pipeline(table=table, query=[query])` - `pipeline({"table": table, "query": query})` - `pipeline({"table": table, "query": [query]})` - `pipeline([{"table": table, "query": query}, {"table": table, "query": query}])` The `table` argument should be a dict or a DataFrame built from that dict, containing the whole table: Example: ```python data = { "actors": ["brad pitt", "leonardo di caprio", "george clooney"], "age": ["56", "45", "59"], "number of movies": ["87", "53", "69"], "date of birth": ["7 february 1967", "10 june 1996", "28 november 1967"], } ``` This dictionary can be passed in as such, or can be converted to a pandas DataFrame: Example: ```python import pandas as pd table = pd.DataFrame.from_dict(data) ``` Args: table (`pd.DataFrame` or `Dict`): Pandas DataFrame or dictionary that will be converted to a DataFrame containing all the table values. See above for an example of dictionary. query (`str` or `list[str]`): Query or list of queries that will be sent to the model alongside the table. sequential (`bool`, *optional*, defaults to `False`): Whether to do inference sequentially or as a batch. Batching is faster, but models like SQA require the inference to be done sequentially to extract relations within sequences, given their conversational nature. padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`): Activates and controls padding. Accepts the following values: - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single sequence if provided). - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum acceptable input length for the model if that argument is not provided. - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different lengths). truncation (`bool`, `str` or [`TapasTruncationStrategy`], *optional*, defaults to `False`): Activates and controls truncation. Accepts the following values: - `True` or `'drop_rows_to_fit'`: Truncate to a maximum length specified with the argument `max_length` or to the maximum acceptable input length for the model if that argument is not provided. This will truncate row by row, removing rows from the table. - `False` or `'do_not_truncate'` (default): No truncation (i.e., can output batch with sequence lengths greater than the model maximum admissible input size). Return: A dictionary or a list of dictionaries containing results: Each result is a dictionary with the following keys: - **answer** (`str`) -- The answer of the query given the table. If there is an aggregator, the answer will be preceded by `AGGREGATOR >`. - **coordinates** (`list[tuple[int, int]]`) -- Coordinates of the cells of the answers. - **cells** (`list[str]`) -- List of strings made up of the answer cell values. - **aggregator** (`str`) -- If the model has an aggregator, this returns the aggregator. rr)rHrFr2r')r-argsr.pipeline_inputsresultsrSs rr2'TableQuestionAnsweringPipeline.__call__sJV++T>#/97;7M7M 34jj))LLLOLG)5RYZ r4cUSnUSnUSnURS:XGaUR(aUSSupVURRX%U5nUup[ U 5V V s0sH(upXR R RU _M* n n n UR R Rn [ U 5V V s0sHupX:wdM XU S-_M nn n O)USnURRX%5nUSn0n 0n/n[ U5HunnUVs/sHnURUPM nnU RUS5nURUS5nUS RU5-UUVs/sHnURUPM snS .nU(aUUS 'URU5 M [W5S:Xa![S UR RS 5eO,URR!USS9Vs/sHnSU0PM nn[U5S:aU$US$s sn n fs sn n fs snfs snfs snf)NrrrrErz > rrz, )answer coordinatescells aggregatorzTable question answeringz Empty answerT)skip_special_tokensrr)r"rOrconvert_logits_to_predictionsrurMrNrCno_aggregation_label_indexiatr%joinrmr'r name_or_path batch_decode)r-rrVrrr^ logits_agg predictionsanswer_coordinates_batchagg_predictionsrpred aggregatorsno_agg_label_indexaggregators_prefixanswersrr coordinaterraggregator_prefixrs r postprocess*TableQuestionAnsweringPipeline.postprocessVsc~.g& * 99 ~~%,Ra[""nnJJ6[ef ( %'"G&/0H&I"{ALM::.M(__UB7 $6$:$:5"$E!/$))E2BB#.FQRk eii 3kR +5F<(v&'J6{a'(BDJJD[D[]kll 9=8S8ST[qu8S8vw8vf&)8vGwg,*w: :?x&N Sxs$'/H/ H5 H5&H;=I I)rHrOr")NNN)TN)F)r6r7r8r9r:default_input_names_pipeline_calls_generate_load_processor_load_image_processor_load_feature_extractor_load_tokenizerr_default_generation_configrrGrWrr2rrrrr; __classcell__)rSs@rr>r>Msw D(#O!#O!1"$I#J Z$ApFPd5& "(;(;r4r>)rsr*rfrc generationrutilsrrrbaser r r r r rimodels.auto.modeling_autorrrr>r5r4rrsn ) ba 2#O2#j,4@Ap;Xp;Bp;r4