hS)VSSKrSSKrSSKJrJrJrJrJrJrJ r SSK J r J r J r Jr SSKJr SSKJr SSKJr SSKJr SS KJrJr SS KJr SS KJr S S KJr S SK J!r! Sr"\ "5RG\"5Sr$Sr%S\\S\\&\44Sjr'S\S\ \(\(44Sjr)"SS\!5r*Sr+g)N)AnyCallableDictIterableListOptionalTuple)ConfigModel Optimizerset_dropout_rate)Floats2d)Errors)Language)Scorer)DocSpan)Example)registry)DEFAULT_SPANS_KEY) TrainablePipea [model] @architectures = "spacy.SpanFinder.v1" [model.scorer] @layers = "spacy.LinearLogistic.v1" nO = 2 [model.tok2vec] @architectures = "spacy.Tok2Vec.v2" [model.tok2vec.embed] @architectures = "spacy.MultiHashEmbed.v2" width = 96 rows = [5000, 1000, 2500, 1000] attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE"] include_static_vectors = false [model.tok2vec.encode] @architectures = "spacy.MaxoutWindowEncoder.v2" width = ${model.tok2vec.embed.width} window_size = 1 maxout_pieces = 3 depth = 4 modelc[$N)span_finder_scoreT/home/james-whalen/.local/lib/python3.13/site-packages/spacy/pipeline/span_finder.pymake_span_finder_scorerr!.s rexamplesreturnc X^^[U5nSmUSmURSTT35 URSU4Sj5 URSU4Sj5 URSS 5 URS S 5 [R"U40UD6nUR USS 3S5 U$) Nspans_ spans_keyattrgettercT>URRU[T5S/5$r)spansgetlen)dockey attr_prefixs r #span_finder_score..8s!399==S5E5G1H"#Mrhas_annotationc">TUR;$r)r*)r-r.s r r0r1:sC3994Dr allow_overlapTlabeledF _per_type)dict setdefaultr score_spanspop)r"kwargsscoresr/r.s @@r rr2s &\FK  C f cU34 M &(DE ot, i'    3F 3F JJ&.!+T2 MrspancbUSRnUSR[US5-nX4$)Nr)idxr,)r=startends r _char_indicesrCBs1 GKKE r(,,T"X &C :rcb\rSrSrSrS!\SSS\S.S\S\\ \ \ 4S\ S \ S \ S \\S \\S \\SS4SjjjrS\ \ 4SjrS\ \ S\ SS4SjrSSSS.S\ \S\ S\\S\\\ \ 4S\\ \ 44 SjjrS\\ \ 44SjrS\\ \ 44SjrSS.S\/\ \4S\\SS4SjjrS rg)" SpanFinderHzMPipeline that learns span boundaries. DOCS: https://spacy.io/api/spanfinder g?N)r& threshold max_length min_lengthscorernlprnamer&rGrHrIrJr#cURUlUbUS:d Ub,US:a&[[RR XvS95eX lX0lXlUUUUS.Ulg)a Initialize the span finder. model (thinc.api.Model): The Thinc Model powering the pipeline component. name (str): The component instance name, used to add entries to the losses during training. threshold (float): Minimum probability to consider a prediction positive. scorer (Optional[Callable]): The scoring method. spans_key (str): Key of the doc.spans dict to save the spans under. During initialization and training, the component will look for spans on the reference document under the same key. max_length (Optional[int]): Maximum length of the produced spans, defaults to None meaning unlimited length. min_length (Optional[int]): Minimum length of the produced spans, defaults to None meaning shortest span length is 1. DOCS: https://spacy.io/api/spanfinder#init Nr)rIrH)rIrHrGr&) vocab ValueErrorrE1053formatrrLrJcfg) selfrKrrLr&rGrHrIrJs r __init__SpanFinder.__init__Nso<YY  "zA~  "zA~ ##z#Q    $$"" $ rdocsc<URRU5nU$)zApply the pipeline's model to a batch of docs, without modifying them. docs (Iterable[Doc]): The documents to predict. RETURNS: The models prediction for each document. DOCS: https://spacy.io/api/spanfinder#predict )rpredict)rSrVr<s r rXSpanFinder.predict}s##D) rr<c Sn[U5GHWupE/URURS'/n/nX#U[U5-n[ XX5HiupU SURS:aUR U R 5 U SURS:dMNUR U R 5 Mk UHn UHn U S-U - n U S:aMURSbURSU ::dM8URSbXRS::dM\URURSR X[U S-5 M M U[U5- nGMZ g)zModify a batch of Doc objects, using pre-computed scores. docs (Iterable[Doc]): The documents to modify. scores: The scores to set, produced by SpanFinder predict method. DOCS: https://spacy.io/api/spanfinder#set_annotations rr&rGrrINrH) enumerater*rRr,zipappendi)rSrVr<offsetr^r-startsends doc_scorestoken token_scorerArB span_lengths r set_annotationsSpanFinder.set_annotationssNoFA/1CIIdhh{+ ,FD#c():;J&)#&:"q>TXXk%::MM%''*q>TXXk%::KK( ';  C"%'E/K"Q .688L1[@.6&((<*@@ $((;"78??CRSG@TU   c#h F3&r)dropsgdlossesr"rirjrkcxUc0nURURS5 UVs/sHoURPM nn[URU5 URR U5upxUR X5upU"U 5 UbURU5 X@R==U - ss'U$s snf)aLearn from a batch of documents and gold-standard information, updating the pipe's model. Delegates to predict and get_loss. examples (Iterable[Example]): A batch of Example objects. drop (float): The dropout rate. sgd (Optional[thinc.api.Optimizer]): The optimizer. losses (Optional[Dict[str, float]]): Optional record of the loss during training. Updated using the component name as the key. RETURNS (Dict[str, float]): The updated losses dictionary. DOCS: https://spacy.io/api/spanfinder#update rh)r8rL predictedr r begin_updateget_loss finish_update) rSr"rirjrkegrmr<backprop_scoreslossd_scoress r updateSpanFinder.updates& >F$))S),45Hb\\H 5T*"&**"9"9)"Dx8! ?   s #yyT! 6sB7cURXRR5up4X RRRU5- nXT-n[ US-R 55nXe4$)a2Find the loss and gradient of loss for the batch of documents and their predicted scores. examples (Iterable[Examples]): The batch of examples. scores: Scores representing the model's predictions. RETURNS (Tuple[float, Floats2d]): The loss and the gradient. DOCS: https://spacy.io/api/spanfinder#get_loss r)_get_aligned_truth_scoresrops asarray2ffloatsum)rSr"r<truthsmasksrtrss r roSpanFinder.get_losss`66xP JJNN44V<<hk&&()~rc/n/nUGHnURRURR:wa&[[R R SS95e[UR5nURRUS4SS9nURRUS4SS9nURSURR;aURRURSHn [U 5upURR!XSS9n [U 5upX:HnX:HnU(aS X|S R"S 4'OS XS R"S 4'U(aS X|S R"S 4'MS XS R"S 4'M UR%U5 UR%U5 GM URR'US S 9nURR'US S 9nX44$) zLAlign scores of the predictions to the references for calculating the loss. span_finder) componentrfloat32)dtyper&expand)alignment_moderrr?)axis)xtextyrOrE1054rQr,rmxpzerosonesrR referencer*rC char_spanr^r] concatenate)rSr"ryr}r~rqn_tokenstruthmaskr=ref_start_char ref_end_char pred_spanpred_start_char pred_end_char start_match end_matchs r rx$SpanFinder._get_aligned_truth_scoressBttyyBDDII% !4!4}!4!MNN2<<(HFFLL(AiL@E66;;!}I;>Dxx $ (:(::LL..txx /DED3@3F0N " 6 6&X!7!I6C95M2O"1"CK - =I"34lnna/023q\^^Q./ 45mooq0134r]__a/0F MM% LL 12##F#3""5q"1}r)rK get_examplescl/nU"5H%n[U5S:dMURU5 M' U(a\UVs/sHoDRPM nnURX0RR 5upgURR XVS9 gURR 5 gs snf)aTInitialize the pipe for training, using a representative set of data examples. get_examples (Callable[[], Iterable[Example]]): Function that returns a representative sample of gold-standard Example objects. nlp (Optional[Language]): The current nlp object the component is part of. DOCS: https://spacy.io/api/spanfinder#initialize )XYN)r,r]rrxrry initialize)rSrrKsubbatchrqrVr_s r rSpanFinder.initializes#%.B8}r!#! +348RLL8D411(JJNNKDA JJ ! !D ! . JJ ! ! # 5sB1)rRrrLrJrN)r)__name__ __module__ __qualname____firstlineno____doc__rrrr rrrstrr{rintrrTrXrfrr rrur rorxr__static_attributes__rrr rErEHs" - +$($(%6- - Xc]H,--  -  - - SM- SM- "-  - ^ HSM !HSM!8!!N#'-1 7#  i  c5j)*  c5j @ E%/,B !%(@R:S!N#' $r8G#445$h  $  $$rrEc|US:Xa"[R"S5nUR$[S[SU35e)Nmake_span_finderzspacy.pipeline.factorieszmodule z has no attribute ) importlib import_modulerAttributeErrorr)rLmodules r __getattr__rsA !!(()CD&&& 78*,>tfE FFr),rsystypingrrrrrrr thinc.apir r r r thinc.typesrerrorsrlanguagerrJrtokensrrtrainingrutilrspancatrtrainable_piperspan_finder_default_configfrom_strDEFAULT_SPAN_FINDER_MODELr!rrrrCrErrrr rs GGG@@ &)4#H--.HI'R  1 S#X  sCx P$P$hGr