icddlZddlmZddlmZmZmZmZmZddl m Z m Z ddl m Z ddlmZddlmZdd lmZmZdd lmZd d lmZd Ze j5edZdZdZdeedeeeffdZdZ GddeZ!dZ"y)N)islice)AnyCallableDictIterableOptional)ConfigModel)Errors)Language)Scorer)Examplevalidate_get_examples)Vocab)TextCategorizeraX [model] @architectures = "spacy.TextCatEnsemble.v2" [model.tok2vec] @architectures = "spacy.Tok2Vec.v2" [model.tok2vec.embed] @architectures = "spacy.MultiHashEmbed.v2" width = 64 rows = [2000, 2000, 500, 1000, 500] attrs = ["NORM", "LOWER", "PREFIX", "SUFFIX", "SHAPE"] include_static_vectors = false [model.tok2vec.encode] @architectures = "spacy.MaxoutWindowEncoder.v2" width = ${model.tok2vec.embed.width} window_size = 1 maxout_pieces = 3 depth = 2 [model.linear_model] @architectures = "spacy.TextCatBOW.v3" exclusive_classes = false length = 262144 ngram_size = 1 no_output_layer = false modelzq [model] @architectures = "spacy.TextCatBOW.v3" exclusive_classes = false ngram_size = 1 no_output_layer = false aa [model] @architectures = "spacy.TextCatReduce.v1" exclusive_classes = false use_reduce_first = false use_reduce_last = false use_reduce_max = false use_reduce_mean = true [model.tok2vec] @architectures = "spacy.HashEmbedCNN.v2" pretrained_vectors = null width = 96 depth = 4 embed_size = 2000 window_size = 1 maxout_pieces = 3 subword_features = true examplesreturnc 4tj|dfddi|S)Ncats multi_labelT)r score_cats)rkwargss r/var/www/vps2.regionflexible.com/Desarrollo/venv/lib/python3.12/site-packages/spacy/pipeline/textcat_multilabel.pytextcat_multilabel_scorerIs/        ctS)N)rrrmake_textcat_multilabel_scorerr!Rs ##rceZdZdZ deddedededede e dd f d Z e d Z d d d d e geefde ede eefdZdeefdZy )MultiLabel_TextCategorizerzlPipeline component for multi-label text classification. DOCS: https://spacy.io/api/textcategorizer )scorervocabrname thresholdr$rNct||_||_||_d|_g|d}t ||_||_y)aInitialize a text categorizer for multi-label classification. vocab (Vocab): The shared vocabulary. 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): Cutoff to consider a prediction "positive". scorer (Optional[Callable]): The scoring method. DOCS: https://spacy.io/api/textcategorizer#init N)labelsr')r%rr&_rehearsal_modeldictcfgr$)selfr%rr&r'r$r,s r__init__z#MultiLabel_TextCategorizer.__init__\s=(   $)49 rcy)NTr )r-s rsupport_missing_valuesz1MultiLabel_TextCategorizer.support_missing_valuesxsr)nlpr) get_examplesr1r)ct|d|9|D].}|jjD]}|j|0n|D]}|j|t t |d}|j ||Dcgc]}|j} }|j|\} } |jt| dkDs/Jtjj|jt| dkDs/Jtjj|j|jj!| | ycc}w)a\Initialize 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 (Language): The current nlp object the component is part of. labels: The labels to add to the component, typically generated by the `init labels` command. If no labels are provided, the get_examples callback is used to extract the labels from the data. DOCS: https://spacy.io/api/textcategorizer#initialize z%MultiLabel_TextCategorizer.initializeN r)r&)XY)ryr add_labellistr_validate_categories reference_examples_to_truth_require_labelslenr E923formatr&r initialize) r-r2r1r)examplecatlabelsubbatcheg doc_sample label_sample_s rrAz%MultiLabel_TextCategorizer.initialize|s4& l,ST >'> ("99>>(CNN3'( (  &u% &|~r23 !!(+-56rbll6 611(; a :"FFKK$6$6DII$6$FF"< 1$Hfkk&8&8dii&8&HH$  l; 7sE rc|D]_}|jjjD]6}|dk(r |dk(rttj j |ay)zThis component allows any type of single- or multi-label annotations. This method overwrites the more strict one from 'textcat'.g?g)valN)r;rvalues ValueErrorr E851r@)r-rexrKs rr:z/MultiLabel_TextCategorizer._validate_categoriessc BB||((//1 Bs cSj$V[[%7%7C%7%@AA B Br)textcat_multilabel)__name__ __module__ __qualname____doc__rrr strfloatrrr.propertyr0rrr rAr:r rrr#r#Vs) &>   " 8#'*. #<r8G#445#<h  #< #' #Brr#cx|dk(r!tjd}|jStdtd|)Nmake_multilabel_textcatzspacy.pipeline.factorieszmodule z has no attribute ) importlib import_modulerYAttributeErrorrQ)r&modules r __getattr__r^sA (((()CD--- 78*,>tfE FFr)#rZ itertoolsrtypingrrrrr thinc.apir r errorsr languager r$rtrainingrrr%rtextcatrmulti_label_default_configfrom_strDEFAULT_MULTI_TEXTCAT_MODELmulti_label_bow_configmulti_label_cnn_configrUrr!r#r^r rrrks::#5$8%h//0JKGT*x'8tCQTH~$RBRBlGr