o i@sddlZddlZddlmZddlmZmZmZmZm Z m Z ddl m Z m Z ddlmZddlmZddlmZdd lmZdd lmZdd lmZmZdd lmZdd lmZddlm Z dZ!e "e!dZ#dZ$dZ%deedee&effddZ'ddZ(Gddde Z)ddZ*dS)N)islice)AnyCallableDictIterableListOptional)ConfigModel)Floats2d)Errors)Language)Scorer)Doc)Examplevalidate_get_examples)registry)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 = ${model.tok2vec.embed.width} window_size = 1 maxout_pieces = 3 depth = 2 [model.linear_model] @architectures = "spacy.TextCatBOW.v3" exclusive_classes = false length = 262144 ngram_size = 1 no_output_layer = false modelzq [model] @architectures = "spacy.TextCatBOW.v3" exclusive_classes = false ngram_size = 1 no_output_layer = false aa [model] @architectures = "spacy.TextCatReduce.v1" exclusive_classes = false use_reduce_first = false use_reduce_last = false use_reduce_max = false use_reduce_mean = true [model.tok2vec] @architectures = "spacy.HashEmbedCNN.v2" pretrained_vectors = null width = 96 depth = 4 embed_size = 2000 window_size = 1 maxout_pieces = 3 subword_features = true examplesreturncKstj|dfddi|S)Ncats multi_labelT)r score_cats)rkwargsrU/home/ubuntu/.local/lib/python3.10/site-packages/spacy/pipeline/textcat_multilabel.pytextcat_multilabel_scoreMsr cCstS)N)r rrrrmake_textcat_multilabel_scorerVsr!c@seZdZdZ deddedededede e d d f d d Z e d dZ d d dde geefde ede eefddZdeefddZd S)MultiLabel_TextCategorizerzlPipeline component for multi-label text classification. DOCS: https://spacy.io/api/textcategorizer textcat_multilabel)scorervocabrname thresholdr$rNcCs6||_||_||_d|_g|d}t||_||_dS)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+rrr__init__`s   z#MultiLabel_TextCategorizer.__init__cCsdS)NTr)r,rrrsupport_missing_values|sz1MultiLabel_TextCategorizer.support_missing_values)nlpr( get_examplesr/r(c Cst|d|dur|D]}|jjD]}||qq n |D]}||qtt|d}||dd|D}||\} } |t |dksUJt j j |j dt | dkseJt j j |j d|jj|| ddS) 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 %MultiLabel_TextCategorizer.initializeN cSsg|]}|jqSr) reference).0egrrr sz9MultiLabel_TextCategorizer.initialize..r)r&)XY)ryr add_labellistr_validate_categories_examples_to_truth_require_labelslenr E923formatr&r initialize) r,r0r/r(examplecatlabelsubbatch doc_sample label_sample_rrrrBs"        r1rcCsB|D]}|jjD]}|dks|dksttjj|dq qdS)zThis component allows any type of single- or multi-label annotations. This method overwrites the more strict one from 'textcat'.g?g)valN)r3rvalues ValueErrorr E851rA)r,rexrJrrrr<sz/MultiLabel_TextCategorizer._validate_categories)r#)__name__ __module__ __qualname____doc__r rr strfloatrrr-propertyr.rrrrBr<rrrrr"Zs<     %r"cCs,|dkr td}|jStdtd|)Nmake_multilabel_textcatzspacy.pipeline.factorieszmodule z has no attribute ) importlib import_modulerVAttributeErrorrO)r&modulerrr __getattr__s r[)+rWsys itertoolsrtypingrrrrrr thinc.apir r thinc.typesr errorsr languagerr$rtokensrtrainingrrutilrr%rtextcatrmulti_label_default_configfrom_strDEFAULT_MULTI_TEXTCAT_MODELmulti_label_bow_configmulti_label_cnn_configrSr r!r"r[rrrrs,            V