plexus.scores package
The plexus.scores module provides a collection of classes and methods for scoring and classification tasks. It includes various classifiers such as machine learning classifiers, deep learning semantic classifiers, and explainable classifiers. These are the score classes that are referenced in the scorecard YAML files.
Subpackages
- plexus.scores.composite package
- plexus.scores.core package
- plexus.scores.nodes package
- Submodules
- plexus.scores.nodes.AgenticExtractor module
- plexus.scores.nodes.BaseNode module
- plexus.scores.nodes.BeforeAfterSlicer module
- plexus.scores.nodes.Classifier module
- plexus.scores.nodes.ContextExtractor module
- plexus.scores.nodes.Extractor module
- plexus.scores.nodes.FuzzyMatchClassifier module
- plexus.scores.nodes.FuzzyMatchExtractor module
- plexus.scores.nodes.Generator module
- plexus.scores.nodes.LogicalClassifier module
- plexus.scores.nodes.LogicalNode module
- plexus.scores.nodes.MultiClassClassifier module
- plexus.scores.nodes.NumericClassifier module
- plexus.scores.nodes.YesOrNoClassifier module
- plexus.scores.nodes.test_classifier_confidence_harmonized module
- plexus.scores.nodes.test_classifier_confidence_integration module
- plexus.scores.nodes.test_logprobs_uncertainty module
- plexus.scores.nodes.test_raw_openai_logprobs module
- plexus.scores.nodes.test_simple_confidence module
- Submodules
Submodules
- plexus.scores.AWSComprehendEntityExtractor module
AWSComprehendEntityExtractorAWSComprehendEntityExtractor.ResultAWSComprehendEntityExtractor.__init__()AWSComprehendEntityExtractor.extract_first_person_entity()AWSComprehendEntityExtractor.extract_quotes_that_include_first_person_entity()AWSComprehendEntityExtractor.predict()AWSComprehendEntityExtractor.predict_validation()AWSComprehendEntityExtractor.register_model()AWSComprehendEntityExtractor.save_model()AWSComprehendEntityExtractor.train_model()
- plexus.scores.AWSComprehendSentimentScore module
AWSComprehendSentimentScoreAWSComprehendSentimentScore.ResultAWSComprehendSentimentScore.__init__()AWSComprehendSentimentScore.create()AWSComprehendSentimentScore.predict()AWSComprehendSentimentScore.predict_validation()AWSComprehendSentimentScore.register_model()AWSComprehendSentimentScore.save_model()AWSComprehendSentimentScore.train_model()
- plexus.scores.AgenticExtractor module
- plexus.scores.AgenticValidator module
AgenticValidatorGraphStateSchoolInfoTextAnalysisValidationState
- plexus.scores.CompositeScore module
CompositeScoreCompositeScore.__init__()CompositeScore.break_text_into_chunks()CompositeScore.compute_element()CompositeScore.compute_element_for_chunk()CompositeScore.compute_explanation_and_relevant_quote()CompositeScore.compute_result()CompositeScore.concatenate_chat_history()CompositeScore.construct_system_prompt()CompositeScore.create_from_markdown()CompositeScore.extract_yaml_section()CompositeScore.filtered_text_is_empty()CompositeScore.get_accumulated_costs()CompositeScore.get_element_by_name()CompositeScore.get_total_token_count()CompositeScore.group_element_results_by_name()CompositeScore.load_results_from_json()CompositeScore.multiple()CompositeScore.na()CompositeScore.no()CompositeScore.normalize_element_name()CompositeScore.return_result_with_context()CompositeScore.save_results_to_json()CompositeScore.select_element_results_to_include()CompositeScore.to_dict()CompositeScore.yes()
- plexus.scores.DeepLearningOneStepSemanticClassifier module
- plexus.scores.DeepLearningSemanticClassifier module
- plexus.scores.DeepLearningSlidingWindowSemanticClassifier module
- plexus.scores.ExplainableClassifier module
ExplainableClassifierExplainableClassifier.ParametersExplainableClassifier.Parameters.decision_thresholdExplainableClassifier.Parameters.include_explanationsExplainableClassifier.Parameters.keywordsExplainableClassifier.Parameters.leaderboard_n_featuresExplainableClassifier.Parameters.model_configExplainableClassifier.Parameters.ngram_rangeExplainableClassifier.Parameters.scale_pos_weight_indexExplainableClassifier.Parameters.target_score_nameExplainableClassifier.Parameters.target_score_valueExplainableClassifier.Parameters.top_n_features
ExplainableClassifier.ResultExplainableClassifier.__init__()ExplainableClassifier.evaluate_model()ExplainableClassifier.explain_model()ExplainableClassifier.predict()ExplainableClassifier.predict_validation()ExplainableClassifier.preprocess_text()ExplainableClassifier.register_model()ExplainableClassifier.save_model()ExplainableClassifier.train_model()ExplainableClassifier.vectorize_transcript()
- plexus.scores.FastTextClassifier module
FastTextClassifierFastTextClassifier.ParametersFastTextClassifier.Parameters.bucket_sizeFastTextClassifier.Parameters.dimensionFastTextClassifier.Parameters.learning_rateFastTextClassifier.Parameters.learning_rate_update_rateFastTextClassifier.Parameters.loss_functionFastTextClassifier.Parameters.maximum_character_ngram_lengthFastTextClassifier.Parameters.minimum_character_ngram_lengthFastTextClassifier.Parameters.minimum_label_countFastTextClassifier.Parameters.minimum_word_countFastTextClassifier.Parameters.model_configFastTextClassifier.Parameters.number_of_epochsFastTextClassifier.Parameters.number_of_negative_samplesFastTextClassifier.Parameters.number_of_threadsFastTextClassifier.Parameters.sampling_thresholdFastTextClassifier.Parameters.window_sizeFastTextClassifier.Parameters.word_ngram_count
FastTextClassifier.__init__()FastTextClassifier.data_filename()FastTextClassifier.get_model_artifact_path()FastTextClassifier.load_context()FastTextClassifier.load_model()FastTextClassifier.predict()FastTextClassifier.predict_validation()FastTextClassifier.process_data()FastTextClassifier.register_model()FastTextClassifier.save_model()FastTextClassifier.save_model_binary()FastTextClassifier.train_model()
- plexus.scores.KeywordClassifier module
- plexus.scores.LLMGenerator module
- plexus.scores.LangGraphScore module
BatchProcessingPauseLangGraphScoreLangGraphScore.GraphStateLangGraphScore.GraphState.at_llm_breakpointLangGraphScore.GraphState.chat_historyLangGraphScore.GraphState.classificationLangGraphScore.GraphState.completionLangGraphScore.GraphState.confidenceLangGraphScore.GraphState.explanationLangGraphScore.GraphState.good_callLangGraphScore.GraphState.good_call_explanationLangGraphScore.GraphState.is_not_emptyLangGraphScore.GraphState.messagesLangGraphScore.GraphState.metadataLangGraphScore.GraphState.model_configLangGraphScore.GraphState.non_qualifying_explanationLangGraphScore.GraphState.non_qualifying_reasonLangGraphScore.GraphState.reasoningLangGraphScore.GraphState.resultsLangGraphScore.GraphState.retry_countLangGraphScore.GraphState.textLangGraphScore.GraphState.value
LangGraphScore.ParametersLangGraphScore.Parameters.checkpoint_db_pathLangGraphScore.Parameters.depends_onLangGraphScore.Parameters.graphLangGraphScore.Parameters.inputLangGraphScore.Parameters.logprobsLangGraphScore.Parameters.max_tokensLangGraphScore.Parameters.model_configLangGraphScore.Parameters.model_nameLangGraphScore.Parameters.model_providerLangGraphScore.Parameters.model_regionLangGraphScore.Parameters.outputLangGraphScore.Parameters.postgres_urlLangGraphScore.Parameters.reasoning_effortLangGraphScore.Parameters.single_line_messagesLangGraphScore.Parameters.temperatureLangGraphScore.Parameters.thread_idLangGraphScore.Parameters.top_logprobsLangGraphScore.Parameters.verbosity
LangGraphScore.ResultLangGraphScore.__init__()LangGraphScore.add_edges()LangGraphScore.async_setup()LangGraphScore.build_compiled_workflow()LangGraphScore.cleanup()LangGraphScore.create()LangGraphScore.create_combined_graphstate_class()LangGraphScore.create_value_setter_node()LangGraphScore.generate_graph_visualization()LangGraphScore.generate_input_aliasing_function()LangGraphScore.generate_output_aliasing_function()LangGraphScore.get_accumulated_costs()LangGraphScore.get_example_refinement_templates()LangGraphScore.get_prompt_templates()LangGraphScore.get_scoring_jobs_for_batch()LangGraphScore.get_token_usage()LangGraphScore.predict()LangGraphScore.predict_validation()LangGraphScore.preprocess_text()LangGraphScore.process_node()LangGraphScore.register_model()LangGraphScore.reset_token_usage()LangGraphScore.save_model()LangGraphScore.train_model()
- plexus.scores.OpenAIEmbeddingsClassifier module
OpenAIEmbeddingsClassifierOpenAIEmbeddingsClassifier.ParametersOpenAIEmbeddingsClassifier.Parameters.batch_sizeOpenAIEmbeddingsClassifier.Parameters.dropout_rateOpenAIEmbeddingsClassifier.Parameters.early_stop_patienceOpenAIEmbeddingsClassifier.Parameters.embeddings_modelOpenAIEmbeddingsClassifier.Parameters.embeddings_model_trainable_layersOpenAIEmbeddingsClassifier.Parameters.l2_regularization_strengthOpenAIEmbeddingsClassifier.Parameters.learning_rate_decayOpenAIEmbeddingsClassifier.Parameters.maximum_tokens_per_windowOpenAIEmbeddingsClassifier.Parameters.maximum_windowsOpenAIEmbeddingsClassifier.Parameters.model_configOpenAIEmbeddingsClassifier.Parameters.multiple_windowsOpenAIEmbeddingsClassifier.Parameters.number_of_epochsOpenAIEmbeddingsClassifier.Parameters.number_of_plateau_epochsOpenAIEmbeddingsClassifier.Parameters.number_of_warmup_epochsOpenAIEmbeddingsClassifier.Parameters.plateau_learning_rateOpenAIEmbeddingsClassifier.Parameters.start_from_endOpenAIEmbeddingsClassifier.Parameters.warmup_learning_rate
OpenAIEmbeddingsClassifier.__init__()OpenAIEmbeddingsClassifier.evaluate_model()OpenAIEmbeddingsClassifier.predict()OpenAIEmbeddingsClassifier.predict_validation()OpenAIEmbeddingsClassifier.process_data()OpenAIEmbeddingsClassifier.train_model()
- plexus.scores.SVMClassifier module
- plexus.scores.Score module
ScoreScore.InputScore.ParametersScore.Parameters.convert_data_percentage()Score.Parameters.dataScore.Parameters.dependenciesScore.Parameters.idScore.Parameters.keyScore.Parameters.label_fieldScore.Parameters.label_score_nameScore.Parameters.model_configScore.Parameters.nameScore.Parameters.number_of_classesScore.Parameters.scorecard_name
Score.ResultScore.SkippedScoreExceptionScore.__init__()Score.apply_processors_to_text()Score.evaluate_model()Score.from_name()Score.get_accumulated_costs()Score.get_label_score_name()Score.is_multi_classScore.is_relevant()Score.load()Score.log_validation_errors()Score.model_directory_path()Score.number_of_classesScore.predict()Score.predict_validation()Score.record_configuration()Score.register_model()Score.report_directory_path()Score.report_file_name()Score.save_model()Score.setup_label_map()Score.train_model()
- plexus.scores.test_langgraphscore_routing module