Functions — github.com/huggingface/evaluate

CodeHub MCPcopy Create free account

hub / github.com/huggingface/evaluate / functions

Functions785 in github.com/huggingface/evaluate

⨍ Functions 785◇ Types & classes 150↳ Endpoints 6

↓ 1 callersFunctionlower

metrics/wiki_split/wiki_split.py:94

↓ 1 callersFunctionlower

metrics/cuad/compute_score.py:45

↓ 1 callersFunctionlower

metrics/squad_v2/compute_score.py:73

↓ 1 callersFunctionlower

metrics/super_glue/record_evaluation.py:28

↓ 1 callersFunctionlower

metrics/squad/compute_score.py:24

↓ 1 callersFunctionmain

metrics/squad_v2/compute_score.py:279

↓ 1 callersFunctionmain

src/evaluate/commands/evaluate_cli.py:48

↓ 1 callersFunctionmean_iou

Calculate Mean Intersection and Union (mIoU). Args: results (`ndarray`): List of prediction segmentation maps, each of shape

metrics/mean_iou/mean_iou.py:210

↓ 1 callersFunctionmetric_max_over_ground_truths

(metric_fn, predictions, ground_truths)

metrics/cuad/compute_score.py:138

↓ 1 callersMethodother_expected_results

tests/test_metric.py:53

↓ 1 callersMethodother_predictions_and_references

tests/test_metric.py:49

↓ 1 callersFunctionparse_args

metrics/squad_v2/compute_score.py:24

↓ 1 callersFunctionparse_gradio_data

Parses data from gradio Dataframe for use in metric.

src/evaluate/utils/gradio.py:56

↓ 1 callersFunctionparse_readme

Parses a repositories README and removes

src/evaluate/utils/gradio.py:44

↓ 1 callersMethodpatch_intensive_calls

(self, evaluation_module_name, module_name)

tests/test_metric_common.py:138

↓ 1 callersFunctionpearson_and_spearman

(preds, labels)

metrics/glue/glue.py:96

↓ 1 callersMethodplot

src/evaluate/visualization.py:127

↓ 1 callersFunctionplot_pr_curve

(precisions, recalls, out_image, title)

metrics/squad_v2/compute_score.py:163

↓ 1 callersFunctionprecision_at_10

(en_sentvecs, in_sentvecs)

metrics/indic_glue/indic_glue.py:89

↓ 1 callersMethodpredictions_processor

Transform the pipeline predictions into a list of predicted labels of the same length as the true labels. Args: predicti

src/evaluate/evaluator/token_classification.py:105

↓ 1 callersMethodpredictions_processor

(self, predictions: List, squad_v2_format: bool, ids: List)

src/evaluate/evaluator/question_answering.py:138

↓ 1 callersMethodpredictions_processor

(self, predictions, label_mapping)

src/evaluate/evaluator/text_classification.py:82

↓ 1 callersMethodprepare_data

(self, data: Union[str, Dataset], input_column: str, label_column: str, join_by: str)

src/evaluate/evaluator/token_classification.py:167

↓ 1 callersMethodprepare_data

src/evaluate/evaluator/question_answering.py:96

↓ 1 callersMethodprepare_data

(self, data: Union[str, Dataset], input_column: str, second_input_column: str, label_column: str)

src/evaluate/evaluator/text_classification.py:65

↓ 1 callersMethodprepare_pipeline

( self, model_or_pipeline: Union[str, "Pipeline", Callable, "PreTrainedModel", "TFPreTrainedMo

src/evaluate/evaluator/token_classification.py:199

↓ 1 callersMethodprocess_string

metrics/xtreme_s/xtreme_s.py:107

↓ 1 callersMethodprocess_string

metrics/cer/cer.py:40

↓ 1 callersFunctionreliability_guard

This disables various destructive functions and prevents the generated code from interfering with the test (e.g. fork bomb, killing other pro

metrics/code_eval/execute.py:158

↓ 1 callersFunctionremove_articles

metrics/wiki_split/wiki_split.py:83

↓ 1 callersFunctionremove_articles

metrics/cuad/compute_score.py:35

↓ 1 callersFunctionremove_articles

metrics/squad_v2/compute_score.py:63

↓ 1 callersFunctionremove_articles

metrics/super_glue/record_evaluation.py:18

↓ 1 callersFunctionremove_articles

metrics/squad/compute_score.py:14

↓ 1 callersFunctionremove_punc

metrics/wiki_split/wiki_split.py:90

↓ 1 callersFunctionremove_punc

metrics/cuad/compute_score.py:41

↓ 1 callersFunctionremove_punc

metrics/squad_v2/compute_score.py:69

↓ 1 callersFunctionremove_punc

metrics/super_glue/record_evaluation.py:24

↓ 1 callersFunctionremove_punc

metrics/squad/compute_score.py:20

↓ 1 callersFunctionrun_precision_recall_analysis

(main_eval, exact_raw, f1_raw, na_probs, qid_to_has_ans, out_image_dir)

metrics/squad_v2/compute_score.py:198

↓ 1 callersMethodseparate_expected_results

tests/test_metric.py:69

↓ 1 callersMethodseparate_predictions_and_references

tests/test_metric.py:65

↓ 1 callersMethodsignature

metrics/bleu/tokenizer_13a.py:74

↓ 1 callersFunctionsimple_accuracy

(preds, labels)

metrics/xnli/xnli.py:65

↓ 1 callersFunctionswallow_io

metrics/code_eval/execute.py:103

↓ 1 callersFunctionsymmetric_mean_absolute_percentage_error

Symmetric Mean absolute percentage error (sMAPE) metric using sklearn's api and helpers. Parameters ---------- y_true : array-like of sha

metrics/smape/smape.py:83

↓ 1 callersFunctiontime_limit

metrics/code_eval/execute.py:90

↓ 1 callersFunctiontotal_intersect_and_union

Calculate Total Intersection and Union, by calculating `intersect_and_union` for each (predicted, ground truth) pair. Args: results (`nda

metrics/mean_iou/mean_iou.py:160

↓ 1 callersFunctiontoxicity

(preds, toxic_classifier, toxic_label)

measurements/toxicity/toxicity.py:96

↓ 1 callersFunctionurl_or_path_join

(base_name: str, *pathnames: str)

src/evaluate/utils/file_utils.py:104

↓ 1 callersMethoduse_legend

src/evaluate/visualization.py:133

↓ 1 callersFunctionwer_and_cer

(preds, labels, concatenate_texts, config_name)

metrics/xtreme_s/xtreme_s.py:191

↓ 1 callersFunctionwhite_space_fix

metrics/wiki_split/wiki_split.py:87

↓ 1 callersFunctionwhite_space_fix

metrics/cuad/compute_score.py:38

↓ 1 callersFunctionwhite_space_fix

metrics/squad_v2/compute_score.py:66

↓ 1 callersFunctionwhite_space_fix

metrics/super_glue/record_evaluation.py:21

↓ 1 callersFunctionwhite_space_fix

metrics/squad/compute_score.py:17

Tokenizes an input line with the tokenizer. :param line: a segment to tokenize :return: the tokenized line

metrics/google_bleu/tokenizer_13a.py:30

Common post-processing tokenizer for `13a` and `zh` tokenizers. :param line: a segment to tokenize :return: the tokenized line

metrics/google_bleu/tokenizer_13a.py:59

Tokenizes an input line using a relatively minimal tokenization that is however equivalent to mteval-v13a, used by WMT. :param line:

metrics/google_bleu/tokenizer_13a.py:81

Tokenizes an input line with the tokenizer. :param line: a segment to tokenize :return: the tokenized line

metrics/bleu/tokenizer_13a.py:30

Common post-processing tokenizer for `13a` and `zh` tokenizers. :param line: a segment to tokenize :return: the tokenized line

metrics/bleu/tokenizer_13a.py:59

Tokenizes an input line using a relatively minimal tokenization that is however equivalent to mteval-v13a, used by WMT. :param line:

metrics/bleu/tokenizer_13a.py:81

(self, *args, **kwargs)

src/evaluate/utils/logging.py:200

(self, inputs, **kwargs)

tests/test_evaluator.py:58

(self, inputs, **kwargs)

tests/test_evaluator.py:67

(self, inputs, **kwargs)

tests/test_evaluator.py:76

(self, images, **kwargs)

tests/test_evaluator.py:86

(self, question, context, **kwargs)

tests/test_evaluator.py:95

(self, inputs, **kwargs)

tests/test_evaluator.py:111

(self, inputs, **kwargs)

tests/test_evaluator.py:129

(self, audio, **kwargs)

tests/test_evaluator.py:137

src/evaluate/module.py:723

Method__enter__

src/evaluate/utils/logging.py:189

(self, type_, value, traceback)

src/evaluate/utils/logging.py:192

Method__getattr__

Return empty function.

src/evaluate/utils/logging.py:181

Method__getitem__

src/evaluate/evaluator/utils.py:14

Method__getitem__

src/evaluate/evaluator/utils.py:71

(self, sentence_delimiter: str = " ")

metrics/xtreme_s/xtreme_s.py:104

(self, sentence_delimiter: str = " ")

metrics/cer/cer.py:37

metrics/google_bleu/tokenizer_13a.py:43

metrics/google_bleu/tokenizer_13a.py:77

(self, tokenizer_func)

metrics/rouge/rouge.py:86

metrics/bleu/tokenizer_13a.py:43

metrics/bleu/tokenizer_13a.py:77

( self, path: str, module_type: str = "metrics", download_config: Optional[Dow

src/evaluate/loading.py:403

( self, name: str, module_type: str = "metrics", revision: Optional[Union[str,

src/evaluate/loading.py:446

( self, name: str, module_type: str = "metrics", dynamic_modules_path: Optiona

src/evaluate/loading.py:517

(self, fig, variables, ranges, n_ring_levels=5, show_scales=True, format_cfg=None)

src/evaluate/visualization.py:24

(self, info: EvaluationModuleInfo)

src/evaluate/module.py:88

( self, config_name: Optional[str] = None, keep_in_memory: bool = False, cache

src/evaluate/module.py:180

(self, evaluation_modules, force_prefix=False)

src/evaluate/module.py:873

(self, *args, **kwargs)

src/evaluate/utils/logging.py:175

(self, task="automatic-speech-recognition", default_metric_name=None)

src/evaluate/evaluator/automatic_speech_recognition.py:57

(self, task="audio-classification", default_metric_name=None)

src/evaluate/evaluator/audio_classification.py:91

(self, task="text2text-generation", default_metric_name=None)

src/evaluate/evaluator/text2text_generation.py:99

(self, task="summarization", default_metric_name=None)

src/evaluate/evaluator/text2text_generation.py:163

(self, dataset: Dataset, key: str)

src/evaluate/evaluator/utils.py:7

Args: dataset (Dataset): dataset to build an iterator on first_col (str): first column name to use in the dataset

src/evaluate/evaluator/utils.py:44

(self, task: str, default_metric_name: str = None)

src/evaluate/evaluator/base.py:112

← previous next →201–300 of 785, ranked by callers