evalscope 0.5.5__py3-none-any.whl → 0.5.5rc0__py3-none-any.whl

evalscope/backend/rag_eval/cmteb/base.py

@@ -1,89 +0,0 @@
-from collections import defaultdict
-from typing import List
-from mteb import AbsTask
-from datasets import DatasetDict
-from modelscope import MsDataset
-import datasets
-from evalscope.backend.rag_eval.cmteb.tasks import CLS_DICT, CLS_RETRIEVAL
-
-__all__ = ["TaskBase"]
-
-
-
-class TaskBase:
-
-    @staticmethod
-    def get_tasks(task_names, **kwargs) -> List[AbsTask]:
-
-        return [TaskBase.get_task(task_name, **kwargs) for task_name in task_names]
-
-    @staticmethod
-    def get_task(task_name, **kwargs) -> AbsTask:
-
-        if task_name not in CLS_DICT:
-            from mteb.overview import TASKS_REGISTRY
-
-            task_cls = TASKS_REGISTRY[task_name]
-            if task_cls.metadata.type != "Retrieval":
-                task_cls.load_data = load_data
-        else:
-            task_cls = CLS_DICT[task_name]
-            task_cls.load_data = load_data
-        # init task instance
-        task_instance = task_cls()
-        return task_instance
-
-
-def load_data(self, **kwargs):
-    """Load dataset from the hub, compatible with ModelScope and Hugging Face."""
-    if self.data_loaded:
-        return
-
-    limits = kwargs.get("limits", None)
-    hub = kwargs.get("hub", "modelscope")
-    name = self.metadata_dict.get("name")
-    path = self.metadata_dict["dataset"].get("path")
-
-    assert path is not None, "Path must be specified in dataset"
-
-    # Loading the dataset based on the source hub
-    if hub == "modelscope":
-        import re
-
-        path = re.sub(r"^mteb/", "MTEB/", path)
-        dataset = MsDataset.load(path)
-    else:
-        dataset = datasets.load_dataset(**self.metadata_dict["dataset"])  # type: ignore
-
-    if limits is not None:
-        dataset = {
-            split: dataset[split].select(range(min(limits, len(dataset[split]))))
-            for split in dataset.keys()
-        }
-
-    if name in CLS_RETRIEVAL:
-        self.corpus, self.queries, self.relevant_docs = load_retrieval_data(
-            dataset,
-            path,
-            self.metadata_dict["eval_splits"],
-        )
-
-    self.dataset = dataset
-    self.dataset_transform()
-    self.data_loaded = True
-
-
-def load_retrieval_data(dataset, dataset_name: str, eval_splits: list) -> tuple:
-    eval_split = eval_splits[0]
-    qrels = MsDataset.load(dataset_name + "-qrels")[eval_split]
-
-    corpus = {e["id"]: {"text": e["text"]} for e in dataset["corpus"]}
-    queries = {e["id"]: e["text"] for e in dataset["queries"]}
-    relevant_docs = defaultdict(dict)
-    for e in qrels:
-        relevant_docs[e["qid"]][e["pid"]] = e["score"]
-
-    corpus = DatasetDict({eval_split: corpus})
-    queries = DatasetDict({eval_split: queries})
-    relevant_docs = DatasetDict({eval_split: relevant_docs})
-    return corpus, queries, relevant_docs

evalscope/backend/rag_eval/cmteb/task_template.py

@@ -1,83 +0,0 @@
-import os
-import mteb
-from evalscope.backend.rag_eval import EmbeddingModel
-from evalscope.backend.rag_eval import cmteb
-from mteb.task_selection import results_to_dataframe
-from evalscope.utils.logger import get_logger
-
-logger = get_logger()
-
-
-def show_results(output_folder, model, results):
-    model_name = model.mteb_model_meta.model_name_as_path()
-    revision = model.mteb_model_meta.revision
-
-    results_df = results_to_dataframe({model_name: {revision: results}})
-
-    save_path = os.path.join(
-        output_folder,
-        model_name,
-        revision,
-    )
-    logger.info(f"Evaluation results:\n{results_df.to_markdown()}")
-    logger.info(f"Evaluation results saved in {os.path.abspath(save_path)}")
-
-
-def one_stage_eval(
-    model_args,
-    eval_args,
-) -> None:
-    # load model
-    model = EmbeddingModel.load(**model_args)
-
-    # load task first to update instructions
-    tasks = cmteb.TaskBase.get_tasks(task_names=eval_args["tasks"])
-    evaluation = mteb.MTEB(tasks=tasks)
-
-    # run evaluation
-    results = evaluation.run(model, **eval_args)
-
-    # save and log results
-    show_results(eval_args["output_folder"], model, results)
-
-
-def two_stage_eval(
-    model1_args,
-    model2_args,
-    eval_args,
-) -> None:
-    """a two-stage run with the second stage reading results saved from the first stage."""
-    # load model
-    dual_encoder = EmbeddingModel.load(**model1_args)
-    cross_encoder = EmbeddingModel.load(**model2_args)
-
-    first_stage_path = f"{eval_args['output_folder']}/stage1"
-    second_stage_path = f"{eval_args['output_folder']}/stage2"
-
-    tasks = cmteb.TaskBase.get_tasks(task_names=eval_args["tasks"])
-    for task in tasks:
-        evaluation = mteb.MTEB(tasks=[task])
-
-        # stage 1: run dual encoder
-        evaluation.run(
-            dual_encoder,
-            save_predictions=True,
-            output_folder=first_stage_path,
-            overwrite_results=True,
-            hub=eval_args["hub"],
-            limits=eval_args["limits"],
-        )
-        # stage 2: run cross encoder
-        results = evaluation.run(
-            cross_encoder,
-            top_k=eval_args["top_k"],
-            save_predictions=True,
-            output_folder=second_stage_path,
-            previous_results=f"{first_stage_path}/{task.metadata.name}_default_predictions.json",
-            overwrite_results=True,
-            hub=eval_args["hub"],
-            limits=eval_args["limits"],
-        )
-
-        # save and log results
-        show_results(second_stage_path, cross_encoder, results)

evalscope/backend/rag_eval/cmteb/tasks/Classification.py

@@ -1,302 +0,0 @@
-from mteb.abstasks.AbsTaskClassification import AbsTaskClassification
-from mteb.abstasks.TaskMetadata import TaskMetadata
-
-
-class TNews(AbsTaskClassification):
-    metadata = TaskMetadata(
-        name="TNews",
-        description="Short Text Classification for News",
-        reference="https://www.cluebenchmarks.com/introduce.html",
-        dataset={
-            "path": "C-MTEB/TNews-classification",
-            "revision": "317f262bf1e6126357bbe89e875451e4b0938fe4",
-        },
-        type="Classification",
-        category="s2s",
-        modalities=["text"],
-        eval_splits=["validation"],
-        eval_langs=["cmn-Hans"],
-        main_score="accuracy",
-        date=None,
-        domains=None,
-        task_subtypes=None,
-        license=None,
-        annotations_creators=None,
-        dialect=None,
-        sample_creation=None,
-        bibtex_citation="""@inproceedings {xu-etal-2020-clue,
- title = "{CLUE}: A {C}hinese Language Understanding Evaluation Benchmark",
- author = "Xu, Liang  and
-    Hu, Hai and
-    Zhang, Xuanwei and
-    Li, Lu and
-    Cao, Chenjie and
-    Li, Yudong and
-    Xu, Yechen and
-    Sun, Kai and
-    Yu, Dian and
-    Yu, Cong and
-    Tian, Yin and
-    Dong, Qianqian and
-    Liu, Weitang and
-    Shi, Bo and
-    Cui, Yiming and
-    Li, Junyi and
-    Zeng, Jun and
-    Wang, Rongzhao and
-    Xie, Weijian and
-    Li, Yanting and
-    Patterson, Yina and
-    Tian, Zuoyu and
-    Zhang, Yiwen and
-    Zhou, He and
-    Liu, Shaoweihua and
-    Zhao, Zhe and
-    Zhao, Qipeng and
-    Yue, Cong and
-    Zhang, Xinrui and
-    Yang, Zhengliang and
-    Richardson, Kyle and
-    Lan, Zhenzhong ",
- booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
- month = dec,
- year = "2020",
- address = "Barcelona, Spain (Online)",
- publisher = "International Committee on Computational Linguistics",
- url = "https://aclanthology.org/2020.coling-main.419",
- doi = "10.18653/v1/2020.coling-main.419",
- pages = "4762--4772",
-}""",
-        descriptive_stats={"n_samples": None, "avg_character_length": None},
-    )
-
-    @property
-    def metadata_dict(self) -> dict[str, str]:
-        metadata_dict = super().metadata_dict
-        metadata_dict["samples_per_label"] = 32
-        return metadata_dict
-
-
-class IFlyTek(AbsTaskClassification):
-    metadata = TaskMetadata(
-        name="IFlyTek",
-        description="Long Text classification for the description of Apps",
-        reference="https://www.cluebenchmarks.com/introduce.html",
-        dataset={
-            "path": "C-MTEB/IFlyTek-classification",
-            "revision": "421605374b29664c5fc098418fe20ada9bd55f8a",
-        },
-        type="Classification",
-        category="s2s",
-        modalities=["text"],
-        eval_splits=["validation"],
-        eval_langs=["cmn-Hans"],
-        main_score="accuracy",
-        date=None,
-        domains=None,
-        task_subtypes=None,
-        license=None,
-        annotations_creators=None,
-        dialect=None,
-        sample_creation=None,
-        bibtex_citation="""@inproceedings {xu-etal-2020-clue,
- title = "{CLUE}: A {C}hinese Language Understanding Evaluation Benchmark",
- author = "Xu, Liang  and
-    Hu, Hai and
-    Zhang, Xuanwei and
-    Li, Lu and
-    Cao, Chenjie and
-    Li, Yudong and
-    Xu, Yechen and
-    Sun, Kai and
-    Yu, Dian and
-    Yu, Cong and
-    Tian, Yin and
-    Dong, Qianqian and
-    Liu, Weitang and
-    Shi, Bo and
-    Cui, Yiming and
-    Li, Junyi and
-    Zeng, Jun and
-    Wang, Rongzhao and
-    Xie, Weijian and
-    Li, Yanting and
-    Patterson, Yina and
-    Tian, Zuoyu and
-    Zhang, Yiwen and
-    Zhou, He and
-    Liu, Shaoweihua and
-    Zhao, Zhe and
-    Zhao, Qipeng and
-    Yue, Cong and
-    Zhang, Xinrui and
-    Yang, Zhengliang and
-    Richardson, Kyle and
-    Lan, Zhenzhong ",
- booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
- month = dec,
- year = "2020",
- address = "Barcelona, Spain (Online)",
- publisher = "International Committee on Computational Linguistics",
- url = "https://aclanthology.org/2020.coling-main.419",
- doi = "10.18653/v1/2020.coling-main.419",
- pages = "4762--4772",
- abstract = "The advent of natural language understanding (NLU) benchmarks for English, such as GLUE and SuperGLUE allows new NLU models to be evaluated across a diverse set of tasks. These comprehensive benchmarks have facilitated a broad range of research and applications in natural language processing (NLP). The problem, however, is that most such benchmarks are limited to English, which has made it difficult to replicate many of the successes in English NLU for other languages. To help remedy this issue, we introduce the first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark. CLUE is an open-ended, community-driven project that brings together 9 tasks spanning several well-established single-sentence/sentence-pair classification tasks, as well as machine reading comprehension, all on original Chinese text. To establish results on these tasks, we report scores using an exhaustive set of current state-of-the-art pre-trained Chinese models (9 in total). We also introduce a number of supplementary datasets and additional tools to help facilitate further progress on Chinese NLU. Our benchmark is released at https://www.cluebenchmarks.com",
-}""",
-        descriptive_stats={"n_samples": None, "avg_character_length": None},
-    )
-
-    @property
-    def metadata_dict(self) -> dict[str, str]:
-        metadata_dict = super().metadata_dict
-        metadata_dict["samples_per_label"] = 32
-        metadata_dict["n_experiments"] = 5
-        return metadata_dict
-
-
-class MultilingualSentiment(AbsTaskClassification):
-    metadata = TaskMetadata(
-        name="MultilingualSentiment",
-        description="A collection of multilingual sentiments datasets grouped into 3 classes -- positive, neutral, negative",
-        reference="https://github.com/tyqiangz/multilingual-sentiment-datasets",
-        dataset={
-            "path": "C-MTEB/MultilingualSentiment-classification",
-            "revision": "46958b007a63fdbf239b7672c25d0bea67b5ea1a",
-        },
-        type="Classification",
-        category="s2s",
-        modalities=["text"],
-        eval_splits=["validation", "test"],
-        eval_langs=["cmn-Hans"],
-        main_score="accuracy",
-        date=None,
-        domains=None,
-        task_subtypes=None,
-        license=None,
-        annotations_creators=None,
-        dialect=None,
-        sample_creation=None,
-        bibtex_citation=None,
-        descriptive_stats={"n_samples": None, "avg_character_length": None},
-    )
-
-    @property
-    def metadata_dict(self) -> dict[str, str]:
-        metadata_dict = super().metadata_dict
-        metadata_dict["samples_per_label"] = 32
-        return metadata_dict
-
-
-class JDReview(AbsTaskClassification):
-    metadata = TaskMetadata(
-        name="JDReview",
-        description="review for iphone",
-        reference="https://aclanthology.org/2023.nodalida-1.20/",
-        dataset={
-            "path": "C-MTEB/JDReview-classification",
-            "revision": "b7c64bd89eb87f8ded463478346f76731f07bf8b",
-        },
-        type="Classification",
-        category="s2s",
-        modalities=["text"],
-        eval_splits=["test"],
-        eval_langs=["cmn-Hans"],
-        main_score="accuracy",
-        date=None,
-        domains=None,
-        task_subtypes=None,
-        license=None,
-        annotations_creators=None,
-        dialect=None,
-        sample_creation=None,
-        bibtex_citation="""@article{xiao2023c,
-  title={C-pack: Packaged resources to advance general chinese embedding},
-  author={Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighof, Niklas},
-  journal={arXiv preprint arXiv:2309.07597},
-  year={2023}
-}""",
-        descriptive_stats={"n_samples": None, "avg_character_length": None},
-    )
-
-    @property
-    def metadata_dict(self) -> dict[str, str]:
-        metadata_dict = super().metadata_dict
-        metadata_dict["samples_per_label"] = 32
-        return metadata_dict
-
-
-class OnlineShopping(AbsTaskClassification):
-    metadata = TaskMetadata(
-        name="OnlineShopping",
-        description="Sentiment Analysis of User Reviews on Online Shopping Websites",
-        reference="https://aclanthology.org/2023.nodalida-1.20/",
-        dataset={
-            "path": "C-MTEB/OnlineShopping-classification",
-            "revision": "e610f2ebd179a8fda30ae534c3878750a96db120",
-        },
-        type="Classification",
-        category="s2s",
-        modalities=["text"],
-        eval_splits=["test"],
-        eval_langs=["cmn-Hans"],
-        main_score="accuracy",
-        date=None,
-        domains=None,
-        task_subtypes=None,
-        license=None,
-        annotations_creators=None,
-        dialect=None,
-        sample_creation=None,
-        bibtex_citation="""@article{xiao2023c,
-  title={C-pack: Packaged resources to advance general chinese embedding},
-  author={Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighof, Niklas},
-  journal={arXiv preprint arXiv:2309.07597},
-  year={2023}
-}""",
-        descriptive_stats={"n_samples": None, "avg_character_length": None},
-    )
-
-    @property
-    def metadata_dict(self) -> dict[str, str]:
-        metadata_dict = super().metadata_dict
-        metadata_dict["samples_per_label"] = 32
-        return metadata_dict
-
-
-class Waimai(AbsTaskClassification):
-    metadata = TaskMetadata(
-        name="Waimai",
-        description="Sentiment Analysis of user reviews on takeaway platforms",
-        reference="https://aclanthology.org/2023.nodalida-1.20/",
-        dataset={
-            "path": "C-MTEB/waimai-classification",
-            "revision": "339287def212450dcaa9df8c22bf93e9980c7023",
-        },
-        type="Classification",
-        category="s2s",
-        modalities=["text"],
-        eval_splits=["test"],
-        eval_langs=["cmn-Hans"],
-        main_score="accuracy",
-        date=None,
-        domains=None,
-        task_subtypes=None,
-        license=None,
-        annotations_creators=None,
-        dialect=None,
-        sample_creation=None,
-        bibtex_citation="""@article{xiao2023c,
-  title={C-pack: Packaged resources to advance general chinese embedding},
-  author={Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighof, Niklas},
-  journal={arXiv preprint arXiv:2309.07597},
-  year={2023}
-}""",
-        descriptive_stats={"n_samples": None, "avg_character_length": None},
-    )
-
-    @property
-    def metadata_dict(self) -> dict[str, str]:
-        metadata_dict = super().metadata_dict
-        metadata_dict["samples_per_label"] = 32
-
-        return metadata_dict