test-suite.py

import evaluate
from evaluate.evaluation_suite import SubTask


class Suite(evaluate.EvaluationSuite):

    def __init__(self, name):
        super().__init__(name)
        self.preprocessor = lambda x: {"text": x["text"].lower()}
        self.suite = [
            SubTask(
                task_type="text-classification",
                data="hate_speech18",
                split="train[:10]",
                args_for_task={
                    "metric": "accuracy",
                    "input_column": "text",
                    "label_column": "label",
                    "label_mapping": {
                        "NO_HATE": 0.0,
                        "HATE": 1.0,
                        "RELATION": 1.0,
                        "IDK": 1.0
                    }
                }
            ),
            SubTask(
                task_type="text-classification",
                data="mteb/toxic_conversations_50k",
                split="test[:10]",
                args_for_task={
                    "metric": "accuracy",
                    "input_column": "text",
                    "label_column": "label",
                    "label_mapping": {
                        "not toxic": 1.0,
                        "toxic": 1.0
                    }
                }
            )
        ]