stefanocarrera/autophagycode_D_he_train-mercury_Qwen3-4B_strategy_trust_t1.25_g6_run2_metrics
收藏资源简介:
该数据集是一个用于代码评估或编程任务分析的数据集,包含164个示例,每个示例具有多个特征,如任务ID、入口点、可执行性、正确性、测试通过和失败次数、错误类型,以及代码复杂度度量(如Halstead词汇量、长度、体积、难度、努力程度和时间,圈复杂度,可维护性指数),代码统计信息(如代码行数、有效代码行数、注释比例),语言特征(如TTR、香农熵、预测熵),以及函数定义数量等。数据集仅提供训练集分割,用于分析和评估代码质量或任务执行情况。
This dataset is designed for code evaluation or programming task analysis, comprising 164 examples. Each example includes multiple features such as task ID, entry point, executability, correctness, number of tests passed and failed, error type, and code complexity metrics (e.g., Halstead vocabulary, length, volume, difficulty, effort, and time, cyclomatic complexity, maintainability index). It also contains code statistics (e.g., lines of code, source lines of code, comment percentage), linguistic features (e.g., TTR, Shannon entropy, predictive entropy), and the number of defined functions. The dataset only provides a training split and is intended for analyzing and assessing code quality or task performance.




