stefanocarrera/autophagycode_D_he_train-mercury_Qwen3-4B_strategy_trust_t1.25_g3_run1_metrics
收藏资源简介:
该数据集包含164个样本,用于代码执行和代码质量分析任务。每个样本包括任务ID(task_id)、入口点(entry_point)、可执行状态(is_executable)、正确性(is_correct)、通过和失败的测试数量(tests_passed, tests_failed)、测试运行时间(test_run_time_ms)、错误类型(error_type),以及多个代码度量指标,如Halstead复杂度(词汇量、长度、体积、难度、努力程度、时间)、圈复杂度(cyclomatic_complexity)、可维护性指数(maintainability_index)、代码行数(loc, sloc)、注释百分比(comment_percentage)、TTR(Type-Token Ratio)、token字典(token_dict)、香农熵(shannon_entropy)、平均和最大预测熵(mean_predictive_entropy, max_predictive_entropy)、定义函数数量(n_func_defined)和入口点重复性(entry_point_repeated)。数据集仅包含训练划分(train),适用于机器学习模型训练,以评估代码性能、错误检测或代码复杂度分析。
This dataset contains 164 samples for code execution and code quality analysis tasks. Each sample includes task ID (task_id), entry point (entry_point), executable status (is_executable), correctness (is_correct), number of tests passed and failed (tests_passed, tests_failed), test run time (test_run_time_ms), error type (error_type), and multiple code metrics such as Halstead complexity (vocabulary, length, volume, difficulty, effort, time), cyclomatic complexity (cyclomatic_complexity), maintainability index (maintainability_index), lines of code (loc, sloc), comment percentage (comment_percentage), TTR (Type-Token Ratio), token dictionary (token_dict), Shannon entropy (shannon_entropy), mean and max predictive entropy (mean_predictive_entropy, max_predictive_entropy), number of functions defined (n_func_defined), and entry point repetition (entry_point_repeated). The dataset only includes a training split (train) and is suitable for machine learning model training to evaluate code performance, error detection, or code complexity analysis.




