添加多个类别关键词,优化数据处理逻辑,支持从arXiv提取和筛选论文数据

This commit is contained in:
2025-07-30 23:05:31 +08:00
parent 7d15721f61
commit 40262648c4
6 changed files with 298 additions and 81 deletions

View File

@@ -11,7 +11,7 @@ from sklearn.metrics import (
)
# 配置参数
RESULT_FILE = "G:\\11\\data-prepare\\20250720-195839.jsonl" # 替换为你的结果文件路径
RESULT_FILE = "G:\\11\\data-prepare\\20250727-084808.jsonl" # 替换为你的结果文件路径
OUTPUT_DIR = "G:\\11\\data-prepare\\analysis_results" # 分析结果输出目录
EXPORT_CSV = True # 是否导出CSV格式的详细结果
PLOT_CONFUSION_MATRIX = True # 是否绘制混淆矩阵