init: KG_ICH 项目初始化

- data/: 非遗地理编码数据（GIS shapefile + CSV） - dofile/kg_project/: 知识图谱构建代码（纳入主仓库） - dofile/visulization/: 可视化数据与路线图 - officefile/: 文献、草稿、bib 文档 - officefile/latex/: Overleaf 同步目录（独立管理，不纳入） - output/: 输出目录 - logs/: 日志目录
2026-05-30 00:52:36 +08:00
commit 834cad729f
44 changed files with 8586 additions and 0 deletions
@@ -0,0 +1,92 @@
+# -*- coding: utf-8 -*-
+"""
+重新抽取失败项目的脚本
+"""
+
+import asyncio
+import pandas as pd
+import yaml
+import json
+from pathlib import Path
+from datetime import datetime
+import sys
+
+# 添加模块路径
+sys.path.append(str(Path(__file__).parent / 'src'))
+
+from knowledge_extraction.deep_entity_extractor import DeepEntityExtractor
+
+async def retry_failed_projects():
+    """重新抽取失败的项目"""
+
+    # 加载配置
+    config_file = Path(__file__).parent / 'config' / 'deep_extraction_config.yaml'
+    with open(config_file, 'r', encoding='utf-8') as f:
+        config = yaml.safe_load(f)
+
+    # 读取原始数据
+    data_file = Path(__file__).parent.parent.parent / 'data' / '黑龙江国家级和省级非遗名单.xlsx'
+    df = pd.read_excel(data_file, engine='openpyxl')
+
+    # 找到失败的项目
+    # 第0列是序号，需要拼接成ICH-xxx格式
+    failed_data = df[df.iloc[:, 0].isin([118, 229])]
+
+    print(f"找到 {len(failed_data)} 个失败项目")
+    print("=" * 60)
+
+    # 初始化抽取器
+    extractor = DeepEntityExtractor(str(config_file))
+
+    results = []
+
+    for idx, row in failed_data.iterrows():
+        project_num = int(row.iloc[0])  # 序号（118, 229）
+        project_id = f'ICH-{project_num}'  # 拼接成ICH-xxx格式
+        project_name = row.iloc[3]  # 项目名称（第4列）
+        description = row.iloc[7] if len(row) > 7 else ""  # 完整描述（第8列备注）
+
+        print(f"\n正在抽取: {project_id} - {project_name}")
+        print(f"描述长度: {len(description)} 字符")
+
+        # 准备输入数据
+        input_data = {
+            'project_id': project_id,
+            'project_name': project_name,
+            'description': description
+        }
+
+        # 抽取实体和关系
+        try:
+            result = await extractor.extract_from_remark(
+                project_id=project_id,
+                project_name=project_name,
+                remark_text=description
+            )
+
+            if result:
+                results.append({
+                    'project_id': project_id,
+                    'project_name': project_name,
+                    'extraction_result': result
+                })
+                print(f"[OK] 抽取成功: {len(result.get('entities', []))} 个实体, {len(result.get('relationships', []))} 条关系")
+            else:
+                print(f"[FAIL] 抽取失败")
+
+        except Exception as e:
+            print(f"[ERROR] 抽取异常: {str(e)}")
+
+    # 保存结果
+    output_file = Path(__file__).parent / 'output' / 'retry_projects.json'
+    with open(output_file, 'w', encoding='utf-8') as f:
+        json.dump(results, f, ensure_ascii=False, indent=2)
+
+    print(f"\n结果已保存到: {output_file}")
+    print(f"成功: {len(results)}/{len(failed_data)}")
+
+    return results
+
+
+if __name__ == '__main__':
+    asyncio.run(retry_failed_projects())