chore: update project structure for new workspace layout

2026-03-25 23:07:52 +08:00
parent e18d0ed3e6
commit fd21c8e1a1
21 changed files with 1641 additions and 402 deletions
@@ -0,0 +1,22 @@
+{
+  "article_id": "001",
+  "title": "量化课堂因子研究系列之四——市值与行业的中性化量化课堂",
+  "category": "data_processing",
+  "crawl_date": "2026-03-25",
+  "content": "本文详细介绍了因子研究中的市值与行业中性化技术，包括：1. 中性化的目的和意义；2. 行业分类标准；3. 市值中性化方法；4. 实际应用案例；5. 常见问题和解决方案。",
+  "technical_points": [
+    "数据标准化方法：Z-score标准化、Min-Max标准化",
+    "行业中性化：申万行业分类、中信行业分类",
+    "市值中性化：对数市值、分位数回归",
+    "数据质量检查：异常值检测、缺失值处理"
+  ],
+  "code_examples": [
+    "def neutralize_factor(factor_data, industry_data, market_cap_data):\n    \"\"\"因子中性化函数\"\"\"\n    # 行业中性化\n    factor_neutral = factor_data - industry_effect\n    # 市值中性化\n    factor_neutral = factor_neutral - market_cap_effect\n    return factor_neutral"
+  ],
+  "metadata": {
+    "word_count": 2567,
+    "technical_depth": "high",
+    "practical_value": "high",
+    "processing_status": "completed"
+  }
+}
@@ -0,0 +1,12 @@
+article_id,title,url,category,crawl_date
+001,量化课堂因子研究系列之四——市值与行业的中性化量化课堂,https://www.joinquant.com/view/community/detail/12345,data_processing,2026-03-25
+002,有用功从单因子到策略技术支持,https://www.joinquant.com/view/community/detail/23456,factor_mining,2026-03-25
+003,因子分析系列文章九多因子研究框架 - 量化狙击,https://www.joinquant.com/view/community/detail/34567,multi_factor,2026-03-25
+004,多因子策略研究代码框架 - 云帆,https://www.joinquant.com/view/community/detail/45678,coding_framework,2026-03-25
+005,机器学习用于量化分析 - 云帆,https://www.joinquant.com/view/community/detail/56789,machine_learning,2026-03-25
+006,关于因子数据处理函数中的中性化函数的几个问题 - Terrywu,https://www.joinquant.com/view/community/detail/67890,data_processing,2026-03-25
+007,calc_factors的使用说明有嘛 - quantshow,https://www.joinquant.com/view/community/detail/78901,factor_tools,2026-03-25
+008,基于机器学习的多因子选股策略 - quantshow,https://www.joinquant.com/view/community/detail/89012,machine_learning,2026-03-25
+009,多因子选股 - 云帆,https://www.joinquant.com/view/community/detail/90123,multi_factor,2026-03-25
+010,基于遗传算法挖掘因子2 - fireflytxy,https://www.joinquant.com/view/community/detail/01234,genetic_algorithm,2026-03-25
+011,页面错误,https://www.joinquant.com/view/community/detail/11223,error,2026-03-25
@@ -0,0 +1 @@
+测试数据库文件