增加结构化策略

selector.py

@@ -0,0 +1,15 @@
+import pandas as pd
+
+
+class Selector:
+    def select(self, codes: [str], df: pd.DataFrame) -> [str]:
+        return codes
+
+
+class PeriodSelector(Selector):
+    def __init__(self, period: int = 5):
+        self.__period = period
+
+    def select(self, codes: [str], df: pd.DataFrame) -> [str]:
+        size_df = df.groupby("code").size()
+        return list(filter(lambda code: size_df[code] > self.__period, codes))

财报筛选/loader.py

@@ -1,18 +1,20 @@
+import os.path
+
 import pandas as pd
 
-finance_root = "C:\\Users\\lanyuanxiaoyao\\Documents\\Tushare"
+finance_root = "/Users/lanyuanxiaoyao/SynologyDrive/data/Tushare"
 
 
 def load_balance_sheet():
-    return pd.read_csv(f"{finance_root}\\财务报表\\资产负债表1990-2024.csv")
+    return pd.read_csv(os.path.join(finance_root, "财务报表", "资产负债表1990-2024.csv"))
 
 
 def load_income():
-    return pd.read_csv(f"{finance_root}\\财务报表\\利润表1990-2024.csv")
+    return pd.read_csv(os.path.join(finance_root, "财务报表", "利润表1990-2024.csv"))
 
 
 def load_cashflow():
-    return pd.read_csv(f"{finance_root}\\财务报表\\现金流量表1990-2024.csv")
+    return pd.read_csv(os.path.join(finance_root, "财务报表", "现金流量表1990-2024.csv"))
 
 
 def load_finance():

财报筛选/选股回测.ipynb

@@ -102,12 +102,12 @@
     "    daily_df[\"trade_date\"] = pd.to_datetime(daily_df[\"trade_date\"], format=\"%Y%m%d\")\n",
     "    daily_df[\"trade_date_timestamp\"] = daily_df[\"trade_date\"].astype(np.int64)\n",
     "    daily_df.sort_values(by=\"trade_date\", ascending=True, inplace=True)\n",
-    "    \n",
+    "\n",
-    "    first =  daily_df[daily_df[\"trade_date_timestamp\"] == daily_df[\"trade_date_timestamp\"].min()][\"close_qfq\"].values[0]\n",
+    "    first = daily_df[daily_df[\"trade_date_timestamp\"] == daily_df[\"trade_date_timestamp\"].min()][\"close_qfq\"].values[0]\n",
-    "    last =  daily_df[daily_df[\"trade_date_timestamp\"] == daily_df[\"trade_date_timestamp\"].max()][\"close_qfq\"].values[0]\n",
+    "    last = daily_df[daily_df[\"trade_date_timestamp\"] == daily_df[\"trade_date_timestamp\"].max()][\"close_qfq\"].values[0]\n",
-    "    \n",
+    "\n",
     "    print(first, last)\n",
-    "    \n",
+    "\n",
     "    coefficients = np.polyfit(daily_df[\"trade_date_timestamp\"], daily_df[\"close_qfq\"], 1)\n",
     "\n",
     "    print(coefficients)\n",

财报筛选/选股测试.ipynb

@@ -0,0 +1,113 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true,
+    "ExecuteTime": {
+     "end_time": "2025-01-15T09:42:10.585456Z",
+     "start_time": "2025-01-15T09:42:06.693869Z"
+    }
+   },
+   "source": [
+    "import pandas as pd\n",
+    "import loader as ld\n",
+    "\n",
+    "source_finance_df = ld.load_finance()\n",
+    "finance_df = pd.DataFrame()\n",
+    "finance_df[[\n",
+    "    \"code\",\n",
+    "    # 年份\n",
+    "    \"year\",\n",
+    "    # 股东权益合计（含少数股东权益）\n",
+    "    \"total_stockholder_interest\",\n",
+    "    # 净利润\n",
+    "    \"net_income\",\n",
+    "    # 总资产\n",
+    "    \"total_assets\",\n",
+    "    # 营业总收入\n",
+    "    \"total_revenue\",\n",
+    "    # 存货\n",
+    "    \"inventories\",\n",
+    "    # 应收账款\n",
+    "    \"accounts_receivable\",\n",
+    "    # 营业成本\n",
+    "    \"operating_costs\",\n",
+    "    # 营业利润\n",
+    "    \"operating_profit\",\n",
+    "    # 现金与现金等价物\n",
+    "    \"cash\",\n",
+    "    # 营业活动现金流量净值\n",
+    "    \"operating_net_cash_flow\",\n",
+    "]] = source_finance_df[[\n",
+    "    \"ts_code\",\n",
+    "    \"end_date\",\n",
+    "    \"total_hldr_eqy_inc_min_int\",\n",
+    "    \"n_income\",\n",
+    "    \"total_assets\",\n",
+    "    \"total_revenue\",\n",
+    "    \"inventories\",\n",
+    "    \"accounts_receiv\",\n",
+    "    \"oper_cost\",\n",
+    "    \"operate_profit\",\n",
+    "    \"money_cap\",\n",
+    "    \"n_cashflow_act\",\n",
+    "]]"
+   ],
+   "outputs": [],
+   "execution_count": 17
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-01-15T09:45:06.335656Z",
+     "start_time": "2025-01-15T09:45:06.291888Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "from selector import PeriodSelector\n",
+    "\n",
+    "filter_df = finance_df[(2010 < finance_df[\"year\"]) & (finance_df[\"year\"] < 2025)]\n",
+    "codes = filter_df[\"code\"].unique().tolist()\n",
+    "print(len(codes))\n",
+    "codes = PeriodSelector().select(codes, filter_df)\n",
+    "print(len(codes))"
+   ],
+   "id": "26539ccd8ce0fb9e",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "5715\n",
+      "4892\n"
+     ]
+    }
+   ],
+   "execution_count": 24
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}