RollingRank赚钱- Sharp-1.43

main/data/is_st.ipynb

@@ -0,0 +1,190 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "17cc645336d4eb18",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-02-08T16:55:19.819017Z",
+     "start_time": "2025-02-08T16:55:18.958639Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import tushare as ts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "48ae71ed02d61819",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-02-08T16:55:27.578361Z",
+     "start_time": "2025-02-08T16:55:19.882313Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "daily_basic = pd.read_hdf('../../data/daily_basic.h5', key='daily_basic')\n",
+    "name_change_df = pd.read_hdf('../../data/name_change.h5', key='name_change')\n",
+    "name_change_df = name_change_df.drop_duplicates(keep='first')\n",
+    "\n",
+    "# 确保 name_change_df 的日期格式正确\n",
+    "name_change_df['start_date'] = pd.to_datetime(name_change_df['start_date'], format='%Y%m%d')\n",
+    "name_change_df['end_date'] = pd.to_datetime(name_change_df['end_date'], format='%Y%m%d', errors='coerce')\n",
+    "name_change_df = name_change_df[name_change_df.name.str.contains('ST')]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "e6606a96e5728b8",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-02-08T16:55:27.938078Z",
+     "start_time": "2025-02-08T16:55:27.584226Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "name_change_dict = {}\n",
+    "for ts_code, group in name_change_df.groupby('ts_code'):\n",
+    "    # 只保留 'ST' 和 '*ST' 的记录\n",
+    "    st_data = group[(group['change_reason'] == 'ST') | (group['change_reason'] == '*ST')]\n",
+    "    if not st_data.empty:\n",
+    "        name_change_dict[ts_code] = st_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "initial_id",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-02-08T16:59:20.537632Z",
+     "start_time": "2025-02-08T16:55:27.971219Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "is st...\n"
+     ]
+    }
+   ],
+   "source": [
+    "from datetime import datetime\n",
+    "import pandas as pd\n",
+    "\n",
+    "\n",
+    "# 判断股票是否为 ST 的函数\n",
+    "#stock_code = 'xxxxxx.SH'\n",
+    "#target_date = '20200830'\n",
+    "#若为ST，返回True；否则返回False\n",
+    "def is_st(name_change_dict, stock_code, target_date):\n",
+    "    target_date = datetime.strptime(target_date, '%Y%m%d')\n",
+    "    if stock_code not in name_change_dict.keys():\n",
+    "        return False\n",
+    "    df = name_change_dict[stock_code]\n",
+    "    for i in range(len(df)):\n",
+    "        sds = df.iloc[i, 2]\n",
+    "        eds = df.iloc[i, 3]\n",
+    "        if eds is None or eds is pd.NaT:\n",
+    "            eds = datetime.now()\n",
+    "        if (target_date - sds).days >= 0 and (target_date - eds).days <= 0:\n",
+    "            return True\n",
+    "    return False\n",
+    "\n",
+    "\n",
+    "print('is st...')\n",
+    "# 创建一个新的列 is_st，判断每只股票是否是 ST\n",
+    "daily_basic['is_st'] = daily_basic.apply(\n",
+    "    lambda row: is_st(name_change_dict, row['ts_code'], row['trade_date']), axis=1\n",
+    ")\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "c74bc633-fc73-48c2-bb44-0a798d2cf070",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Empty DataFrame\n",
+      "Columns: [ts_code, trade_date, close, turnover_rate, turnover_rate_f, volume_ratio, pe, pe_ttm, pb, ps, ps_ttm, dv_ratio, dv_ttm, total_share, float_share, free_share, total_mv, circ_mv, is_st]\n",
+      "Index: []\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(daily_basic[(daily_basic['is_st'] != True) & (daily_basic['is_st'] != False)])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "0464ce15-320c-40d4-b499-2e18bac5910f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "     ts_code trade_date  is_st\n",
+      "0  002512.SZ   20250211  False\n",
+      "1  600966.SH   20250211  False\n",
+      "2  600358.SH   20250211   True\n",
+      "3  002893.SZ   20250211  False\n",
+      "4  300648.SZ   20250211  False\n"
+     ]
+    }
+   ],
+   "source": [
+    "# 保存结果到新的 HDF5 文件\n",
+    "daily_basic.to_hdf('../../data/daily_basic.h5', key='daily_basic', mode='w', format='table')\n",
+    "\n",
+    "# 输出部分结果\n",
+    "print(daily_basic[['ts_code', 'trade_date', 'is_st']].head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "30c882de-3a89-4056-900d-459a3a012af9",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}