增加数据采集

.gitignore

@@ -116,4 +116,5 @@ cython_debug/
 
 # Custom
 temp/
-temp/**/*
+temp/**/*
+.idea/**/csv-editor.xml

.idea/codeStyles/codeStyleConfig.xml

@@ -0,0 +1,5 @@
+<component name="ProjectCodeStyleConfiguration">
+  <state>
+    <option name="PREFERRED_PROJECT_CODE_STYLE" value="Default" />
+  </state>
+</component>

.idea/vcs.xml

@@ -1,5 +1,11 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
+  <component name="CommitMessageInspectionProfile">
+    <profile version="1.0">
+      <inspection_tool class="CommitFormat" enabled="true" level="WARNING" enabled_by_default="true" />
+      <inspection_tool class="CommitNamingConvention" enabled="true" level="WARNING" enabled_by_default="true" />
+    </profile>
+  </component>
   <component name="VcsDirectoryMappings">
     <mapping directory="$PROJECT_DIR$" vcs="Git" />
   </component>

note.md

@@ -0,0 +1,10 @@
+talib安装
+macOS
+```
+poetry run pip install TA-Lib
+```
+Windows
+> https://github.com/cgohlke/talib-build
+```
+poetry run pip install ta_lib-0.6.3-cp312-cp312-win_amd64.whl
+```

pyproject.toml

@@ -14,6 +14,9 @@ jupyter = "^1.1.1"
 matplotlib = "^3.10.0"
 prophet = "^1.1.6"
 mplfinance = "^0.12.10b0"
+scipy = "^1.15.1"
+backtrader = "^1.9.78.123"
+backtesting = "^0.6.1"
 
 
 [build-system]

strategy.py

@@ -0,0 +1,44 @@
+import pandas as pd
+
+
+class Selector:
+    def select(self, codes: [str], df: pd.DataFrame) -> [str]:
+        return codes
+
+
+class Strategy:
+    def __init__(self, selectors: [Selector]):
+        self.selectors = selectors
+
+    def select(self, codes: [str], df: pd.DataFrame) -> [str]:
+        return list(map(lambda code: self.selectors.select(code, df), 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))
+
+
+class PyramidSelector(Selector):
+    def select(self, codes: [str], df: pd.DataFrame) -> [str]:
+        target_df = df[df["code"].isin(codes)]
+        target_df["score"] = 0
+        group_df = target_df.groupby("code")
+
+        target_df["prev_total_stockholder_interest"] = group_df["total_stockholder_interest"].shift(1)
+        target_df["roe"] = target_df["net_income"] / ((target_df["prev_total_stockholder_interest"] + target_df["total_stockholder_interest"]) / 2)
+        target_df["average_roe"] = target_df["roe"].mean()
+        target_df[target_df["average_roe"] >= 35] = target_df["score"] + 550
+        target_df[(target_df["average_roe"] < 35) & (target_df["average_roe"] >= 30)] = target_df["score"] + 500
+        target_df[(target_df["average_roe"] < 30) & (target_df["average_roe"] >= 25)] = target_df["score"] + 450
+        target_df[(target_df["average_roe"] < 25) & (target_df["average_roe"] >= 15)] = target_df["score"] + 300
+        target_df[(target_df["average_roe"] < 15) & (target_df["average_roe"] >= 10)] = target_df["score"] + 250
+
+        target_df["prev_total_assets"] = group_df["total_assets"].shift(1)
+        target_df["roa"] = target_df["net_income"] / ((target_df["prev_total_assets"] + target_df["total_assets"]) / 2)
+
+        return super().select(codes, df)

材料准备/ta-lib.ipynb

@@ -0,0 +1,587 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true,
+    "ExecuteTime": {
+     "end_time": "2025-02-11T06:31:19.433336Z",
+     "start_time": "2025-02-11T06:31:18.884130Z"
+    }
+   },
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "# source_df = \\\n",
+    "#     pd.read_csv(\"C:\\\\Users\\\\lanyuanxiaoyao\\\\SynologyDrive\\\\data\\\\Tushare\\\\日线行情 1990-2024\\\\分组行情\\\\000001.SZ.csv\") \\\n",
+    "source_df = pd.read_csv(\"/Users/lanyuanxiaoyao/SynologyDrive/data/Tushare/日线行情 1990-2024/分组行情/600519.SH.csv\") \\\n",
+    "    [[\"trade_date\", \"vol\", \"open_qfq\", \"close_qfq\", \"high_qfq\", \"low_qfq\", \"macd\", \"macd_dif\", \"macd_dea\"]]\n",
+    "df = pd.DataFrame()\n",
+    "df[[\"date\", \"volume\", \"open\", \"close\", \"high\", \"low\", \"macd\", \"macd_dif\", \"macd_dea\"]] = \\\n",
+    "    source_df[[\"trade_date\", \"vol\", \"open_qfq\", \"close_qfq\", \"high_qfq\", \"low_qfq\", \"macd\", \"macd_dif\", \"macd_dea\"]]\n",
+    "df[\"datetime\"] = pd.to_datetime(df[\"date\"], format=\"%Y%m%d\")\n",
+    "df[\"datetime_text\"] = df[\"datetime\"].apply(lambda x: x.strftime(\"%Y%m%d\"))\n",
+    "df.sort_values(by='datetime', inplace=True)\n",
+    "df"
+   ],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "          date     volume        open       close        high         low  \\\n",
+       "2187  20010827  406318.00     4.23675     4.36443     4.63820     4.03295   \n",
+       "2188  20010828  129647.79     4.29568     4.52525     4.54244     4.24902   \n",
+       "2189  20010829   53252.75     4.53999     4.46632     4.54244     4.43195   \n",
+       "2190  20010830   48013.06     4.45405     4.55472     4.60505     4.41967   \n",
+       "2191  20010831   23231.48     4.56086     4.54367     4.61856     4.51789   \n",
+       "...        ...        ...         ...         ...         ...         ...   \n",
+       "2182  20241225   17123.39  1538.80000  1530.00000  1538.80000  1526.10000   \n",
+       "2183  20241226   18286.51  1534.00000  1527.79000  1538.78000  1523.00000   \n",
+       "2184  20241227   20759.32  1528.90000  1528.97000  1536.00000  1519.50000   \n",
+       "2185  20241230   25129.82  1533.97000  1525.00000  1543.96000  1525.00000   \n",
+       "2186  20241231   39354.45  1525.40000  1524.00000  1545.00000  1522.01000   \n",
+       "\n",
+       "       macd  macd_dif  macd_dea   datetime datetime_text  \n",
+       "2187  0.000     0.000     0.000 2001-08-27      20010827  \n",
+       "2188  0.021     0.013     0.003 2001-08-28      20010828  \n",
+       "2189  0.025     0.018     0.006 2001-08-29      20010829  \n",
+       "2190  0.037     0.029     0.010 2001-08-30      20010830  \n",
+       "2191  0.042     0.036     0.016 2001-08-31      20010831  \n",
+       "...     ...       ...       ...        ...           ...  \n",
+       "2182  5.430     5.063     2.348 2024-12-25      20241225  \n",
+       "2183  4.192     4.968     2.872 2024-12-26      20241226  \n",
+       "2184  3.295     4.931     3.283 2024-12-27      20241227  \n",
+       "2185  1.993     4.529     3.533 2024-12-30      20241230  \n",
+       "2186  0.880     4.083     3.643 2024-12-31      20241231  \n",
+       "\n",
+       "[5591 rows x 11 columns]"
+      ],
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>date</th>\n",
+       "      <th>volume</th>\n",
+       "      <th>open</th>\n",
+       "      <th>close</th>\n",
+       "      <th>high</th>\n",
+       "      <th>low</th>\n",
+       "      <th>macd</th>\n",
+       "      <th>macd_dif</th>\n",
+       "      <th>macd_dea</th>\n",
+       "      <th>datetime</th>\n",
+       "      <th>datetime_text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2187</th>\n",
+       "      <td>20010827</td>\n",
+       "      <td>406318.00</td>\n",
+       "      <td>4.23675</td>\n",
+       "      <td>4.36443</td>\n",
+       "      <td>4.63820</td>\n",
+       "      <td>4.03295</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>2001-08-27</td>\n",
+       "      <td>20010827</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2188</th>\n",
+       "      <td>20010828</td>\n",
+       "      <td>129647.79</td>\n",
+       "      <td>4.29568</td>\n",
+       "      <td>4.52525</td>\n",
+       "      <td>4.54244</td>\n",
+       "      <td>4.24902</td>\n",
+       "      <td>0.021</td>\n",
+       "      <td>0.013</td>\n",
+       "      <td>0.003</td>\n",
+       "      <td>2001-08-28</td>\n",
+       "      <td>20010828</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2189</th>\n",
+       "      <td>20010829</td>\n",
+       "      <td>53252.75</td>\n",
+       "      <td>4.53999</td>\n",
+       "      <td>4.46632</td>\n",
+       "      <td>4.54244</td>\n",
+       "      <td>4.43195</td>\n",
+       "      <td>0.025</td>\n",
+       "      <td>0.018</td>\n",
+       "      <td>0.006</td>\n",
+       "      <td>2001-08-29</td>\n",
+       "      <td>20010829</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2190</th>\n",
+       "      <td>20010830</td>\n",
+       "      <td>48013.06</td>\n",
+       "      <td>4.45405</td>\n",
+       "      <td>4.55472</td>\n",
+       "      <td>4.60505</td>\n",
+       "      <td>4.41967</td>\n",
+       "      <td>0.037</td>\n",
+       "      <td>0.029</td>\n",
+       "      <td>0.010</td>\n",
+       "      <td>2001-08-30</td>\n",
+       "      <td>20010830</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2191</th>\n",
+       "      <td>20010831</td>\n",
+       "      <td>23231.48</td>\n",
+       "      <td>4.56086</td>\n",
+       "      <td>4.54367</td>\n",
+       "      <td>4.61856</td>\n",
+       "      <td>4.51789</td>\n",
+       "      <td>0.042</td>\n",
+       "      <td>0.036</td>\n",
+       "      <td>0.016</td>\n",
+       "      <td>2001-08-31</td>\n",
+       "      <td>20010831</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2182</th>\n",
+       "      <td>20241225</td>\n",
+       "      <td>17123.39</td>\n",
+       "      <td>1538.80000</td>\n",
+       "      <td>1530.00000</td>\n",
+       "      <td>1538.80000</td>\n",
+       "      <td>1526.10000</td>\n",
+       "      <td>5.430</td>\n",
+       "      <td>5.063</td>\n",
+       "      <td>2.348</td>\n",
+       "      <td>2024-12-25</td>\n",
+       "      <td>20241225</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2183</th>\n",
+       "      <td>20241226</td>\n",
+       "      <td>18286.51</td>\n",
+       "      <td>1534.00000</td>\n",
+       "      <td>1527.79000</td>\n",
+       "      <td>1538.78000</td>\n",
+       "      <td>1523.00000</td>\n",
+       "      <td>4.192</td>\n",
+       "      <td>4.968</td>\n",
+       "      <td>2.872</td>\n",
+       "      <td>2024-12-26</td>\n",
+       "      <td>20241226</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2184</th>\n",
+       "      <td>20241227</td>\n",
+       "      <td>20759.32</td>\n",
+       "      <td>1528.90000</td>\n",
+       "      <td>1528.97000</td>\n",
+       "      <td>1536.00000</td>\n",
+       "      <td>1519.50000</td>\n",
+       "      <td>3.295</td>\n",
+       "      <td>4.931</td>\n",
+       "      <td>3.283</td>\n",
+       "      <td>2024-12-27</td>\n",
+       "      <td>20241227</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2185</th>\n",
+       "      <td>20241230</td>\n",
+       "      <td>25129.82</td>\n",
+       "      <td>1533.97000</td>\n",
+       "      <td>1525.00000</td>\n",
+       "      <td>1543.96000</td>\n",
+       "      <td>1525.00000</td>\n",
+       "      <td>1.993</td>\n",
+       "      <td>4.529</td>\n",
+       "      <td>3.533</td>\n",
+       "      <td>2024-12-30</td>\n",
+       "      <td>20241230</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2186</th>\n",
+       "      <td>20241231</td>\n",
+       "      <td>39354.45</td>\n",
+       "      <td>1525.40000</td>\n",
+       "      <td>1524.00000</td>\n",
+       "      <td>1545.00000</td>\n",
+       "      <td>1522.01000</td>\n",
+       "      <td>0.880</td>\n",
+       "      <td>4.083</td>\n",
+       "      <td>3.643</td>\n",
+       "      <td>2024-12-31</td>\n",
+       "      <td>20241231</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5591 rows × 11 columns</p>\n",
+       "</div>"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 2
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-02-11T06:33:12.365001Z",
+     "start_time": "2025-02-11T06:33:12.329227Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "import talib\n",
+    "\n",
+    "dif, dea, hist = talib.MACD(df[\"close\"], fastperiod=12, slowperiod=26, signalperiod=9)\n",
+    "\n",
+    "# 将结果添加到数据框\n",
+    "df['DIF'] = dif\n",
+    "df['DEA'] = dea\n",
+    "df['MACD'] = hist\n",
+    "\n",
+    "#根据close列计算macd值\n",
+    "talib.SMA(df[\"close\"], timeperiod=26, step=10)\n",
+    "\n",
+    "df"
+   ],
+   "id": "72b1c0c3f57e8b8e",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "          date     volume        open       close        high         low  \\\n",
+       "2187  20010827  406318.00     4.23675     4.36443     4.63820     4.03295   \n",
+       "2188  20010828  129647.79     4.29568     4.52525     4.54244     4.24902   \n",
+       "2189  20010829   53252.75     4.53999     4.46632     4.54244     4.43195   \n",
+       "2190  20010830   48013.06     4.45405     4.55472     4.60505     4.41967   \n",
+       "2191  20010831   23231.48     4.56086     4.54367     4.61856     4.51789   \n",
+       "...        ...        ...         ...         ...         ...         ...   \n",
+       "2182  20241225   17123.39  1538.80000  1530.00000  1538.80000  1526.10000   \n",
+       "2183  20241226   18286.51  1534.00000  1527.79000  1538.78000  1523.00000   \n",
+       "2184  20241227   20759.32  1528.90000  1528.97000  1536.00000  1519.50000   \n",
+       "2185  20241230   25129.82  1533.97000  1525.00000  1543.96000  1525.00000   \n",
+       "2186  20241231   39354.45  1525.40000  1524.00000  1545.00000  1522.01000   \n",
+       "\n",
+       "       macd  macd_dif  macd_dea   datetime datetime_text       DIF       DEA  \\\n",
+       "2187  0.000     0.000     0.000 2001-08-27      20010827       NaN       NaN   \n",
+       "2188  0.021     0.013     0.003 2001-08-28      20010828       NaN       NaN   \n",
+       "2189  0.025     0.018     0.006 2001-08-29      20010829       NaN       NaN   \n",
+       "2190  0.037     0.029     0.010 2001-08-30      20010830       NaN       NaN   \n",
+       "2191  0.042     0.036     0.016 2001-08-31      20010831       NaN       NaN   \n",
+       "...     ...       ...       ...        ...           ...       ...       ...   \n",
+       "2182  5.430     5.063     2.348 2024-12-25      20241225  5.062711  2.347629   \n",
+       "2183  4.192     4.968     2.872 2024-12-26      20241226  4.967756  2.871654   \n",
+       "2184  3.295     4.931     3.283 2024-12-27      20241227  4.930880  3.283499   \n",
+       "2185  1.993     4.529     3.533 2024-12-30      20241230  4.529101  3.532620   \n",
+       "2186  0.880     4.083     3.643 2024-12-31      20241231  4.082931  3.642682   \n",
+       "\n",
+       "          MACD  \n",
+       "2187       NaN  \n",
+       "2188       NaN  \n",
+       "2189       NaN  \n",
+       "2190       NaN  \n",
+       "2191       NaN  \n",
+       "...        ...  \n",
+       "2182  2.715082  \n",
+       "2183  2.096102  \n",
+       "2184  1.647381  \n",
+       "2185  0.996481  \n",
+       "2186  0.440249  \n",
+       "\n",
+       "[5591 rows x 14 columns]"
+      ],
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>date</th>\n",
+       "      <th>volume</th>\n",
+       "      <th>open</th>\n",
+       "      <th>close</th>\n",
+       "      <th>high</th>\n",
+       "      <th>low</th>\n",
+       "      <th>macd</th>\n",
+       "      <th>macd_dif</th>\n",
+       "      <th>macd_dea</th>\n",
+       "      <th>datetime</th>\n",
+       "      <th>datetime_text</th>\n",
+       "      <th>DIF</th>\n",
+       "      <th>DEA</th>\n",
+       "      <th>MACD</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2187</th>\n",
+       "      <td>20010827</td>\n",
+       "      <td>406318.00</td>\n",
+       "      <td>4.23675</td>\n",
+       "      <td>4.36443</td>\n",
+       "      <td>4.63820</td>\n",
+       "      <td>4.03295</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>2001-08-27</td>\n",
+       "      <td>20010827</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2188</th>\n",
+       "      <td>20010828</td>\n",
+       "      <td>129647.79</td>\n",
+       "      <td>4.29568</td>\n",
+       "      <td>4.52525</td>\n",
+       "      <td>4.54244</td>\n",
+       "      <td>4.24902</td>\n",
+       "      <td>0.021</td>\n",
+       "      <td>0.013</td>\n",
+       "      <td>0.003</td>\n",
+       "      <td>2001-08-28</td>\n",
+       "      <td>20010828</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2189</th>\n",
+       "      <td>20010829</td>\n",
+       "      <td>53252.75</td>\n",
+       "      <td>4.53999</td>\n",
+       "      <td>4.46632</td>\n",
+       "      <td>4.54244</td>\n",
+       "      <td>4.43195</td>\n",
+       "      <td>0.025</td>\n",
+       "      <td>0.018</td>\n",
+       "      <td>0.006</td>\n",
+       "      <td>2001-08-29</td>\n",
+       "      <td>20010829</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2190</th>\n",
+       "      <td>20010830</td>\n",
+       "      <td>48013.06</td>\n",
+       "      <td>4.45405</td>\n",
+       "      <td>4.55472</td>\n",
+       "      <td>4.60505</td>\n",
+       "      <td>4.41967</td>\n",
+       "      <td>0.037</td>\n",
+       "      <td>0.029</td>\n",
+       "      <td>0.010</td>\n",
+       "      <td>2001-08-30</td>\n",
+       "      <td>20010830</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2191</th>\n",
+       "      <td>20010831</td>\n",
+       "      <td>23231.48</td>\n",
+       "      <td>4.56086</td>\n",
+       "      <td>4.54367</td>\n",
+       "      <td>4.61856</td>\n",
+       "      <td>4.51789</td>\n",
+       "      <td>0.042</td>\n",
+       "      <td>0.036</td>\n",
+       "      <td>0.016</td>\n",
+       "      <td>2001-08-31</td>\n",
+       "      <td>20010831</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2182</th>\n",
+       "      <td>20241225</td>\n",
+       "      <td>17123.39</td>\n",
+       "      <td>1538.80000</td>\n",
+       "      <td>1530.00000</td>\n",
+       "      <td>1538.80000</td>\n",
+       "      <td>1526.10000</td>\n",
+       "      <td>5.430</td>\n",
+       "      <td>5.063</td>\n",
+       "      <td>2.348</td>\n",
+       "      <td>2024-12-25</td>\n",
+       "      <td>20241225</td>\n",
+       "      <td>5.062711</td>\n",
+       "      <td>2.347629</td>\n",
+       "      <td>2.715082</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2183</th>\n",
+       "      <td>20241226</td>\n",
+       "      <td>18286.51</td>\n",
+       "      <td>1534.00000</td>\n",
+       "      <td>1527.79000</td>\n",
+       "      <td>1538.78000</td>\n",
+       "      <td>1523.00000</td>\n",
+       "      <td>4.192</td>\n",
+       "      <td>4.968</td>\n",
+       "      <td>2.872</td>\n",
+       "      <td>2024-12-26</td>\n",
+       "      <td>20241226</td>\n",
+       "      <td>4.967756</td>\n",
+       "      <td>2.871654</td>\n",
+       "      <td>2.096102</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2184</th>\n",
+       "      <td>20241227</td>\n",
+       "      <td>20759.32</td>\n",
+       "      <td>1528.90000</td>\n",
+       "      <td>1528.97000</td>\n",
+       "      <td>1536.00000</td>\n",
+       "      <td>1519.50000</td>\n",
+       "      <td>3.295</td>\n",
+       "      <td>4.931</td>\n",
+       "      <td>3.283</td>\n",
+       "      <td>2024-12-27</td>\n",
+       "      <td>20241227</td>\n",
+       "      <td>4.930880</td>\n",
+       "      <td>3.283499</td>\n",
+       "      <td>1.647381</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2185</th>\n",
+       "      <td>20241230</td>\n",
+       "      <td>25129.82</td>\n",
+       "      <td>1533.97000</td>\n",
+       "      <td>1525.00000</td>\n",
+       "      <td>1543.96000</td>\n",
+       "      <td>1525.00000</td>\n",
+       "      <td>1.993</td>\n",
+       "      <td>4.529</td>\n",
+       "      <td>3.533</td>\n",
+       "      <td>2024-12-30</td>\n",
+       "      <td>20241230</td>\n",
+       "      <td>4.529101</td>\n",
+       "      <td>3.532620</td>\n",
+       "      <td>0.996481</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2186</th>\n",
+       "      <td>20241231</td>\n",
+       "      <td>39354.45</td>\n",
+       "      <td>1525.40000</td>\n",
+       "      <td>1524.00000</td>\n",
+       "      <td>1545.00000</td>\n",
+       "      <td>1522.01000</td>\n",
+       "      <td>0.880</td>\n",
+       "      <td>4.083</td>\n",
+       "      <td>3.643</td>\n",
+       "      <td>2024-12-31</td>\n",
+       "      <td>20241231</td>\n",
+       "      <td>4.082931</td>\n",
+       "      <td>3.642682</td>\n",
+       "      <td>0.440249</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5591 rows × 14 columns</p>\n",
+       "</div>"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 3
+  }
+ ],
+ "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
+}

材料准备/财报信息.ipynb

@@ -4,7 +4,11 @@
    "cell_type": "code",
    "id": "initial_id",
    "metadata": {
-    "collapsed": true
+    "collapsed": true,
+    "ExecuteTime": {
+     "end_time": "2025-01-13T01:30:08.643756Z",
+     "start_time": "2025-01-13T01:30:06.177472Z"
+    }
    },
    "source": [
     "import pandas as pd\n",
@@ -13,10 +17,15 @@
     "ts_pro = ts.pro_api(token=\"64ebff4fa679167600b905ee45dd88e76f3963c0ff39157f3f085f0e\")"
    ],
    "outputs": [],
-   "execution_count": null
+   "execution_count": 1
   },
   {
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-01-13T01:30:08.652416Z",
+     "start_time": "2025-01-13T01:30:08.646084Z"
+    }
+   },
    "cell_type": "code",
    "source": [
     "def get_balance_sheet_df(start_year, end_year):\n",
@@ -59,55 +68,272 @@
    ],
    "id": "14a28ff4952f0df8",
    "outputs": [],
-   "execution_count": null
+   "execution_count": 2
   },
   {
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-01-13T09:08:04.607819Z",
+     "start_time": "2025-01-13T09:08:04.602640Z"
+    }
+   },
    "cell_type": "code",
    "source": [
-    "start_year = 2014\n",
+    "start_year = 1990\n",
     "end_year = 2024"
    ],
    "id": "dc68cde196159626",
    "outputs": [],
-   "execution_count": null
+   "execution_count": 11
   },
   {
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-01-13T09:09:36.004427Z",
+     "start_time": "2025-01-13T09:08:33.797018Z"
+    }
+   },
    "cell_type": "code",
    "source": [
     "# 财务负债表\n",
     "balance_sheet_df = clean_df(get_balance_sheet_df(start_year, end_year))\n",
-    "balance_sheet_df.to_csv(\"../temp/balance_sheet.csv\", index=False)"
+    "balance_sheet_df.to_csv(f\"/Users/lanyuanxiaoyao/SynologyDrive/data/Tushare/财务报表/资产负债表{start_year}-{end_year}.csv\", index=False)"
    ],
    "id": "33cd797a12ad567e",
-   "outputs": [],
-   "execution_count": null
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Pull balance sheet: 1990\n",
+      "Pull balance sheet: 1991\n",
+      "Pull balance sheet: 1992\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/7h/w0cmp4zj6mn9br_6nyj310m40000gn/T/ipykernel_50121/709533518.py:8: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
+      "  result = pd.concat([result, temp], ignore_index=True)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Pull balance sheet: 1993\n",
+      "Pull balance sheet: 1994\n",
+      "Pull balance sheet: 1995\n",
+      "Pull balance sheet: 1996\n",
+      "Pull balance sheet: 1997\n",
+      "Pull balance sheet: 1998\n",
+      "Pull balance sheet: 1999\n",
+      "Pull balance sheet: 2000\n",
+      "Pull balance sheet: 2001\n",
+      "Pull balance sheet: 2002\n",
+      "Pull balance sheet: 2003\n",
+      "Pull balance sheet: 2004\n",
+      "Pull balance sheet: 2005\n",
+      "Pull balance sheet: 2006\n",
+      "Pull balance sheet: 2007\n",
+      "Pull balance sheet: 2008\n",
+      "Pull balance sheet: 2009\n",
+      "Pull balance sheet: 2010\n",
+      "Pull balance sheet: 2011\n",
+      "Pull balance sheet: 2012\n",
+      "Pull balance sheet: 2013\n",
+      "Pull balance sheet: 2014\n",
+      "Pull balance sheet: 2015\n",
+      "Pull balance sheet: 2016\n",
+      "Pull balance sheet: 2017\n",
+      "Pull balance sheet: 2018\n",
+      "Pull balance sheet: 2019\n",
+      "Pull balance sheet: 2020\n",
+      "Pull balance sheet: 2021\n",
+      "Pull balance sheet: 2022\n",
+      "Pull balance sheet: 2023\n",
+      "Pull balance sheet: 2024\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/7h/w0cmp4zj6mn9br_6nyj310m40000gn/T/ipykernel_50121/709533518.py:8: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
+      "  result = pd.concat([result, temp], ignore_index=True)\n"
+     ]
+    }
+   ],
+   "execution_count": 12
   },
   {
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-01-13T09:11:33.507055Z",
+     "start_time": "2025-01-13T09:10:33.447304Z"
+    }
+   },
    "cell_type": "code",
    "source": [
     "income_df = clean_df(get_income_df(start_year, end_year))\n",
-    "income_df.to_csv(\"../temp/income.csv\", index=False)"
+    "income_df.to_csv(f\"/Users/lanyuanxiaoyao/SynologyDrive/data/Tushare/财务报表/利润表{start_year}-{end_year}.csv\", index=False)"
    ],
    "id": "17306c1524f5e173",
-   "outputs": [],
-   "execution_count": null
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Pull income: 1990\n",
+      "Pull income: 1991\n",
+      "Pull income: 1992\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/7h/w0cmp4zj6mn9br_6nyj310m40000gn/T/ipykernel_50121/709533518.py:19: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
+      "  result = pd.concat([result, temp], ignore_index=True)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Pull income: 1993\n",
+      "Pull income: 1994\n",
+      "Pull income: 1995\n",
+      "Pull income: 1996\n",
+      "Pull income: 1997\n",
+      "Pull income: 1998\n",
+      "Pull income: 1999\n",
+      "Pull income: 2000\n",
+      "Pull income: 2001\n",
+      "Pull income: 2002\n",
+      "Pull income: 2003\n",
+      "Pull income: 2004\n",
+      "Pull income: 2005\n",
+      "Pull income: 2006\n",
+      "Pull income: 2007\n",
+      "Pull income: 2008\n",
+      "Pull income: 2009\n",
+      "Pull income: 2010\n",
+      "Pull income: 2011\n",
+      "Pull income: 2012\n",
+      "Pull income: 2013\n",
+      "Pull income: 2014\n",
+      "Pull income: 2015\n",
+      "Pull income: 2016\n",
+      "Pull income: 2017\n",
+      "Pull income: 2018\n",
+      "Pull income: 2019\n",
+      "Pull income: 2020\n",
+      "Pull income: 2021\n",
+      "Pull income: 2022\n",
+      "Pull income: 2023\n",
+      "Pull income: 2024\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/7h/w0cmp4zj6mn9br_6nyj310m40000gn/T/ipykernel_50121/709533518.py:19: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
+      "  result = pd.concat([result, temp], ignore_index=True)\n"
+     ]
+    }
+   ],
+   "execution_count": 13
   },
   {
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-01-13T09:13:32.890801Z",
+     "start_time": "2025-01-13T09:12:46.032342Z"
+    }
+   },
    "cell_type": "code",
    "source": [
     "cash_flow_df = clean_df(get_cash_flow_df(start_year, end_year))\n",
-    "cash_flow_df.to_csv(\"../temp/cash_flow.csv\", index=False)"
+    "cash_flow_df.to_csv(f\"/Users/lanyuanxiaoyao/SynologyDrive/data/Tushare/财务报表/现金流量表{start_year}-{end_year}.csv\", index=False)"
    ],
    "id": "334dbe20f2047a1e",
-   "outputs": [],
-   "execution_count": null
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Pull cash flow: 1990\n",
+      "Pull cash flow: 1991\n",
+      "Pull cash flow: 1992\n",
+      "Pull cash flow: 1993\n",
+      "Pull cash flow: 1994\n",
+      "Pull cash flow: 1995\n",
+      "Pull cash flow: 1996\n",
+      "Pull cash flow: 1997\n",
+      "Pull cash flow: 1998\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/7h/w0cmp4zj6mn9br_6nyj310m40000gn/T/ipykernel_50121/709533518.py:30: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
+      "  result = pd.concat([result, temp], ignore_index=True)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Pull cash flow: 1999\n",
+      "Pull cash flow: 2000\n",
+      "Pull cash flow: 2001\n",
+      "Pull cash flow: 2002\n",
+      "Pull cash flow: 2003\n",
+      "Pull cash flow: 2004\n",
+      "Pull cash flow: 2005\n",
+      "Pull cash flow: 2006\n",
+      "Pull cash flow: 2007\n",
+      "Pull cash flow: 2008\n",
+      "Pull cash flow: 2009\n",
+      "Pull cash flow: 2010\n",
+      "Pull cash flow: 2011\n",
+      "Pull cash flow: 2012\n",
+      "Pull cash flow: 2013\n",
+      "Pull cash flow: 2014\n",
+      "Pull cash flow: 2015\n",
+      "Pull cash flow: 2016\n",
+      "Pull cash flow: 2017\n",
+      "Pull cash flow: 2018\n",
+      "Pull cash flow: 2019\n",
+      "Pull cash flow: 2020\n",
+      "Pull cash flow: 2021\n",
+      "Pull cash flow: 2022\n",
+      "Pull cash flow: 2023\n",
+      "Pull cash flow: 2024\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/7h/w0cmp4zj6mn9br_6nyj310m40000gn/T/ipykernel_50121/709533518.py:30: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
+      "  result = pd.concat([result, temp], ignore_index=True)\n"
+     ]
+    }
+   ],
+   "execution_count": 15
   },
   {
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-01-13T01:46:57.717599Z",
+     "start_time": "2025-01-13T01:46:46.377806Z"
+    }
+   },
    "cell_type": "code",
    "source": [
     "finance_df = pd.merge(balance_sheet_df, income_df, on=[\"ts_code\", \"end_date\"])\n",
@@ -116,13 +342,13 @@
    ],
    "id": "f8bea62f377b5e2",
    "outputs": [],
-   "execution_count": null
+   "execution_count": 7
   },
   {
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2025-01-12T12:04:00.424439Z",
-     "start_time": "2025-01-12T12:04:00.364557Z"
+     "end_time": "2025-01-13T01:46:57.814028Z",
+     "start_time": "2025-01-13T01:46:57.728111Z"
     }
    },
    "cell_type": "code",
@@ -512,12 +738,408 @@
        "</div>"
       ]
      },
-     "execution_count": 29,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
-   "execution_count": 29
+   "execution_count": 8
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-01-13T09:37:00.340262Z",
+     "start_time": "2025-01-13T09:36:59.184110Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "import akshare as ak\n",
+    "\n",
+    "# ak.stock_balance_sheet_by_yearly_em(\"SZ000001\")\n",
+    "# df = ak.stock_financial_report_sina(\"sz000001\", symbol=\"资产负债表\")\n",
+    "df = ak.stock_financial_benefit_ths(\"000001\")\n",
+    "# df[df[\"报告日\"].str.endswith(\"1231\")]\n",
+    "df"
+   ],
+   "id": "582154dbc28b6bd",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "            报告期 报表核心指标      *净利润    *营业总收入     *营业支出 *归属于母公司所有者的净利润  \\\n",
+       "0    2024-09-30          397.29亿  1115.82亿   637.13亿        397.29亿   \n",
+       "1    2024-06-30          258.79亿   771.32亿   450.45亿        258.79亿   \n",
+       "2    2024-03-31          149.32亿   387.70亿   202.16亿        149.32亿   \n",
+       "3    2023-12-31          464.55亿  1646.99亿  1067.71亿        464.55亿   \n",
+       "4    2023-09-30          396.35亿  1276.34亿   785.87亿        396.35亿   \n",
+       "..          ...    ...       ...       ...       ...            ...   \n",
+       "110  1993-06-30            1.37亿     2.66亿     False          1.37亿   \n",
+       "111  1992-12-31            1.72亿     4.76亿     False          1.72亿   \n",
+       "112  1991-12-31            1.13亿     3.35亿     False          1.13亿   \n",
+       "113  1990-12-31         7087.50万     False     False       7087.50万   \n",
+       "114  1989-12-31         4302.00万     False     False       4302.00万   \n",
+       "\n",
+       "    *扣除非经常性损益后的净利润 报表全部指标   一、营业总收入   其中：营业收入  ... 少数股东损益 扣除非经常性损益后的利润 六、每股收益  \\\n",
+       "0          397.48亿         1115.82亿  1115.82亿  ...  False      397.48亿          \n",
+       "1          258.80亿          771.32亿   771.32亿  ...  False      258.80亿          \n",
+       "2          149.06亿          387.70亿   387.70亿  ...  False      149.06亿          \n",
+       "3          464.31亿         1646.99亿  1646.99亿  ...  False      464.31亿          \n",
+       "4          395.68亿         1276.34亿  1276.34亿  ...  False      395.68亿          \n",
+       "..             ...    ...       ...       ...  ...    ...          ...    ...   \n",
+       "110          False            2.66亿     2.66亿  ...  False        False          \n",
+       "111          False            4.76亿     4.76亿  ...  False        False          \n",
+       "112          False            3.35亿     3.35亿  ...  False        False          \n",
+       "113          False            False     False  ...  False        False          \n",
+       "114          False            False     False  ...  False        False          \n",
+       "\n",
+       "    （一）基本每股收益 （二）稀释每股收益 七、其他综合收益 归属母公司所有者的其他综合收益 八、综合收益总额 归属于母公司股东的综合收益总额  \\\n",
+       "0        1.94      1.94   -7.86亿          -7.86亿  389.43亿           False   \n",
+       "1        1.23      1.23   -3.56亿          -3.56亿  255.23亿           False   \n",
+       "2        0.66      0.66    3.45亿           3.45亿  152.77亿           False   \n",
+       "3        2.25      2.25   -3.72亿          -3.72亿  460.83亿           False   \n",
+       "4        1.94      1.94   -8.38亿          -8.38亿  387.97亿           False   \n",
+       "..        ...       ...      ...             ...      ...             ...   \n",
+       "110     False     False    False           False    False           False   \n",
+       "111     False     False    False           False    False           False   \n",
+       "112     False     False    False           False    False           False   \n",
+       "113     False     False    False           False    False           False   \n",
+       "114     False     False    False           False    False           False   \n",
+       "\n",
+       "    归属于少数股东的综合收益总额  \n",
+       "0            False  \n",
+       "1            False  \n",
+       "2            False  \n",
+       "3            False  \n",
+       "4            False  \n",
+       "..             ...  \n",
+       "110          False  \n",
+       "111          False  \n",
+       "112          False  \n",
+       "113          False  \n",
+       "114          False  \n",
+       "\n",
+       "[115 rows x 43 columns]"
+      ],
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>报告期</th>\n",
+       "      <th>报表核心指标</th>\n",
+       "      <th>*净利润</th>\n",
+       "      <th>*营业总收入</th>\n",
+       "      <th>*营业支出</th>\n",
+       "      <th>*归属于母公司所有者的净利润</th>\n",
+       "      <th>*扣除非经常性损益后的净利润</th>\n",
+       "      <th>报表全部指标</th>\n",
+       "      <th>一、营业总收入</th>\n",
+       "      <th>其中：营业收入</th>\n",
+       "      <th>...</th>\n",
+       "      <th>少数股东损益</th>\n",
+       "      <th>扣除非经常性损益后的利润</th>\n",
+       "      <th>六、每股收益</th>\n",
+       "      <th>（一）基本每股收益</th>\n",
+       "      <th>（二）稀释每股收益</th>\n",
+       "      <th>七、其他综合收益</th>\n",
+       "      <th>归属母公司所有者的其他综合收益</th>\n",
+       "      <th>八、综合收益总额</th>\n",
+       "      <th>归属于母公司股东的综合收益总额</th>\n",
+       "      <th>归属于少数股东的综合收益总额</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2024-09-30</td>\n",
+       "      <td></td>\n",
+       "      <td>397.29亿</td>\n",
+       "      <td>1115.82亿</td>\n",
+       "      <td>637.13亿</td>\n",
+       "      <td>397.29亿</td>\n",
+       "      <td>397.48亿</td>\n",
+       "      <td></td>\n",
+       "      <td>1115.82亿</td>\n",
+       "      <td>1115.82亿</td>\n",
+       "      <td>...</td>\n",
+       "      <td>False</td>\n",
+       "      <td>397.48亿</td>\n",
+       "      <td></td>\n",
+       "      <td>1.94</td>\n",
+       "      <td>1.94</td>\n",
+       "      <td>-7.86亿</td>\n",
+       "      <td>-7.86亿</td>\n",
+       "      <td>389.43亿</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2024-06-30</td>\n",
+       "      <td></td>\n",
+       "      <td>258.79亿</td>\n",
+       "      <td>771.32亿</td>\n",
+       "      <td>450.45亿</td>\n",
+       "      <td>258.79亿</td>\n",
+       "      <td>258.80亿</td>\n",
+       "      <td></td>\n",
+       "      <td>771.32亿</td>\n",
+       "      <td>771.32亿</td>\n",
+       "      <td>...</td>\n",
+       "      <td>False</td>\n",
+       "      <td>258.80亿</td>\n",
+       "      <td></td>\n",
+       "      <td>1.23</td>\n",
+       "      <td>1.23</td>\n",
+       "      <td>-3.56亿</td>\n",
+       "      <td>-3.56亿</td>\n",
+       "      <td>255.23亿</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2024-03-31</td>\n",
+       "      <td></td>\n",
+       "      <td>149.32亿</td>\n",
+       "      <td>387.70亿</td>\n",
+       "      <td>202.16亿</td>\n",
+       "      <td>149.32亿</td>\n",
+       "      <td>149.06亿</td>\n",
+       "      <td></td>\n",
+       "      <td>387.70亿</td>\n",
+       "      <td>387.70亿</td>\n",
+       "      <td>...</td>\n",
+       "      <td>False</td>\n",
+       "      <td>149.06亿</td>\n",
+       "      <td></td>\n",
+       "      <td>0.66</td>\n",
+       "      <td>0.66</td>\n",
+       "      <td>3.45亿</td>\n",
+       "      <td>3.45亿</td>\n",
+       "      <td>152.77亿</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2023-12-31</td>\n",
+       "      <td></td>\n",
+       "      <td>464.55亿</td>\n",
+       "      <td>1646.99亿</td>\n",
+       "      <td>1067.71亿</td>\n",
+       "      <td>464.55亿</td>\n",
+       "      <td>464.31亿</td>\n",
+       "      <td></td>\n",
+       "      <td>1646.99亿</td>\n",
+       "      <td>1646.99亿</td>\n",
+       "      <td>...</td>\n",
+       "      <td>False</td>\n",
+       "      <td>464.31亿</td>\n",
+       "      <td></td>\n",
+       "      <td>2.25</td>\n",
+       "      <td>2.25</td>\n",
+       "      <td>-3.72亿</td>\n",
+       "      <td>-3.72亿</td>\n",
+       "      <td>460.83亿</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2023-09-30</td>\n",
+       "      <td></td>\n",
+       "      <td>396.35亿</td>\n",
+       "      <td>1276.34亿</td>\n",
+       "      <td>785.87亿</td>\n",
+       "      <td>396.35亿</td>\n",
+       "      <td>395.68亿</td>\n",
+       "      <td></td>\n",
+       "      <td>1276.34亿</td>\n",
+       "      <td>1276.34亿</td>\n",
+       "      <td>...</td>\n",
+       "      <td>False</td>\n",
+       "      <td>395.68亿</td>\n",
+       "      <td></td>\n",
+       "      <td>1.94</td>\n",
+       "      <td>1.94</td>\n",
+       "      <td>-8.38亿</td>\n",
+       "      <td>-8.38亿</td>\n",
+       "      <td>387.97亿</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>110</th>\n",
+       "      <td>1993-06-30</td>\n",
+       "      <td></td>\n",
+       "      <td>1.37亿</td>\n",
+       "      <td>2.66亿</td>\n",
+       "      <td>False</td>\n",
+       "      <td>1.37亿</td>\n",
+       "      <td>False</td>\n",
+       "      <td></td>\n",
+       "      <td>2.66亿</td>\n",
+       "      <td>2.66亿</td>\n",
+       "      <td>...</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td></td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111</th>\n",
+       "      <td>1992-12-31</td>\n",
+       "      <td></td>\n",
+       "      <td>1.72亿</td>\n",
+       "      <td>4.76亿</td>\n",
+       "      <td>False</td>\n",
+       "      <td>1.72亿</td>\n",
+       "      <td>False</td>\n",
+       "      <td></td>\n",
+       "      <td>4.76亿</td>\n",
+       "      <td>4.76亿</td>\n",
+       "      <td>...</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td></td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>112</th>\n",
+       "      <td>1991-12-31</td>\n",
+       "      <td></td>\n",
+       "      <td>1.13亿</td>\n",
+       "      <td>3.35亿</td>\n",
+       "      <td>False</td>\n",
+       "      <td>1.13亿</td>\n",
+       "      <td>False</td>\n",
+       "      <td></td>\n",
+       "      <td>3.35亿</td>\n",
+       "      <td>3.35亿</td>\n",
+       "      <td>...</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td></td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>113</th>\n",
+       "      <td>1990-12-31</td>\n",
+       "      <td></td>\n",
+       "      <td>7087.50万</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>7087.50万</td>\n",
+       "      <td>False</td>\n",
+       "      <td></td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>...</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td></td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>114</th>\n",
+       "      <td>1989-12-31</td>\n",
+       "      <td></td>\n",
+       "      <td>4302.00万</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>4302.00万</td>\n",
+       "      <td>False</td>\n",
+       "      <td></td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>...</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td></td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>115 rows × 43 columns</p>\n",
+       "</div>"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 21
   }
  ],
  "metadata": {

财报筛选/loader.py

@@ -0,0 +1,25 @@
+import os.path
+
+import pandas as pd
+
+finance_root = "/Users/lanyuanxiaoyao/SynologyDrive/data/Tushare"
+# finance_root = "C:\\Users\\lanyuanxiaoyao\\Documents\\Tushare"
+
+
+def load_balance_sheet():
+    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(os.path.join(finance_root, "财务报表", "利润表1990-2024.csv"))
+
+
+def load_cashflow():
+    return pd.read_csv(os.path.join(finance_root, "财务报表", "现金流量表1990-2024.csv"))
+
+
+def load_finance():
+    finance_df = load_balance_sheet()
+    finance_df = pd.merge(finance_df, load_income(), on=["ts_code", "end_date"])
+    finance_df = pd.merge(finance_df, load_cashflow(), on=["ts_code", "end_date"])
+    return finance_df

财报筛选/选股回测.ipynb

@@ -0,0 +1,159 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true
+   },
+   "source": [
+    "import pandas as pd\n",
+    "import tushare as ts\n",
+    "\n",
+    "ts_pro = ts.pro_api(token=\"64ebff4fa679167600b905ee45dd88e76f3963c0ff39157f3f085f0e\")"
+   ],
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": [
+    "sse_df = ts_pro.trade_cal(exchange=\"SSE\")[[\"cal_date\", \"is_open\"]]\n",
+    "szse_df = ts_pro.trade_cal(exchange=\"SZSE\")[[\"cal_date\", \"is_open\"]]\n",
+    "merge_df = pd.merge(sse_df, szse_df, on=\"cal_date\", how=\"left\")\n",
+    "merge_df = merge_df.fillna(value=0)\n",
+    "merge_df[\"is_open\"] = (merge_df[\"is_open_x\"] + merge_df[\"is_open_y\"]) > 0\n",
+    "trade_date_df = merge_df[[\"cal_date\", \"is_open\"]]\n",
+    "trade_date_df"
+   ],
+   "id": "fe5b7f88c1739a13",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": [
+    "import os\n",
+    "import time\n",
+    "\n",
+    "for year in range(1990, 2025):\n",
+    "    target_path = f\"../temp/stk_factor/{year}.csv\"\n",
+    "    # 判断target_path文件是否存在\n",
+    "    if os.path.exists(target_path):\n",
+    "        continue\n",
+    "    result_df = pd.DataFrame()\n",
+    "    for trade_date in trade_date_df[(trade_date_df[\"cal_date\"].str.startswith(f\"{year}\")) & trade_date_df[\"is_open\"]][\n",
+    "        \"cal_date\"].values:\n",
+    "        time.sleep(1)\n",
+    "        print(f\"{trade_date} downloading...\")\n",
+    "        stk_df = ts_pro.stk_factor(trade_date=trade_date)\n",
+    "        result_df = pd.concat([result_df, stk_df])\n",
+    "    result_df.sort_values(by=[\"trade_date\", \"ts_code\"], ascending=True, inplace=True)\n",
+    "    result_df.to_csv(f\"/Users/lanyuanxiaoyao/SynologyDrive/data/Tushare/日线行情/{year}.csv\", index=False)"
+   ],
+   "id": "bde839364048fb89",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-01-14T02:29:02.535840Z",
+     "start_time": "2025-01-14T02:28:19.578528Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "root = \"/Users/lanyuanxiaoyao/SynologyDrive/data/Tushare/日线行情\"\n",
+    "\n",
+    "\n",
+    "def get_daily_df(start_year, end_year):\n",
+    "    daily_df = pd.read_csv(f\"{root}/{start_year}.csv\")\n",
+    "    for year in range(start_year + 1, end_year + 1):\n",
+    "        daily_df = pd.concat([daily_df, pd.read_csv(f\"{root}/{year}.csv\")])\n",
+    "    return daily_df"
+   ],
+   "id": "d0701612c56add14",
+   "outputs": [],
+   "execution_count": 39
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": "daily_df = get_daily_df(2019, 2024)",
+   "id": "ffc7072a7c5a44f9"
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": [
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
+    "\n",
+    "def is_ascending(code, year):\n",
+    "    daily_df = get_daily_df(year, year)\n",
+    "    daily_df = daily_df[daily_df[\"ts_code\"] == code][[\"trade_date\", \"close_qfq\"]]\n",
+    "    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",
+    "    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",
+    "\n",
+    "    print(first, last)\n",
+    "\n",
+    "    coefficients = np.polyfit(daily_df[\"trade_date_timestamp\"], daily_df[\"close_qfq\"], 1)\n",
+    "\n",
+    "    print(coefficients)\n",
+    "    fn = np.poly1d(coefficients)\n",
+    "    daily_df[\"close_predict\"] = fn(daily_df[\"trade_date_timestamp\"])\n",
+    "\n",
+    "    plt.figure(figsize=(25, 8))\n",
+    "    plt.scatter(daily_df[\"trade_date\"], daily_df[\"close_qfq\"])\n",
+    "    plt.plot(daily_df[\"trade_date\"], daily_df[\"close_predict\"], color=\"orange\")\n",
+    "\n",
+    "    plt.gcf().autofmt_xdate()\n",
+    "    plt.show()\n",
+    "\n",
+    "    return bool((coefficients[0] > 0) and (last > first))\n",
+    "\n",
+    "\n",
+    "print(is_ascending(\"000001.SZ\", 2020))\n",
+    "print(is_ascending(\"000001.SZ\", 2021))\n",
+    "print(is_ascending(\"000001.SZ\", 2022))\n",
+    "print(is_ascending(\"000001.SZ\", 2023))\n",
+    "print(is_ascending(\"000001.SZ\", 2024))"
+   ],
+   "id": "e58494f608dcb055",
+   "outputs": [],
+   "execution_count": null
+  }
+ ],
+ "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
+}

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": "2025-01-16T07:57:04.498115Z",
+     "start_time": "2025-01-16T07:57:00.401734Z"
+    }
+   },
+   "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": 1
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-01-16T07:57:04.552251Z",
+     "start_time": "2025-01-16T07:57:04.499999Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "from strategy 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": 2
+  }
+ ],
+ "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
+}