391 lines
15 KiB
Plaintext
391 lines
15 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"id": "initial_id",
|
||
"metadata": {
|
||
"collapsed": true,
|
||
"ExecuteTime": {
|
||
"end_time": "2025-01-11T13:37:21.407428Z",
|
||
"start_time": "2025-01-11T13:37:18.600140Z"
|
||
}
|
||
},
|
||
"source": [
|
||
"import pandas as pd\n",
|
||
"import tushare as ts\n",
|
||
"from numpy.ma.extras import column_stack\n",
|
||
"\n",
|
||
"ts_pro = ts.pro_api(token=\"64ebff4fa679167600b905ee45dd88e76f3963c0ff39157f3f085f0e\")"
|
||
],
|
||
"outputs": [],
|
||
"execution_count": 1
|
||
},
|
||
{
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-01-11T15:15:46.117153Z",
|
||
"start_time": "2025-01-11T15:15:46.107715Z"
|
||
}
|
||
},
|
||
"cell_type": "code",
|
||
"source": [
|
||
"def get_blancesheet_df(start_year, end_year):\n",
|
||
" fields = [\"ts_code\", \"end_date\", \"total_assets\", \"total_hldr_eqy_inc_min_int\", \"money_cap\", \"accounts_receiv\",\n",
|
||
" \"accounts_receiv_bill\",\n",
|
||
" \"oth_rcv_total\", \"inventories\"]\n",
|
||
" result = pd.DataFrame(columns=fields)\n",
|
||
" for year in range(start_year, end_year + 1):\n",
|
||
" period = f\"{year}1231\"\n",
|
||
" temp = ts_pro.balancesheet_vip(period=period, fields=\",\".join(fields))\n",
|
||
" result = pd.concat([result, temp], ignore_index=True)\n",
|
||
" return result\n",
|
||
"\n",
|
||
"\n",
|
||
"def get_income_df(start_year, end_year):\n",
|
||
" fields = [\"ts_code\", \"end_date\", \"n_income\", \"revenue\", \"total_revenue\", \"oper_cost\", \"operate_profit\",\n",
|
||
" \"total_cogs\"]\n",
|
||
" result = pd.DataFrame(columns=fields)\n",
|
||
" for year in range(start_year, end_year + 1):\n",
|
||
" period = f\"{year}1231\"\n",
|
||
" temp = ts_pro.income_vip(period=period, fields=\",\".join(fields))\n",
|
||
" result = pd.concat([result, temp], ignore_index=True)\n",
|
||
" return result\n",
|
||
"\n",
|
||
"\n",
|
||
"def clean_df(df):\n",
|
||
" df = df.drop_duplicates(subset=[\"ts_code\", \"end_date\"])\n",
|
||
" df[\"end_date\"] = df[\"end_date\"].str[:4]\n",
|
||
" return df"
|
||
],
|
||
"id": "3100e2f517963834",
|
||
"outputs": [],
|
||
"execution_count": 107
|
||
},
|
||
{
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-01-11T15:16:10.137410Z",
|
||
"start_time": "2025-01-11T15:15:51.266092Z"
|
||
}
|
||
},
|
||
"cell_type": "code",
|
||
"source": [
|
||
"blancesheet_df = clean_df(get_blancesheet_df(2018, 2024))\n",
|
||
"income_df = clean_df(get_income_df(2018, 2024))"
|
||
],
|
||
"id": "66ab3d52c88888ea",
|
||
"outputs": [
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"C:\\Users\\lanyuanxiaoyao\\AppData\\Local\\Temp\\ipykernel_32660\\3334449392.py:9: 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",
|
||
"C:\\Users\\lanyuanxiaoyao\\AppData\\Local\\Temp\\ipykernel_32660\\3334449392.py:9: 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",
|
||
"C:\\Users\\lanyuanxiaoyao\\AppData\\Local\\Temp\\ipykernel_32660\\3334449392.py:20: 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",
|
||
"C:\\Users\\lanyuanxiaoyao\\AppData\\Local\\Temp\\ipykernel_32660\\3334449392.py:20: 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": 108
|
||
},
|
||
{
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-01-11T15:16:38.476024Z",
|
||
"start_time": "2025-01-11T15:16:38.460593Z"
|
||
}
|
||
},
|
||
"cell_type": "code",
|
||
"source": [
|
||
"def cal_roe(df):\n",
|
||
" df_group = stock_df.groupby(\"ts_code\")\n",
|
||
" df[\"prev_total_hldr_eqy_inc_min_int\"] = df_group[\"total_hldr_eqy_inc_min_int\"].shift(1)\n",
|
||
" df[\"roe\"] = df[\"n_income\"] / (\n",
|
||
" (df[\"prev_total_hldr_eqy_inc_min_int\"] + df[\"total_hldr_eqy_inc_min_int\"]) / 2)\n",
|
||
" df[\"roe\"] = df[\"roe\"].round(4)\n",
|
||
" df.drop(columns=[\"prev_total_hldr_eqy_inc_min_int\"], inplace=True)\n",
|
||
"\n",
|
||
"\n",
|
||
"def cal_roa(df):\n",
|
||
" df_group = stock_df.groupby(\"ts_code\")\n",
|
||
" df[\"prev_toral_assets\"] = df_group[\"total_assets\"].shift(1)\n",
|
||
" df[\"roa\"] = df[\"n_income\"] / ((df[\"prev_toral_assets\"] + df[\"total_assets\"]) / 2)\n",
|
||
" df[\"roa\"] = df[\"roa\"].round(4)\n",
|
||
" df.drop(columns=[\"prev_toral_assets\"], inplace=True)\n",
|
||
"\n",
|
||
"\n",
|
||
"# 总资产周转率\n",
|
||
"def cal_total_assets_turnover(df):\n",
|
||
" df_group = stock_df.groupby(\"ts_code\")\n",
|
||
" df[\"prev_toral_assets\"] = df_group[\"total_assets\"].shift(1)\n",
|
||
" df[\"total_assets_turnover\"] = df[\"total_revenue\"] / ((df[\"prev_toral_assets\"] + df[\"total_assets\"]) / 2)\n",
|
||
" df[\"total_assets_turnover\"] = df[\"total_assets_turnover\"].round(2)\n",
|
||
" df.drop(columns=[\"prev_toral_assets\"], inplace=True)\n",
|
||
"\n",
|
||
"\n",
|
||
"# 现金比率\n",
|
||
"def cal_cash_ratio(df):\n",
|
||
" df[\"cash_ratio\"] = df[\"money_cap\"] / df[\"total_assets\"]\n",
|
||
" df[\"cash_ratio\"] = df[\"cash_ratio\"].round(4)\n",
|
||
"\n",
|
||
"\n",
|
||
"# 毛利率\n",
|
||
"def cal_gross_profit(df):\n",
|
||
" df[\"gross_profit\"] = (df[\"total_revenue\"] - df[\"oper_cost\"]) / df[\"total_revenue\"]\n",
|
||
" df[\"gross_profit\"] = df[\"gross_profit\"].round(4)\n",
|
||
"\n",
|
||
"\n",
|
||
"# 经营利润率\n",
|
||
"def cal_operating_profit(df):\n",
|
||
" df[\"operating_profit\"] = df[\"operate_profit\"] / df[\"total_revenue\"]\n",
|
||
" df[\"operating_profit\"] = df[\"operating_profit\"].round(4)\n",
|
||
"\n",
|
||
"\n",
|
||
"# 经营安全边际\n",
|
||
"def cal_operating_safety_margin(df):\n",
|
||
" df[\"operating_safety_margin\"] = df[\"operating_profit\"] / df[\"gross_profit\"]\n",
|
||
" df[\"operating_safety_margin\"] = df[\"operating_safety_margin\"].round(4)\n",
|
||
"\n",
|
||
"\n",
|
||
"# 收现日数\n",
|
||
"def cal_collection_cash_period(df):\n",
|
||
" df[\"collection_cash_period\"] = 360 / (df[\"total_revenue\"] / df[\"accounts_receiv\"])\n",
|
||
" df[\"collection_cash_period\"] = df[\"collection_cash_period\"].round(2)\n",
|
||
"\n",
|
||
"\n",
|
||
"# 销货日数\n",
|
||
"def cal_sales_period(df):\n",
|
||
" df[\"sales_period\"] = 360 / (df[\"oper_cost\"] / df[\"inventories\"])\n",
|
||
" df[\"sales_period\"] = df[\"sales_period\"].round(2)"
|
||
],
|
||
"id": "85618db7e29a25eb",
|
||
"outputs": [],
|
||
"execution_count": 110
|
||
},
|
||
{
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-01-11T15:24:45.366231Z",
|
||
"start_time": "2025-01-11T15:24:45.251939Z"
|
||
}
|
||
},
|
||
"cell_type": "code",
|
||
"source": [
|
||
"stock_df = pd.merge(blancesheet_df, income_df, on=[\"ts_code\", \"end_date\"])\n",
|
||
"\n",
|
||
"cal_roe(stock_df)\n",
|
||
"cal_roa(stock_df)\n",
|
||
"cal_total_assets_turnover(stock_df)\n",
|
||
"cal_cash_ratio(stock_df)\n",
|
||
"cal_gross_profit(stock_df)\n",
|
||
"cal_operating_profit(stock_df)\n",
|
||
"cal_operating_safety_margin(stock_df)\n",
|
||
"cal_collection_cash_period(stock_df)\n",
|
||
"cal_sales_period(stock_df)\n",
|
||
"\n",
|
||
"stock_df[\n",
|
||
" # [\"ts_code\", \"end_date\", \"roe\", \"roa\", \"total_assets_turnover\", \"cash_ratio\", \"gross_profit\", \"operating_profit\", \"operating_safety_margin\"]\n",
|
||
" [\"ts_code\", \"end_date\", \"collection_cash_period\", \"sales_period\", \"oper_cost\", \"total_cogs\"]\n",
|
||
"]"
|
||
],
|
||
"id": "cc0d2f7406bb447e",
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
" ts_code end_date collection_cash_period sales_period oper_cost \\\n",
|
||
"0 301093.SZ 2018 93.76 137.78 2.160737e+08 \n",
|
||
"1 301092.SZ 2018 67.58 141.15 2.604383e+08 \n",
|
||
"2 688280.SH 2018 212.32 137.55 7.666165e+08 \n",
|
||
"3 688739.SH 2018 124.23 314.40 2.063751e+08 \n",
|
||
"4 688257.SH 2018 101.39 148.16 4.092993e+08 \n",
|
||
"... ... ... ... ... ... \n",
|
||
"31118 873896.BJ 2023 40.83 1.20 2.687648e+08 \n",
|
||
"31119 873911.BJ 2023 41.27 377.77 1.362851e+08 \n",
|
||
"31120 873755.BJ 2023 63.15 155.20 1.354382e+08 \n",
|
||
"31121 603091.SH 2023 36.89 93.67 9.023004e+08 \n",
|
||
"31122 301622.SZ 2023 134.91 116.69 7.020213e+08 \n",
|
||
"\n",
|
||
" total_cogs \n",
|
||
"0 3.352792e+08 \n",
|
||
"1 3.321345e+08 \n",
|
||
"2 1.110642e+09 \n",
|
||
"3 6.802215e+08 \n",
|
||
"4 5.354176e+08 \n",
|
||
"... ... \n",
|
||
"31118 3.891025e+08 \n",
|
||
"31119 2.304407e+08 \n",
|
||
"31120 1.716143e+08 \n",
|
||
"31121 1.057946e+09 \n",
|
||
"31122 8.257937e+08 \n",
|
||
"\n",
|
||
"[31123 rows x 6 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>ts_code</th>\n",
|
||
" <th>end_date</th>\n",
|
||
" <th>collection_cash_period</th>\n",
|
||
" <th>sales_period</th>\n",
|
||
" <th>oper_cost</th>\n",
|
||
" <th>total_cogs</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>301093.SZ</td>\n",
|
||
" <td>2018</td>\n",
|
||
" <td>93.76</td>\n",
|
||
" <td>137.78</td>\n",
|
||
" <td>2.160737e+08</td>\n",
|
||
" <td>3.352792e+08</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>301092.SZ</td>\n",
|
||
" <td>2018</td>\n",
|
||
" <td>67.58</td>\n",
|
||
" <td>141.15</td>\n",
|
||
" <td>2.604383e+08</td>\n",
|
||
" <td>3.321345e+08</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>688280.SH</td>\n",
|
||
" <td>2018</td>\n",
|
||
" <td>212.32</td>\n",
|
||
" <td>137.55</td>\n",
|
||
" <td>7.666165e+08</td>\n",
|
||
" <td>1.110642e+09</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>688739.SH</td>\n",
|
||
" <td>2018</td>\n",
|
||
" <td>124.23</td>\n",
|
||
" <td>314.40</td>\n",
|
||
" <td>2.063751e+08</td>\n",
|
||
" <td>6.802215e+08</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>688257.SH</td>\n",
|
||
" <td>2018</td>\n",
|
||
" <td>101.39</td>\n",
|
||
" <td>148.16</td>\n",
|
||
" <td>4.092993e+08</td>\n",
|
||
" <td>5.354176e+08</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",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>31118</th>\n",
|
||
" <td>873896.BJ</td>\n",
|
||
" <td>2023</td>\n",
|
||
" <td>40.83</td>\n",
|
||
" <td>1.20</td>\n",
|
||
" <td>2.687648e+08</td>\n",
|
||
" <td>3.891025e+08</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>31119</th>\n",
|
||
" <td>873911.BJ</td>\n",
|
||
" <td>2023</td>\n",
|
||
" <td>41.27</td>\n",
|
||
" <td>377.77</td>\n",
|
||
" <td>1.362851e+08</td>\n",
|
||
" <td>2.304407e+08</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>31120</th>\n",
|
||
" <td>873755.BJ</td>\n",
|
||
" <td>2023</td>\n",
|
||
" <td>63.15</td>\n",
|
||
" <td>155.20</td>\n",
|
||
" <td>1.354382e+08</td>\n",
|
||
" <td>1.716143e+08</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>31121</th>\n",
|
||
" <td>603091.SH</td>\n",
|
||
" <td>2023</td>\n",
|
||
" <td>36.89</td>\n",
|
||
" <td>93.67</td>\n",
|
||
" <td>9.023004e+08</td>\n",
|
||
" <td>1.057946e+09</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>31122</th>\n",
|
||
" <td>301622.SZ</td>\n",
|
||
" <td>2023</td>\n",
|
||
" <td>134.91</td>\n",
|
||
" <td>116.69</td>\n",
|
||
" <td>7.020213e+08</td>\n",
|
||
" <td>8.257937e+08</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"<p>31123 rows × 6 columns</p>\n",
|
||
"</div>"
|
||
]
|
||
},
|
||
"execution_count": 112,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"execution_count": 112
|
||
}
|
||
],
|
||
"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
|
||
}
|