{ "cells": [ { "cell_type": "code", "id": "initial_id", "metadata": { "collapsed": true, "ExecuteTime": { "end_time": "2025-01-19T16:42:26.631868Z", "start_time": "2025-01-19T16:42:26.628635Z" } }, "source": [ "import numpy as np\n", "import pandas as pd\n", "import tushare as ts\n", "\n", "ts_pro = ts.pro_api(token=\"64ebff4fa679167600b905ee45dd88e76f3963c0ff39157f3f085f0e\")" ], "outputs": [], "execution_count": 459 }, { "metadata": { "ExecuteTime": { "end_time": "2025-01-19T16:42:27.857016Z", "start_time": "2025-01-19T16:42:26.639161Z" } }, "cell_type": "code", "source": [ "import loader as loader\n", "\n", "# 加载财报信息\n", "source_finance_df = loader.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", "]]\n", "finance_df[\"score\"] = 0\n", "finance_df = finance_df.sort_values(by=[\"code\", \"year\"], ascending=True).reset_index(drop=True)" ], "id": "68b2debc14502fd5", "outputs": [], "execution_count": 460 }, { "metadata": {}, "cell_type": "markdown", "source": "过滤上市时间大于5年的企业，由于计算很多数值需要与前一年比，所以实际上需要的是上市时间至少6年的企业", "id": "3052b8c4442f3643" }, { "metadata": { "ExecuteTime": { "end_time": "2025-01-19T16:42:27.931899Z", "start_time": "2025-01-19T16:42:27.868963Z" } }, "cell_type": "code", "source": "finance_df = finance_df.groupby(\"code\").filter(lambda x: len(x) > 6)", "id": "4293bd93ea8f9ed", "outputs": [], "execution_count": 461 }, { "metadata": {}, "cell_type": "markdown", "source": [ "ROE\n", "\n", "股东权益报酬率(%) RoE\t股东权益报酬率RoE 是判断股票是否具备”长期上涨潜力“最重要的指标之一， RoE 如果既稳定又优秀，那这家公司的其他指标也基本不会差。 \n", "RoE均值 >= 35\t550分 \n", "35 > RoE均值 >= 30\t500分 \n", "30 > RoE均值 >= 25\t450分 \n", "25 > RoE均值 >= 20\t400分 \n", "20 > RoE均值 >= 15\t300分 \n", "15 > RoE均值 >= 10\t250分 \n", "10 > RoE均值 或 0 >= 其中一年\t0分 " ], "id": "336aa970ee46709d" }, { "metadata": { "ExecuteTime": { "end_time": "2025-01-19T16:42:29.192712Z", "start_time": "2025-01-19T16:42:27.946033Z" } }, "cell_type": "code", "source": [ "finance_df[\"prev_total_stockholder_interest\"] = finance_df.groupby(\"code\")[\"total_stockholder_interest\"].shift(1)\n", "finance_df[\"roe\"] = finance_df[\"net_income\"] / (\n", " (finance_df[\"prev_total_stockholder_interest\"] + finance_df[\"total_stockholder_interest\"]) / 2)\n", "finance_df[\"average_roe\"] = finance_df.groupby(\"code\")[\"roe\"].rolling(window=5).mean().reset_index(0, drop=True)\n", "finance_df[\"score_roe\"] = 0\n", "finance_df.loc[finance_df[\"average_roe\"] >= 0.35, \"score_roe\"] += 550\n", "finance_df.loc[(finance_df[\"average_roe\"] >= 0.30) & (finance_df[\"average_roe\"] < 0.35), \"score_roe\"] = 500\n", "finance_df.loc[(finance_df[\"average_roe\"] >= 0.25) & (finance_df[\"average_roe\"] < 0.30), \"score_roe\"] = 450\n", "finance_df.loc[(finance_df[\"average_roe\"] >= 0.20) & (finance_df[\"average_roe\"] < 0.25), \"score_roe\"] = 400\n", "finance_df.loc[(finance_df[\"average_roe\"] >= 0.15) & (finance_df[\"average_roe\"] < 0.20), \"score_roe\"] = 300\n", "finance_df.loc[(finance_df[\"average_roe\"] >= 0.10) & (finance_df[\"average_roe\"] < 0.15), \"score_roe\"] = 250\n", "finance_df[\"score\"] += finance_df[\"score_roe\"]\n", "\n", "\n", "def reset_score_for_average_roe(group):\n", " group.loc[group['average_roe'].rolling(window=5, min_periods=1).min() < 0, 'score'] = 0\n", " return group\n", "\n", "\n", "finance_df = finance_df.groupby(\"code\").apply(reset_score_for_average_roe).reset_index(drop=True)" ], "id": "f050d33c4a0cd720", "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\lanyuanxiaoyao\\AppData\\Local\\Temp\\ipykernel_28824\\1604170078.py:20: DeprecationWarning: DataFrameGroupBy.apply operated on the grouping columns. This behavior is deprecated, and in a future version of pandas the grouping columns will be excluded from the operation. Either pass `include_groups=False` to exclude the groupings or explicitly select the grouping columns after groupby to silence this warning.\n", " finance_df = finance_df.groupby(\"code\").apply(reset_score_for_average_roe).reset_index(drop=True)\n" ] } ], "execution_count": 462 }, { "metadata": {}, "cell_type": "markdown", "source": [ "总资产报酬率(%) RoA\t总资产报酬率RoA 能真实反映出一家公司的获利能力， 相当于一家公司的 「投资年化率」，当然越高越好。\n", "RoA均值 >= 15\t100分\n", "15 > RoA均值 >= 11\t80分\n", "11 > RoA均值 >= 7\t50分\n", "7 > RoA均值\t0分" ], "id": "6c2e1c602898e342" }, { "metadata": { "ExecuteTime": { "end_time": "2025-01-19T16:42:29.363249Z", "start_time": "2025-01-19T16:42:29.219453Z" } }, "cell_type": "code", "source": [ "finance_df[\"prev_total_assets\"] = finance_df.groupby(\"code\")[\"total_assets\"].shift(1)\n", "finance_df[\"roa\"] = finance_df[\"net_income\"] / ((finance_df[\"prev_total_assets\"] + finance_df[\"total_assets\"]) / 2)\n", "finance_df[\"average_roa\"] = finance_df.groupby(\"code\")[\"roa\"].rolling(window=5).mean().reset_index(0, drop=True)\n", "finance_df[\"score_roa\"] = 0\n", "finance_df.loc[finance_df[\"average_roa\"] >= 0.15, \"score_roa\"] += 100\n", "finance_df.loc[(finance_df[\"average_roa\"] >= 0.11) & (finance_df[\"average_roa\"] < 0.15), \"score_roa\"] += 80\n", "finance_df.loc[(finance_df[\"average_roa\"] >= 0.07) & (finance_df[\"average_roa\"] < 0.11), \"score_roa\"] += 50\n", "finance_df[\"score\"] += finance_df[\"score_roa\"]" ], "id": "3b585cf8e2eb5e3", "outputs": [], "execution_count": 463 }, { "metadata": {}, "cell_type": "markdown", "source": [ "税后净利 规模(百万)\t获利规模大，那股价的”长期上涨潜力“也就会越稳健、越确定。选择时，大公司的优先级要高于小公司。\n", "税后净利均值 >= 10000\t150分\n", "10000 > 税后净利均值 >= 1000\t100分\n", "1000 > 税后净利均值\t0分" ], "id": "dbcb1d6b23582f3e" }, { "metadata": { "ExecuteTime": { "end_time": "2025-01-19T16:42:29.878285Z", "start_time": "2025-01-19T16:42:29.369862Z" } }, "cell_type": "code", "source": [ "finance_df['average_net_income'] = finance_df.groupby('code')['net_income'].transform(lambda x: x.rolling(5).mean())\n", "finance_df[\"score_net_income\"] = 0\n", "finance_df.loc[finance_df[\"average_net_income\"] >= 10000 * 10000000, \"score_net_income\"] = 150\n", "finance_df.loc[(finance_df[\"average_net_income\"] >= 1000 * 10000000) & (\n", " finance_df[\"average_net_income\"] < 10000 * 10000000), \"score_net_income\"] = 100\n", "finance_df[\"score\"] += finance_df[\"score_net_income\"]" ], "id": "fd5582e080102e20", "outputs": [], "execution_count": 464 }, { "metadata": {}, "cell_type": "markdown", "source": [ "现金状况 分析\t总资产周转率 与 现金与约当现金占总资产的关系，可以看出公司的现金状况是否健康。\n", "规则①：总资产周转率 > 0.8 且 现金与约当现金占总资产(%) >= 10\t50分\n", "规则②：总资产周转率 < 0.8 且 现金与约当现金占总资产(%) >= 20\t50分\n", "不符合 规则① 或 规则②\t0分" ], "id": "2c6c934a376eef0d" }, { "metadata": { "ExecuteTime": { "end_time": "2025-01-19T16:42:29.905727Z", "start_time": "2025-01-19T16:42:29.889468Z" } }, "cell_type": "code", "source": [ "finance_df[\"prev_total_assets\"] = finance_df.groupby(\"code\")[\"total_assets\"].shift(1)\n", "finance_df[\"total_assets_turnover_ratio\"] = finance_df[\"total_revenue\"] / (\n", " (finance_df[\"prev_total_assets\"] + finance_df[\"total_assets\"]) / 2)\n", "\n", "finance_df[\"cash_ratio\"] = finance_df[\"cash\"] / finance_df[\"total_assets\"]\n", "\n", "finance_df[\"score_assets_turnover_and_cash\"] = 0\n", "finance_df.loc[(finance_df[\"total_assets_turnover_ratio\"] >= 0.8) & (\n", " finance_df[\"cash_ratio\"] >= 0.1), \"score_assets_turnover_and_cash\"] = 50\n", "finance_df.loc[(finance_df[\"total_assets_turnover_ratio\"] < 0.8) & (\n", " finance_df[\"cash_ratio\"] >= 0.2), \"score_assets_turnover_and_cash\"] = 50\n", "finance_df[\"score\"] += finance_df[\"score_assets_turnover_and_cash\"]" ], "id": "bc92e050c82c3768", "outputs": [], "execution_count": 465 }, { "metadata": {}, "cell_type": "markdown", "source": [ "收现日数(日)\t平均收现日数越短，说明公司的经营能力越强。\n", "30 >= 平均收现日数\t20分\n", "平均收现日数 > 30\t0分\n", "\n", "销货日数(日)\t平均销货日数越短，说明公司商品越畅销。\n", "30 >= 平均销货日数\t20分\n", "平均销货日数 > 30\t0分\n", "\n", "收现日数+销货日数(日)\t生意周期 是否足够优秀，越短说明每年能做的生意趟数越多，经营能力就越强。\n", "40 >= 收现日数+销货日数\t20分\n", "60 >= 收现日数+销货日数 > 40\t10分\n", "平均销货日数 > 60\t0分" ], "id": "41ac526b0296b44b" }, { "metadata": { "ExecuteTime": { "end_time": "2025-01-19T16:42:29.923829Z", "start_time": "2025-01-19T16:42:29.916781Z" } }, "cell_type": "code", "source": [ "# 收现日数\n", "finance_df[\"collection_cash_period\"] = 360 / (finance_df[\"total_revenue\"] / finance_df[\"accounts_receivable\"])\n", "# 销货日数\n", "finance_df[\"sales_period\"] = 360 / (finance_df[\"operating_costs\"] / finance_df[\"accounts_receivable\"])\n", "\n", "finance_df[\"score_collection_cash_period\"] = 0\n", "finance_df.loc[(not finance_df[\"score_collection_cash_period\"].isna) & (\n", " finance_df[\"collection_cash_period\"] < 30), \"score_collection_cash_period\"] = 20\n", "finance_df[\"score\"] += finance_df[\"score_collection_cash_period\"]\n", "\n", "finance_df[\"score_sales_period\"] = 0\n", "finance_df.loc[\n", " (not finance_df[\"score_sales_period\"].isna) & (finance_df[\"score_sales_period\"] < 30), \"score_sales_period\"] = 20\n", "finance_df[\"score\"] += finance_df[\"score_sales_period\"]\n", "\n", "finance_df[\"score_collection_cash_period_and_sales_period\"] = 0\n", "finance_df.loc[(finance_df[\"collection_cash_period\"] + finance_df[\n", " \"sales_period\"]) < 40, \"score_collection_cash_period_and_sales_period\"] = 20\n", "finance_df.loc[(finance_df[\"collection_cash_period\"] + finance_df[\n", " \"sales_period\"]) < 60, \"score_collection_cash_period_and_sales_period\"] = 10\n", "finance_df[\"score\"] += finance_df[\"score_collection_cash_period_and_sales_period\"]" ], "id": "baeb44a4fb28b60b", "outputs": [], "execution_count": 466 }, { "metadata": {}, "cell_type": "markdown", "source": [ "毛利率(%)\t毛利率 是否保持平稳，不大起大落。\n", "30% >= 毛利率平均波动幅度\t50分\n", "毛利率平均波动幅度 > 30%\t0分" ], "id": "a53bfdb799df8f48" }, { "metadata": { "ExecuteTime": { "end_time": "2025-01-19T16:42:30.005541Z", "start_time": "2025-01-19T16:42:29.935348Z" } }, "cell_type": "code", "source": [ "finance_df[\"gross_profit_ratio\"] = (finance_df[\"total_revenue\"] - finance_df[\"operating_costs\"]) / finance_df[\n", " \"total_revenue\"]\n", "finance_df[\"gross_profit_ratio_std\"] = finance_df.groupby(\"code\")[\"gross_profit_ratio\"].rolling(\n", " window=5).std().reset_index(0, drop=True)\n", "finance_df[\"score_gross_profit_ratio\"] = 0\n", "finance_df[(not finance_df[\"gross_profit_ratio_std\"].isna) & (finance_df[\"gross_profit_ratio_std\"] < 30)] = 50\n", "finance_df[\"score\"] += finance_df[\"score_gross_profit_ratio\"]" ], "id": "9d23bdf60a1839c9", "outputs": [], "execution_count": 467 }, { "metadata": {}, "cell_type": "markdown", "source": [ "经营安全边际率(%)\t经营安全边际率越高，说明公司能够很好的控制成本，把大部分利润转化成实际收益， 获利能力很强，有利于抵御经济波动和价格竞争等影响。\n", "经营安全边际率 >= 70\t50分\n", "70 > 经营安全边际率 >= 50\t30分\n", "50 > 经营安全边际率 >= 30\t10分\n", "30 > 经营安全边际率\t0分" ], "id": "6613ab8263d4afef" }, { "metadata": { "ExecuteTime": { "end_time": "2025-01-19T16:42:30.022774Z", "start_time": "2025-01-19T16:42:30.016550Z" } }, "cell_type": "code", "source": [ "finance_df[\"operating_profit_ratio\"] = finance_df[\"operating_profit\"] / finance_df[\"total_revenue\"]\n", "finance_df[\"operating_safety_margin\"] = finance_df[\"operating_profit_ratio\"] / finance_df[\"gross_profit_ratio\"]\n", "finance_df[\"score_operating_safety_margin\"] = 0\n", "finance_df.loc[finance_df[\"operating_safety_margin\"] >= 70, \"score_operating_safety_margin\"] = 50\n", "finance_df.loc[finance_df[\"operating_safety_margin\"] >= 50, \"score_operating_safety_margin\"] = 30\n", "finance_df.loc[finance_df[\"operating_safety_margin\"] >= 30, \"score_operating_safety_margin\"] = 10\n", "finance_df[\"score\"] += finance_df[\"score_operating_safety_margin\"]" ], "id": "f7d9486af89cb710", "outputs": [], "execution_count": 468 }, { "metadata": {}, "cell_type": "markdown", "source": [ "税后净利\n", "年份由近(A)~远(E)\t公司赚的钱是否在逐年增长，是股价能长期上涨的基础。\n", "A年 > B年 (+) / A年 < B年 (-)\t+30分 / -30分\n", "B年 > C年 (+) / B年 < C年 (-)\t+25分 / -25分\n", "C年 > D年 (+) / C年 < D年 (-)\t+20分 / -20分\n", "D年 > E年 (+) / D年 < E年 (-)\t+15分 / -15分" ], "id": "2ee3712525455954" }, { "metadata": { "ExecuteTime": { "end_time": "2025-01-19T16:42:46.378919Z", "start_time": "2025-01-19T16:42:30.718209Z" } }, "cell_type": "code", "source": [ "def score_by_net_income_ascending(group):\n", " # 计算 score_net_income_1\n", " group['net_income_shift_1'] = group['net_income'].shift(1)\n", " group['score_net_income_1'] = (group['net_income'] > group['net_income_shift_1']).map(\n", " {True: 30, False: -30})\n", " group = group.mask(pd.isna(group[\"net_income_shift_1\"]), other=0)\n", " # 计算 score_net_income_2\n", " group['net_income_shift_2'] = group['net_income'].shift(2)\n", " group['score_net_income_2'] = (group['net_income_shift_1'] > group['net_income_shift_2']).map(\n", " {True: 25, False: -25})\n", " # 计算 score_net_income_3\n", " group['net_income_shift_3'] = group['net_income'].shift(3)\n", " group['score_net_income_3'] = (group['net_income_shift_2'] > group['net_income_shift_3']).map(\n", " {True: 20, False: -20})\n", " # 计算 score_net_income_4\n", " group['net_income_shift_4'] = group['net_income'].shift(4)\n", " group['score_net_income_4'] = (group['net_income_shift_3'] > group['net_income_shift_4']).map(\n", " {True: 15, False: -15}).fillna(0)\n", " return group\n", "\n", "\n", "finance_df = finance_df.groupby(\"code\").apply(score_by_net_income_ascending).reset_index(drop=True)\n", "finance_df[\"score_net_income_ascending\"] = np.sum(\n", " [finance_df[\"score_net_income_1\"], finance_df[\"score_net_income_2\"], finance_df[\"score_net_income_3\"],\n", " finance_df[\"score_net_income_4\"]], axis=0)\n", "finance_df" ], "id": "2d1ca7fc7873ce71", "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\lanyuanxiaoyao\\AppData\\Local\\Temp\\ipykernel_28824\\3206398043.py:22: DeprecationWarning: DataFrameGroupBy.apply operated on the grouping columns. This behavior is deprecated, and in a future version of pandas the grouping columns will be excluded from the operation. Either pass `include_groups=False` to exclude the groupings or explicitly select the grouping columns after groupby to silence this warning.\n", " finance_df = finance_df.groupby(\"code\").apply(score_by_net_income_ascending).reset_index(drop=True)\n" ] }, { "data": { "text/plain": [ " code year total_stockholder_interest net_income \\\n", "0 0 0 0.000000e+00 0.000000e+00 \n", "1 000001.SZ 2006 6.474463e+09 1.302907e+09 \n", "2 000001.SZ 2007 1.300606e+10 2.649903e+09 \n", "3 000001.SZ 2008 1.640079e+10 6.140350e+08 \n", "4 000001.SZ 2009 2.046961e+10 5.030729e+09 \n", "... ... ... ... ... \n", "70725 871981.BJ 2019 1.484536e+08 1.933833e+07 \n", "70726 871981.BJ 2020 1.963500e+08 3.113004e+07 \n", "70727 871981.BJ 2021 4.901179e+08 6.549797e+07 \n", "70728 871981.BJ 2022 5.238630e+08 4.359533e+07 \n", "70729 871981.BJ 2023 5.044336e+08 -5.665176e+06 \n", "\n", " total_assets total_revenue inventories accounts_receivable \\\n", "0 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 \n", "1 2.605763e+11 7.135218e+09 NaN NaN \n", "2 3.525394e+11 1.080750e+10 NaN NaN \n", "3 4.744402e+11 1.451312e+10 NaN NaN \n", "4 5.878110e+11 1.511444e+10 NaN NaN \n", "... ... ... ... ... \n", "70725 3.438787e+08 2.288707e+08 6.439933e+07 9.145441e+07 \n", "70726 4.407381e+08 3.221584e+08 7.076865e+07 1.028702e+08 \n", "70727 7.806398e+08 4.748939e+08 1.102946e+08 1.094223e+08 \n", "70728 8.141886e+08 3.872667e+08 1.034502e+08 7.252802e+07 \n", "70729 7.671820e+08 3.613133e+08 1.070212e+08 7.962033e+07 \n", "\n", " operating_costs operating_profit ... score_operating_safety_margin \\\n", "0 0.000000e+00 0.000000e+00 ... 0 \n", "1 NaN 1.905169e+09 ... 0 \n", "2 NaN 3.721942e+09 ... 0 \n", "3 NaN 8.034260e+08 ... 0 \n", "4 NaN 6.159127e+09 ... 0 \n", "... ... ... ... ... \n", "70725 1.759984e+08 1.982603e+07 ... 0 \n", "70726 2.444144e+08 3.466142e+07 ... 0 \n", "70727 3.501988e+08 7.194507e+07 ... 0 \n", "70728 3.141146e+08 2.827675e+07 ... 0 \n", "70729 3.220560e+08 -1.192680e+07 ... 0 \n", "\n", " net_income_shift_1 score_net_income_1 net_income_shift_2 \\\n", "0 0.000000e+00 0 NaN \n", "1 3.110076e+08 30 NaN \n", "2 1.302907e+09 30 0.000000e+00 \n", "3 2.649903e+09 -30 1.302907e+09 \n", "4 6.140350e+08 30 2.649903e+09 \n", "... ... ... ... \n", "70725 1.875294e+07 30 9.625220e+06 \n", "70726 1.933833e+07 30 1.875294e+07 \n", "70727 3.113004e+07 30 1.933833e+07 \n", "70728 6.549797e+07 -30 3.113004e+07 \n", "70729 4.359533e+07 -30 6.549797e+07 \n", "\n", " score_net_income_2 net_income_shift_3 score_net_income_3 \\\n", "0 -25 NaN -20 \n", "1 -25 NaN -20 \n", "2 25 NaN -20 \n", "3 25 0.000000e+00 20 \n", "4 -25 1.302907e+09 20 \n", "... ... ... ... \n", "70725 25 0.000000e+00 20 \n", "70726 25 9.625220e+06 20 \n", "70727 25 1.875294e+07 20 \n", "70728 25 1.933833e+07 20 \n", "70729 -25 3.113004e+07 20 \n", "\n", " net_income_shift_4 score_net_income_4 score_net_income_ascending \n", "0 NaN -15 -60 \n", "1 NaN -15 -30 \n", "2 NaN -15 20 \n", "3 NaN -15 0 \n", "4 0.00 15 40 \n", "... ... ... ... \n", "70725 NaN -15 60 \n", "70726 0.00 15 90 \n", "70727 9625220.11 15 90 \n", "70728 18752944.38 15 30 \n", "70729 19338331.78 15 -20 \n", "\n", "[70730 rows x 46 columns]" ], "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
codeyeartotal_stockholder_interestnet_incometotal_assetstotal_revenueinventoriesaccounts_receivableoperating_costsoperating_profit...score_operating_safety_marginnet_income_shift_1score_net_income_1net_income_shift_2score_net_income_2net_income_shift_3score_net_income_3net_income_shift_4score_net_income_4score_net_income_ascending
0000.000000e+000.000000e+000.000000e+000.000000e+000.000000e+000.000000e+000.000000e+000.000000e+00...00.000000e+000NaN-25NaN-20NaN-15-60
1000001.SZ20066.474463e+091.302907e+092.605763e+117.135218e+09NaNNaNNaN1.905169e+09...03.110076e+0830NaN-25NaN-20NaN-15-30
2000001.SZ20071.300606e+102.649903e+093.525394e+111.080750e+10NaNNaNNaN3.721942e+09...01.302907e+09300.000000e+0025NaN-20NaN-1520
3000001.SZ20081.640079e+106.140350e+084.744402e+111.451312e+10NaNNaNNaN8.034260e+08...02.649903e+09-301.302907e+09250.000000e+0020NaN-150
4000001.SZ20092.046961e+105.030729e+095.878110e+111.511444e+10NaNNaNNaN6.159127e+09...06.140350e+08302.649903e+09-251.302907e+09200.001540
..................................................................
70725871981.BJ20191.484536e+081.933833e+073.438787e+082.288707e+086.439933e+079.145441e+071.759984e+081.982603e+07...01.875294e+07309.625220e+06250.000000e+0020NaN-1560
70726871981.BJ20201.963500e+083.113004e+074.407381e+083.221584e+087.076865e+071.028702e+082.444144e+083.466142e+07...01.933833e+07301.875294e+07259.625220e+06200.001590
70727871981.BJ20214.901179e+086.549797e+077.806398e+084.748939e+081.102946e+081.094223e+083.501988e+087.194507e+07...03.113004e+07301.933833e+07251.875294e+07209625220.111590
70728871981.BJ20225.238630e+084.359533e+078.141886e+083.872667e+081.034502e+087.252802e+073.141146e+082.827675e+07...06.549797e+07-303.113004e+07251.933833e+072018752944.381530
70729871981.BJ20235.044336e+08-5.665176e+067.671820e+083.613133e+081.070212e+087.962033e+073.220560e+08-1.192680e+07...04.359533e+07-306.549797e+07-253.113004e+072019338331.7815-20
\n", "

70730 rows × 46 columns

\n", "
" ] }, "execution_count": 469, "metadata": {}, "output_type": "execute_result" } ], "execution_count": 469 }, { "metadata": {}, "cell_type": "code", "source": [ "def score_by_net_income_ascending(code):\n", " temp_df = finance_df[finance_df[\"code\"] == code].copy()[[\"year\", \"net_income\"]]\n", " temp_df.sort_values(by=\"year\", ascending=False, inplace=True)\n", " temp_df.set_index(keys=\"year\", drop=True, inplace=True)\n", "\n", " score = 0\n", " if temp_df.iloc[0].values[0] > temp_df.iloc[1].values[0]:\n", " score += 30\n", " else:\n", " score -= 30\n", "\n", " if temp_df.iloc[1].values[0] > temp_df.iloc[2].values[0]:\n", " score += 25\n", " else:\n", " score -= 25\n", "\n", " if temp_df.iloc[2].values[0] > temp_df.iloc[3].values[0]:\n", " score += 20\n", " else:\n", " score -= 20\n", "\n", " if temp_df.iloc[3].values[0] > temp_df.iloc[4].values[0]:\n", " score += 15\n", " else:\n", " score -= 15\n", "\n", " return score\n", "\n", "\n", "codes = list(map(lambda x: add_score(x, score_by_net_income_ascending(x[0])), codes))" ], "id": "4ab6a7b485dc9349", "outputs": [], "execution_count": null }, { "metadata": {}, "cell_type": "code", "source": [ "def score_by_operating_net_cash_flow_ascending(code):\n", " temp_df = finance_df[finance_df[\"code\"] == code].copy()[[\"year\", \"operating_net_cash_flow\"]]\n", " temp_df.sort_values(by=\"year\", ascending=False, inplace=True)\n", " temp_df.set_index(keys=\"year\", drop=True, inplace=True)\n", "\n", " score = 0\n", " if temp_df.iloc[0].values[0] > temp_df.iloc[1].values[0]:\n", " score += 30\n", " else:\n", " score -= 30\n", "\n", " if temp_df.iloc[1].values[0] > temp_df.iloc[2].values[0]:\n", " score += 25\n", " else:\n", " score -= 25\n", "\n", " if temp_df.iloc[2].values[0] > temp_df.iloc[3].values[0]:\n", " score += 20\n", " else:\n", " score -= 20\n", "\n", " if temp_df.iloc[3].values[0] > temp_df.iloc[4].values[0]:\n", " score += 15\n", " else:\n", " score -= 15\n", "\n", " return score\n", "\n", "\n", "codes = list(map(lambda x: add_score(x, score_by_operating_net_cash_flow_ascending(x[0])), codes))" ], "id": "d6644089e803a79d", "outputs": [], "execution_count": null }, { "metadata": {}, "cell_type": "code", "source": [ "df = pd.DataFrame(\n", " codes,\n", " columns=[\"code\", \"name\", \"score\", \"roe_score\", \"roa_score\", \"net_income\", \"assets_turnover_and_cash\",\n", " \"collection_cash_period_and_sales_period\", \"gross_profit_ratio_volatility\",\n", " \"operating_safety_margin\", \"net_income_ascending\",\n", " \"operating_net_cash_flow_ascending\"]\n", ")\n", "df.sort_values(by=\"score\", ascending=False, inplace=True)\n", "df" ], "id": "ef9e6259efc1c1d0", "outputs": [], "execution_count": null }, { "metadata": {}, "cell_type": "code", "source": "df[:100][\"code\"]", "id": "32b5b4778985afaa", "outputs": [], "execution_count": null }, { "metadata": {}, "cell_type": "code", "source": [ "temp_df = finance_df[finance_df[\"code\"] == \"600763.SH\"]\n", "cal_roe(temp_df)\n", "cal_roa(temp_df)\n", "temp_df[[\"year\", \"roe\", \"roa\"]]" ], "id": "e6d973f4ff98ebef", "outputs": [], "execution_count": null }, { "metadata": {}, "cell_type": "code", "source": [ "temp_df = ts_pro.fina_indicator(\n", " ts_code=\"600763.SH\", start_date=\"20140101\", end_date=\"20241231\",\n", " fields=\"ts_code,end_date,roe,roa\"\n", ")\n", "temp_df = temp_df[temp_df[\"end_date\"].str.endswith(\"1231\")]\n", "# temp_df[\"end_date\"] = temp_df[\"end_date\"].str[:4]\n", "# temp_df = temp_df.drop_duplicates(subset=[\"end_date\"], keep=\"last\")\n", "temp_df" ], "id": "b220252765677c76", "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 }