2025-02-12 00:21:33 +08:00
|
|
|
|
{
|
|
|
|
|
|
"cells": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
2025-05-06 23:42:40 +08:00
|
|
|
|
"execution_count": 1,
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"id": "18d1d622-b083-4cc4-a6f8-7c1ed2d0edd2",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-04-10 23:17:22 +08:00
|
|
|
|
"end_time": "2025-04-09T14:57:36.913044Z",
|
|
|
|
|
|
"start_time": "2025-04-09T14:57:36.159612Z"
|
2025-02-12 00:21:33 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
2025-05-06 23:42:40 +08:00
|
|
|
|
"outputs": [],
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"source": [
|
|
|
|
|
|
"import tushare as ts\n",
|
|
|
|
|
|
"ts.set_token('3a0741c702ee7e5e5f2bf1f0846bafaafe4e320833240b2a7e4a685f')\n",
|
|
|
|
|
|
"pro = ts.pro_api()"
|
2025-05-06 23:42:40 +08:00
|
|
|
|
]
|
2025-02-12 00:21:33 +08:00
|
|
|
|
},
|
|
|
|
|
|
{
|
2025-02-15 23:33:34 +08:00
|
|
|
|
"cell_type": "code",
|
2025-05-13 15:30:06 +08:00
|
|
|
|
"execution_count": 2,
|
2025-02-15 23:33:34 +08:00
|
|
|
|
"id": "14671a7f72de2564",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-04-10 23:17:22 +08:00
|
|
|
|
"end_time": "2025-04-09T14:57:39.128278Z",
|
|
|
|
|
|
"start_time": "2025-04-09T14:57:36.918051Z"
|
2025-02-12 00:21:33 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
2025-05-06 23:42:40 +08:00
|
|
|
|
"outputs": [],
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"source": [
|
|
|
|
|
|
"from datetime import datetime\n",
|
|
|
|
|
|
"import pandas as pd\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"import warnings\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"warnings.filterwarnings(\"ignore\")\n",
|
|
|
|
|
|
"def filter_rows(df):\n",
|
|
|
|
|
|
" # 按照 name 和 start_date 分组\n",
|
|
|
|
|
|
" def select_row(group):\n",
|
|
|
|
|
|
" # 如果有 end_date 不为 NaT 的行，优先保留这些行\n",
|
|
|
|
|
|
" valid_rows = group[group['end_date'].notna()]\n",
|
|
|
|
|
|
" if not valid_rows.empty:\n",
|
|
|
|
|
|
" return valid_rows.iloc[0] # 返回第一个有效行\n",
|
|
|
|
|
|
" else:\n",
|
|
|
|
|
|
" return group.iloc[0] # 如果没有有效行，返回第一行\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" filtered_df = df.groupby(['name', 'start_date'], group_keys=False).apply(select_row)\n",
|
|
|
|
|
|
" filtered_df = filtered_df.reset_index(drop=True)\n",
|
|
|
|
|
|
" return filtered_df\n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"\n",
|
|
|
|
|
|
"def is_st(name_change_dict, stock_code, target_date):\n",
|
|
|
|
|
|
" target_date = datetime.strptime(target_date, '%Y%m%d')\n",
|
|
|
|
|
|
" if stock_code not in name_change_dict.keys():\n",
|
|
|
|
|
|
" return False\n",
|
|
|
|
|
|
" df = name_change_dict[stock_code]\n",
|
|
|
|
|
|
" for i in range(len(df)):\n",
|
|
|
|
|
|
" sds = df.iloc[i, 2]\n",
|
|
|
|
|
|
" eds = df.iloc[i, 3]\n",
|
|
|
|
|
|
" if eds is None or eds is pd.NaT:\n",
|
|
|
|
|
|
" eds = datetime.now()\n",
|
|
|
|
|
|
" if (target_date - sds).days >= 0 and (target_date - eds).days <= 0:\n",
|
|
|
|
|
|
" return True\n",
|
|
|
|
|
|
" return False\n",
|
|
|
|
|
|
"\n",
|
2025-06-02 22:23:44 +08:00
|
|
|
|
"name_change_df = pd.read_hdf('/mnt/d/PyProject/NewStock/data/name_change.h5', key='name_change')\n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"name_change_df = name_change_df.drop_duplicates(keep='first')\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"# 确保 name_change_df 的日期格式正确\n",
|
|
|
|
|
|
"name_change_df['start_date'] = pd.to_datetime(name_change_df['start_date'], format='%Y%m%d')\n",
|
|
|
|
|
|
"name_change_df['end_date'] = pd.to_datetime(name_change_df['end_date'], format='%Y%m%d', errors='coerce')\n",
|
2025-05-08 15:42:17 +08:00
|
|
|
|
"# name_change_df = name_change_df[name_change_df.name.str.contains('ST') ]\n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"name_change_dict = {}\n",
|
|
|
|
|
|
"for ts_code, group in name_change_df.groupby('ts_code'):\n",
|
|
|
|
|
|
" # 只保留 'ST' 和 '*ST' 的记录\n",
|
2025-05-06 23:42:40 +08:00
|
|
|
|
" # st_data = group[(group['change_reason'] == 'ST') | (group['change_reason'] == '*ST')]\n",
|
2025-05-08 15:42:17 +08:00
|
|
|
|
" st_data = group[(group['name'].str.contains('ST')) | (group['name'].str.contains('退'))]\n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
" if not st_data.empty:\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
" name_change_dict[ts_code] = filter_rows(st_data)"
|
2025-05-06 23:42:40 +08:00
|
|
|
|
]
|
2025-02-12 00:21:33 +08:00
|
|
|
|
},
|
|
|
|
|
|
{
|
2025-02-15 23:33:34 +08:00
|
|
|
|
"cell_type": "code",
|
2025-05-13 15:30:06 +08:00
|
|
|
|
"execution_count": 3,
|
2025-02-15 23:33:34 +08:00
|
|
|
|
"id": "e7f8cce2f80e2f20",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-04-10 23:17:22 +08:00
|
|
|
|
"end_time": "2025-04-09T14:58:09.296046Z",
|
|
|
|
|
|
"start_time": "2025-04-09T14:57:39.339423Z"
|
2025-02-12 00:21:33 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
2025-05-06 23:42:40 +08:00
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
|
"text": [
|
|
|
|
|
|
"<class 'pandas.core.frame.DataFrame'>\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
"Index: 9547667 entries, 0 to 27281\n",
|
2025-05-06 23:42:40 +08:00
|
|
|
|
"Data columns (total 2 columns):\n",
|
|
|
|
|
|
" # Column Dtype \n",
|
|
|
|
|
|
"--- ------ ----- \n",
|
|
|
|
|
|
" 0 ts_code object\n",
|
|
|
|
|
|
" 1 trade_date object\n",
|
|
|
|
|
|
"dtypes: object(2)\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
"memory usage: 218.5+ MB\n",
|
2025-05-06 23:42:40 +08:00
|
|
|
|
"None\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
"20260116\n",
|
|
|
|
|
|
"20260119\n"
|
2025-05-06 23:42:40 +08:00
|
|
|
|
]
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"source": [
|
|
|
|
|
|
"import time\n",
|
|
|
|
|
|
"from concurrent.futures import ThreadPoolExecutor, as_completed\n",
|
|
|
|
|
|
"\n",
|
2025-06-02 22:23:44 +08:00
|
|
|
|
"h5_filename = '/mnt/d/PyProject/NewStock/data/daily_basic.h5'\n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"key = '/daily_basic'\n",
|
|
|
|
|
|
"max_date = None\n",
|
|
|
|
|
|
"with pd.HDFStore(h5_filename, mode='r') as store:\n",
|
|
|
|
|
|
" df = store[key][['ts_code', 'trade_date']]\n",
|
|
|
|
|
|
" print(df.info())\n",
|
|
|
|
|
|
" max_date = df['trade_date'].max()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"print(max_date)\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
"trade_cal = pro.trade_cal(exchange='', start_date='20170101', end_date='20260201')\n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"trade_cal = trade_cal[trade_cal['is_open'] == 1] # 只保留交易日\n",
|
|
|
|
|
|
"trade_dates = trade_cal[trade_cal['cal_date'] > max_date]['cal_date'].tolist()\n",
|
|
|
|
|
|
"start_date = min(trade_dates)\n",
|
|
|
|
|
|
"print(start_date)"
|
2025-05-06 23:42:40 +08:00
|
|
|
|
]
|
2025-04-09 22:57:01 +08:00
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
2025-05-13 15:30:06 +08:00
|
|
|
|
"execution_count": 4,
|
2025-04-09 22:57:01 +08:00
|
|
|
|
"id": "553cfb36-f560-4cc4-b2bc-68323ccc5072",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-04-10 23:17:22 +08:00
|
|
|
|
"end_time": "2025-04-09T14:58:16.817010Z",
|
|
|
|
|
|
"start_time": "2025-04-09T14:58:09.326485Z"
|
2025-05-06 23:42:40 +08:00
|
|
|
|
},
|
|
|
|
|
|
"scrolled": true
|
2025-04-09 22:57:01 +08:00
|
|
|
|
},
|
2025-05-06 23:42:40 +08:00
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
|
"text": [
|
2026-01-27 00:52:35 +08:00
|
|
|
|
"任务 20260130 完成\n",
|
|
|
|
|
|
"任务 20260129 完成\n"
|
|
|
|
|
|
]
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
|
"text": [
|
|
|
|
|
|
"任务 20260127 完成\n",
|
|
|
|
|
|
"任务 20260128 完成\n",
|
|
|
|
|
|
"任务 20260126 完成\n",
|
|
|
|
|
|
"任务 20260123 完成\n",
|
|
|
|
|
|
"任务 20260122 完成\n",
|
|
|
|
|
|
"任务 20260121 完成\n",
|
|
|
|
|
|
"任务 20260120 完成\n",
|
|
|
|
|
|
"任务 20260119 完成\n"
|
2025-05-06 23:42:40 +08:00
|
|
|
|
]
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"source": [
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"# 使用 HDFStore 存储数据\n",
|
|
|
|
|
|
"all_daily_data = []\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"# API 调用计数和时间控制变量\n",
|
|
|
|
|
|
"api_call_count = 0\n",
|
|
|
|
|
|
"batch_start_time = time.time()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def get_data(trade_date):\n",
|
|
|
|
|
|
" daily_basic_data = pro.daily_basic(ts_code='', trade_date=trade_date)\n",
|
|
|
|
|
|
" if daily_basic_data is not None and not daily_basic_data.empty:\n",
|
|
|
|
|
|
" # 添加交易日期列标识\n",
|
|
|
|
|
|
" daily_basic_data['trade_date'] = trade_date\n",
|
|
|
|
|
|
" daily_basic_data['is_st'] = daily_basic_data.apply(\n",
|
|
|
|
|
|
" lambda row: is_st(name_change_dict, row['ts_code'], row['trade_date']), axis=1\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
" time.sleep(0.2)\n",
|
|
|
|
|
|
" # print(f\"成功获取并保存 {trade_date} 的每日基础数据\")\n",
|
|
|
|
|
|
" return daily_basic_data\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"# 遍历每个交易日期并获取数据\n",
|
|
|
|
|
|
"with ThreadPoolExecutor(max_workers=2) as executor:\n",
|
|
|
|
|
|
" future_to_date = {executor.submit(get_data, td): td for td in trade_dates}\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" for future in as_completed(future_to_date):\n",
|
|
|
|
|
|
" trade_date = future_to_date[future] # 获取对应的交易日期\n",
|
|
|
|
|
|
" try:\n",
|
|
|
|
|
|
" result = future.result() # 获取任务执行的结果\n",
|
|
|
|
|
|
" all_daily_data.append(result)\n",
|
|
|
|
|
|
" print(f\"任务 {trade_date} 完成\")\n",
|
|
|
|
|
|
" except Exception as e:\n",
|
|
|
|
|
|
" print(f\"获取 {trade_date} 数据时出错: {e}\")\n",
|
|
|
|
|
|
" # 计数一次 API 调用\n",
|
|
|
|
|
|
" api_call_count += 1\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 每调用 300 次，检查时间是否少于 1 分钟，如果少于则等待剩余时间\n",
|
|
|
|
|
|
" if api_call_count % 150 == 0:\n",
|
|
|
|
|
|
" elapsed = time.time() - batch_start_time\n",
|
|
|
|
|
|
" if elapsed < 60:\n",
|
|
|
|
|
|
" sleep_time = 60 - elapsed\n",
|
|
|
|
|
|
" print(f\"已调用 150 次 API，等待 {sleep_time:.2f} 秒以满足速率限制...\")\n",
|
|
|
|
|
|
" time.sleep(sleep_time)\n",
|
|
|
|
|
|
" # 重置批次起始时间\n",
|
|
|
|
|
|
" batch_start_time = time.time()\n",
|
|
|
|
|
|
"\n"
|
2025-05-06 23:42:40 +08:00
|
|
|
|
]
|
2025-02-12 00:21:33 +08:00
|
|
|
|
},
|
|
|
|
|
|
{
|
2025-02-15 23:33:34 +08:00
|
|
|
|
"cell_type": "code",
|
2025-05-13 15:30:06 +08:00
|
|
|
|
"execution_count": 5,
|
2025-02-15 23:33:34 +08:00
|
|
|
|
"id": "919023c693d7a47a",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-04-10 23:17:22 +08:00
|
|
|
|
"end_time": "2025-04-09T14:58:16.864178Z",
|
|
|
|
|
|
"start_time": "2025-04-09T14:58:16.855084Z"
|
2025-02-12 00:21:33 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
|
"text": [
|
2026-01-27 00:52:35 +08:00
|
|
|
|
" ts_code trade_date close turnover_rate turnover_rate_f \\\n",
|
|
|
|
|
|
"0 301586.SZ 20260123 52.80 4.4195 6.0484 \n",
|
|
|
|
|
|
"1 600871.SH 20260123 2.63 3.5599 17.1067 \n",
|
|
|
|
|
|
"2 002067.SZ 20260123 5.91 9.5542 9.8833 \n",
|
|
|
|
|
|
"3 601225.SH 20260123 21.41 0.4692 1.3502 \n",
|
|
|
|
|
|
"4 688800.SH 20260123 90.22 4.3421 7.2546 \n",
|
|
|
|
|
|
"... ... ... ... ... ... \n",
|
|
|
|
|
|
"27321 688659.SH 20260119 10.42 1.7256 3.1386 \n",
|
|
|
|
|
|
"27322 301021.SZ 20260119 55.92 5.8451 10.3979 \n",
|
|
|
|
|
|
"27323 300102.SZ 20260119 34.23 14.1090 22.0304 \n",
|
|
|
|
|
|
"27324 300088.SZ 20260119 6.36 1.9148 2.3308 \n",
|
|
|
|
|
|
"27325 002261.SZ 20260119 33.77 4.6567 5.1897 \n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
" volume_ratio pe pe_ttm pb ps ps_ttm dv_ratio \\\n",
|
|
|
|
|
|
"0 0.98 43.6343 68.1615 3.4308 6.9893 5.8003 0.9091 \n",
|
|
|
|
|
|
"1 1.91 78.9369 79.8327 5.2226 0.6148 0.6127 NaN \n",
|
|
|
|
|
|
"2 0.80 122.3105 140.3743 1.3170 1.5908 1.5491 NaN \n",
|
|
|
|
|
|
"3 1.02 9.2832 10.8507 2.1981 1.1272 1.1740 5.9699 \n",
|
|
|
|
|
|
"4 0.79 105.8709 61.3816 8.0916 7.6847 5.8974 0.2971 \n",
|
|
|
|
|
|
"... ... ... ... ... ... ... ... \n",
|
|
|
|
|
|
"27321 1.01 NaN NaN 3.1071 2.6478 2.4387 NaN \n",
|
|
|
|
|
|
"27322 0.72 391.5181 198.4990 8.4757 19.1357 17.1491 0.1772 \n",
|
|
|
|
|
|
"27323 0.69 327.8681 232.9793 7.4375 12.9485 9.5346 0.1313 \n",
|
|
|
|
|
|
"27324 0.52 44.5231 45.4726 1.8179 1.4366 1.3961 0.9198 \n",
|
|
|
|
|
|
"27325 0.38 NaN NaN 16.3185 10.3586 13.1287 NaN \n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
" dv_ttm total_share float_share free_share total_mv \\\n",
|
|
|
|
|
|
"0 0.3788 8.297550e+03 5.291107e+03 3866.1069 4.381107e+05 \n",
|
|
|
|
|
|
"1 NaN 1.895705e+06 1.354701e+06 281911.5987 4.985703e+06 \n",
|
|
|
|
|
|
"2 NaN 1.474854e+05 1.337604e+05 129305.3853 8.716386e+05 \n",
|
|
|
|
|
|
"3 5.4881 9.695000e+05 9.695000e+05 336903.9335 2.075700e+07 \n",
|
|
|
|
|
|
"4 0.2971 2.056743e+04 2.056743e+04 12310.0935 1.855594e+06 \n",
|
|
|
|
|
|
"... ... ... ... ... ... \n",
|
|
|
|
|
|
"27321 NaN 1.600000e+04 1.600000e+04 8796.6880 1.667200e+05 \n",
|
|
|
|
|
|
"27322 0.1772 1.528528e+04 1.527393e+04 8586.0802 8.547528e+05 \n",
|
|
|
|
|
|
"27323 0.1313 9.203339e+04 9.163399e+04 58685.2206 3.150303e+06 \n",
|
|
|
|
|
|
"27324 0.9198 2.497734e+05 2.485504e+05 204186.7350 1.588559e+06 \n",
|
|
|
|
|
|
"27325 NaN 1.259831e+05 1.145652e+05 102798.2760 4.254451e+06 \n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
" circ_mv is_st \n",
|
|
|
|
|
|
"0 2.793704e+05 False \n",
|
|
|
|
|
|
"1 3.562864e+06 False \n",
|
|
|
|
|
|
"2 7.905239e+05 False \n",
|
|
|
|
|
|
"3 2.075700e+07 False \n",
|
|
|
|
|
|
"4 1.855594e+06 False \n",
|
|
|
|
|
|
"... ... ... \n",
|
|
|
|
|
|
"27321 1.667200e+05 False \n",
|
|
|
|
|
|
"27322 8.541180e+05 False \n",
|
|
|
|
|
|
"27323 3.136631e+06 False \n",
|
|
|
|
|
|
"27324 1.580780e+06 False \n",
|
|
|
|
|
|
"27325 3.868868e+06 False \n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
"[27326 rows x 19 columns]\n"
|
2025-02-12 00:21:33 +08:00
|
|
|
|
]
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
2025-05-06 23:42:40 +08:00
|
|
|
|
"source": [
|
|
|
|
|
|
"all_daily_data_df = pd.concat(all_daily_data, ignore_index=True)\n",
|
|
|
|
|
|
"print(all_daily_data_df)"
|
|
|
|
|
|
]
|
2025-02-12 00:21:33 +08:00
|
|
|
|
},
|
|
|
|
|
|
{
|
2025-02-15 23:33:34 +08:00
|
|
|
|
"cell_type": "code",
|
2025-05-13 15:30:06 +08:00
|
|
|
|
"execution_count": 6,
|
2025-02-15 23:33:34 +08:00
|
|
|
|
"id": "28cb78d032671b20",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-04-10 23:17:22 +08:00
|
|
|
|
"end_time": "2025-04-09T14:58:16.881685Z",
|
|
|
|
|
|
"start_time": "2025-04-09T14:58:16.871184Z"
|
2025-02-12 00:21:33 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
|
"text": [
|
2026-01-27 00:52:35 +08:00
|
|
|
|
" ts_code trade_date close turnover_rate turnover_rate_f \\\n",
|
|
|
|
|
|
"54 000615.SZ 20260123 3.32 0.7420 0.9114 \n",
|
|
|
|
|
|
"60 600228.SH 20260123 5.63 3.4275 4.8943 \n",
|
|
|
|
|
|
"88 000430.SZ 20260123 7.30 1.4748 2.3665 \n",
|
|
|
|
|
|
"96 603389.SH 20260123 48.20 0.8319 2.1042 \n",
|
|
|
|
|
|
"110 000752.SZ 20260123 10.96 1.4753 1.8177 \n",
|
|
|
|
|
|
"... ... ... ... ... ... \n",
|
|
|
|
|
|
"27130 002586.SZ 20260119 4.68 1.7164 2.9874 \n",
|
|
|
|
|
|
"27154 600265.SH 20260119 19.29 0.2879 0.8066 \n",
|
|
|
|
|
|
"27193 688287.SH 20260119 6.44 0.9802 1.9881 \n",
|
|
|
|
|
|
"27195 300338.SZ 20260119 3.61 1.4127 1.5675 \n",
|
|
|
|
|
|
"27223 000669.SZ 20260119 2.79 1.1437 1.4424 \n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
" volume_ratio pe pe_ttm pb ps ps_ttm dv_ratio \\\n",
|
|
|
|
|
|
"54 0.72 NaN NaN NaN 5.4217 5.8063 NaN \n",
|
|
|
|
|
|
"60 1.60 NaN NaN 5.6813 9.6204 6.3997 NaN \n",
|
|
|
|
|
|
"88 1.11 NaN NaN 22.0731 13.6938 12.9047 NaN \n",
|
|
|
|
|
|
"96 0.95 NaN NaN 54.1434 62.5718 60.6578 NaN \n",
|
|
|
|
|
|
"110 0.96 110.3513 19.6504 4.7026 6.8589 6.4652 NaN \n",
|
|
|
|
|
|
"... ... ... ... ... ... ... ... \n",
|
|
|
|
|
|
"27130 1.55 NaN NaN 1.7970 2.1568 2.2158 NaN \n",
|
|
|
|
|
|
"27154 0.79 NaN NaN 288.1848 5.6010 10.1170 NaN \n",
|
|
|
|
|
|
"27193 0.59 NaN NaN 3.1120 26.5172 26.3673 NaN \n",
|
|
|
|
|
|
"27195 0.58 NaN NaN NaN 8.5110 10.1280 NaN \n",
|
|
|
|
|
|
"27223 0.84 NaN NaN NaN 1.4522 1.5001 NaN \n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
" dv_ttm total_share float_share free_share total_mv \\\n",
|
|
|
|
|
|
"54 NaN 178749.2693 92531.6398 75331.7788 5.934476e+05 \n",
|
|
|
|
|
|
"60 NaN 41667.2427 41603.7177 29135.5053 2.345866e+05 \n",
|
|
|
|
|
|
"88 NaN 80963.5372 37055.6486 23092.8156 5.910338e+05 \n",
|
|
|
|
|
|
"96 NaN 26275.2000 26275.2000 10387.7487 1.266465e+06 \n",
|
|
|
|
|
|
"110 NaN 26375.8491 26375.8491 21407.3042 2.890793e+05 \n",
|
|
|
|
|
|
"... ... ... ... ... ... \n",
|
|
|
|
|
|
"27130 NaN 114422.3714 108751.8003 62484.0799 5.354967e+05 \n",
|
|
|
|
|
|
"27154 NaN 12980.0000 12980.0000 4633.1947 2.503842e+05 \n",
|
|
|
|
|
|
"27193 NaN 37051.5600 37051.5600 18267.2898 2.386120e+05 \n",
|
|
|
|
|
|
"27195 NaN 40262.4692 34936.1242 31485.3582 1.453475e+05 \n",
|
|
|
|
|
|
"27223 NaN 68040.8797 68040.8797 53950.9653 1.898341e+05 \n",
|
2025-06-02 22:23:44 +08:00
|
|
|
|
"\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
" circ_mv is_st \n",
|
|
|
|
|
|
"54 3.072050e+05 True \n",
|
|
|
|
|
|
"60 2.342289e+05 True \n",
|
|
|
|
|
|
"88 2.705062e+05 True \n",
|
|
|
|
|
|
"96 1.266465e+06 True \n",
|
|
|
|
|
|
"110 2.890793e+05 True \n",
|
|
|
|
|
|
"... ... ... \n",
|
|
|
|
|
|
"27130 5.089584e+05 True \n",
|
|
|
|
|
|
"27154 2.503842e+05 True \n",
|
|
|
|
|
|
"27193 2.386120e+05 True \n",
|
|
|
|
|
|
"27195 1.261194e+05 True \n",
|
|
|
|
|
|
"27223 1.898341e+05 True \n",
|
2025-11-29 00:23:12 +08:00
|
|
|
|
"\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
"[886 rows x 19 columns]\n"
|
2025-02-12 00:21:33 +08:00
|
|
|
|
]
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
2025-05-06 23:42:40 +08:00
|
|
|
|
"source": [
|
|
|
|
|
|
"print(all_daily_data_df[all_daily_data_df['is_st']])"
|
|
|
|
|
|
]
|
2025-02-12 00:21:33 +08:00
|
|
|
|
},
|
|
|
|
|
|
{
|
2025-02-15 23:33:34 +08:00
|
|
|
|
"cell_type": "code",
|
2025-05-13 15:30:06 +08:00
|
|
|
|
"execution_count": 7,
|
2025-02-15 23:33:34 +08:00
|
|
|
|
"id": "692b58674b7462c9",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-04-10 23:17:22 +08:00
|
|
|
|
"end_time": "2025-04-09T14:58:17.773453Z",
|
|
|
|
|
|
"start_time": "2025-04-09T14:58:16.903459Z"
|
2025-02-12 00:21:33 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
|
"text": [
|
|
|
|
|
|
"所有每日基础数据获取并保存完毕！\n"
|
|
|
|
|
|
]
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
2025-05-06 23:42:40 +08:00
|
|
|
|
"source": [
|
|
|
|
|
|
"# 将数据保存为 HDF5 文件（table 格式）\n",
|
|
|
|
|
|
"all_daily_data_df.to_hdf(h5_filename, key='daily_basic', mode='a', format='table', append=True, data_columns=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"print(\"所有每日基础数据获取并保存完毕！\")\n"
|
|
|
|
|
|
]
|
2025-02-12 00:21:33 +08:00
|
|
|
|
},
|
|
|
|
|
|
{
|
2025-02-15 23:33:34 +08:00
|
|
|
|
"cell_type": "code",
|
2025-05-13 15:30:06 +08:00
|
|
|
|
"execution_count": 8,
|
2025-02-15 23:33:34 +08:00
|
|
|
|
"id": "d7a773fc20293477",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-04-10 23:17:22 +08:00
|
|
|
|
"end_time": "2025-04-09T14:58:24.305403Z",
|
|
|
|
|
|
"start_time": "2025-04-09T14:58:17.816332Z"
|
2025-02-12 00:21:33 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
|
"text": [
|
|
|
|
|
|
"<class 'pandas.core.frame.DataFrame'>\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
"Index: 9574993 entries, 0 to 27325\n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"Data columns (total 3 columns):\n",
|
|
|
|
|
|
" # Column Dtype \n",
|
|
|
|
|
|
"--- ------ ----- \n",
|
|
|
|
|
|
" 0 ts_code object\n",
|
|
|
|
|
|
" 1 trade_date object\n",
|
|
|
|
|
|
" 2 is_st bool \n",
|
|
|
|
|
|
"dtypes: bool(1), object(2)\n",
|
2026-01-27 00:52:35 +08:00
|
|
|
|
"memory usage: 228.3+ MB\n",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"None\n"
|
|
|
|
|
|
]
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
2025-05-06 23:42:40 +08:00
|
|
|
|
"source": [
|
|
|
|
|
|
"with pd.HDFStore(h5_filename, mode='r') as store:\n",
|
|
|
|
|
|
" df = store[key][['ts_code', 'trade_date', 'is_st']]\n",
|
|
|
|
|
|
" print(df.info())"
|
|
|
|
|
|
]
|
2025-02-12 00:21:33 +08:00
|
|
|
|
}
|
|
|
|
|
|
],
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"kernelspec": {
|
2025-06-02 22:23:44 +08:00
|
|
|
|
"display_name": "stock",
|
2025-02-12 00:21:33 +08:00
|
|
|
|
"language": "python",
|
|
|
|
|
|
"name": "python3"
|
|
|
|
|
|
},
|
|
|
|
|
|
"language_info": {
|
|
|
|
|
|
"codemirror_mode": {
|
|
|
|
|
|
"name": "ipython",
|
|
|
|
|
|
"version": 3
|
|
|
|
|
|
},
|
|
|
|
|
|
"file_extension": ".py",
|
|
|
|
|
|
"mimetype": "text/x-python",
|
|
|
|
|
|
"name": "python",
|
|
|
|
|
|
"nbconvert_exporter": "python",
|
|
|
|
|
|
"pygments_lexer": "ipython3",
|
2025-11-29 00:23:12 +08:00
|
|
|
|
"version": "3.12.11"
|
2025-02-12 00:21:33 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"nbformat": 4,
|
|
|
|
|
|
"nbformat_minor": 5
|
|
|
|
|
|
}
|
