475 lines
18 KiB
Plaintext
475 lines
18 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"id": "18d1d622-b083-4cc4-a6f8-7c1ed2d0edd2",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-09T14:57:36.913044Z",
|
||
"start_time": "2025-04-09T14:57:36.159612Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import tushare as ts\n",
|
||
"ts.set_token('3a0741c702ee7e5e5f2bf1f0846bafaafe4e320833240b2a7e4a685f')\n",
|
||
"pro = ts.pro_api()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"id": "14671a7f72de2564",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-09T14:57:39.128278Z",
|
||
"start_time": "2025-04-09T14:57:36.918051Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"from datetime import datetime\n",
|
||
"import pandas as pd\n",
|
||
"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",
|
||
"\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",
|
||
"name_change_df = pd.read_hdf('/mnt/d/PyProject/NewStock/data/name_change.h5', key='name_change')\n",
|
||
"name_change_df = name_change_df.drop_duplicates(keep='first')\n",
|
||
"\n",
|
||
"# 确保 name_change_df 的日期格式正确\n",
|
||
"name_change_df['start_date'] = pd.to_datetime(name_change_df['start_date'], format='%Y%m%d')\n",
|
||
"name_change_df['end_date'] = pd.to_datetime(name_change_df['end_date'], format='%Y%m%d', errors='coerce')\n",
|
||
"# name_change_df = name_change_df[name_change_df.name.str.contains('ST') ]\n",
|
||
"name_change_dict = {}\n",
|
||
"for ts_code, group in name_change_df.groupby('ts_code'):\n",
|
||
" # 只保留 'ST' 和 '*ST' 的记录\n",
|
||
" # st_data = group[(group['change_reason'] == 'ST') | (group['change_reason'] == '*ST')]\n",
|
||
" st_data = group[(group['name'].str.contains('ST')) | (group['name'].str.contains('退'))]\n",
|
||
" if not st_data.empty:\n",
|
||
" name_change_dict[ts_code] = filter_rows(st_data)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"id": "e7f8cce2f80e2f20",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-09T14:58:09.296046Z",
|
||
"start_time": "2025-04-09T14:57:39.339423Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"<class 'pandas.core.frame.DataFrame'>\n",
|
||
"Index: 8674588 entries, 0 to 26945\n",
|
||
"Data columns (total 2 columns):\n",
|
||
" # Column Dtype \n",
|
||
"--- ------ ----- \n",
|
||
" 0 ts_code object\n",
|
||
" 1 trade_date object\n",
|
||
"dtypes: object(2)\n",
|
||
"memory usage: 198.5+ MB\n",
|
||
"None\n",
|
||
"20250523\n",
|
||
"20250526\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import time\n",
|
||
"from concurrent.futures import ThreadPoolExecutor, as_completed\n",
|
||
"\n",
|
||
"h5_filename = '/mnt/d/PyProject/NewStock/data/daily_basic.h5'\n",
|
||
"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",
|
||
"trade_cal = pro.trade_cal(exchange='', start_date='20170101', end_date='20250720')\n",
|
||
"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)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"id": "553cfb36-f560-4cc4-b2bc-68323ccc5072",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-09T14:58:16.817010Z",
|
||
"start_time": "2025-04-09T14:58:09.326485Z"
|
||
},
|
||
"scrolled": true
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"任务 20250718 完成\n",
|
||
"任务 20250717 完成\n",
|
||
"任务 20250716 完成\n",
|
||
"任务 20250715 完成\n",
|
||
"任务 20250714 完成\n",
|
||
"任务 20250711 完成\n",
|
||
"任务 20250709 完成\n",
|
||
"任务 20250710 完成\n",
|
||
"任务 20250708 完成\n",
|
||
"任务 20250707 完成\n",
|
||
"任务 20250704 完成\n",
|
||
"任务 20250703 完成\n",
|
||
"任务 20250702 完成\n",
|
||
"任务 20250701 完成\n",
|
||
"任务 20250630 完成\n",
|
||
"任务 20250627 完成\n",
|
||
"任务 20250626 完成\n",
|
||
"任务 20250625 完成\n",
|
||
"任务 20250624 完成\n",
|
||
"任务 20250623 完成\n",
|
||
"任务 20250620 完成\n",
|
||
"任务 20250619 完成\n",
|
||
"任务 20250618 完成\n",
|
||
"任务 20250617 完成\n",
|
||
"任务 20250616 完成\n",
|
||
"任务 20250613 完成\n",
|
||
"任务 20250612 完成\n",
|
||
"任务 20250611 完成\n",
|
||
"任务 20250610 完成\n",
|
||
"任务 20250609 完成\n",
|
||
"任务 20250606 完成\n",
|
||
"任务 20250605 完成\n",
|
||
"任务 20250603 完成\n",
|
||
"任务 20250604 完成\n",
|
||
"任务 20250530 完成\n",
|
||
"任务 20250529 完成\n",
|
||
"任务 20250528 完成\n",
|
||
"任务 20250527 完成\n",
|
||
"任务 20250526 完成\n"
|
||
]
|
||
}
|
||
],
|
||
"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"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"id": "919023c693d7a47a",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-09T14:58:16.864178Z",
|
||
"start_time": "2025-04-09T14:58:16.855084Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" ts_code trade_date close turnover_rate turnover_rate_f \\\n",
|
||
"0 603990.SH 20250530 14.96 3.7919 4.9168 \n",
|
||
"1 603666.SH 20250530 33.72 2.4954 4.7137 \n",
|
||
"2 001339.SZ 20250530 45.78 7.0710 7.0710 \n",
|
||
"3 002006.SZ 20250530 16.67 2.4368 3.4806 \n",
|
||
"4 603353.SH 20250530 15.21 1.3567 4.1316 \n",
|
||
"... ... ... ... ... ... \n",
|
||
"26918 002670.SZ 20250526 11.86 0.7662 2.3092 \n",
|
||
"26919 839946.BJ 20250526 9.67 4.8520 6.8863 \n",
|
||
"26920 688076.SH 20250526 49.59 5.9483 9.5054 \n",
|
||
"26921 300519.SZ 20250526 14.44 2.4601 3.8976 \n",
|
||
"26922 300468.SZ 20250526 18.15 6.8275 8.8410 \n",
|
||
"\n",
|
||
" volume_ratio pe pe_ttm pb ps ps_ttm \\\n",
|
||
"0 0.65 NaN NaN 5.5665 9.8735 11.0137 \n",
|
||
"1 1.15 NaN NaN 3.2133 11.8990 10.3525 \n",
|
||
"2 1.22 91.7742 74.3709 5.3909 2.8419 2.7478 \n",
|
||
"3 0.81 58.9666 65.5384 3.6508 5.0124 5.4591 \n",
|
||
"4 1.10 90.1163 80.8019 1.5917 0.9380 0.9517 \n",
|
||
"... ... ... ... ... ... ... \n",
|
||
"26918 0.75 137.0866 106.8454 2.0610 15093.0115 14821.3328 \n",
|
||
"26919 0.55 NaN NaN 5.7695 2.5489 2.4978 \n",
|
||
"26920 3.15 27.5757 22.7263 3.7628 6.8632 6.0784 \n",
|
||
"26921 1.14 45.8504 44.3443 2.7022 8.6318 8.8737 \n",
|
||
"26922 1.08 142.9746 150.8960 5.8350 13.0086 13.6702 \n",
|
||
"\n",
|
||
" dv_ratio dv_ttm total_share float_share free_share total_mv \\\n",
|
||
"0 0.0000 NaN 30628.2731 30628.2731 23620.5583 4.581990e+05 \n",
|
||
"1 0.0000 NaN 20649.0816 20649.0816 10931.3716 6.962870e+05 \n",
|
||
"2 0.2622 0.3498 25042.9670 7313.0995 7313.0995 1.146467e+06 \n",
|
||
"3 0.7749 0.7749 51979.3440 45516.0000 31865.7600 8.664957e+05 \n",
|
||
"4 0.6462 1.3036 17339.4000 17041.8000 5596.0000 2.637323e+05 \n",
|
||
"... ... ... ... ... ... ... \n",
|
||
"26918 0.0000 NaN 193508.4653 162335.0634 53860.6790 2.295010e+06 \n",
|
||
"26919 NaN NaN 13499.0443 9702.8595 6836.5574 1.305358e+05 \n",
|
||
"26920 NaN NaN 22487.0915 22487.0915 14071.9565 1.115135e+06 \n",
|
||
"26921 2.7701 2.7701 16000.0000 11410.0000 7201.9100 2.310400e+05 \n",
|
||
"26922 0.3306 0.3306 53064.9275 52979.4065 40913.5262 9.631284e+05 \n",
|
||
"\n",
|
||
" circ_mv is_st \n",
|
||
"0 4.581990e+05 False \n",
|
||
"1 6.962870e+05 False \n",
|
||
"2 3.347937e+05 False \n",
|
||
"3 7.587517e+05 False \n",
|
||
"4 2.592058e+05 False \n",
|
||
"... ... ... \n",
|
||
"26918 1.925294e+06 False \n",
|
||
"26919 9.382665e+04 False \n",
|
||
"26920 1.115135e+06 False \n",
|
||
"26921 1.647604e+05 False \n",
|
||
"26922 9.615762e+05 False \n",
|
||
"\n",
|
||
"[26923 rows x 19 columns]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"all_daily_data_df = pd.concat(all_daily_data, ignore_index=True)\n",
|
||
"print(all_daily_data_df)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"id": "28cb78d032671b20",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-09T14:58:16.881685Z",
|
||
"start_time": "2025-04-09T14:58:16.871184Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" ts_code trade_date close turnover_rate turnover_rate_f \\\n",
|
||
"16 300536.SZ 20250530 8.67 2.8854 3.5632 \n",
|
||
"78 000668.SZ 20250530 7.94 4.1498 7.0226 \n",
|
||
"112 002231.SZ 20250530 3.28 8.9944 10.0552 \n",
|
||
"147 300313.SZ 20250530 6.28 6.0110 12.4720 \n",
|
||
"158 603838.SH 20250530 5.73 0.9777 2.6542 \n",
|
||
"... ... ... ... ... ... \n",
|
||
"26733 603828.SH 20250526 4.98 0.9734 1.9562 \n",
|
||
"26751 600599.SH 20250526 7.46 2.5125 6.3118 \n",
|
||
"26785 000820.SZ 20250526 3.02 13.6997 14.0750 \n",
|
||
"26885 002005.SZ 20250526 1.77 0.3214 0.5145 \n",
|
||
"26905 603869.SH 20250526 6.15 0.3000 0.7946 \n",
|
||
"\n",
|
||
" volume_ratio pe pe_ttm pb ps ps_ttm dv_ratio \\\n",
|
||
"16 0.55 NaN NaN 4.9112 10.9775 12.1174 0.0 \n",
|
||
"78 1.07 NaN NaN 1.6212 8.7361 5.6924 0.0 \n",
|
||
"112 0.74 NaN NaN 4.3227 3.9056 5.3690 0.0 \n",
|
||
"147 0.92 NaN NaN NaN 14.2840 13.5826 0.0 \n",
|
||
"158 1.06 NaN NaN 1.9039 6.4291 5.8279 0.0 \n",
|
||
"... ... ... ... ... ... ... ... \n",
|
||
"26733 0.56 345.783 1670.8958 3.9261 1.2065 1.3013 0.0 \n",
|
||
"26751 0.68 NaN NaN 11.2319 3.8238 3.9211 0.0 \n",
|
||
"26785 2.40 NaN NaN 12.4588 15.8309 20.1399 0.0 \n",
|
||
"26885 0.48 NaN NaN 15.9120 4.2066 4.2221 0.0 \n",
|
||
"26905 1.00 149.594 167.2545 0.8344 4.6640 5.0668 0.0 \n",
|
||
"\n",
|
||
" dv_ttm total_share float_share free_share total_mv \\\n",
|
||
"16 NaN 29328.8133 29325.3240 23747.3240 254280.8113 \n",
|
||
"78 NaN 14684.1890 14684.1890 8677.2104 116592.4607 \n",
|
||
"112 NaN 34685.0017 29481.8767 26371.6067 113766.8056 \n",
|
||
"147 NaN 31297.7396 19735.2789 9511.5479 196549.8047 \n",
|
||
"158 NaN 32001.6000 32001.6000 11788.1468 183369.1680 \n",
|
||
"... ... ... ... ... ... \n",
|
||
"26733 NaN 59596.0158 59593.9625 29654.2988 296788.1587 \n",
|
||
"26751 NaN 16600.0000 16600.0000 6607.7948 123836.0000 \n",
|
||
"26785 NaN 64655.5179 29696.6877 28904.9696 195259.6641 \n",
|
||
"26885 NaN 175242.4858 175199.3158 109452.0915 310179.1999 \n",
|
||
"26905 NaN 50450.0508 50450.0508 19045.9689 310267.8124 \n",
|
||
"\n",
|
||
" circ_mv is_st \n",
|
||
"16 254250.5591 True \n",
|
||
"78 116592.4607 True \n",
|
||
"112 96700.5556 True \n",
|
||
"147 123937.5515 True \n",
|
||
"158 183369.1680 True \n",
|
||
"... ... ... \n",
|
||
"26733 296777.9333 True \n",
|
||
"26751 123836.0000 True \n",
|
||
"26785 89683.9969 True \n",
|
||
"26885 310102.7890 True \n",
|
||
"26905 310267.8124 True \n",
|
||
"\n",
|
||
"[944 rows x 19 columns]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"print(all_daily_data_df[all_daily_data_df['is_st']])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"id": "692b58674b7462c9",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-09T14:58:17.773453Z",
|
||
"start_time": "2025-04-09T14:58:16.903459Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"所有每日基础数据获取并保存完毕！\n"
|
||
]
|
||
}
|
||
],
|
||
"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"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"id": "d7a773fc20293477",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-09T14:58:24.305403Z",
|
||
"start_time": "2025-04-09T14:58:17.816332Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"<class 'pandas.core.frame.DataFrame'>\n",
|
||
"Index: 8701511 entries, 0 to 26922\n",
|
||
"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",
|
||
"memory usage: 207.5+ MB\n",
|
||
"None\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"with pd.HDFStore(h5_filename, mode='r') as store:\n",
|
||
" df = store[key][['ts_code', 'trade_date', 'is_st']]\n",
|
||
" print(df.info())"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "stock",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.13.2"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|