liaozhaorun/NewStock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

更新 .gitignore

Browse Source
This commit is contained in:
liaozhaorun
2025-10-13 21:41:50 +08:00
parent fdee45bda0
commit 6016f2c059
4 changed files with 332 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@@ -18,3 +18,4 @@ model
!.gitignore
!.git
!/.vscode

2
dev.env
View File

@@ -1,2 +0,0 @@
WORKSPACE_FOLDER=/mnt/d/PyProject/NewStock/main
PYTHONPATH=${workspaceFolder}/main:${PYTHONPATH}

155
main/train/Classify2.ipynb
View File

@@ -18,7 +18,20 @@
"name": "stdout",
"output_type": "stream",
"text": [
"/mnt/d/PyProject/NewStock\n"
"The autoreload extension is already loaded. To reload it, use:\n",
" %reload_ext autoreload\n",
"/mnt/d/PyProject/NewStock/main/train\n"
]
},
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'main.factor'; 'main' is not a package",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mModuleNotFoundError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[2]\u001b[39m\u001b[32m, line 15\u001b[39m\n\u001b[32m 13\u001b[39m \u001b[38;5;28mprint\u001b[39m(os.getcwd())\n\u001b[32m 14\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mpandas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mpd\u001b[39;00m\n\u001b[32m---> \u001b[39m\u001b[32m15\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mmain\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mfactor\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mfactor\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m get_rolling_factor, get_simple_factor\n\u001b[32m 16\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mmain\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mutils\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mfactor\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m read_industry_data\n\u001b[32m 17\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mmain\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mutils\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mfactor_processor\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m calculate_score\n",
"\u001b[31mModuleNotFoundError\u001b[39m: No module named 'main.factor'; 'main' is not a package"
]
}
],
@@ -31,6 +44,10 @@
"import os\n",
"import sys\n",
"sys.path.append('/mnt/d/PyProject/NewStock/')\n",
"import sys\n",
"sys.path.append('/mnt/d/PyProject/NewStock/main/')\n",
"import sys\n",
"sys.path.append('/mnt/d/PyProject/NewStock/train')\n",
"print(os.getcwd())\n",
"import pandas as pd\n",
"from main.factor.factor import get_rolling_factor, get_simple_factor\n",
@@ -45,7 +62,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"id": "4a481c60",
"metadata": {},
"outputs": [],
@@ -57,7 +74,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": null,
"id": "a79cafb06a7e0e43",
"metadata": {
"ExecuteTime": {
@@ -71,56 +88,30 @@
"name": "stdout",
"output_type": "stream",
"text": [
"daily data\n",
"daily basic\n",
"inner merge on ['ts_code', 'trade_date']\n",
"stk limit\n",
"left merge on ['ts_code', 'trade_date']\n",
"money flow\n",
"left merge on ['ts_code', 'trade_date']\n",
"cyq perf\n",
"left merge on ['ts_code', 'trade_date']\n",
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 8820754 entries, 0 to 8820753\n",
"Data columns (total 33 columns):\n",
" # Column Dtype \n",
"--- ------ ----- \n",
" 0 ts_code object \n",
" 1 trade_date datetime64[ns]\n",
" 2 open float64 \n",
" 3 close float64 \n",
" 4 high float64 \n",
" 5 low float64 \n",
" 6 vol float64 \n",
" 7 amount float64 \n",
" 8 pct_chg float64 \n",
" 9 turnover_rate float64 \n",
" 10 pe_ttm float64 \n",
" 11 circ_mv float64 \n",
" 12 total_mv float64 \n",
" 13 volume_ratio float64 \n",
" 14 is_st bool \n",
" 15 up_limit float64 \n",
" 16 down_limit float64 \n",
" 17 buy_sm_vol float64 \n",
" 18 sell_sm_vol float64 \n",
" 19 buy_lg_vol float64 \n",
" 20 sell_lg_vol float64 \n",
" 21 buy_elg_vol float64 \n",
" 22 sell_elg_vol float64 \n",
" 23 net_mf_vol float64 \n",
" 24 his_low float64 \n",
" 25 his_high float64 \n",
" 26 cost_5pct float64 \n",
" 27 cost_15pct float64 \n",
" 28 cost_50pct float64 \n",
" 29 cost_85pct float64 \n",
" 30 cost_95pct float64 \n",
" 31 weight_avg float64 \n",
" 32 winner_rate float64 \n",
"dtypes: bool(1), datetime64[ns](1), float64(30), object(1)\n",
"memory usage: 2.1+ GB\n",
"None\n"
"daily data\n"
]
},
{
"ename": "ImportError",
"evalue": "Missing optional dependency 'pytables'. Use pip or conda to install pytables.",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mModuleNotFoundError\u001b[39m Traceback (most recent call last)",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/quant/lib/python3.12/site-packages/pandas/compat/_optional.py:135\u001b[39m, in \u001b[36mimport_optional_dependency\u001b[39m\u001b[34m(name, extra, errors, min_version)\u001b[39m\n\u001b[32m 134\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m135\u001b[39m module = \u001b[43mimportlib\u001b[49m\u001b[43m.\u001b[49m\u001b[43mimport_module\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 136\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m:\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/quant/lib/python3.12/importlib/__init__.py:90\u001b[39m, in \u001b[36mimport_module\u001b[39m\u001b[34m(name, package)\u001b[39m\n\u001b[32m 89\u001b[39m level += \u001b[32m1\u001b[39m\n\u001b[32m---> \u001b[39m\u001b[32m90\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_bootstrap\u001b[49m\u001b[43m.\u001b[49m\u001b[43m_gcd_import\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname\u001b[49m\u001b[43m[\u001b[49m\u001b[43mlevel\u001b[49m\u001b[43m:\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpackage\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlevel\u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[36mFile \u001b[39m\u001b[32m<frozen importlib._bootstrap>:1387\u001b[39m, in \u001b[36m_gcd_import\u001b[39m\u001b[34m(name, package, level)\u001b[39m\n",
"\u001b[36mFile \u001b[39m\u001b[32m<frozen importlib._bootstrap>:1360\u001b[39m, in \u001b[36m_find_and_load\u001b[39m\u001b[34m(name, import_)\u001b[39m\n",
"\u001b[36mFile \u001b[39m\u001b[32m<frozen importlib._bootstrap>:1324\u001b[39m, in \u001b[36m_find_and_load_unlocked\u001b[39m\u001b[34m(name, import_)\u001b[39m\n",
"\u001b[31mModuleNotFoundError\u001b[39m: No module named 'tables'",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001b[31mImportError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[3]\u001b[39m\u001b[32m, line 4\u001b[39m\n\u001b[32m 1\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mmain\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mutils\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mutils\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m read_and_merge_h5_data\n\u001b[32m 3\u001b[39m \u001b[38;5;28mprint\u001b[39m(\u001b[33m'\u001b[39m\u001b[33mdaily data\u001b[39m\u001b[33m'\u001b[39m)\n\u001b[32m----> \u001b[39m\u001b[32m4\u001b[39m df = \u001b[43mread_and_merge_h5_data\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43m/mnt/d/PyProject/NewStock/data/daily_data.h5\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mdaily_data\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m 5\u001b[39m \u001b[43m \u001b[49m\u001b[43mcolumns\u001b[49m\u001b[43m=\u001b[49m\u001b[43m[\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mts_code\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mtrade_date\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mopen\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mclose\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mhigh\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mlow\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mvol\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mamount\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mpct_chg\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 6\u001b[39m \u001b[43m \u001b[49m\u001b[43mdf\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[32m 8\u001b[39m \u001b[38;5;28mprint\u001b[39m(\u001b[33m'\u001b[39m\u001b[33mdaily basic\u001b[39m\u001b[33m'\u001b[39m)\n\u001b[32m 9\u001b[39m df = read_and_merge_h5_data(\u001b[33m'\u001b[39m\u001b[33m/mnt/d/PyProject/NewStock/data/daily_basic.h5\u001b[39m\u001b[33m'\u001b[39m, key=\u001b[33m'\u001b[39m\u001b[33mdaily_basic\u001b[39m\u001b[33m'\u001b[39m,\n\u001b[32m 10\u001b[39m columns=[\u001b[33m'\u001b[39m\u001b[33mts_code\u001b[39m\u001b[33m'\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mtrade_date\u001b[39m\u001b[33m'\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mturnover_rate\u001b[39m\u001b[33m'\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mpe_ttm\u001b[39m\u001b[33m'\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mcirc_mv\u001b[39m\u001b[33m'\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mtotal_mv\u001b[39m\u001b[33m'\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mvolume_ratio\u001b[39m\u001b[33m'\u001b[39m,\n\u001b[32m 11\u001b[39m \u001b[33m'\u001b[39m\u001b[33mis_st\u001b[39m\u001b[33m'\u001b[39m], df=df, join=\u001b[33m'\u001b[39m\u001b[33minner\u001b[39m\u001b[33m'\u001b[39m)\n",
"\u001b[36mFile \u001b[39m\u001b[32m/mnt/d/PyProject/NewStock/main/utils/utils.py:14\u001b[39m, in \u001b[36mread_and_merge_h5_data\u001b[39m\u001b[34m(h5_filename, key, columns, df, join, on, prefix)\u001b[39m\n\u001b[32m 11\u001b[39m processed_columns.append(col)\n\u001b[32m 13\u001b[39m \u001b[38;5;66;03m# 从 HDF5 文件读取数据，选择需要的列\u001b[39;00m\n\u001b[32m---> \u001b[39m\u001b[32m14\u001b[39m data = \u001b[43mpd\u001b[49m\u001b[43m.\u001b[49m\u001b[43mread_hdf\u001b[49m\u001b[43m(\u001b[49m\u001b[43mh5_filename\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m=\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcolumns\u001b[49m\u001b[43m=\u001b[49m\u001b[43mprocessed_columns\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 16\u001b[39m \u001b[38;5;66;03m# 修改列名，如果列名以前有 _，加上 _\u001b[39;00m\n\u001b[32m 17\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m col \u001b[38;5;129;01min\u001b[39;00m data.columns:\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/quant/lib/python3.12/site-packages/pandas/io/pytables.py:431\u001b[39m, in \u001b[36mread_hdf\u001b[39m\u001b[34m(path_or_buf, key, mode, errors, where, start, stop, columns, iterator, chunksize, **kwargs)\u001b[39m\n\u001b[32m 428\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m exists:\n\u001b[32m 429\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mFileNotFoundError\u001b[39;00m(\u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mFile \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpath_or_buf\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m does not exist\u001b[39m\u001b[33m\"\u001b[39m)\n\u001b[32m--> \u001b[39m\u001b[32m431\u001b[39m store = \u001b[43mHDFStore\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath_or_buf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m=\u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[43m=\u001b[49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 432\u001b[39m \u001b[38;5;66;03m# can't auto open/close if we are using an iterator\u001b[39;00m\n\u001b[32m 433\u001b[39m \u001b[38;5;66;03m# so delegate to the iterator\u001b[39;00m\n\u001b[32m 434\u001b[39m auto_close = \u001b[38;5;28;01mTrue\u001b[39;00m\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/quant/lib/python3.12/site-packages/pandas/io/pytables.py:571\u001b[39m, in \u001b[36mHDFStore.__init__\u001b[39m\u001b[34m(self, path, mode, complevel, complib, fletcher32, **kwargs)\u001b[39m\n\u001b[32m 568\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[33mformat\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m kwargs:\n\u001b[32m 569\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[33m\"\u001b[39m\u001b[33mformat is not a defined argument for HDFStore\u001b[39m\u001b[33m\"\u001b[39m)\n\u001b[32m--> \u001b[39m\u001b[32m571\u001b[39m tables = \u001b[43mimport_optional_dependency\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtables\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[32m 573\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m complib \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m complib \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m tables.filters.all_complibs:\n\u001b[32m 574\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[32m 575\u001b[39m \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mcomplib only supports \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mtables.filters.all_complibs\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m compression.\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m 576\u001b[39m )\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/quant/lib/python3.12/site-packages/pandas/compat/_optional.py:138\u001b[39m, in \u001b[36mimport_optional_dependency\u001b[39m\u001b[34m(name, extra, errors, min_version)\u001b[39m\n\u001b[32m 136\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m:\n\u001b[32m 137\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m errors == \u001b[33m\"\u001b[39m\u001b[33mraise\u001b[39m\u001b[33m\"\u001b[39m:\n\u001b[32m--> \u001b[39m\u001b[32m138\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m(msg)\n\u001b[32m 139\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m 141\u001b[39m \u001b[38;5;66;03m# Handle submodules: if we have submodule, grab parent module from sys.modules\u001b[39;00m\n",
"\u001b[31mImportError\u001b[39m: Missing optional dependency 'pytables'. Use pip or conda to install pytables."
]
}
],
@@ -157,7 +148,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": null,
"id": "cac01788dac10678",
"metadata": {
"ExecuteTime": {
@@ -225,7 +216,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": null,
"id": "c4e9e1d31da6dba6",
"metadata": {
"ExecuteTime": {
@@ -325,7 +316,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": null,
"id": "a735bc02ceb4d872",
"metadata": {
"ExecuteTime": {
@@ -341,7 +332,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": null,
"id": "53f86ddc0677a6d7",
"metadata": {
"ExecuteTime": {
@@ -408,7 +399,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": null,
"id": "dbe2fd8021b9417f",
"metadata": {
"ExecuteTime": {
@@ -436,7 +427,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": null,
"id": "85c3e3d0235ffffa",
"metadata": {
"ExecuteTime": {
@@ -468,7 +459,7 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": null,
"id": "92d84ce15a562ec6",
"metadata": {
"ExecuteTime": {
@@ -718,7 +709,7 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": null,
"id": "b87b938028afa206",
"metadata": {
"ExecuteTime": {
@@ -756,7 +747,7 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": null,
"id": "f4f16d63ad18d1bc",
"metadata": {
"ExecuteTime": {
@@ -982,7 +973,7 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": null,
"id": "40e6b68a91b30c79",
"metadata": {
"ExecuteTime": {
@@ -1302,7 +1293,7 @@
},
{
"cell_type": "code",
"execution_count": 15,
"execution_count": null,
"id": "47c12bb34062ae7a",
"metadata": {
"ExecuteTime": {
@@ -1336,7 +1327,7 @@
},
{
"cell_type": "code",
"execution_count": 16,
"execution_count": null,
"id": "29221dde",
"metadata": {},
"outputs": [
@@ -1379,7 +1370,7 @@
},
{
"cell_type": "code",
"execution_count": 17,
"execution_count": null,
"id": "03ee5daf",
"metadata": {},
"outputs": [],
@@ -1392,7 +1383,7 @@
},
{
"cell_type": "code",
"execution_count": 18,
"execution_count": null,
"id": "b76ea08a",
"metadata": {},
"outputs": [
@@ -1610,7 +1601,7 @@
},
{
"cell_type": "code",
"execution_count": 19,
"execution_count": null,
"id": "3ff2d1c5",
"metadata": {},
"outputs": [],
@@ -1751,7 +1742,7 @@
},
{
"cell_type": "code",
"execution_count": 20,
"execution_count": null,
"id": "c6eb5cd4-e714-420a-ac48-39af3e11ee81",
"metadata": {
"ExecuteTime": {
@@ -1825,7 +1816,7 @@
},
{
"cell_type": "code",
"execution_count": 21,
"execution_count": null,
"id": "5d1522a7538db91b",
"metadata": {
"ExecuteTime": {
@@ -1863,7 +1854,7 @@
},
{
"cell_type": "code",
"execution_count": 22,
"execution_count": null,
"id": "c1c40917",
"metadata": {},
"outputs": [
@@ -1882,16 +1873,16 @@
"# 你可以根据需要调整日期格式，例如 '%Y%m%d' 会得到 '20250706'\n",
"date_str = current_date.strftime('%Y-%m-%d')\n",
"\n",
"# 3. 构建包含日期的模型文件名\n",
"model_filename = f'/mnt/d/PyProject/NewStock/main/train/catboost_model/catboost_model_2025-06-01.cbm'\n",
"# # 3. 构建包含日期的模型文件名\n",
"# model_filename = f'/mnt/d/PyProject/NewStock/main/train/catboost_model/catboost_model_2025-06-01.cbm'\n",
"\n",
"model.save_model(model_filename)\n",
"print(f\"模型已保存到: {model_filename}\")"
"# model.save_model(model_filename)\n",
"# print(f\"模型已保存到: {model_filename}\")"
]
},
{
"cell_type": "code",
"execution_count": 23,
"execution_count": null,
"id": "09b1799e",
"metadata": {},
"outputs": [
@@ -1913,7 +1904,7 @@
},
{
"cell_type": "code",
"execution_count": 24,
"execution_count": null,
"id": "e53b209a",
"metadata": {},
"outputs": [
@@ -1946,7 +1937,7 @@
},
{
"cell_type": "code",
"execution_count": 25,
"execution_count": null,
"id": "364e821a",
"metadata": {},
"outputs": [],
@@ -2030,7 +2021,7 @@
},
{
"cell_type": "code",
"execution_count": 26,
"execution_count": null,
"id": "1f6e6336",
"metadata": {},
"outputs": [
@@ -2099,7 +2090,7 @@
},
{
"cell_type": "code",
"execution_count": 27,
"execution_count": null,
"id": "7e9023cc",
"metadata": {},
"outputs": [],
@@ -2299,7 +2290,7 @@
},
{
"cell_type": "code",
"execution_count": 28,
"execution_count": null,
"id": "a0000d75",
"metadata": {},
"outputs": [
@@ -2545,7 +2536,7 @@
},
{
"cell_type": "code",
"execution_count": 29,
"execution_count": null,
"id": "a436dba4",
"metadata": {},
"outputs": [

292
main/train/Classify2_load_model.ipynb
View File

@@ -15,7 +15,18 @@
"name": "stdout",
"output_type": "stream",
"text": [
"/mnt/d/PyProject/NewStock\n"
"/mnt/d/PyProject/NewStock/main/train\n"
]
},
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'main.factor'; 'main' is not a package",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mModuleNotFoundError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[1]\u001b[39m\u001b[32m, line 11\u001b[39m\n\u001b[32m 9\u001b[39m \u001b[38;5;28mprint\u001b[39m(os.getcwd())\n\u001b[32m 10\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mpandas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mpd\u001b[39;00m\n\u001b[32m---> \u001b[39m\u001b[32m11\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mmain\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mfactor\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mfactor\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m get_rolling_factor, get_simple_factor\n\u001b[32m 12\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mmain\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mutils\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mfactor\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m read_industry_data\n\u001b[32m 13\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mmain\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mutils\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mfactor_processor\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m calculate_score\n",
"\u001b[31mModuleNotFoundError\u001b[39m: No module named 'main.factor'; 'main' is not a package"
]
}
],
@@ -42,10 +53,20 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": null,
"id": "4a481c60",
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"# 设置使用核心\n",
"import os\n",
@@ -54,7 +75,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"id": "a79cafb06a7e0e43",
"metadata": {
"ExecuteTime": {
@@ -119,6 +140,15 @@
"memory usage: 2.2+ GB\n",
"None\n"
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
@@ -154,7 +184,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": null,
"id": "cac01788dac10678",
"metadata": {
"ExecuteTime": {
@@ -169,6 +199,15 @@
"text": [
"industry\n"
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
@@ -222,7 +261,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": null,
"id": "c4e9e1d31da6dba6",
"metadata": {
"ExecuteTime": {
@@ -233,7 +272,17 @@
"source_hidden": true
}
},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"from main.factor.factor import *\n",
"\n",
@@ -322,7 +371,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": null,
"id": "a735bc02ceb4d872",
"metadata": {
"ExecuteTime": {
@@ -330,7 +379,17 @@
"start_time": "2025-04-03T12:47:10.751831Z"
}
},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"import talib\n",
"import numpy as np"
@@ -338,7 +397,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": null,
"id": "53f86ddc0677a6d7",
"metadata": {
"ExecuteTime": {
@@ -350,7 +409,17 @@
},
"scrolled": true
},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"from main.utils.factor import get_act_factor\n",
"\n",
@@ -405,7 +474,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": null,
"id": "dbe2fd8021b9417f",
"metadata": {
"ExecuteTime": {
@@ -420,6 +489,15 @@
"text": [
"['ts_code', 'open', 'close', 'high', 'low', 'amount', 'circ_mv', 'total_mv', 'is_st', 'up_limit', 'down_limit', 'buy_sm_vol', 'sell_sm_vol', 'buy_lg_vol', 'sell_lg_vol', 'buy_elg_vol', 'sell_elg_vol', 'net_mf_vol', 'his_low', 'his_high', 'cost_5pct', 'cost_15pct', 'cost_50pct', 'cost_85pct', 'cost_95pct', 'weight_avg', 'in_date']\n"
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
@@ -433,7 +511,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": null,
"id": "85c3e3d0235ffffa",
"metadata": {
"ExecuteTime": {
@@ -441,7 +519,17 @@
"start_time": "2025-04-03T12:47:15.990101Z"
}
},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"fina_indicator_df = read_and_merge_h5_data('/mnt/d/PyProject/NewStock/data/fina_indicator.h5', key='fina_indicator',\n",
" columns=['ts_code', 'ann_date', 'undist_profit_ps', 'ocfps', 'bps', 'roa', 'roe'],\n",
@@ -465,7 +553,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": null,
"id": "92d84ce15a562ec6",
"metadata": {
"ExecuteTime": {
@@ -607,6 +695,15 @@
"None\n",
"['ts_code', 'trade_date', 'open', 'close', 'high', 'low', 'vol', 'amount', 'pct_chg', 'turnover_rate', 'pe_ttm', 'circ_mv', 'total_mv', 'volume_ratio', 'is_st', 'up_limit', 'down_limit', 'buy_sm_vol', 'sell_sm_vol', 'buy_lg_vol', 'sell_lg_vol', 'buy_elg_vol', 'sell_elg_vol', 'net_mf_vol', 'his_low', 'his_high', 'cost_5pct', 'cost_15pct', 'cost_50pct', 'cost_85pct', 'cost_95pct', 'weight_avg', 'winner_rate', 'cat_l2_code', 'undist_profit_ps', 'ocfps', 'roa', 'roe', 'AR', 'BR', 'AR_BR', 'log_circ_mv', 'cashflow_to_ev_factor', 'book_to_price_ratio', 'turnover_rate_mean_5', 'variance_20', 'bbi_ratio_factor', 'daily_deviation', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity', 'sm_net_buy_vol', 'flow_divergence_diff', 'flow_divergence_ratio', 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change', 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel', 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy', 'cost_support_15pct_change', 'cat_winner_price_zone', 'flow_chip_consistency', 'profit_taking_vs_absorb', 'cat_is_positive', 'upside_vol', 'downside_vol', 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'vol_std_5', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'return_5', 'return_20', 'std_return_5', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', 'alpha_007', 'alpha_013', 'vol_break', 'weight_roc5', 'price_cost_divergence', 'smallcap_concentration', 'cost_stability', 'high_cost_break_days', 'liquidity_risk', 'turnover_std', 'mv_volatility', 'volume_growth', 'mv_growth', 'momentum_factor', 'resonance_factor', 'log_close', 'cat_vol_spike', 'up', 'down', 'obv_maobv_6', 'std_return_5_over_std_return_90', 'std_return_90_minus_std_return_90_2', 'cat_af2', 'cat_af3', 'cat_af4', 'act_factor5', 'act_factor6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'ctrl_strength', 'low_cost_dev', 'asymmetry', 'lock_factor', 'cat_vol_break', 'cost_atr_adj', 'cat_golden_resonance', 'mv_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume', 'mv_volume_ratio', 'mv_momentum', 'lg_flow_mom_corr_20_60', 'lg_flow_accel', 'profit_pressure', 'underwater_resistance', 'cost_conc_std_20', 'profit_decay_20', 'vol_amp_loss_20', 'vol_drop_profit_cnt_5', 'lg_flow_vol_interact_20', 'cost_break_confirm_cnt_5', 'atr_norm_channel_pos_14', 'turnover_diff_skew_20', 'lg_sm_flow_diverge_20', 'pullback_strong_20_20', 'vol_wgt_hist_pos_20', 'vol_adj_roc_20', 'cs_rank_net_lg_flow_val', 'cs_rank_flow_divergence', 'cs_rank_ind_adj_lg_flow', 'cs_rank_elg_buy_ratio', 'cs_rank_rel_profit_margin', 'cs_rank_cost_breadth', 'cs_rank_dist_to_upper_cost', 'cs_rank_winner_rate', 'cs_rank_intraday_range', 'cs_rank_close_pos_in_range', 'cs_rank_opening_gap', 'cs_rank_pos_in_hist_range', 'cs_rank_vol_x_profit_margin', 'cs_rank_lg_flow_price_concordance', 'cs_rank_turnover_per_winner', 'cs_rank_ind_cap_neutral_pe', 'cs_rank_volume_ratio', 'cs_rank_elg_buy_sell_sm_ratio', 'cs_rank_cost_dist_vol_ratio', 'cs_rank_size']\n"
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
@@ -717,12 +814,22 @@
"execution_count": null,
"id": "3f80b2f9",
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": []
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": null,
"id": "b87b938028afa206",
"metadata": {
"ExecuteTime": {
@@ -730,7 +837,17 @@
"start_time": "2025-04-03T13:08:02.469611Z"
}
},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"from scipy.stats import ks_2samp, wasserstein_distance\n",
"\n",
@@ -760,7 +877,7 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": null,
"id": "f4f16d63ad18d1bc",
"metadata": {
"ExecuteTime": {
@@ -768,7 +885,17 @@
"start_time": "2025-04-03T13:08:03.665739Z"
}
},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"import numpy as np\n",
"import statsmodels.api as sm # 用于中性化回归\n",
@@ -986,7 +1113,7 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": null,
"id": "40e6b68a91b30c79",
"metadata": {
"ExecuteTime": {
@@ -994,7 +1121,17 @@
"start_time": "2025-04-03T13:08:03.694904Z"
}
},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"def remove_outliers_label_percentile(label: pd.Series, lower_percentile: float = 0.01, upper_percentile: float = 0.99,\n",
" log=True):\n",
@@ -1306,7 +1443,7 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": null,
"id": "47c12bb34062ae7a",
"metadata": {
"ExecuteTime": {
@@ -1314,7 +1451,17 @@
"start_time": "2025-04-03T14:49:25.889057Z"
}
},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"days = 5\n",
"validation_days = 120\n",
@@ -1340,7 +1487,7 @@
},
{
"cell_type": "code",
"execution_count": 15,
"execution_count": null,
"id": "29221dde",
"metadata": {},
"outputs": [
@@ -1350,6 +1497,15 @@
"text": [
"191\n"
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
@@ -1383,10 +1539,20 @@
},
{
"cell_type": "code",
"execution_count": 16,
"execution_count": null,
"id": "03ee5daf",
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"# df = fill_nan_with_daily_median(df, feature_columns)\n",
"for feature_col in [col for col in feature_columns if col in df.columns]:\n",
@@ -1396,7 +1562,7 @@
},
{
"cell_type": "code",
"execution_count": 17,
"execution_count": null,
"id": "b76ea08a",
"metadata": {},
"outputs": [
@@ -1491,6 +1657,15 @@
"1 000001.SZ 2019-01-03 16.583965\n",
"2 000001.SZ 2019-01-04 16.633371\n"
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
@@ -1621,10 +1796,20 @@
},
{
"cell_type": "code",
"execution_count": 18,
"execution_count": null,
"id": "3ff2d1c5",
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.linear_model import LogisticRegression\n",
@@ -1762,7 +1947,7 @@
},
{
"cell_type": "code",
"execution_count": 19,
"execution_count": null,
"id": "a5bbb8be",
"metadata": {},
"outputs": [
@@ -1775,6 +1960,15 @@
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
@@ -1787,7 +1981,7 @@
},
{
"cell_type": "code",
"execution_count": 20,
"execution_count": null,
"id": "5d1522a7538db91b",
"metadata": {
"ExecuteTime": {
@@ -1795,7 +1989,17 @@
"start_time": "2025-04-03T15:04:39.298483Z"
}
},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"score_df = test_data.groupby('trade_date', group_keys=False).apply(lambda x: x.nsmallest(300, 'total_mv'))\n",
"# score_df = fill_nan_with_daily_median(score_df, ['pe_ttm'])\n",
@@ -1825,7 +2029,7 @@
},
{
"cell_type": "code",
"execution_count": 21,
"execution_count": null,
"id": "09b1799e",
"metadata": {},
"outputs": [
@@ -1837,6 +2041,15 @@
"['vol', 'pct_chg', 'turnover_rate', 'volume_ratio', 'winner_rate', 'undist_profit_ps', 'ocfps', 'AR', 'BR', 'AR_BR', 'cashflow_to_ev_factor', 'book_to_price_ratio', 'turnover_rate_mean_5', 'variance_20', 'bbi_ratio_factor', 'daily_deviation', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity', 'sm_net_buy_vol', 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change', 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel', 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy', 'cost_support_15pct_change', 'cat_winner_price_zone', 'flow_chip_consistency', 'profit_taking_vs_absorb', 'cat_is_positive', 'upside_vol', 'downside_vol', 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'vol_std_5', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'return_5', 'return_20', 'std_return_5', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', 'alpha_007', 'alpha_013', 'vol_break', 'weight_roc5', 'smallcap_concentration', 'cost_stability', 'high_cost_break_days', 'liquidity_risk', 'turnover_std', 'mv_volatility', 'volume_growth', 'mv_growth', 'momentum_factor', 'resonance_factor', 'log_close', 'cat_vol_spike', 'up', 'down', 'obv_maobv_6', 'std_return_5_over_std_return_90', 'std_return_90_minus_std_return_90_2', 'cat_af2', 'cat_af3', 'cat_af4', 'act_factor5', 'act_factor6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'ctrl_strength', 'low_cost_dev', 'asymmetry', 'lock_factor', 'cat_vol_break', 'cost_atr_adj', 'cat_golden_resonance', 'mv_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume', 'mv_volume_ratio', 'mv_momentum', 'lg_flow_mom_corr_20_60', 'lg_flow_accel', 'profit_pressure', 'underwater_resistance', 'cost_conc_std_20', 'profit_decay_20', 'vol_amp_loss_20', 'vol_drop_profit_cnt_5', 'lg_flow_vol_interact_20', 'cost_break_confirm_cnt_5', 'atr_norm_channel_pos_14', 'turnover_diff_skew_20', 'lg_sm_flow_diverge_20', 'pullback_strong_20_20', 'vol_wgt_hist_pos_20', 'vol_adj_roc_20', 'cs_rank_net_lg_flow_val', 'cs_rank_elg_buy_ratio', 'cs_rank_rel_profit_margin', 'cs_rank_cost_breadth', 'cs_rank_dist_to_upper_cost', 'cs_rank_winner_rate', 'cs_rank_intraday_range', 'cs_rank_close_pos_in_range', 'cs_rank_pos_in_hist_range', 'cs_rank_vol_x_profit_margin', 'cs_rank_lg_flow_price_concordance', 'cs_rank_turnover_per_winner', 'cs_rank_volume_ratio', 'cs_rank_elg_buy_sell_sm_ratio', 'cs_rank_cost_dist_vol_ratio', 'cs_rank_size', 'cat_up_limit', 'industry_obv', 'industry_return_5', 'industry_return_20', 'industry__ema_5', 'industry__ema_13', 'industry__ema_20', 'industry__ema_60', 'industry_act_factor1', 'industry_act_factor2', 'industry_act_factor3', 'industry_act_factor4', 'industry_act_factor5', 'industry_act_factor6', 'industry_rank_act_factor1', 'industry_rank_act_factor2', 'industry_rank_act_factor3', 'industry_return_5_percentile', 'industry_return_20_percentile', '000852.SH_MACD', '000905.SH_MACD', '399006.SZ_MACD', '000852.SH_MACD_hist', '000905.SH_MACD_hist', '399006.SZ_MACD_hist', '000852.SH_RSI', '000905.SH_RSI', '399006.SZ_RSI', '000852.SH_Signal_line', '000905.SH_Signal_line', '399006.SZ_Signal_line', '000852.SH_amount_change_rate', '000905.SH_amount_change_rate', '399006.SZ_amount_change_rate', '000852.SH_amount_mean', '000905.SH_amount_mean', '399006.SZ_amount_mean', '000852.SH_daily_return', '000905.SH_daily_return', '399006.SZ_daily_return', '000852.SH_up_ratio_20d', '000905.SH_up_ratio_20d', '399006.SZ_up_ratio_20d', '000852.SH_volatility', '000905.SH_volatility', '399006.SZ_volatility', '000852.SH_volume_change_rate', '000905.SH_volume_change_rate', '399006.SZ_volume_change_rate']\n",
"[]\n"
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
@@ -1847,7 +2060,7 @@
},
{
"cell_type": "code",
"execution_count": 22,
"execution_count": null,
"id": "e53b209a",
"metadata": {},
"outputs": [
@@ -1871,6 +2084,15 @@
"\n",
"[2045675 rows x 3 columns]\n"
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mnotebook controller is DISPOSED. \n",
"\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [