diff --git a/.gitignore b/.gitignore index d7dbb55..ef35b54 100644 --- a/.gitignore +++ b/.gitignore @@ -10,11 +10,7 @@ __pycache__/ # Distribution / packaging .Python build/ -dataset/ -yuanyoudataset/ -yuanyouzhoududataset/ -yuanyouyuedudataset/ -juxitingdataset/ +*dataset/ logs/ develop-eggs/ dist/ diff --git a/aisenzhecode/石油苯/日度价格预测_最佳模型.pkl b/aisenzhecode/石油苯/日度价格预测_最佳模型.pkl new file mode 100644 index 0000000..06b4fce Binary files /dev/null and b/aisenzhecode/石油苯/日度价格预测_最佳模型.pkl differ diff --git a/aisenzhecode/石油苯/纯苯价格预测-自定义日期ytj.ipynb b/aisenzhecode/石油苯/纯苯价格预测-自定义日期ytj.ipynb index 131ade0..7ffd738 100644 --- a/aisenzhecode/石油苯/纯苯价格预测-自定义日期ytj.ipynb +++ b/aisenzhecode/石油苯/纯苯价格预测-自定义日期ytj.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 11, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -706,27 +706,28 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "20241017\n" + "20250201\n", + "{'dataDate': '20250201', 'dataItemNo': 'C01100047|TURNOVER'}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:280: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", "\n", - "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.602e+05, tolerance: 3.845e+04\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.321e+05, tolerance: 4.074e+04\n", "\n" ] }, @@ -734,7 +735,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Using matplotlib backend: QtAgg\n", + "Using matplotlib backend: \n", "%pylab is deprecated, use %matplotlib inline and import the required libraries.\n", "Populating the interactive namespace from numpy and matplotlib\n", "Fitting 3 folds for each of 180 candidates, totalling 540 fits\n" @@ -749,11 +750,11 @@ "pylab import has clobbered these variables: ['datetime', '__version__', 'plot', 'random']\n", "`%matplotlib` prevents importing * from pylab and numpy\n", "\n", - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:233: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:263: FutureWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", "\n", "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", "\n" @@ -764,24 +765,25 @@ "output_type": "stream", "text": [ "Date\n", - "2024-10-17 7541.753418\n", + "2025-02-01 7738.433105\n", "Name: 日度预测价格, dtype: float32\n", - "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20241017', 'dataStatus': 'add', 'dataValue': 7541.75}]}\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250201', 'dataStatus': 'add', 'dataValue': 7738.43}]}\n", "{\"confirmFlg\":false,\"status\":true}\n", - "20241018\n" + "20250202\n", + "{'dataDate': '20250202', 'dataItemNo': 'C01100047|TURNOVER'}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:280: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", "\n", - "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.716e+05, tolerance: 3.895e+04\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.506e+05, tolerance: 4.089e+04\n", "\n" ] }, @@ -799,11 +801,11 @@ "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:233: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:263: FutureWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", "\n", "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", "\n" @@ -814,24 +816,25 @@ "output_type": "stream", "text": [ "Date\n", - "2024-10-18 7399.281738\n", + "2025-02-02 7700.021484\n", "Name: 日度预测价格, dtype: float32\n", - "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20241018', 'dataStatus': 'add', 'dataValue': 7399.28}]}\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250202', 'dataStatus': 'add', 'dataValue': 7700.02}]}\n", "{\"confirmFlg\":false,\"status\":true}\n", - "20241019\n" + "20250203\n", + "{'dataDate': '20250203', 'dataItemNo': 'C01100047|TURNOVER'}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:280: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", "\n", - "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.669e+05, tolerance: 3.913e+04\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.696e+05, tolerance: 4.096e+04\n", "\n" ] }, @@ -849,11 +852,11 @@ "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:233: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:263: FutureWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", "\n", "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", "\n" @@ -864,24 +867,25 @@ "output_type": "stream", "text": [ "Date\n", - "2024-10-19 7404.584473\n", + "2025-02-03 7693.463379\n", "Name: 日度预测价格, dtype: float32\n", - "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20241019', 'dataStatus': 'add', 'dataValue': 7404.58}]}\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250203', 'dataStatus': 'add', 'dataValue': 7693.46}]}\n", "{\"confirmFlg\":false,\"status\":true}\n", - "20241020\n" + "20250204\n", + "{'dataDate': '20250204', 'dataItemNo': 'C01100047|TURNOVER'}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:280: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", "\n", - "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.833e+05, tolerance: 3.773e+04\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.780e+05, tolerance: 4.200e+04\n", "\n" ] }, @@ -899,11 +903,11 @@ "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:233: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:263: FutureWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", "\n", "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", "\n" @@ -914,24 +918,25 @@ "output_type": "stream", "text": [ "Date\n", - "2024-10-20 7375.245605\n", + "2025-02-04 7798.116211\n", "Name: 日度预测价格, dtype: float32\n", - "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20241020', 'dataStatus': 'add', 'dataValue': 7375.25}]}\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250204', 'dataStatus': 'add', 'dataValue': 7798.12}]}\n", "{\"confirmFlg\":false,\"status\":true}\n", - "20241021\n" + "20250205\n", + "{'dataDate': '20250205', 'dataItemNo': 'C01100047|TURNOVER'}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:280: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", "\n", - "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.912e+05, tolerance: 3.684e+04\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.551e+05, tolerance: 4.144e+04\n", "\n" ] }, @@ -949,11 +954,11 @@ "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:233: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:263: FutureWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", "\n", "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", "\n" @@ -964,24 +969,24 @@ "output_type": "stream", "text": [ "Date\n", - "2024-10-21 7272.15332\n", + "2025-02-05 7865.974609\n", "Name: 日度预测价格, dtype: float32\n", - "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20241021', 'dataStatus': 'add', 'dataValue': 7272.15}]}\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250205', 'dataStatus': 'add', 'dataValue': 7865.97}]}\n", "{\"confirmFlg\":false,\"status\":true}\n", - "20241022\n" + "20250206\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:280: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", "\n", - "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.991e+05, tolerance: 3.700e+04\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.553e+05, tolerance: 4.144e+04\n", "\n" ] }, @@ -999,11 +1004,11 @@ "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:233: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:263: FutureWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", "\n", "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", "\n" @@ -1014,24 +1019,24 @@ "output_type": "stream", "text": [ "Date\n", - "2024-10-22 7265.592773\n", + "2025-02-06 7896.265137\n", "Name: 日度预测价格, dtype: float32\n", - "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20241022', 'dataStatus': 'add', 'dataValue': 7265.59}]}\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250206', 'dataStatus': 'add', 'dataValue': 7896.27}]}\n", "{\"confirmFlg\":false,\"status\":true}\n", - "20241023\n" + "20250207\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:280: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", "\n", - "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.866e+05, tolerance: 3.682e+04\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.955e+05, tolerance: 4.168e+04\n", "\n" ] }, @@ -1049,11 +1054,11 @@ "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:233: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:263: FutureWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", "\n", "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", "\n" @@ -1064,24 +1069,24 @@ "output_type": "stream", "text": [ "Date\n", - "2024-10-23 7314.694336\n", + "2025-02-07 7841.537109\n", "Name: 日度预测价格, dtype: float32\n", - "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20241023', 'dataStatus': 'add', 'dataValue': 7314.69}]}\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250207', 'dataStatus': 'add', 'dataValue': 7841.54}]}\n", "{\"confirmFlg\":false,\"status\":true}\n", - "20241024\n" + "20250208\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:280: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", "\n", - "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.886e+05, tolerance: 3.690e+04\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.733e+05, tolerance: 4.197e+04\n", "\n" ] }, @@ -1099,11 +1104,11 @@ "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:233: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:263: FutureWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", "\n", "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", "\n" @@ -1114,24 +1119,24 @@ "output_type": "stream", "text": [ "Date\n", - "2024-10-24 7340.938477\n", + "2025-02-08 7814.474609\n", "Name: 日度预测价格, dtype: float32\n", - "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20241024', 'dataStatus': 'add', 'dataValue': 7340.94}]}\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250208', 'dataStatus': 'add', 'dataValue': 7814.47}]}\n", "{\"confirmFlg\":false,\"status\":true}\n", - "20241025\n" + "20250209\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:280: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", "\n", - "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.843e+05, tolerance: 3.691e+04\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.675e+05, tolerance: 4.062e+04\n", "\n" ] }, @@ -1149,11 +1154,11 @@ "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:233: UserWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", "\n", "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", "\n", - "C:\\Users\\Hello\\AppData\\Local\\Temp\\ipykernel_13372\\3095856616.py:263: FutureWarning:\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", "\n", "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", "\n" @@ -1164,9 +1169,463 @@ "output_type": "stream", "text": [ "Date\n", - "2024-10-25 7299.914062\n", + "2025-02-09 7832.284668\n", "Name: 日度预测价格, dtype: float32\n", - "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20241025', 'dataStatus': 'add', 'dataValue': 7299.91}]}\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250209', 'dataStatus': 'add', 'dataValue': 7832.28}]}\n", + "{\"confirmFlg\":false,\"status\":true}\n", + "20250210\n", + "{'dataDate': '20250210', 'dataItemNo': 'C01100047|TURNOVER'}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", + "\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.531e+05, tolerance: 4.103e+04\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Using matplotlib backend: QtAgg\n", + "%pylab is deprecated, use %matplotlib inline and import the required libraries.\n", + "Populating the interactive namespace from numpy and matplotlib\n", + "Fitting 3 folds for each of 180 candidates, totalling 540 fits\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", + "\n", + "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Date\n", + "2025-02-10 7917.837891\n", + "Name: 日度预测价格, dtype: float32\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250210', 'dataStatus': 'add', 'dataValue': 7917.84}]}\n", + "{\"confirmFlg\":false,\"status\":true}\n", + "20250211\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", + "\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.307e+05, tolerance: 4.073e+04\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Using matplotlib backend: QtAgg\n", + "%pylab is deprecated, use %matplotlib inline and import the required libraries.\n", + "Populating the interactive namespace from numpy and matplotlib\n", + "Fitting 3 folds for each of 180 candidates, totalling 540 fits\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", + "\n", + "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Date\n", + "2025-02-11 7919.563965\n", + "Name: 日度预测价格, dtype: float32\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250211', 'dataStatus': 'add', 'dataValue': 7919.56}]}\n", + "{\"confirmFlg\":false,\"status\":true}\n", + "20250212\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", + "\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.644e+05, tolerance: 4.133e+04\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Using matplotlib backend: QtAgg\n", + "%pylab is deprecated, use %matplotlib inline and import the required libraries.\n", + "Populating the interactive namespace from numpy and matplotlib\n", + "Fitting 3 folds for each of 180 candidates, totalling 540 fits\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", + "\n", + "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Date\n", + "2025-02-12 7902.145508\n", + "Name: 日度预测价格, dtype: float32\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250212', 'dataStatus': 'add', 'dataValue': 7902.15}]}\n", + "{\"confirmFlg\":false,\"status\":true}\n", + "20250213\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", + "\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.711e+05, tolerance: 4.105e+04\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Using matplotlib backend: QtAgg\n", + "%pylab is deprecated, use %matplotlib inline and import the required libraries.\n", + "Populating the interactive namespace from numpy and matplotlib\n", + "Fitting 3 folds for each of 180 candidates, totalling 540 fits\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", + "\n", + "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Date\n", + "2025-02-13 8001.087891\n", + "Name: 日度预测价格, dtype: float32\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250213', 'dataStatus': 'add', 'dataValue': 8001.09}]}\n", + "{\"confirmFlg\":false,\"status\":true}\n", + "20250214\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", + "\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.949e+05, tolerance: 4.129e+04\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Using matplotlib backend: QtAgg\n", + "%pylab is deprecated, use %matplotlib inline and import the required libraries.\n", + "Populating the interactive namespace from numpy and matplotlib\n", + "Fitting 3 folds for each of 180 candidates, totalling 540 fits\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", + "\n", + "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Date\n", + "2025-02-14 8032.705566\n", + "Name: 日度预测价格, dtype: float32\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250214', 'dataStatus': 'add', 'dataValue': 8032.71}]}\n", + "{\"confirmFlg\":false,\"status\":true}\n", + "20250215\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", + "\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.966e+05, tolerance: 4.129e+04\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Using matplotlib backend: QtAgg\n", + "%pylab is deprecated, use %matplotlib inline and import the required libraries.\n", + "Populating the interactive namespace from numpy and matplotlib\n", + "Fitting 3 folds for each of 180 candidates, totalling 540 fits\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", + "\n", + "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Date\n", + "2025-02-15 8040.26709\n", + "Name: 日度预测价格, dtype: float32\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250215', 'dataStatus': 'add', 'dataValue': 8040.27}]}\n", + "{\"confirmFlg\":false,\"status\":true}\n", + "20250216\n", + "{'dataDate': '20250216', 'dataItemNo': 'C01100047|TURNOVER'}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", + "\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.442e+05, tolerance: 4.138e+04\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Using matplotlib backend: QtAgg\n", + "%pylab is deprecated, use %matplotlib inline and import the required libraries.\n", + "Populating the interactive namespace from numpy and matplotlib\n", + "Fitting 3 folds for each of 180 candidates, totalling 540 fits\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", + "\n", + "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Date\n", + "2025-02-16 8044.537109\n", + "Name: 日度预测价格, dtype: float32\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250216', 'dataStatus': 'add', 'dataValue': 8044.54}]}\n", + "{\"confirmFlg\":false,\"status\":true}\n", + "20250217\n", + "{'dataDate': '20250217', 'dataItemNo': 'C01100047|TURNOVER'}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", + "\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.555e+05, tolerance: 4.072e+04\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Using matplotlib backend: QtAgg\n", + "%pylab is deprecated, use %matplotlib inline and import the required libraries.\n", + "Populating the interactive namespace from numpy and matplotlib\n", + "Fitting 3 folds for each of 180 candidates, totalling 540 fits\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", + "\n", + "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Date\n", + "2025-02-17 7998.32373\n", + "Name: 日度预测价格, dtype: float32\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250217', 'dataStatus': 'add', 'dataValue': 7998.32}]}\n", + "{\"confirmFlg\":false,\"status\":true}\n", + "20250218\n", + "{'dataDate': '20250218', 'dataItemNo': 'C01100047|TURNOVER'}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:280: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "d:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_coordinate_descent.py:631: ConvergenceWarning:\n", + "\n", + "Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.680e+05, tolerance: 4.121e+04\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Using matplotlib backend: QtAgg\n", + "%pylab is deprecated, use %matplotlib inline and import the required libraries.\n", + "Populating the interactive namespace from numpy and matplotlib\n", + "Fitting 3 folds for each of 180 candidates, totalling 540 fits\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:233: UserWarning:\n", + "\n", + "The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n", + "\n", + "C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_21000\\3095856616.py:263: FutureWarning:\n", + "\n", + "Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Date\n", + "2025-02-18 7988.078125\n", + "Name: 日度预测价格, dtype: float32\n", + "{'funcModule': '数据表信息列表', 'funcOperation': '新增', 'data': [{'dataItemNo': 'C01100047|FORECAST_PRICE', 'dataDate': '20250218', 'dataStatus': 'add', 'dataValue': 7988.08}]}\n", "{\"confirmFlg\":false,\"status\":true}\n" ] } @@ -1174,16 +1633,23 @@ "source": [ "from datetime import datetime, timedelta\n", "\n", - "start_date = datetime(2024, 10, 17)\n", - "end_date = datetime(2024, 10, 26)\n", + "start_date = datetime(2025, 2, 1)\n", + "end_date = datetime(2025, 2, 19)\n", "\n", "while start_date < end_date:\n", " print(start_date.strftime('%Y%m%d'))\n", " start(start_date)\n", - " # time.sleep(1)\n", + " # time.sleep(2)\n", " # start_1(start_date)\n", " start_date += timedelta(days=1)" ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { diff --git a/aisenzhecode/石油苯/纯苯数据项.xls b/aisenzhecode/石油苯/纯苯数据项.xls index 5c50fdf..076c47f 100644 Binary files a/aisenzhecode/石油苯/纯苯数据项.xls and b/aisenzhecode/石油苯/纯苯数据项.xls differ diff --git a/aisenzhecode/石油苯/纯苯数据项2025年2月18日备份.xls b/aisenzhecode/石油苯/纯苯数据项2025年2月18日备份.xls new file mode 100644 index 0000000..744b968 Binary files /dev/null and b/aisenzhecode/石油苯/纯苯数据项2025年2月18日备份.xls differ diff --git a/config_jingbo.py b/config_jingbo.py index e7ba947..e6038ad 100644 --- a/config_jingbo.py +++ b/config_jingbo.py @@ -95,9 +95,9 @@ ClassifyId = 1214 server_host = '192.168.100.53' login_pushreport_url = f"http://{server_host}:8080/jingbo-dev/api/server/login" -upload_url = f"http://{server_host}:8080/jingbo-dev/api/analysis/reportInfo/researchUploadReportSave" -upload_warning_url = f"http://{server_host}:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/save" -query_data_list_item_nos_url = f"http://{server_host}:8080/jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos" +upload_url = f"http://{server_host}:8080/jingbo-dev/api/analysis/reportInfo/researchUploadReportSave" # 上传报告 +upload_warning_url = f"http://{server_host}:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/save" # 停更预警 +query_data_list_item_nos_url = f"http://{server_host}:8080/jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos" # 查询数据项编码 login_data = { "data": { @@ -162,8 +162,8 @@ table_name = 'v_tbl_crude_oil_warning' ### 开关 is_train = False # 是否训练 -is_debug = False # 是否调试 -is_eta = True # 是否使用eta接口 +is_debug = True # 是否调试 +is_eta = False # 是否使用eta接口 is_market = True # 是否通过市场信息平台获取特征 ,在is_eta 为true 的情况下生效 is_timefurture = True # 是否使用时间特征 is_fivemodels = False # 是否使用之前保存的最佳的5个模型 @@ -185,7 +185,7 @@ print("数据库连接成功",host,dbname,dbusername) # 数据截取日期 start_year = 2020 # 数据开始年份 -end_time = '' # 数据截取日期 +end_time = '' # 数据截取日期 格式为 2024-01-01 freq = 'B' # 时间频率，"D": 天 "W": 周"M": 月"Q": 季度"A": 年 "H": 小时 "T": 分钟 "S": 秒 "B": 工作日 delweekenday = True if freq == 'B' else False # 是否删除周末数据 is_corr = False # 特征是否参与滞后领先提升相关系数 @@ -194,7 +194,8 @@ if add_kdj and is_edbnamelist: edbnamelist = edbnamelist+['K','D','J'] ### 模型参数 -y = 'Brent连1合约价格' # 原油指标数据的目标变量 Brent连1合约价格 Brent活跃合约 +y = 'Brent连1合约价格' # 原油指标数据的目标变量 Brent连1合约价格 Brent活跃合约 +# y = 'Brent连1合约价格' # 原油指标数据的目标变量 Brent连1合约价格 Brent活跃合约 horizon =5 # 预测的步长 input_size = 40 # 输入序列长度 train_steps = 50 if is_debug else 1000 # 训练步数,用来限定epoch次数 diff --git a/config_juxiting.py b/config_juxiting.py index 503eaed..a08c9f5 100644 --- a/config_juxiting.py +++ b/config_juxiting.py @@ -157,6 +157,7 @@ upload_data = { "funcModule":'研究报告信息', "funcOperation":'上传聚烯烃PP价格预测报告', "data":{ + "groupNo": "000127", "ownerAccount":'arui', #报告所属用户账号 "reportType":'OIL_PRICE_FORECAST', # 报告类型，固定为OIL_PRICE_FORECAST "fileName": '2000-40-5-50--100-原油指标数据.xlsx-Brent活跃合约--2024-09-06-15-01-29-预测报告.pdf', #文件名称 @@ -174,6 +175,7 @@ warning_data = { "funcModule":'原油特征停更预警', "funcOperation":'原油特征停更预警', "data":{ + "groupNo": "000127", 'WARNING_TYPE_NAME':'特征数据停更预警', 'WARNING_CONTENT':'', 'WARNING_DATE':'' @@ -202,16 +204,16 @@ table_name = 'v_tbl_crude_oil_warning' ### 开关 is_train = False # 是否训练 -is_debug = False # 是否调试 +is_debug = True # 是否调试 is_eta = False # 是否使用eta接口 is_market = False # 是否通过市场信息平台获取特征 ,在is_eta 为true 的情况下生效 is_timefurture = True # 是否使用时间特征 is_fivemodels = False # 是否使用之前保存的最佳的5个模型 is_edbcode = False # 特征使用edbcoding列表中的 is_edbnamelist = False # 自定义特征，对应上面的edbnamelist -is_update_eta = True # 预测结果上传到eta +is_update_eta = False # 预测结果上传到eta is_update_report = True # 是否上传报告 -is_update_warning_data = False # 是否上传预警数据 +is_update_warning_data = True # 是否上传预警数据 is_del_corr = 0.6 # 是否删除相关性高的特征,取值为 0-1 ，0 为不删除，0.6 表示删除相关性小于0.6的特征 is_del_tow_month = True # 是否删除两个月不更新的特征 diff --git a/config_juxiting_zhoudu.py b/config_juxiting_zhoudu.py new file mode 100644 index 0000000..8cfc725 --- /dev/null +++ b/config_juxiting_zhoudu.py @@ -0,0 +1,318 @@ +import logging +import os +import logging.handlers +import datetime +from lib.tools import MySQLDB,SQLiteHandler + + +# eta 接口token +APPID = "XNLDvxZHHugj7wJ7" +SECRET = "iSeU4s6cKKBVbt94htVY1p0sqUMqb2xa" + +# eta 接口url +sourcelisturl = 'http://10.189.2.78:8108/v1/edb/source/list' +classifylisturl = 'http://10.189.2.78:8108/v1/edb/classify/list?ClassifyType=' +uniquecodedataurl = 'http://10.189.2.78:8108/v1/edb/data?UniqueCode=4991c37becba464609b409909fe4d992&StartDate=2024-02-01' +classifyidlisturl = 'http://10.189.2.78:8108/v1/edb/list?ClassifyId=' +edbcodedataurl = 'http://10.189.2.78:8108/v1/edb/data?EdbCode=' +edbdatapushurl = 'http://10.189.2.78:8108/v1/edb/push' +edbdeleteurl = 'http://10.189.2.78:8108/v1/edb/business/edb/del' +edbbusinessurl = 'http://10.189.2.78:8108/v1/edb/business/data/del' +edbcodelist = ['ID01385938','lmcads03 lme comdty', +'GC1 COMB Comdty', +'C2404171822', +'dxy curncy', +'S5443199 ', +'S5479800', +'S5443108', +'H7358586', +'LC3FM1 INDEX', +'CNY REGN Curncy', +'s0105897', +'M0067419', +'M0066351', +'S0266372', +'S0266438', +'S0266506', +'ID01384463'] + +# 临时写死用指定的列,与上面的edbcode对应，后面更改 +edbnamelist = [ + 'ds','y', + 'LME铜价', + '黄金连1合约', + 'Brent-WTI', + '美元指数', + '甲醇鲁南价格', + '甲醇太仓港口价格', + '山东丙烯主流价', + '丙烷（山东）', + 'FEI丙烷 M1', + '在岸人民币汇率', + '南华工业品指数', + 'PVC期货主力', + 'PE期货收盘价', +'PP连续-1月', +'PP连续-5月', +'PP连续-9月', +'PP：拉丝：L5E89：出厂价：华北（第二区域）：内蒙古久泰新材料（日）' + ] + +edbcodenamedict = { +'ID01385938':'PP：拉丝：1102K：市场价：青州：国家能源宁煤（日）', +'ID01384463':'PP：拉丝：L5E89：出厂价：华北（第二区域）：内蒙古久泰新材料（日）', +'lmcads03 lme comdty':'LME铜价', +'GC1 COMB Comdty':'黄金连1合约', +'C2404171822':'Brent-WTI', +'dxy curncy':'美元指数', +'S5443199 ':'甲醇鲁南价格', +'S5479800':'甲醇太仓港口价格', +'S5443108':'山东丙烯主流价', +'H7358586':'丙烷（山东）', +'LC3FM1 INDEX':'FEI丙烷 M1', +'CNY REGN Curncy':'在岸人民币汇率', +'s0105897':'南华工业品指数', +'M0067419':'PVC期货主力', +'M0066351':'PE期货收盘价', +'S0266372':'PP连续-1月', +'S0266438':'PP连续-5月', +'S0266506':'PP连续-9月', + +} + +# eta自有数据指标编码 +modelsindex = { + 'NHITS': 'SELF0000077', + 'Informer':'SELF0000078', + 'LSTM':'SELF0000079', + 'iTransformer':'SELF0000080', + 'TSMixer':'SELF0000081', + 'TSMixerx':'SELF0000082', + 'PatchTST':'SELF0000083', + 'RNN':'SELF0000084', + 'GRU':'SELF0000085', + 'TCN':'SELF0000086', + 'BiTCN':'SELF0000087', + 'DilatedRNN':'SELF0000088', + 'MLP':'SELF0000089', + 'DLinear':'SELF0000090', + 'NLinear':'SELF0000091', + 'TFT':'SELF0000092', + 'FEDformer':'SELF0000093', + 'StemGNN':'SELF0000094', + 'MLPMultivariate':'SELF0000095', + 'TiDE':'SELF0000096', + 'DeepNPTS':'SELF0000097' + } + + + +# eta 上传预测结果的请求体，后面发起请求的时候更改 model datalist 数据 +data = { + "IndexCode": "", + "IndexName": "价格预测模型", + "Unit": "无", + "Frequency": "日度", + "SourceName": f"价格预测", + "Remark": 'ddd', + "DataList": [ + { + "Date": "2024-05-02", + "Value": 333444 + } + ] + } + +# eta 分类 +# level：3才可以获取到数据，所以需要人工把能源化工下所有的level3级都找到 + # url = 'http://10.189.2.78:8108/v1/edb/list?ClassifyId=1214' + #ParentId ":1160, 能源化工 + # ClassifyId ":1214,原油 + #ParentId ":1214,"，就是原油下所有的数据。 +ClassifyId = 1161 + + + +############################################################################################################### 变量定义--测试环境 +server_host = '192.168.100.53' + +login_pushreport_url = f"http://{server_host}:8080/jingbo-dev/api/server/login" +upload_url = f"http://{server_host}:8080/jingbo-dev/api/analysis/reportInfo/researchUploadReportSave" +upload_warning_url = f"http://{server_host}:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/save" +query_data_list_item_nos_url = f"http://{server_host}:8080/jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos" + +login_data = { + "data": { + "account": "api_test", + # "password": "MmVmNzNlOWI0MmY0ZDdjZGUwNzE3ZjFiMDJiZDZjZWU=", # Shihua@123456 + "password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=", # 123456 + "tenantHashCode": "8a4577dbd919675758d57999a1e891fe", + "terminal": "API" + }, + "funcModule": "API", + "funcOperation": "获取token" +} + +upload_data = { + "funcModule":'研究报告信息', + "funcOperation":'上传聚烯烃PP价格预测报告', + "data":{ + "ownerAccount":'arui', #报告所属用户账号 + "reportType":'OIL_PRICE_FORECAST', # 报告类型，固定为OIL_PRICE_FORECAST + "fileName": '2000-40-5-50--100-原油指标数据.xlsx-Brent活跃合约--2024-09-06-15-01-29-预测报告.pdf', #文件名称 + "fileBase64": '' ,#文件内容base64 + "categoryNo":'yyjgycbg', # 研究报告分类编码 + "smartBusinessClassCode":'JXTJGYCBG', #分析报告分类编码 + "reportEmployeeCode":"E40116", # 报告人 + "reportDeptCode" :"D0044" ,# 报告部门 + "productGroupCode":"RAW_MATERIAL" # 商品分类 + } +} + + +warning_data = { + "funcModule":'原油特征停更预警', + "funcOperation":'原油特征停更预警', + "data":{ + 'WARNING_TYPE_NAME':'特征数据停更预警', + 'WARNING_CONTENT':'', + 'WARNING_DATE':'' + } +} + +query_data_list_item_nos_data = { + "funcModule": "数据项", + "funcOperation": "查询", + "data": { + "dateStart":"20200101", + "dateEnd":"20241231", + "dataItemNoList":["Brentzdj","Brentzgj"] # 数据项编码,代表 brent最低价和最高价 + } +} + + +# 北京环境数据库 +host = '192.168.101.27' +port = 3306 +dbusername ='root' +password = '123456' +dbname = 'jingbo_test' +table_name = 'v_tbl_crude_oil_warning' + + +### 开关 +is_train = False # 是否训练 +is_debug = False # 是否调试 +is_eta = False # 是否使用eta接口 +is_market = False # 是否通过市场信息平台获取特征 ,在is_eta 为true 的情况下生效 +is_timefurture = True # 是否使用时间特征 +is_fivemodels = False # 是否使用之前保存的最佳的5个模型 +is_edbcode = False # 特征使用edbcoding列表中的 +is_edbnamelist = False # 自定义特征，对应上面的edbnamelist +is_update_eta = True # 预测结果上传到eta +is_update_report = True # 是否上传报告 +is_update_warning_data = False # 是否上传预警数据 +is_del_corr = 0.6 # 是否删除相关性高的特征,取值为 0-1 ，0 为不删除，0.6 表示删除相关性小于0.6的特征 +is_del_tow_month = True # 是否删除两个月不更新的特征 + + + +# 连接到数据库 +db_mysql = MySQLDB(host=host, user=dbusername, password=password, database=dbname) +db_mysql.connect() +print("数据库连接成功",host,dbname,dbusername) + + +# 数据截取日期 +start_year = 2020 # 数据开始年份 +end_time = '2025-01-27' # 数据截取日期 +freq = 'W' # 时间频率，"D": 天 "W": 周"M": 月"Q": 季度"A": 年 "H": 小时 "T": 分钟 "S": 秒 "B": 工作日 +delweekenday = True if freq == 'B' else False # 是否删除周末数据 +is_corr = False # 特征是否参与滞后领先提升相关系数 +add_kdj = False # 是否添加kdj指标 +if add_kdj and is_edbnamelist: + edbnamelist = edbnamelist+['K','D','J'] + +### 模型参数 +y = 'AVG-金能大唐久泰青州' +avg_cols = [ + 'PP：拉丝：1102K：出厂价：青州：国家能源宁煤（日）', + 'PP：拉丝：L5E89：出厂价：华北（第二区域）：内蒙古久泰新材料（日）', + 'PP：拉丝：L5E89：出厂价：河北、鲁北：大唐内蒙多伦（日）', + 'PP：拉丝：HP550J：市场价：青岛：金能化学（日）' +] +offsite = 80 +offsite_col = ['PP：拉丝：HP550J：市场价：青岛：金能化学（日）'] +horizon =1 # 预测的步长 +input_size = 7 # 输入序列长度 +train_steps = 50 if is_debug else 1000 # 训练步数,用来限定epoch次数 +val_check_steps = 30 # 评估频率 +early_stop_patience_steps = 5 # 早停的耐心步数 +# --- 交叉验证用的参数 +test_size = 200 # 测试集大小，定义100，后面使用的时候重新赋值 +val_size = test_size # 验证集大小,同测试集大小 + +### 特征筛选用到的参数 +k = 100 # 特征筛选数量，如果是0或者值比特征数量大，代表全部特征 +corr_threshold = 0.6 # 相关性大于0.6的特征 +rote = 0.06 # 绘图上下界阈值 + +### 计算准确率 +weight_dict = [0.4,0.15,0.1,0.1,0.25] # 权重 + + +### 文件 +data_set = 'PP指标数据.xlsx' # 数据集文件 +dataset = 'juxitingzhududataset' # 数据集文件夹 + +# 数据库名称 +db_name = os.path.join(dataset,'jbsh_juxiting.db') +sqlitedb = SQLiteHandler(db_name) +sqlitedb.connect() + +settings = f'{input_size}-{horizon}-{train_steps}--{k}-{data_set}-{y}' +# 获取日期时间 +# now = datetime.datetime.now().strftime('%Y%m%d%H%M%S') # 获取当前日期时间 +now = datetime.datetime.now().strftime('%Y-%m-%d') # 获取当前日期时间 +reportname = f'PP大模型预测报告--{end_time}.pdf' # 报告文件名 +reportname = reportname.replace(':', '-') # 替换冒号 +if end_time == '': + end_time = now +### 邮件配置 +username='1321340118@qq.com' +passwd='wgczgyhtyyyyjghi' +# recv=['liurui_test@163.com','52585119@qq.com'] +recv=['liurui_test@163.com'] +# recv=['liurui_test@163.com'] +title='reportname' +content=y+'预测报告请看附件' +file=os.path.join(dataset,'reportname') +# file=os.path.join(dataset,'14-7-50--100-原油指标数据.xlsx-Brent连1合约价格--20240731175936-预测报告.pdf') +ssl=True + + +### 日志配置 + +# 创建日志目录（如果不存在） +log_dir = 'logs' +if not os.path.exists(log_dir): + os.makedirs(log_dir) + +# 配置日志记录器 +logger = logging.getLogger('my_logger') +logger.setLevel(logging.INFO) + +# 配置文件处理器，将日志记录到文件 +file_handler = logging.handlers.RotatingFileHandler(os.path.join(log_dir, 'pricepredict.log'), maxBytes=1024 * 1024, backupCount=5) +file_handler.setFormatter(logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')) + +# 配置控制台处理器，将日志打印到控制台 +console_handler = logging.StreamHandler() +console_handler.setFormatter(logging.Formatter('%(message)s')) + +# 将处理器添加到日志记录器 +logger.addHandler(file_handler) +logger.addHandler(console_handler) + +# logger.info('当前配置：'+settings) + diff --git a/lib/dataread.py b/lib/dataread.py index 44b430a..2d4f838 100644 --- a/lib/dataread.py +++ b/lib/dataread.py @@ -44,8 +44,9 @@ plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号 # from config_jingbo import * # from config_jingbo_zhoudu import * # from config_yongan import * -# from config_juxiting import * -from config_juxiting_pro import * +from config_juxiting import * +# from config_juxiting_zhoudu import * +# from config_juxiting_pro import * @@ -259,12 +260,13 @@ def upload_warning_info(df_count): try: # 获取当前日期 warning_date = datetime.datetime.now().strftime('%Y-%m-%d') + warning_date2 = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S') # 构建预警内容 content = f'{warning_date}有{df_count}个停更' # 更新预警数据中的日期和内容 - warning_data['data']['WARNING_DATE'] = warning_date + warning_data['data']['WARNING_DATE'] = warning_date2 warning_data['data']['WARNING_CONTENT'] = content # 调用 upload_warning_data 函数上传预警数据 diff --git a/main_juxiting.py b/main_juxiting.py index 7b3a525..f7563d2 100644 --- a/main_juxiting.py +++ b/main_juxiting.py @@ -188,33 +188,35 @@ def predict_main(): sqlitedb.insert_data('most_model', (datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'), most_common_model,), columns=('ds', 'most_common_model',)) try: - if is_weekday: - # if True: - logger.info('今天是周一，发送特征预警') - # 上传预警信息到数据库 - warning_data_df = df_zhibiaoliebiao.copy() - warning_data_df = warning_data_df[warning_data_df['停更周期']> 3 ][['指标名称', '指标id', '频度','更新周期','指标来源','最后更新时间','停更周期']] - # 重命名列名 - warning_data_df = warning_data_df.rename(columns={'指标名称': 'INDICATOR_NAME', '指标id': 'INDICATOR_ID', '频度': 'FREQUENCY', '更新周期': 'UPDATE_FREQUENCY', '指标来源': 'DATA_SOURCE', '最后更新时间': 'LAST_UPDATE_DATE', '停更周期': 'UPDATE_SUSPENSION_CYCLE'}) - from sqlalchemy import create_engine - import urllib - global password - if '@' in password: - password = urllib.parse.quote_plus(password) + # if is_weekday: + if True: + # logger.info('今天是周一，发送特征预警') + # # 上传预警信息到数据库 + # warning_data_df = df_zhibiaoliebiao.copy() + # warning_data_df = warning_data_df[warning_data_df['停更周期']> 3 ][['指标名称', '指标id', '频度','更新周期','指标来源','最后更新时间','停更周期']] + # # 重命名列名 + # warning_data_df = warning_data_df.rename(columns={'指标名称': 'INDICATOR_NAME', '指标id': 'INDICATOR_ID', '频度': 'FREQUENCY', '更新周期': 'UPDATE_FREQUENCY', '指标来源': 'DATA_SOURCE', '最后更新时间': 'LAST_UPDATE_DATE', '停更周期': 'UPDATE_SUSPENSION_CYCLE'}) + # from sqlalchemy import create_engine + # import urllib + # global password + # if '@' in password: + # password = urllib.parse.quote_plus(password) - engine = create_engine(f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}') - warning_data_df['WARNING_DATE'] = datetime.date.today().strftime("%Y-%m-%d %H:%M:%S") - warning_data_df['TENANT_CODE'] = 'T0004' - # 插入数据之前查询表数据然后新增id列 - existing_data = pd.read_sql(f"SELECT * FROM {table_name}", engine) - if not existing_data.empty: - max_id = existing_data['ID'].astype(int).max() - warning_data_df['ID'] = range(max_id + 1, max_id + 1 + len(warning_data_df)) - else: - warning_data_df['ID'] = range(1, 1 + len(warning_data_df)) - warning_data_df.to_sql(table_name, con=engine, if_exists='append', index=False) + # engine = create_engine(f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}') + # warning_data_df['WARNING_DATE'] = datetime.date.today().strftime("%Y-%m-%d %H:%M:%S") + # warning_data_df['TENANT_CODE'] = 'T0004' + # # 插入数据之前查询表数据然后新增id列 + # existing_data = pd.read_sql(f"SELECT * FROM {table_name}", engine) + # if not existing_data.empty: + # max_id = existing_data['ID'].astype(int).max() + # warning_data_df['ID'] = range(max_id + 1, max_id + 1 + len(warning_data_df)) + # else: + # warning_data_df['ID'] = range(1, 1 + len(warning_data_df)) + # warning_data_df.to_sql(table_name, con=engine, if_exists='append', index=False) + # if is_update_warning_data: + # upload_warning_info(len(warning_data_df)) if is_update_warning_data: - upload_warning_info(len(warning_data_df)) + upload_warning_info(10) except: logger.info('上传预警信息到数据库失败') @@ -226,26 +228,26 @@ def predict_main(): row, col = df.shape now = datetime.datetime.now().strftime('%Y%m%d%H%M%S') - ex_Model_Juxiting(df, - horizon=horizon, - input_size=input_size, - train_steps=train_steps, - val_check_steps=val_check_steps, - early_stop_patience_steps=early_stop_patience_steps, - is_debug=is_debug, - dataset=dataset, - is_train=is_train, - is_fivemodels=is_fivemodels, - val_size=val_size, - test_size=test_size, - settings=settings, - now=now, - etadata=etadata, - modelsindex=modelsindex, - data=data, - is_eta=is_eta, - end_time=end_time, - ) + # ex_Model_Juxiting(df, + # horizon=horizon, + # input_size=input_size, + # train_steps=train_steps, + # val_check_steps=val_check_steps, + # early_stop_patience_steps=early_stop_patience_steps, + # is_debug=is_debug, + # dataset=dataset, + # is_train=is_train, + # is_fivemodels=is_fivemodels, + # val_size=val_size, + # test_size=test_size, + # settings=settings, + # now=now, + # etadata=etadata, + # modelsindex=modelsindex, + # data=data, + # is_eta=is_eta, + # end_time=end_time, + # ) logger.info('模型训练完成') diff --git a/main_juxiting_zhoudu.py b/main_juxiting_zhoudu.py new file mode 100644 index 0000000..7b3a525 --- /dev/null +++ b/main_juxiting_zhoudu.py @@ -0,0 +1,301 @@ +# 读取配置 +from lib.dataread import * +from lib.tools import SendMail,exception_logger +from models.nerulforcastmodels import ex_Model_Juxiting,model_losss,model_losss_juxiting,brent_export_pdf,tansuanli_export_pdf,pp_export_pdf,model_losss_juxiting + +import glob +import torch +torch.set_float32_matmul_precision("high") + + + +def predict_main(): + """ + 主预测函数，用于从 ETA 获取数据、处理数据、训练模型并进行预测。 + + 参数: + signature (BinanceAPI): Binance API 实例。 + etadata (EtaReader): ETA 数据读取器实例。 + is_eta (bool): 是否从 ETA 获取数据。 + data_set (str): 数据集名称。 + dataset (str): 数据集路径。 + add_kdj (bool): 是否添加 KDJ 指标。 + is_timefurture (bool): 是否添加时间衍生特征。 + end_time (str): 结束时间。 + is_edbnamelist (bool): 是否使用 EDB 名称列表。 + edbnamelist (list): EDB 名称列表。 + y (str): 预测目标列名。 + sqlitedb (SQLiteDB): SQLite 数据库实例。 + is_corr (bool): 是否进行相关性分析。 + horizon (int): 预测时域。 + input_size (int): 输入数据大小。 + train_steps (int): 训练步数。 + val_check_steps (int): 验证检查步数。 + early_stop_patience_steps (int): 早停耐心步数。 + is_debug (bool): 是否调试模式。 + dataset (str): 数据集名称。 + is_train (bool): 是否训练模型。 + is_fivemodels (bool): 是否使用五个模型。 + val_size (float): 验证集大小。 + test_size (float): 测试集大小。 + settings (dict): 模型设置。 + now (str): 当前时间。 + etadata (EtaReader): ETA 数据读取器实例。 + modelsindex (list): 模型索引列表。 + data (str): 数据类型。 + is_eta (bool): 是否从 ETA 获取数据。 + + 返回: + None + """ + global end_time + signature = BinanceAPI(APPID, SECRET) + etadata = EtaReader(signature=signature, + classifylisturl=classifylisturl, + classifyidlisturl=classifyidlisturl, + edbcodedataurl=edbcodedataurl, + edbcodelist=edbcodelist, + edbdatapushurl=edbdatapushurl, + edbdeleteurl=edbdeleteurl, + edbbusinessurl=edbbusinessurl + ) + # 获取数据 + if is_eta: + logger.info('从eta获取数据...') + signature = BinanceAPI(APPID, SECRET) + etadata = EtaReader(signature=signature, + classifylisturl=classifylisturl, + classifyidlisturl=classifyidlisturl, + edbcodedataurl=edbcodedataurl, + edbcodelist=edbcodelist, + edbdatapushurl=edbdatapushurl, + edbdeleteurl=edbdeleteurl, + edbbusinessurl=edbbusinessurl, + ) + df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_pp_data(data_set=data_set, dataset=dataset) # 原始数据，未处理 + + if is_market: + logger.info('从市场信息平台获取数据...') + try: + # 如果是测试环境，最高价最低价取excel文档 + if server_host == '192.168.100.53': + logger.info('从excel文档获取最高价最低价') + df_zhibiaoshuju = get_high_low_data(df_zhibiaoshuju) + else: + logger.info('从市场信息平台获取数据') + df_zhibiaoshuju = get_market_data(end_time,df_zhibiaoshuju) + + except : + logger.info('最高最低价拼接失败') + + # 保存到xlsx文件的sheet表 + with pd.ExcelWriter(os.path.join(dataset,data_set)) as file: + df_zhibiaoshuju.to_excel(file, sheet_name='指标数据', index=False) + df_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False) + + + # 数据处理 + df = datachuli_juxiting(df_zhibiaoshuju, df_zhibiaoliebiao, y=y, dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture, + end_time=end_time) + + else: + # 读取数据 + logger.info('读取本地数据：' + os.path.join(dataset, data_set)) + df,df_zhibiaoliebiao = getdata_juxiting(filename=os.path.join(dataset, data_set), y=y, dataset=dataset, add_kdj=add_kdj, + is_timefurture=is_timefurture, end_time=end_time) # 原始数据，未处理 + + # 更改预测列名称 + df.rename(columns={y: 'y'}, inplace=True) + + if is_edbnamelist: + df = df[edbnamelist] + df.to_csv(os.path.join(dataset, '指标数据.csv'), index=False) + # 保存最新日期的y值到数据库 + # 取第一行数据存储到数据库中 + first_row = df[['ds', 'y']].tail(1) + # 判断y的类型是否为float + if not isinstance(first_row['y'].values[0], float): + logger.info(f'{end_time}预测目标数据为空，跳过') + return None + + # 将最新真实值保存到数据库 + if not sqlitedb.check_table_exists('trueandpredict'): + first_row.to_sql('trueandpredict', sqlitedb.connection, index=False) + else: + for row in first_row.itertuples(index=False): + row_dict = row._asdict() + row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d %H:%M:%S') + check_query = sqlitedb.select_data('trueandpredict', where_condition=f"ds = '{row.ds}'") + if len(check_query) > 0: + set_clause = ", ".join([f"{key} = '{value}'" for key, value in row_dict.items()]) + sqlitedb.update_data('trueandpredict', set_clause, where_condition=f"ds = '{row.ds}'") + continue + sqlitedb.insert_data('trueandpredict', tuple(row_dict.values()), columns=row_dict.keys()) + + # 更新accuracy表的y值 + if not sqlitedb.check_table_exists('accuracy'): + pass + else: + update_y = sqlitedb.select_data('accuracy',where_condition="y is null") + if len(update_y) > 0: + logger.info('更新accuracy表的y值') + # 找到update_y 中ds且df中的y的行 + update_y = update_y[update_y['ds']<=end_time] + logger.info(f'要更新y的信息：{update_y}') + # try: + for row in update_y.itertuples(index=False): + try: + row_dict = row._asdict() + yy = df[df['ds']==row_dict['ds']]['y'].values[0] + LOW = df[df['ds']==row_dict['ds']]['Brentzdj'].values[0] + HIGH = df[df['ds']==row_dict['ds']]['Brentzgj'].values[0] + sqlitedb.update_data('accuracy', f"y = {yy},LOW_PRICE = {LOW},HIGH_PRICE = {HIGH}", where_condition=f"ds = '{row_dict['ds']}'") + except: + logger.info(f'更新accuracy表的y值失败：{row_dict}') + # except Exception as e: + # logger.info(f'更新accuracy表的y值失败：{e}') + + import datetime + # 判断当前日期是不是周一 + is_weekday = datetime.datetime.now().weekday() == 0 + if is_weekday: + logger.info('今天是周一，更新预测模型') + # 计算最近60天预测残差最低的模型名称 + model_results = sqlitedb.select_data('trueandpredict', order_by="ds DESC", limit="60") + # 删除空值率为90%以上的列 + if len(model_results) > 10: + model_results = model_results.dropna(thresh=len(model_results)*0.1,axis=1) + # 删除空行 + model_results = model_results.dropna() + modelnames = model_results.columns.to_list()[2:-1] + for col in model_results[modelnames].select_dtypes(include=['object']).columns: + model_results[col] = model_results[col].astype(np.float32) + # 计算每个预测值与真实值之间的偏差率 + for model in modelnames: + model_results[f'{model}_abs_error_rate'] = abs(model_results['y'] - model_results[model]) / model_results['y'] + # 获取每行对应的最小偏差率值 + min_abs_error_rate_values = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].min(), axis=1) + # 获取每行对应的最小偏差率值对应的列名 + min_abs_error_rate_column_name = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].idxmin(), axis=1) + # 将列名索引转换为列名 + min_abs_error_rate_column_name = min_abs_error_rate_column_name.map(lambda x: x.split('_')[0]) + # 取出现次数最多的模型名称 + most_common_model = min_abs_error_rate_column_name.value_counts().idxmax() + logger.info(f"最近60天预测残差最低的模型名称：{most_common_model}") + # 保存结果到数据库 + if not sqlitedb.check_table_exists('most_model'): + sqlitedb.create_table('most_model', columns="ds datetime, most_common_model TEXT") + sqlitedb.insert_data('most_model', (datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'), most_common_model,), columns=('ds', 'most_common_model',)) + + try: + if is_weekday: + # if True: + logger.info('今天是周一，发送特征预警') + # 上传预警信息到数据库 + warning_data_df = df_zhibiaoliebiao.copy() + warning_data_df = warning_data_df[warning_data_df['停更周期']> 3 ][['指标名称', '指标id', '频度','更新周期','指标来源','最后更新时间','停更周期']] + # 重命名列名 + warning_data_df = warning_data_df.rename(columns={'指标名称': 'INDICATOR_NAME', '指标id': 'INDICATOR_ID', '频度': 'FREQUENCY', '更新周期': 'UPDATE_FREQUENCY', '指标来源': 'DATA_SOURCE', '最后更新时间': 'LAST_UPDATE_DATE', '停更周期': 'UPDATE_SUSPENSION_CYCLE'}) + from sqlalchemy import create_engine + import urllib + global password + if '@' in password: + password = urllib.parse.quote_plus(password) + + engine = create_engine(f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}') + warning_data_df['WARNING_DATE'] = datetime.date.today().strftime("%Y-%m-%d %H:%M:%S") + warning_data_df['TENANT_CODE'] = 'T0004' + # 插入数据之前查询表数据然后新增id列 + existing_data = pd.read_sql(f"SELECT * FROM {table_name}", engine) + if not existing_data.empty: + max_id = existing_data['ID'].astype(int).max() + warning_data_df['ID'] = range(max_id + 1, max_id + 1 + len(warning_data_df)) + else: + warning_data_df['ID'] = range(1, 1 + len(warning_data_df)) + warning_data_df.to_sql(table_name, con=engine, if_exists='append', index=False) + if is_update_warning_data: + upload_warning_info(len(warning_data_df)) + except: + logger.info('上传预警信息到数据库失败') + + if is_corr: + df = corr_feature(df=df) + + df1 = df.copy() # 备份一下，后面特征筛选完之后加入ds y 列用 + logger.info(f"开始训练模型...") + row, col = df.shape + + now = datetime.datetime.now().strftime('%Y%m%d%H%M%S') + ex_Model_Juxiting(df, + horizon=horizon, + input_size=input_size, + train_steps=train_steps, + val_check_steps=val_check_steps, + early_stop_patience_steps=early_stop_patience_steps, + is_debug=is_debug, + dataset=dataset, + is_train=is_train, + is_fivemodels=is_fivemodels, + val_size=val_size, + test_size=test_size, + settings=settings, + now=now, + etadata=etadata, + modelsindex=modelsindex, + data=data, + is_eta=is_eta, + end_time=end_time, + ) + + + logger.info('模型训练完成') + + logger.info('训练数据绘图ing') + model_results3 = model_losss_juxiting(sqlitedb) + logger.info('训练数据绘图end') + + # 模型报告 + logger.info('制作报告ing') + title = f'{settings}--{end_time}-预测报告' # 报告标题 + reportname = f'PP大模型预测报告--{end_time}.pdf' # 报告文件名 + reportname = reportname.replace(':', '-') # 替换冒号 + pp_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time, + reportname=reportname,sqlitedb=sqlitedb), + + logger.info('制作报告end') + logger.info('模型训练完成') + + # # LSTM 单变量模型 + # ex_Lstm(df,input_seq_len=input_size,output_seq_len=horizon,is_debug=is_debug,dataset=dataset) + + # # lstm 多变量模型 + # ex_Lstm_M(df,n_days=input_size,out_days=horizon,is_debug=is_debug,datasetpath=dataset) + + # # GRU 模型 + # # ex_GRU(df) + + # 发送邮件 + m = SendMail( + username=username, + passwd=passwd, + recv=recv, + title=title, + content=content, + file=max(glob.glob(os.path.join(dataset,'*.pdf')), key=os.path.getctime), + ssl=ssl, + ) + # m.send_mail() + + +if __name__ == '__main__': + # global end_time + # is_on = True + # # 遍历2024-11-25 到 2024-12-3 之间的工作日日期 + # for i_time in pd.date_range('2025-1-20', '2025-2-6', freq='B'): + # end_time = i_time.strftime('%Y-%m-%d') + # try: + # predict_main() + # except: + # pass + + predict_main() \ No newline at end of file diff --git a/main_yuanyou.py b/main_yuanyou.py index 5c754dd..d24d65d 100644 --- a/main_yuanyou.py +++ b/main_yuanyou.py @@ -186,6 +186,8 @@ def predict_main(): if not sqlitedb.check_table_exists('most_model'): sqlitedb.create_table('most_model', columns="ds datetime, most_common_model TEXT") sqlitedb.insert_data('most_model', (datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'), most_common_model,), columns=('ds', 'most_common_model',)) + if is_update_warning_data: + upload_warning_info(len(warning_data_df)) try: if is_weekday: @@ -229,32 +231,32 @@ def predict_main(): row, col = df.shape now = datetime.datetime.now().strftime('%Y%m%d%H%M%S') - # ex_Model(df, - # horizon=horizon, - # input_size=input_size, - # train_steps=train_steps, - # val_check_steps=val_check_steps, - # early_stop_patience_steps=early_stop_patience_steps, - # is_debug=is_debug, - # dataset=dataset, - # is_train=is_train, - # is_fivemodels=is_fivemodels, - # val_size=val_size, - # test_size=test_size, - # settings=settings, - # now=now, - # etadata=etadata, - # modelsindex=modelsindex, - # data=data, - # is_eta=is_eta, - # end_time=end_time, - # ) + ex_Model(df, + horizon=horizon, + input_size=input_size, + train_steps=train_steps, + val_check_steps=val_check_steps, + early_stop_patience_steps=early_stop_patience_steps, + is_debug=is_debug, + dataset=dataset, + is_train=is_train, + is_fivemodels=is_fivemodels, + val_size=val_size, + test_size=test_size, + settings=settings, + now=now, + etadata=etadata, + modelsindex=modelsindex, + data=data, + is_eta=is_eta, + end_time=end_time, + ) logger.info('模型训练完成') logger.info('训练数据绘图ing') - # model_results3 = model_losss(sqlitedb,end_time=end_time) + model_results3 = model_losss(sqlitedb,end_time=end_time) logger.info('训练数据绘图end') # 模型报告 @@ -262,8 +264,8 @@ def predict_main(): title = f'{settings}--{end_time}-预测报告' # 报告标题 reportname = f'Brent原油大模型预测--{end_time}.pdf' # 报告文件名 reportname = reportname.replace(':', '-') # 替换冒号 - # brent_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time, - # reportname=reportname,sqlitedb=sqlitedb), + brent_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time, + reportname=reportname,sqlitedb=sqlitedb), logger.info('制作报告end') logger.info('模型训练完成') diff --git a/models/nerulforcastmodels.py b/models/nerulforcastmodels.py index b17d55c..3fa05a9 100644 --- a/models/nerulforcastmodels.py +++ b/models/nerulforcastmodels.py @@ -379,16 +379,17 @@ def ex_Model_Juxiting(df,horizon,input_size,train_steps,val_check_steps,early_st logger.info('读取模型：'+ filename) nf = load(filename) # 测试集预测 - # nf_test_preds = nf.cross_validation(df=df_test, val_size=val_size, test_size=test_size, n_windows=None) - # # 测试集预测结果保存 - # nf_test_preds.to_csv(os.path.join(dataset,"cross_validation.csv"),index=False) + nf_test_preds = nf.cross_validation(df=df_test, val_size=val_size, test_size=test_size, n_windows=None) + # 测试集预测结果保存 + nf_test_preds.to_csv(os.path.join(dataset,"cross_validation.csv"),index=False) - # df_test['ds'] = pd.to_datetime(df_test['ds'], errors='coerce') + df_test['ds'] = pd.to_datetime(df_test['ds'], errors='coerce') #进行未来时间预测 df_predict=nf.predict(df_test).reset_index() # 去掉index列 - df_predict.drop(columns=['index'], inplace=True) + if 'index' in df_predict.columns: + df_predict.drop(columns=['index'], inplace=True) # 处理非有限值（NA 或 inf），将其替换为 0 df_predict = df_predict.fillna(0) df_predict = df_predict.replace([np.inf, -np.inf], 0)