2024-12-09 13:59:33 +08:00
{
"cells": [
{
"cell_type": "code",
2024-12-18 17:51:01 +08:00
"execution_count": 2,
2024-12-09 13:59:33 +08:00
"id": "9daadf20-caa6-4b25-901c-6cc3ef563f58",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-12-18 17:51:01 +08:00
"(85, 28)\n",
2024-12-09 13:59:33 +08:00
"(20, 4)\n",
2024-12-18 17:51:01 +08:00
"(85, 31)\n",
" ds NHITS Informer LSTM iTransformer TSMixer \\\n",
"0 2024-11-25 75.714300 75.523370 73.614220 75.27068 75.03936 \n",
"1 2024-11-26 76.039635 75.558270 73.692310 75.04110 74.60100 \n",
"2 2024-11-27 77.375790 75.361885 73.826140 74.99121 74.37731 \n",
"3 2024-11-28 78.872400 76.339920 73.883484 75.79425 74.04826 \n",
"4 2024-11-29 79.576970 76.333170 73.876396 75.89008 74.07330 \n",
2024-12-09 13:59:33 +08:00
"\n",
2024-12-18 17:51:01 +08:00
" TSMixerx PatchTST RNN GRU ... y \\\n",
"0 74.581190 75.70277 74.721280 74.512060 ... 73.010002 \n",
"1 73.496025 75.97611 74.588060 74.713425 ... 72.809998 \n",
"2 73.522026 76.48628 74.486400 74.946010 ... 72.830002 \n",
"3 73.416306 76.38267 75.195710 74.946014 ... 73.279999 \n",
"4 73.521570 76.20661 75.089966 74.935165 ... 72.940002 \n",
2024-12-09 13:59:33 +08:00
"\n",
2024-12-18 17:51:01 +08:00
" min_within_quantile max_within_quantile id CREAT_DATE min_price \\\n",
"0 74.41491 75.29100 1 2024-11-22 74.414910 \n",
"1 74.11780 74.95678 2 2024-11-22 73.496025 \n",
"2 73.93820 74.50395 3 2024-11-22 73.522026 \n",
"3 73.85808 74.46382 4 2024-11-22 73.416306 \n",
"4 73.96690 74.81860 5 2024-11-22 73.521570 \n",
"\n",
" max_price 序号 LOW_PRICE HIGH_PRICE \n",
"0 75.959854 10.0 72.30 74.83 \n",
"1 77.182580 9.0 71.63 73.80 \n",
"2 78.378624 8.0 71.71 72.85 \n",
"3 79.415400 7.0 71.85 72.96 \n",
"4 79.576970 6.0 71.75 73.34 \n",
"\n",
"[5 rows x 31 columns]\n",
" ds NHITS Informer LSTM iTransformer TSMixer \\\n",
"80 2024-12-16 74.53431 73.944080 71.68200 74.022340 74.295820 \n",
"81 2024-12-17 74.81450 73.830450 71.95232 74.314950 74.167290 \n",
"82 2024-12-18 75.55861 73.525100 72.00824 74.441380 74.212180 \n",
"83 2024-12-19 75.36518 74.012215 72.20199 74.397190 74.330130 \n",
"84 2024-12-20 74.78187 73.929596 72.23908 74.510895 74.208084 \n",
"\n",
" TSMixerx PatchTST RNN GRU ... y min_within_quantile \\\n",
"80 74.41700 74.587390 73.607780 73.747700 ... NaN 74.231680 \n",
"81 74.36576 74.363060 73.688736 73.833950 ... NaN 73.735420 \n",
"82 74.29719 74.073555 73.456700 74.146034 ... NaN 74.073555 \n",
"83 73.79145 74.529945 74.230125 74.144520 ... NaN 74.330130 \n",
"84 74.59672 74.231255 74.201860 73.996100 ... NaN 74.083810 \n",
"\n",
" max_within_quantile id CREAT_DATE min_price max_price 序号 LOW_PRICE \\\n",
"80 74.621160 81 2024-12-16 72.75007 74.62116 NaN NaN \n",
"81 74.682365 82 2024-12-16 72.72196 74.81450 NaN NaN \n",
"82 75.157074 83 2024-12-16 73.12483 75.55861 NaN NaN \n",
"83 75.339240 84 2024-12-16 73.07359 75.36518 NaN NaN \n",
"84 74.604610 85 2024-12-16 72.93583 74.78187 NaN NaN \n",
"\n",
" HIGH_PRICE \n",
"80 NaN \n",
"81 NaN \n",
"82 NaN \n",
"83 NaN \n",
"84 NaN \n",
"\n",
"[5 rows x 31 columns]\n"
2024-12-09 13:59:33 +08:00
]
}
],
"source": [
"import sqlite3\n",
"import os\n",
"import pandas as pd\n",
"\n",
"# 预测价格数据\n",
2024-12-18 17:51:01 +08:00
"# dbfilename = os.path.join(r'D:\\code\\PriceForecast\\yuanyoudataset','jbsh_yuanyou.db')\n",
"# conn = sqlite3.connect(dbfilename)\n",
"# query = 'SELECT * FROM accuracy'\n",
"# df1 = pd.read_sql_query(query, conn)\n",
"# df1['ds'] = df1['PREDICT_DATE']\n",
"# conn.close()\n",
"# print(df1.shape)\n",
2024-12-10 17:06:26 +08:00
"\n",
2024-12-18 17:51:01 +08:00
"# 预测价格数据\n",
"dfcsvfilename = os.path.join(r'D:\\code\\PriceForecast\\yuanyoudataset','accuracy_ten.csv')\n",
"df1 = pd.read_csv(dfcsvfilename)\n",
"print(df1.shape)\n",
2024-12-10 17:06:26 +08:00
"\n",
2024-12-09 13:59:33 +08:00
"# 最高最低价\n",
"xlsfilename = os.path.join(r'D:\\code\\PriceForecast\\yuanyoudataset','数据项下载.xls')\n",
"df2 = pd.read_excel(xlsfilename)[5:]\n",
2024-12-10 17:06:26 +08:00
"df2 = df2.rename(columns = {'数据项名称':'ds','布伦特最低价':'LOW_PRICE','布伦特最高价':'HIGH_PRICE'})\n",
2024-12-09 13:59:33 +08:00
"print(df2.shape)\n",
"\n",
2024-12-10 17:06:26 +08:00
"\n",
"\n",
"df = pd.merge(df1,df2,on=['ds'],how='left')\n",
"\n",
"df['ds'] = pd.to_datetime(df['ds'])\n",
2024-12-18 17:51:01 +08:00
"# df['PREDICT_DATE'] = pd.to_datetime(df['PREDICT_DATE'])\n",
2024-12-09 13:59:33 +08:00
"df = df.reindex()\n",
"\n",
"print(df.shape)\n",
"\n",
"df.to_csv(os.path.join(r'D:\\code\\PriceForecast\\yuanyoudataset','123.csv'))\n",
"# df = df[['ds','min_within_quantile','max_within_quantile']]\n",
"\n",
"\n",
"\n",
"# 打印数据框的前几行\n",
"print(df.head())\n",
"print(df.tail())\n"
]
},
{
"cell_type": "code",
2024-12-18 17:51:01 +08:00
"execution_count": 3,
2024-12-09 13:59:33 +08:00
"id": "e51c3fd0-6bff-45de-b8b6-971e7986c7a7",
"metadata": {},
2024-12-10 17:06:26 +08:00
"outputs": [
{
2024-12-18 17:51:01 +08:00
"ename": "KeyError",
"evalue": "\"None of [Index(['HIGH_PRICE_y', 'LOW_PRICE_y', 'MIN_PRICE', 'MAX_PRICE'], dtype='object')] are in the [columns]\"",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[3], line 15\u001b[0m\n\u001b[0;32m 12\u001b[0m \u001b[38;5;66;03m# 使用 apply 函数来应用计算准确率的函数\u001b[39;00m\n\u001b[0;32m 14\u001b[0m columns \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mHIGH_PRICE_y\u001b[39m\u001b[38;5;124m'\u001b[39m,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mLOW_PRICE_y\u001b[39m\u001b[38;5;124m'\u001b[39m,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mMIN_PRICE\u001b[39m\u001b[38;5;124m'\u001b[39m,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mMAX_PRICE\u001b[39m\u001b[38;5;124m'\u001b[39m]\n\u001b[1;32m---> 15\u001b[0m df[columns] \u001b[38;5;241m=\u001b[39m df[columns]\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mfloat\u001b[39m)\n\u001b[0;32m 16\u001b[0m df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mACCURACY\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m df\u001b[38;5;241m.\u001b[39mapply(calculate_accuracy, axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[0;32m 19\u001b[0m \u001b[38;5;66;03m# 打印结果\u001b[39;00m\n",
"File \u001b[1;32md:\\ProgramData\\anaconda3\\Lib\\site-packages\\pandas\\core\\frame.py:3899\u001b[0m, in \u001b[0;36mDataFrame.__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 3897\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_iterator(key):\n\u001b[0;32m 3898\u001b[0m key \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(key)\n\u001b[1;32m-> 3899\u001b[0m indexer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcolumns\u001b[38;5;241m.\u001b[39m_get_indexer_strict(key, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolumns\u001b[39m\u001b[38;5;124m\"\u001b[39m)[\u001b[38;5;241m1\u001b[39m]\n\u001b[0;32m 3901\u001b[0m \u001b[38;5;66;03m# take() does not accept boolean indexers\u001b[39;00m\n\u001b[0;32m 3902\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mgetattr\u001b[39m(indexer, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdtype\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m) \u001b[38;5;241m==\u001b[39m \u001b[38;5;28mbool\u001b[39m:\n",
"File \u001b[1;32md:\\ProgramData\\anaconda3\\Lib\\site-packages\\pandas\\core\\indexes\\base.py:6115\u001b[0m, in \u001b[0;36mIndex._get_indexer_strict\u001b[1;34m(self, key, axis_name)\u001b[0m\n\u001b[0;32m 6112\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 6113\u001b[0m keyarr, indexer, new_indexer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_reindex_non_unique(keyarr)\n\u001b[1;32m-> 6115\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_raise_if_missing(keyarr, indexer, axis_name)\n\u001b[0;32m 6117\u001b[0m keyarr \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtake(indexer)\n\u001b[0;32m 6118\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(key, Index):\n\u001b[0;32m 6119\u001b[0m \u001b[38;5;66;03m# GH 42790 - Preserve name from an Index\u001b[39;00m\n",
"File \u001b[1;32md:\\ProgramData\\anaconda3\\Lib\\site-packages\\pandas\\core\\indexes\\base.py:6176\u001b[0m, in \u001b[0;36mIndex._raise_if_missing\u001b[1;34m(self, key, indexer, axis_name)\u001b[0m\n\u001b[0;32m 6174\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m use_interval_msg:\n\u001b[0;32m 6175\u001b[0m key \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(key)\n\u001b[1;32m-> 6176\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNone of [\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mkey\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m] are in the [\u001b[39m\u001b[38;5;132;01m{\u001b[39;00maxis_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m]\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 6178\u001b[0m not_found \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(ensure_index(key)[missing_mask\u001b[38;5;241m.\u001b[39mnonzero()[\u001b[38;5;241m0\u001b[39m]]\u001b[38;5;241m.\u001b[39munique())\n\u001b[0;32m 6179\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mnot_found\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m not in index\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
"\u001b[1;31mKeyError\u001b[0m: \"None of [Index(['HIGH_PRICE_y', 'LOW_PRICE_y', 'MIN_PRICE', 'MAX_PRICE'], dtype='object')] are in the [columns]\""
2024-12-10 17:06:26 +08:00
]
}
],
"source": [
"# 定义一个函数来计算准确率\n",
"def calculate_accuracy(row):\n",
" if row['HIGH_PRICE_y'] > row['MIN_PRICE']:\n",
" sorted_prices = sorted([row['LOW_PRICE_y'], row['MIN_PRICE'], row['MAX_PRICE'], row['HIGH_PRICE_y']])\n",
" middle_diff = sorted_prices[2] - sorted_prices[1]\n",
" price_range = row['HIGH_PRICE_y'] - row['LOW_PRICE_y']\n",
" accuracy = middle_diff / price_range\n",
" return accuracy\n",
" else:\n",
" return 0\n",
"\n",
"# 使用 apply 函数来应用计算准确率的函数\n",
"\n",
"columns = ['HIGH_PRICE_y','LOW_PRICE_y','MIN_PRICE','MAX_PRICE']\n",
"df[columns] = df[columns].astype(float)\n",
"df['ACCURACY'] = df.apply(calculate_accuracy, axis=1)\n",
"\n",
"\n",
"# 打印结果\n",
"print(df[['ds','ACCURACY',]+columns])\n",
"\n",
"df = df[['ds','ACCURACY','PREDICT_DATE','CREAT_DATE']+columns]"
]
},
{
"cell_type": "code",
2024-12-11 14:52:45 +08:00
"execution_count": 138,
2024-12-10 17:06:26 +08:00
"id": "0f942c69",
"metadata": {},
"outputs": [],
"source": [
"import datetime\n",
"# ds 按周取\n",
"df['Ds_Week'] = df['ds'].apply(lambda x: x.strftime('%U'))\n",
"df['Pre_Week'] = df['PREDICT_DATE'].apply(lambda x: x.strftime('%U'))"
]
},
{
"cell_type": "code",
2024-12-11 14:52:45 +08:00
"execution_count": 139,
2024-12-10 17:06:26 +08:00
"id": "a7b05510",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ds</th>\n",
" <th>ACCURACY</th>\n",
" <th>PREDICT_DATE</th>\n",
" <th>CREAT_DATE</th>\n",
" <th>HIGH_PRICE_y</th>\n",
" <th>LOW_PRICE_y</th>\n",
" <th>MIN_PRICE</th>\n",
" <th>MAX_PRICE</th>\n",
" <th>Ds_Week</th>\n",
" <th>Pre_Week</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2024-11-26</td>\n",
" <td>1.000000</td>\n",
" <td>2024-11-26</td>\n",
" <td>2024-11-25</td>\n",
" <td>73.80</td>\n",
" <td>71.63</td>\n",
" <td>71.071556</td>\n",
" <td>76.006900</td>\n",
" <td>47</td>\n",
" <td>47</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2024-11-27</td>\n",
" <td>1.000000</td>\n",
" <td>2024-11-27</td>\n",
" <td>2024-11-25</td>\n",
" <td>72.85</td>\n",
" <td>71.71</td>\n",
" <td>71.003624</td>\n",
" <td>75.580560</td>\n",
" <td>47</td>\n",
" <td>47</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2024-11-28</td>\n",
" <td>0.789324</td>\n",
" <td>2024-11-28</td>\n",
" <td>2024-11-25</td>\n",
" <td>72.96</td>\n",
" <td>71.85</td>\n",
" <td>72.083850</td>\n",
" <td>76.204260</td>\n",
" <td>47</td>\n",
" <td>47</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2024-11-29</td>\n",
" <td>1.000000</td>\n",
" <td>2024-11-29</td>\n",
" <td>2024-11-25</td>\n",
" <td>73.34</td>\n",
" <td>71.75</td>\n",
" <td>71.329730</td>\n",
" <td>75.703950</td>\n",
" <td>47</td>\n",
" <td>47</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2024-12-02</td>\n",
" <td>0.853412</td>\n",
" <td>2024-12-02</td>\n",
" <td>2024-11-25</td>\n",
" <td>72.89</td>\n",
" <td>71.52</td>\n",
" <td>71.720825</td>\n",
" <td>76.264275</td>\n",
" <td>48</td>\n",
" <td>48</td>\n",
" </tr>\n",
" <tr>\n",
2024-12-11 14:52:45 +08:00
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
2024-12-10 17:06:26 +08:00
" </tr>\n",
" <tr>\n",
2024-12-11 14:52:45 +08:00
" <th>70</th>\n",
" <td>2024-11-25</td>\n",
" <td>0.118328</td>\n",
" <td>2024-11-25</td>\n",
" <td>2024-11-22</td>\n",
" <td>74.83</td>\n",
" <td>72.30</td>\n",
" <td>74.530630</td>\n",
" <td>76.673140</td>\n",
2024-12-10 17:06:26 +08:00
" <td>47</td>\n",
" <td>47</td>\n",
" </tr>\n",
" <tr>\n",
2024-12-11 14:52:45 +08:00
" <th>71</th>\n",
2024-12-10 17:06:26 +08:00
" <td>2024-11-26</td>\n",
2024-12-11 14:52:45 +08:00
" <td>0.000000</td>\n",
" <td>2024-11-26</td>\n",
" <td>2024-11-22</td>\n",
" <td>73.80</td>\n",
" <td>71.63</td>\n",
" <td>74.440430</td>\n",
" <td>76.874565</td>\n",
2024-12-10 17:06:26 +08:00
" <td>47</td>\n",
" <td>47</td>\n",
" </tr>\n",
" <tr>\n",
2024-12-11 14:52:45 +08:00
" <th>72</th>\n",
" <td>2024-11-27</td>\n",
" <td>0.000000</td>\n",
" <td>2024-11-27</td>\n",
" <td>2024-11-22</td>\n",
" <td>72.85</td>\n",
" <td>71.71</td>\n",
" <td>74.663180</td>\n",
" <td>76.734130</td>\n",
" <td>47</td>\n",
" <td>47</td>\n",
2024-12-10 17:06:26 +08:00
" </tr>\n",
" <tr>\n",
2024-12-11 14:52:45 +08:00
" <th>73</th>\n",
2024-12-10 17:06:26 +08:00
" <td>2024-11-28</td>\n",
2024-12-11 14:52:45 +08:00
" <td>0.000000</td>\n",
2024-12-10 17:06:26 +08:00
" <td>2024-11-28</td>\n",
2024-12-11 14:52:45 +08:00
" <td>2024-11-22</td>\n",
2024-12-10 17:06:26 +08:00
" <td>72.96</td>\n",
" <td>71.85</td>\n",
2024-12-11 14:52:45 +08:00
" <td>74.708410</td>\n",
" <td>77.141050</td>\n",
2024-12-10 17:06:26 +08:00
" <td>47</td>\n",
" <td>47</td>\n",
" </tr>\n",
" <tr>\n",
2024-12-11 14:52:45 +08:00
" <th>74</th>\n",
2024-12-10 17:06:26 +08:00
" <td>2024-11-29</td>\n",
2024-12-11 14:52:45 +08:00
" <td>0.000000</td>\n",
2024-12-10 17:06:26 +08:00
" <td>2024-11-29</td>\n",
2024-12-11 14:52:45 +08:00
" <td>2024-11-22</td>\n",
2024-12-10 17:06:26 +08:00
" <td>73.34</td>\n",
" <td>71.75</td>\n",
2024-12-11 14:52:45 +08:00
" <td>74.703210</td>\n",
" <td>77.746170</td>\n",
2024-12-10 17:06:26 +08:00
" <td>47</td>\n",
" <td>47</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
2024-12-11 14:52:45 +08:00
"<p>75 rows ×
2024-12-10 17:06:26 +08:00
"</div>"
],
"text/plain": [
" ds ACCURACY PREDICT_DATE CREAT_DATE HIGH_PRICE_y LOW_PRICE_y \\\n",
"0 2024-11-26 1.000000 2024-11-26 2024-11-25 73.80 71.63 \n",
"1 2024-11-27 1.000000 2024-11-27 2024-11-25 72.85 71.71 \n",
"2 2024-11-28 0.789324 2024-11-28 2024-11-25 72.96 71.85 \n",
"3 2024-11-29 1.000000 2024-11-29 2024-11-25 73.34 71.75 \n",
"4 2024-12-02 0.853412 2024-12-02 2024-11-25 72.89 71.52 \n",
2024-12-11 14:52:45 +08:00
".. ... ... ... ... ... ... \n",
"70 2024-11-25 0.118328 2024-11-25 2024-11-22 74.83 72.30 \n",
"71 2024-11-26 0.000000 2024-11-26 2024-11-22 73.80 71.63 \n",
"72 2024-11-27 0.000000 2024-11-27 2024-11-22 72.85 71.71 \n",
"73 2024-11-28 0.000000 2024-11-28 2024-11-22 72.96 71.85 \n",
"74 2024-11-29 0.000000 2024-11-29 2024-11-22 73.34 71.75 \n",
2024-12-10 17:06:26 +08:00
"\n",
" MIN_PRICE MAX_PRICE Ds_Week Pre_Week \n",
"0 71.071556 76.006900 47 47 \n",
"1 71.003624 75.580560 47 47 \n",
"2 72.083850 76.204260 47 47 \n",
"3 71.329730 75.703950 47 47 \n",
"4 71.720825 76.264275 48 48 \n",
2024-12-11 14:52:45 +08:00
".. ... ... ... ... \n",
"70 74.530630 76.673140 47 47 \n",
"71 74.440430 76.874565 47 47 \n",
"72 74.663180 76.734130 47 47 \n",
"73 74.708410 77.141050 47 47 \n",
"74 74.703210 77.746170 47 47 \n",
"\n",
"[75 rows x 10 columns]"
2024-12-10 17:06:26 +08:00
]
},
2024-12-11 14:52:45 +08:00
"execution_count": 139,
2024-12-10 17:06:26 +08:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
2024-12-11 14:52:45 +08:00
"execution_count": 140,
2024-12-10 17:06:26 +08:00
"id": "1374e354",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-12-11 14:52:45 +08:00
"['2024-11-22', '2024-11-23', '2024-11-24', '2024-11-25', '2024-11-26', '2024-11-27', '2024-11-28', '2024-11-29']\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-12-10 17:06:26 +08:00
"(15, 10)\n"
]
}
],
"source": [
"# 取结束日期上一周的日期\n",
2024-12-11 14:52:45 +08:00
"endtime = '2024-12-3'\n",
2024-12-10 17:06:26 +08:00
"endtimeweek = datetime.datetime.strptime(endtime, '%Y-%m-%d')\n",
"up_week = endtimeweek - datetime.timedelta(days=endtimeweek.weekday() + 14)\n",
"up_week_dates = [up_week + datetime.timedelta(days=i) for i in range(14)][4:-2]\n",
"up_week_dates = [date.strftime('%Y-%m-%d') for date in up_week_dates]\n",
"print(up_week_dates)\n",
"\n",
"\n",
"df3 = df.copy()\n",
"df3 = df3[df3['CREAT_DATE'].isin(up_week_dates)]\n",
"df3 = df3[df3['PREDICT_DATE'].isin(up_week_dates)]\n",
"print(df3.shape)\n",
"df3.to_csv('up_week_dates.csv',index=False)"
]
},
{
"cell_type": "code",
2024-12-11 14:52:45 +08:00
"execution_count": 141,
2024-12-10 17:06:26 +08:00
"id": "8aa47e90",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-12-11 14:52:45 +08:00
"2024-11-25 00:00:00\n",
2024-12-10 17:06:26 +08:00
"权重： 0.07\n",
2024-12-11 14:52:45 +08:00
"准确率： 1.7749209486165771\n",
"2024-11-26 00:00:00\n",
2024-12-10 17:06:26 +08:00
"权重： 0.13\n",
"准确率： 7.5\n",
2024-12-11 14:52:45 +08:00
"2024-11-27 00:00:00\n",
2024-12-10 17:06:26 +08:00
"权重： 0.2\n",
2024-12-11 14:52:45 +08:00
"准确率： 8.034364035087705\n",
"2024-11-28 00:00:00\n",
2024-12-10 17:06:26 +08:00
"权重： 0.27\n",
2024-12-11 14:52:45 +08:00
"准确率： 9.718006756756724\n",
"2024-11-29 00:00:00\n",
2024-12-10 17:06:26 +08:00
"权重： 0.33\n",
2024-12-11 14:52:45 +08:00
"准确率： 10.824716981132076\n",
"37.85200872159308\n"
2024-12-10 17:06:26 +08:00
]
}
],
"source": [
"total = len(df3)\n",
"accuracy_rote = 0\n",
"# for i,group in df3.groupby('CREAT_DATE'):\n",
"for i,group in df3.groupby('ds'):\n",
" print(i)\n",
" print('权重：',round(len(group)/total,2))\n",
" print('准确率：',group['ACCURACY'].sum()/(len(group)/total))\n",
" accuracy_rote += group['ACCURACY'].sum()/(len(group)/total)\n",
"\n",
"print(accuracy_rote)"
]
2024-12-09 13:59:33 +08:00
}
],
"metadata": {
"kernelspec": {
2024-12-10 17:06:26 +08:00
"display_name": "base",
2024-12-09 13:59:33 +08:00
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
