{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"WARNING:tensorflow:From C:\\Users\\EDY\\AppData\\Roaming\\Python\\Python311\\site-packages\\keras\\src\\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.\n",
"\n"
]
},
{
"data": {
"text/html": [
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import requests\n",
"import json\n",
"import xlrd\n",
"import xlwt\n",
"from datetime import datetime,timedelta\n",
"import time\n",
"# 变量定义\n",
"login_url = \"http://10.200.32.39/jingbo-api/api/server/login\"\n",
"search_url = \"http://10.200.32.39/jingbo-api/api/warehouse/dwDataItem/queryByItemNos\"\n",
"\n",
"login_push_url = \"http://10.200.32.39/jingbo-api/api/server/login\"\n",
"upload_url = \"http://10.200.32.39/jingbo-api/api/dw/dataValue/pushDataValueList\"\n",
"\n",
"login_data = {\n",
" \"data\": {\n",
" \"account\": \"api_dev\",\n",
" \"password\": \"ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=\",\n",
" \"tenantHashCode\": \"8a4577dbd919675758d57999a1e891fe\",\n",
" \"terminal\": \"API\"\n",
" },\n",
" \"funcModule\": \"API\",\n",
" \"funcOperation\": \"获取token\"\n",
"}\n",
"\n",
"login_push_data = {\n",
" \"data\": {\n",
" \"account\": \"api_dev\",\n",
" \"password\": \"ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=\",\n",
" \"tenantHashCode\": \"8a4577dbd919675758d57999a1e891fe\",\n",
" \"terminal\": \"API\"\n",
" },\n",
" \"funcModule\": \"API\",\n",
" \"funcOperation\": \"获取token\"\n",
"}\n",
"\n",
"read_file_path_name = \"液化气数据.xls\"\n",
"one_cols = []\n",
"two_cols = []\n",
"\n",
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sn\n",
"import random\n",
"import time\n",
"\n",
"\n",
"\n",
"\n",
"from plotly import __version__\n",
"from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot\n",
"\n",
"from sklearn import preprocessing\n",
"\n",
"from pandas import Series,DataFrame\n",
"\n",
"import matplotlib.pyplot as plt\n",
"\n",
"import sklearn.datasets as datasets\n",
"\n",
"#导入机器学习算法模型\n",
"from sklearn.linear_model import Lasso\n",
"from xgboost import XGBRegressor\n",
"\n",
"import statsmodels.api as sm\n",
"try:\n",
" from keras.preprocessing.sequence import TimeseriesGenerator\n",
"except:\n",
" from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator\n",
"\n",
"import plotly.express as px\n",
"import plotly.graph_objects as go\n",
"\n",
"import xgboost as xgb\n",
"from xgboost import plot_importance, plot_tree\n",
"from sklearn.metrics import mean_absolute_error\n",
"from statsmodels.tools.eval_measures import mse,rmse\n",
"from sklearn.model_selection import GridSearchCV\n",
"from xgboost import XGBRegressor\n",
"import warnings\n",
"import pickle\n",
"\n",
"from sklearn.metrics import mean_squared_error\n",
"\n",
"#切割训练数据和样本数据\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"#用于模型评分\n",
"from sklearn.metrics import r2_score\n",
"\n",
"le = preprocessing.LabelEncoder()\n",
"\n",
"# print(__version__) # requires version >= 1.9.0\n",
"\n",
"\n",
"import cufflinks as cf\n",
"cf.go_offline()\n",
"\n",
"random.seed(100)\n",
"\n",
"%matplotlib inline\n",
"\n",
"# 数据获取\n",
"\n",
"def get_head_auth():\n",
" login_res = requests.post(url=login_url, json=login_data, timeout=(3, 5))\n",
" text = json.loads(login_res.text)\n",
" if text[\"status\"]:\n",
" token = text[\"data\"][\"accessToken\"]\n",
" return token\n",
" else:\n",
" print(\"获取认证失败\")\n",
" return None\n",
"\n",
"\n",
"def get_data_value(token, dataItemNoList,date):\n",
" search_data = {\n",
" \"data\": {\n",
" \"date\": date,\n",
" \"dataItemNoList\": dataItemNoList\n",
" },\n",
" \"funcModule\": \"数据项\",\n",
" \"funcOperation\": \"查询\"\n",
" }\n",
" headers = {\"Authorization\": token}\n",
" search_res = requests.post(url=search_url, headers=headers, json=search_data, timeout=(3, 5))\n",
" print(search_data)\n",
" \n",
" try:\n",
" search_value = json.loads(search_res.text)[\"data\"]\n",
" print(search_value)\n",
" except json.JSONDecodeError as e:\n",
" print(f\"Error decoding JSON: {e}\")\n",
" print(\"Response content:\", search_res.text)\n",
" return None \n",
" if search_value:\n",
" return search_value\n",
" else:\n",
" print(\"今天没有新数据\")\n",
" return search_value\n",
"\n",
"\n",
"\n",
"# xls文件处理\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"def write_xls(data):\n",
" # 创建一个Workbook对象\n",
" workbook = xlwt.Workbook()\n",
"\n",
" # 创建一个Sheet对象，可指定名称\n",
" sheet = workbook.load('Sheet1')\n",
"\n",
" # 写入数据行\n",
" for row_index, row_data in enumerate(data):\n",
" for col_index, cell_data in enumerate(row_data):\n",
" sheet.write(row_index, col_index, cell_data)\n",
"\n",
" # 保存Workbook到文件\n",
" workbook.save(get_cur_time()[0] + '.xls')\n",
"\n",
"\n",
"def get_cur_time(date = ''):\n",
" if date == '':\n",
" now = datetime.now()\n",
" else:\n",
" now = date\n",
" year = now.year\n",
" month = now.month\n",
" day = now.day\n",
"\n",
" if month < 10:\n",
" month = \"0\" + str(month)\n",
" if day < 10:\n",
" day = \"0\" + str(day)\n",
" cur_time = str(year) + str(month) + str(day)\n",
" cur_time2 = str(year) + \"-\" + str(month) + \"-\" + str(day)\n",
"# cur_time = '20231011'\n",
"# cur_time2 = '2023-10-11'\n",
" return cur_time, cur_time2\n",
"\n",
"\n",
"\n",
"def get_head_push_auth():\n",
" login_res = requests.post(url=login_push_url, json=login_push_data, timeout=(3, 5))\n",
" text = json.loads(login_res.text)\n",
" if text[\"status\"]:\n",
" token = text[\"data\"][\"accessToken\"]\n",
" return token\n",
" else:\n",
" print(\"获取认证失败\")\n",
" return None\n",
"\n",
"\n",
"\n",
"def upload_data_to_system(token_push,date):\n",
" data = {\n",
" \"funcModule\": \"数据表信息列表\",\n",
" \"funcOperation\": \"新增\",\n",
" \"data\": [\n",
" {\"dataItemNo\": \"250855713|Forecast_Price|ACN\",\n",
" \"dataDate\": date,\n",
" \"dataStatus\": \"add\",\n",
" \"dataValue\": forecast_price()\n",
" }\n",
"\n",
" ]\n",
" }\n",
" headers = {\"Authorization\": token_push}\n",
" res = requests.post(url=upload_url, headers=headers, json=data, timeout=(3, 5))\n",
" # print(res.text)\n",
"\n",
" \n",
"# def upload_data_to_system(token):\n",
"# data = {\n",
"# \"funcModule\": \"数据表信息列表\",\n",
"# \"funcOperation\": \"新增\",\n",
"# \"data\": [\n",
"# {\"dataItemNo\": \"C01100036|Forecast_ Price|ACN\",\n",
"# \"dataDate\": '20230706',\n",
"# \"dataStatus\": \"add\",\n",
"# \"dataValue\": 3780.0\n",
"# }\n",
"\n",
"# ]\n",
"# }\n",
"# headers = {\"Authorization\": token}\n",
"# res = requests.post(url=upload_url, headers=headers, json=data, timeout=(3, 5))\n",
"# print(res.text)\n",
"\n",
"price_list = []\n",
" \n",
"def forecast_price():\n",
" # df_test = pd.read_csv('定价模型数据收集0212.csv')\n",
" df_test = pd.read_excel('液化气数据.xls')\n",
" df_test.drop([0],inplace=True)\n",
" try:\n",
" df_test['Date']=pd.to_datetime(df_test['Date'], format='%m/%d/%Y',infer_datetime_format=True)\n",
" except:\n",
" df_test['Date']=pd.to_datetime(df_test['Date'], format=r'%Y-%m-%d',infer_datetime_format=True)\n",
"\n",
"\n",
" df_test_1 = df_test\n",
" df_test_1=df_test_1.fillna(df_test.ffill())\n",
" df_test_1=df_test_1.fillna(df_test_1.bfill())\n",
"\n",
" # 选择用于模型训练的列名称\n",
" col_for_training = df_test_1.columns\n",
"\n",
"\n",
"\n",
"\n",
" import joblib\n",
" Best_model_DalyLGPrice = joblib.load(\"日度价格预测_液化气最佳模型.pkl\")\n",
" # 最新的一天为最后一行的数据\n",
" \n",
" df_test_1_Day = df_test_1.tail(1)\n",
" # 移除不需要的列\n",
" df_test_1_Day.index = df_test_1_Day[\"Date\"]\n",
" df_test_1_Day = df_test_1_Day.drop([\"Date\"], axis= 1)\n",
" df_test_1_Day=df_test_1_Day.drop('Price',axis=1)\n",
" df_test_1_Day=df_test_1_Day.dropna()\n",
"\n",
" for col in df_test_1_Day.columns:\n",
" df_test_1_Day[col] = pd.to_numeric(df_test_1_Day[col],errors='coerce')\n",
" #预测今日价格，显示至小数点后两位\n",
" Ypredict_Today=Best_model_DalyLGPrice.predict(df_test_1_Day)\n",
"\n",
" df_test_1_Day['日度预测价格']=Ypredict_Today\n",
" print(df_test_1_Day['日度预测价格'])\n",
" a = df_test_1_Day['日度预测价格']\n",
" a = a[0]\n",
" a = float(a)\n",
" a = round(a,2)\n",
" price_list.append(a)\n",
" return a\n",
"def optimize_Model():\n",
" from sklearn.model_selection import train_test_split\n",
" from sklearn.impute import SimpleImputer\n",
" from sklearn.preprocessing import OrdinalEncoder\n",
" from sklearn.feature_selection import SelectFromModel\n",
" from sklearn.metrics import mean_squared_error, r2_score\n",
" import pandas as pd\n",
"\n",
" pd.set_option('display.max_rows',40) \n",
" pd.set_option('display.max_columns',40) \n",
" df_test = pd.read_excel('液化气数据.xls')\n",
" df_test.drop([0],inplace=True)\n",
" try:\n",
" df_test['Date']=pd.to_datetime(df_test['Date'], format='%m/%d/%Y',infer_datetime_format=True)\n",
" except:\n",
" df_test['Date']=pd.to_datetime(df_test['Date'], format=r'%Y-%m-%d',infer_datetime_format=True)\n",
"\n",
" \n",
" #将缺失值补为前一个或者后一个数值\n",
" df_test_1 = df_test\n",
" df_test_1=df_test_1.fillna(df_test.ffill())\n",
" df_test_1=df_test_1.fillna(df_test_1.bfill())\n",
" df_test_1[\"Date\"] = pd.to_datetime(df_test_1[\"Date\"])\n",
" df_test_1.index = df_test_1[\"Date\"]\n",
" df_test_1 = df_test_1.drop([\"Date\"], axis= 1)\n",
" df_test_1 = df_test_1.astype('float')\n",
" \n",
" \n",
" import numpy as np\n",
" import pandas as pd\n",
" from pandas import Series,DataFrame\n",
"\n",
" import matplotlib.pyplot as plt\n",
"\n",
" import sklearn.datasets as datasets\n",
"\n",
" #导入机器学习算法模型\n",
" from sklearn.linear_model import Lasso\n",
" from xgboost import XGBRegressor\n",
"\n",
" import statsmodels.api as sm\n",
" try:\n",
" from keras.preprocessing.sequence import TimeseriesGenerator\n",
" except:\n",
" from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator\n",
"\n",
" import plotly.express as px\n",
" import plotly.graph_objects as go\n",
"\n",
" import xgboost as xgb\n",
" from xgboost import plot_importance, plot_tree\n",
" from sklearn.metrics import mean_absolute_error\n",
" from statsmodels.tools.eval_measures import mse,rmse\n",
" from sklearn.model_selection import GridSearchCV\n",
" from xgboost import XGBRegressor\n",
" import warnings\n",
" import pickle\n",
"\n",
" from sklearn.metrics import mean_squared_error\n",
"\n",
" #切割训练数据和样本数据\n",
" from sklearn.model_selection import train_test_split\n",
"\n",
" #用于模型评分\n",
" from sklearn.metrics import r2_score\n",
"\n",
" dataset1=df_test_1.drop('Price',axis=1)#.astype(float)\n",
"\n",
" y=df_test_1['Price']\n",
"\n",
" x=dataset1 \n",
"\n",
" train = x\n",
" target = y\n",
"\n",
" #切割数据样本集合测试集\n",
" X_train,x_test,y_train,y_true = train_test_split(train,target,test_size=0.2,random_state=0)\n",
"\n",
" #模型缩写\n",
" Lasso = Lasso(random_state=0)\n",
" XGBR = XGBRegressor(random_state=0)\n",
" #训练模型\n",
" Lasso.fit(X_train,y_train)\n",
" XGBR.fit(X_train,y_train)\n",
" #模型拟合\n",
" y_pre_Lasso = Lasso.predict(x_test)\n",
" y_pre_XGBR = XGBR.predict(x_test)\n",
"\n",
" #计算Lasso、XGBR、RandomForestR、AdaBoostR、GradientBoostingR、BaggingRegressor各模型的R²\n",
" Lasso_score = r2_score(y_true,y_pre_Lasso)\n",
" XGBR_score=r2_score(y_true,y_pre_XGBR)\n",
"\n",
" #计算Lasso、XGBR的MSE和RMSE\n",
" Lasso_MSE=mean_squared_error(y_true, y_pre_Lasso)\n",
" XGBR_MSE=mean_squared_error(y_true, y_pre_XGBR)\n",
"\n",
" Lasso_RMSE=np.sqrt(Lasso_MSE)\n",
" XGBR_RMSE=np.sqrt(XGBR_MSE)\n",
" # 将不同模型的不同误差值整合成一个表格\n",
" model_results = pd.DataFrame([['Lasso', Lasso_RMSE, Lasso_score],\n",
" ['XgBoost', XGBR_RMSE, XGBR_score]],\n",
" columns = ['模型(Model)','均方根误差(RMSE)', 'R^2 score'])\n",
" #将模型名称(Model)列设置为索引\n",
" model_results1=model_results.set_index('模型(Model)')\n",
"\n",
" model_results1\n",
" #定义plot_feature_importance函数，该函数用于计算特征重要性。此部分代码无需调整\n",
" def plot_feature_importance(importance,names,model_type):\n",
" feature_importance = np.array(importance)\n",
" feature_names = np.array(names)\n",
"\n",
" data={'feature_names':feature_names,'feature_importance':feature_importance}\n",
" fi_df = pd.DataFrame(data)\n",
"\n",
" fi_df.sort_values(by=['feature_importance'], ascending=False,inplace=True)\n",
"\n",
" plt.figure(figsize=(10,8))\n",
" sn.barplot(x=fi_df['feature_importance'], y=fi_df['feature_names'])\n",
"\n",
" plt.title(model_type + \" \"+'FEATURE IMPORTANCE')\n",
" plt.xlabel('FEATURE IMPORTANCE')\n",
" plt.ylabel('FEATURE NAMES')\n",
" from pylab import mpl\n",
" %pylab\n",
" mpl.rcParams['font.sans-serif'] = ['SimHei']\n",
" ## Xgboost 模型参数优化-初步\n",
" #参考: https://juejin.im/post/6844903661013827598 \n",
" #每次调参时，备选参数数值以同数量级的1、3、10设置即可（比如设置1、3、10，或0.1、0.3、1.0，或0.01,0.03,0.10即可）\n",
"\n",
" from xgboost import XGBRegressor\n",
" from sklearn.model_selection import GridSearchCV\n",
"\n",
" estimator = XGBRegressor(random_state=0,\n",
" nthread=4,\n",
" seed=0\n",
" )\n",
" parameters = {\n",
" 'max_depth': range (2, 11, 2), # 树的最大深度\n",
" 'n_estimators': range (50, 101, 10), # 迭代次数\n",
" 'learning_rate': [0.01, 0.03, 0.1, 0.3, 0.5, 1]\n",
" }\n",
"\n",
" grid_search_XGB = GridSearchCV(\n",
" estimator=estimator,\n",
" param_grid=parameters,\n",
" # n_jobs = 10,\n",
" cv = 3,\n",
" verbose=True\n",
" )\n",
"\n",
" grid_search_XGB.fit(X_train, y_train)\n",
" #如果电脑在此步骤报错，可能是因为计算量太大，超过硬件可支持程度，可注释掉“n_jobs=10”一行\n",
"\n",
" best_parameters = grid_search_XGB.best_estimator_.get_params()\n",
" y_pred = grid_search_XGB.predict(x_test)\n",
"\n",
" op_XGBR_score = r2_score(y_true,y_pred)\n",
" op_XGBR_MSE= mean_squared_error(y_true, y_pred)\n",
" op_XGBR_RMSE= np.sqrt(op_XGBR_MSE)\n",
"\n",
" model_results2 = pd.DataFrame([['Optimized_Xgboost', op_XGBR_RMSE, op_XGBR_score]],\n",
" columns = ['模型(Model)', '均方根误差(RMSE)', 'R^2 score'])\n",
" model_results2=model_results2.set_index('模型(Model)')\n",
"\n",
" try:\n",
" results = model_results1.append(model_results2, ignore_index = False)\n",
" except:\n",
" results = pd.concat([model_results1,model_results2],ignore_index=True)\n",
" import pickle\n",
"\n",
" Pkl_Filename = \"日度价格预测_液化气最佳模型.pkl\" \n",
"\n",
" with open(Pkl_Filename, 'wb') as file: \n",
" pickle.dump(grid_search_XGB, file)\n",
"\n",
"\n",
" \n",
"\n",
"def read_xls_data():\n",
" global one_cols, two_cols\n",
" # 打开 XLS 文件\n",
" workbook = xlrd.open_workbook(read_file_path_name)\n",
"\n",
" # 获取所有表格名称\n",
" # sheet_names = workbook.sheet_names()\n",
"\n",
" # 选择第一个表格\n",
" sheet = workbook.sheet_by_index(0)\n",
"\n",
" # 获取行数和列数\n",
" num_rows = sheet.nrows\n",
" # num_cols = sheet.ncols\n",
"\n",
" # 遍历每一行，获取单元格数据\n",
" # for i in range(num_rows):\n",
" # row_data = sheet.row_values(i)\n",
" # one_cols.append(row_data)\n",
" # two_cols.append(row_data[1])\n",
"\n",
" row_data = sheet.row_values(1)\n",
" one_cols = row_data\n",
"\n",
" # 关闭 XLS 文件\n",
" # workbook.close()\n",
"\n",
"\n",
"\n",
"def start(date=''):\n",
" read_xls_data()\n",
"\n",
" token = get_head_auth()\n",
" if not token:\n",
" return\n",
" token_push = get_head_push_auth()\n",
" if not token_push:\n",
" return\n",
" cur_time,cur_time2 = getNow(date)\n",
" datas = get_data_value(token, one_cols[1:],cur_time)\n",
"# if not datas:\n",
"# return\n",
"\n",
" # data_list = [two_cols, one_cols]\n",
" append_rows = [cur_time2]\n",
" dataItemNo_dataValue = {}\n",
" for data_value in datas:\n",
" if \"dataValue\" not in data_value:\n",
" print(data_value)\n",
" dataItemNo_dataValue[data_value[\"dataItemNo\"]] = \"\"\n",
" else:\n",
" dataItemNo_dataValue[data_value[\"dataItemNo\"]] = data_value[\"dataValue\"]\n",
" \n",
" for value in one_cols[1:]:\n",
" if value in dataItemNo_dataValue:\n",
" append_rows.append(dataItemNo_dataValue[value])\n",
" else:\n",
" append_rows.append(\"\")\n",
" save_xls(append_rows)\n",
" optimize_Model()\n",
" upload_data_to_system(token_push,cur_time)\n",
" \n",
" \n",
" \n",
" # data_list.append(three_cols)\n",
" # write_xls(data_list)\n",
"\n",
"def getNow(date='',offset=0):\n",
" from datetime import datetime\n",
" if date == '':\n",
" now = datetime.now() - timedelta(days=offset)\n",
" else:\n",
" try:\n",
" date = datetime.strptime(date, \"%Y-%m-%d\")\n",
" except:\n",
" date = datetime.strptime(date, \"%Y%m%d\")\n",
" pass\n",
" now = date\n",
" print(now,type(now))\n",
"\n",
" year = now.year\n",
" month = now.month\n",
" day = now.day\n",
"\n",
" if month < 10:\n",
" month = \"0\" + str(month)\n",
" if day < 10:\n",
" day = \"0\" + str(day)\n",
" cur_time = str(year) + str(month) + str(day)\n",
" cur_time2 = str(year) + \"-\" + str(month) + \"-\" + str(day)\n",
" return cur_time,cur_time2\n",
" \n",
"def start_1(date=''):\n",
" read_xls_data()\n",
"\n",
" token = get_head_auth()\n",
" if not token:\n",
" return\n",
" \n",
" cur_time,cur_time2 = getNow(date)\n",
" datas = get_data_value(token, one_cols[1:],date=cur_time)\n",
"# if not datas:\n",
"# return\n",
"\n",
" # data_list = [two_cols, one_cols]\n",
" append_rows = [cur_time2]\n",
" dataItemNo_dataValue = {}\n",
" for data_value in datas:\n",
" if \"dataValue\" not in data_value:\n",
" print(data_value)\n",
" dataItemNo_dataValue[data_value[\"dataItemNo\"]] = \"\"\n",
" else:\n",
" dataItemNo_dataValue[data_value[\"dataItemNo\"]] = data_value[\"dataValue\"]\n",
" \n",
" for value in one_cols[1:]:\n",
" if value in dataItemNo_dataValue:\n",
" append_rows.append(dataItemNo_dataValue[value])\n",
" else:\n",
" append_rows.append(\"\")\n",
" save_xls_1(append_rows)\n",
"\n",
" \n",
" # data_list.append(three_cols)\n",
" # write_xls(data_list)\n",
" \n",
"def save_xls_1(append_rows):\n",
"\n",
" # 打开xls文件\n",
" workbook = xlrd.open_workbook('液化气数据.xls')\n",
"\n",
" # 获取所有sheet的个数\n",
" sheet_count = len(workbook.sheet_names())\n",
"\n",
" # 获取所有sheet的名称\n",
" sheet_names = workbook.sheet_names()\n",
"\n",
" new_workbook = xlwt.Workbook()\n",
" for i in range(sheet_count):\n",
" # 获取当前sheet\n",
" sheet = workbook.sheet_by_index(i)\n",
"\n",
" # 获取sheet的行数和列数\n",
" row_count = sheet.nrows - 1\n",
" col_count = sheet.ncols\n",
" # 获取原有数据\n",
" data = []\n",
" for row in range(row_count):\n",
" row_data = []\n",
" for col in range(col_count):\n",
" row_data.append(sheet.cell_value(row, col))\n",
" data.append(row_data)\n",
" # 创建xlwt的Workbook对象\n",
" # 创建sheet\n",
" new_sheet = new_workbook.add_sheet(sheet_names[i])\n",
"\n",
" # 将原有的数据写入新的sheet\n",
" for row in range(row_count):\n",
" for col in range(col_count):\n",
" new_sheet.write(row, col, data[row][col])\n",
"\n",
" if i == 0:\n",
" # 在新的sheet中添加数据\n",
" for col in range(col_count):\n",
" new_sheet.write(row_count, col, append_rows[col])\n",
"\n",
" # 保存新的xls文件\n",
" new_workbook.save(\"液化气数据.xls\") \n",
"\n",
" \n",
" \n",
" \n",
"def check_data(dataItemNo):\n",
" token = get_head_auth()\n",
" if not token:\n",
" return\n",
"\n",
" datas = get_data_value(token, dataItemNo)\n",
" if not datas:\n",
" return\n",
"\n",
"\n",
"def save_xls(append_rows):\n",
"\n",
" # 打开xls文件\n",
" workbook = xlrd.open_workbook('液化气数据.xls')\n",
"\n",
" # 获取所有sheet的个数\n",
" sheet_count = len(workbook.sheet_names())\n",
"\n",
" # 获取所有sheet的名称\n",
" sheet_names = workbook.sheet_names()\n",
"\n",
" new_workbook = xlwt.Workbook()\n",
" for i in range(sheet_count):\n",
" # 获取当前sheet\n",
" sheet = workbook.sheet_by_index(i)\n",
"\n",
" # 获取sheet的行数和列数\n",
" row_count = sheet.nrows\n",
" col_count = sheet.ncols\n",
" # 获取原有数据\n",
" data = []\n",
" for row in range(row_count):\n",
" row_data = []\n",
" for col in range(col_count):\n",
" row_data.append(sheet.cell_value(row, col))\n",
" data.append(row_data)\n",
" # 创建xlwt的Workbook对象\n",
" # 创建sheet\n",
" new_sheet = new_workbook.add_sheet(sheet_names[i])\n",
"\n",
" # 将原有的数据写入新的sheet\n",
" for row in range(row_count):\n",
" for col in range(col_count):\n",
" new_sheet.write(row, col, data[row][col])\n",
"\n",
" if i == 0:\n",
" # 在新的sheet中添加数据\n",
" for col in range(col_count):\n",
" new_sheet.write(row_count, col, append_rows[col])\n",
"\n",
" # 保存新的xls文件\n",
" new_workbook.save(\"液化气数据.xls\")\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"\n",
"# if __name__ == \"__main__\":\n",
"# print('运行中')\n",
"# # 需要单独运行放开\n",
"# # start()\n",
"# # start_1(date='2025-01-22')\n",
"# # start_1()\n",
"\n",
"# # 每天定时12点运行\n",
"# while True:\n",
"# try:\n",
"# # 获取当前时间\n",
"# current_time = time.strftime(\"%H:%M:%S\", time.localtime())\n",
"# current_time_1 = time.strftime(\"%H:%M:%S\", time.localtime())\n",
"# # print(current_time_1)\n",
"\n",
"# # 判断当前时间是否为执行任务的时间点\n",
"# if current_time == \"09:15:00\":\n",
"# print(\"执行定时任务\")\n",
"# start()\n",
"\n",
"# # 休眠1秒钟，避免过多占用CPU资源\n",
"# time.sleep(1)\n",
"\n",
"# elif current_time_1 == \"20:00:00\":\n",
"# print(\"更新数据\")\n",
"# start_1()\n",
"# time.sleep(1)\n",
"# except:\n",
"# print('执行错误')\n",
"# time.sleep(1)\n",
"\n",
"\n",
"# # 检测数据准确性, 需要检测放开\n",
"# # check_data(\"100028098|LISTING_PRICE\")\n",
"# # check_data(\"9137070016544622XB|DAY_Yield\")\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"20250204 \n",
"2025-02-04 00:00:00 \n",
"{'data': {'date': '20250204', 'dataItemNoList': ['251926669|STRIKE_PRICE', 'C01100008|CORTED_VALUE', 'C01100008|AUCTION_MAX_PRICE', 'C01100008|YEDAY_AMOUNT', 'ICE_CL0_LAST_YEDAY_PRICE\\n', '100028046|LISTING_PRICE', 'C01100008|PLAN_SALE', '91370200163576944B|C01100008|STRIKE_PRICE', '9137078672073757X8|C01100008|STRIKE_PRICE', '91370500674526498A|C01100008|STRIKE_PRICE', '91370305773165341A|C01100008|STRIKE_PRICE', '91370521164880008P|C01100008|STRIKE_PRICE', '91370321164425136B|C01100008|STRIKE_PRICE', 'SD|GC|ZDW|LIST_PRICE', '370500|ISOBUTANE|LIST_PRICE', 'SD|YT|SG|LIST_PRICE', '91110000710926094P|C01100008|SUPPLY_MERE', '91110000710932515R|C01100008|SUPPLY_MERE', '91370500674526498A|C01100008|SUPPLY_MERE', '91370321164425136B|C01100008|SUPPLY_MERE', 'C01100008|OTHER|SUPPLY_MERE', 'SD|WJH|DEMANDS', 'C01100008|SUY_DED_DAP', 'C01100008|EFFECTIVE_STOCK', '912102117169477344|C01100008|STRIKE_PRICE', '91110304102767480H|C01100008|STRIKE_PRICE', '91130193670310403L|C01100008|STRIKE_PRICE', 'HD|LPG|IMPORT_PRICE', 'SD|WJH|SALES_PRICE']}, 'funcModule': '数据项', 'funcOperation': '查询'}\n",
"[{'dataDate': '20250204', 'dataItemNo': '100028046|LISTING_PRICE', 'dataValue': 8905.0}, {'dataDate': '20250204', 'dataItemNo': '251926669|STRIKE_PRICE', 'dataValue': 5450.0}, {'dataDate': '20250204', 'dataItemNo': '91110000710926094P|C01100008|SUPPLY_MERE', 'dataValue': 1300.0}, {'dataDate': '20250204', 'dataItemNo': '91110000710932515R|C01100008|SUPPLY_MERE'}, {'dataDate': '20250204', 'dataItemNo': '91110304102767480H|C01100008|STRIKE_PRICE', 'dataValue': 5000.0}, {'dataDate': '20250204', 'dataItemNo': '91130193670310403L|C01100008|STRIKE_PRICE', 'dataValue': 4900.0}, {'dataDate': '20250204', 'dataItemNo': '912102117169477344|C01100008|STRIKE_PRICE', 'dataValue': 4690.0}, {'dataDate': '20250204', 'dataItemNo': '91370200163576944B|C01100008|STRIKE_PRICE', 'dataValue': 5050.0}, {'dataDate': '20250204', 'dataItemNo': '91370305773165341A|C01100008|STRIKE_PRICE', 'dataValue': 5600.0}, {'dataDate': '20250204', 'dataItemNo': '91370321164425136B|C01100008|STRIKE_PRICE', 'dataValue': 5500.0}, {'dataDate': '20250204', 'dataItemNo': '91370321164425136B|C01100008|SUPPLY_MERE', 'dataValue': 200.0}, {'dataDate': '20250204', 'dataItemNo': '91370500674526498A|C01100008|STRIKE_PRICE', 'dataValue': 5608.0}, {'dataDate': '20250204', 'dataItemNo': '91370500674526498A|C01100008|SUPPLY_MERE', 'dataValue': 175.0}, {'dataDate': '20250204', 'dataItemNo': '91370521164880008P|C01100008|STRIKE_PRICE', 'dataValue': 5605.0}, {'dataDate': '20250204', 'dataItemNo': 'C01100008|AUCTION_MAX_PRICE', 'dataValue': 5400.0}, {'dataDate': '20250204', 'dataItemNo': 'C01100008|CORTED_VALUE', 'dataValue': 5400.0}, {'dataDate': '20250204', 'dataItemNo': 'C01100008|EFFECTIVE_STOCK', 'dataValue': 105.9453}, {'dataDate': '20250204', 'dataItemNo': 'C01100008|OTHER|SUPPLY_MERE', 'dataValue': 5000.0}, {'dataDate': '20250204', 'dataItemNo': 'C01100008|PLAN_SALE'}, {'dataDate': '20250204', 'dataItemNo': 'C01100008|SUY_DED_DAP', 'dataValue': -150.0}, {'dataDate': '20250204', 'dataItemNo': 'HD|LPG|IMPORT_PRICE', 'dataValue': 5450.0}, {'dataDate': '20250204', 'dataItemNo': 'SD|WJH|DEMANDS', 'dataValue': 8500.0}, {'dataDate': '20250204', 'dataItemNo': 'SD|WJH|SALES_PRICE', 'dataValue': 6900.0}]\n",
"{'dataDate': '20250204', 'dataItemNo': '91110000710932515R|C01100008|SUPPLY_MERE'}\n",
"{'dataDate': '20250204', 'dataItemNo': 'C01100008|PLAN_SALE'}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_10368\\3326068263.py:293: 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_10368\\3326068263.py:295: 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"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Using matplotlib backend: