液化气预测调试

aisenzhecode/液化石油气/液化气每日价格预测.py

@@ -1,3 +1,30 @@
+from statsmodels.tools.eval_measures import mse, rmse
+from pandas import Series, DataFrame
+import cufflinks as cf
+from sklearn.metrics import r2_score
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import mean_squared_error
+import pickle
+import warnings
+from sklearn.model_selection import GridSearchCV
+from sklearn.metrics import mean_absolute_error
+from xgboost import plot_importance, plot_tree
+import xgboost as xgb
+import plotly.graph_objects as go
+import plotly.express as px
+import statsmodels.api as sm
+from xgboost import XGBRegressor
+from sklearn.linear_model import Lasso
+import sklearn.datasets as datasets
+from sklearn import preprocessing
+from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
+from plotly import __version__
+import time
+import random
+import seaborn as sn
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
 import requests
 import json
 
@@ -38,60 +65,24 @@ read_file_path_name = "液化气数据.xlsx"
 one_cols = []
 two_cols = []
 
-import pandas as pd
-import numpy as np
-import matplotlib.pyplot as plt
-import seaborn as sn
-import random
-import time
-
-from plotly import __version__
-from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
-
-from sklearn import preprocessing
-
-from pandas import Series,DataFrame
-
-import matplotlib.pyplot as plt
-
-import sklearn.datasets as datasets
 
 # 导入机器学习算法模型
-from sklearn.linear_model import Lasso
-from xgboost import XGBRegressor
 
-import statsmodels.api as sm
 try:
     from keras.preprocessing.sequence import TimeseriesGenerator
 except:
     from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator
 
-import plotly.express as px
-import plotly.graph_objects as go
-
-import xgboost as xgb
-from xgboost import plot_importance, plot_tree
-from sklearn.metrics import mean_absolute_error
-from statsmodels.tools.eval_measures import mse,rmse
-from sklearn.model_selection import GridSearchCV
-from xgboost import XGBRegressor
-import warnings
-import pickle
-
-from sklearn.metrics import mean_squared_error
 
 # 切割训练数据和样本数据
-from sklearn.model_selection import train_test_split
 
 # 用于模型评分
-from sklearn.metrics import r2_score
 
 le = preprocessing.LabelEncoder()
 
 # print(__version__) # requires version >= 1.9.0
 
 
-import cufflinks as cf
 cf.go_offline()
 
 random.seed(100)
@@ -121,9 +112,9 @@ def get_data_value(token, dataItemNoList,date):
         "funcOperation": "查询"
     }
 
-    
     headers = {"Authorization": token}
-    search_res = requests.post(url=search_url, headers=headers, json=search_data, timeout=(3, 5))
+    search_res = requests.post(
+        url=search_url, headers=headers, json=search_data, timeout=(3, 5))
     print('数据项查询参数search_data：')
     print(search_data)
     print('数据项查询结果search_res：')
@@ -145,7 +136,8 @@ def get_data_value(token, dataItemNoList,date):
 
 
 def get_head_push_auth():
-    login_res = requests.post(url=login_push_url, json=login_push_data, timeout=(3, 5))
+    login_res = requests.post(
+        url=login_push_url, json=login_push_data, timeout=(3, 5))
     text = json.loads(login_res.text)
     if text["status"]:
         token = text["data"]["accessToken"]
@@ -155,7 +147,6 @@ def get_head_push_auth():
         return None
 
 
-
 def upload_data_to_system(token_push, date):
     data = {
         "funcModule": "数据表信息列表",
@@ -170,22 +161,25 @@ def upload_data_to_system(token_push,date):
         ]
     }
     headers = {"Authorization": token_push}
-    res = requests.post(url=upload_url, headers=headers, json=data, timeout=(3, 5))
+    res = requests.post(url=upload_url, headers=headers,
+                        json=data, timeout=(3, 5))
     print(res.text)
     print('预测值：', data['data'][0]['dataValue'])
 
 
 price_list = []
 
+
 def forecast_price():
     # df_test = pd.read_csv('定价模型数据收集0212.csv')
     df_test = pd.read_excel('液化气数据.xlsx')
     df_test.drop([0], inplace=True)
     try:
-        df_test['Date']=pd.to_datetime(df_test['Date'],  format='%m/%d/%Y',infer_datetime_format=True)
+        df_test['Date'] = pd.to_datetime(
+            df_test['Date'],  format='%m/%d/%Y', infer_datetime_format=True)
     except:
-        df_test['Date']=pd.to_datetime(df_test['Date'],  format=r'%Y-%m-%d',infer_datetime_format=True)
+        df_test['Date'] = pd.to_datetime(
-
+            df_test['Date'],  format=r'%Y-%m-%d', infer_datetime_format=True)
 
     df_test_1 = df_test
     df_test_1 = df_test_1.fillna(df_test.ffill())
@@ -194,9 +188,6 @@ def forecast_price():
     # 选择用于模型训练的列名称
     col_for_training = df_test_1.columns
 
-
-
-
     import joblib
     Best_model_DalyLGPrice = joblib.load("日度价格预测_液化气最佳模型.pkl")
     # 最新的一天为最后一行的数据
@@ -221,6 +212,8 @@ def forecast_price():
     a = round(a, 2)
     price_list.append(a)
     return a
+
+
 def optimize_Model():
     from sklearn.model_selection import train_test_split
     from sklearn.impute import SimpleImputer
@@ -234,10 +227,11 @@ def optimize_Model():
     df_test = pd.read_excel('液化气数据.xlsx')
     df_test.drop([0], inplace=True)
     try:
-        df_test['Date']=pd.to_datetime(df_test['Date'],  format='%m/%d/%Y',infer_datetime_format=True)
+        df_test['Date'] = pd.to_datetime(
+            df_test['Date'],  format='%m/%d/%Y', infer_datetime_format=True)
     except:
-        df_test['Date']=pd.to_datetime(df_test['Date'],  format=r'%Y-%m-%d',infer_datetime_format=True)
+        df_test['Date'] = pd.to_datetime(
-
+            df_test['Date'],  format=r'%Y-%m-%d', infer_datetime_format=True)
 
     # 将缺失值补为前一个或者后一个数值
     df_test_1 = df_test
@@ -248,7 +242,6 @@ def optimize_Model():
     df_test_1 = df_test_1.drop(["Date"], axis=1)
     df_test_1 = df_test_1.astype('float')
 
-    
     import numpy as np
     import pandas as pd
     from pandas import Series, DataFrame
@@ -297,7 +290,8 @@ def optimize_Model():
     target = y
 
     # 切割数据样本集合测试集
-    X_train,x_test,y_train,y_true = train_test_split(train,target,test_size=0.2,random_state=0)
+    X_train, x_test, y_train, y_true = train_test_split(
+        train, target, test_size=0.2, random_state=0)
 
     # 模型缩写
     Lasso = Lasso(random_state=0)
@@ -328,14 +322,17 @@ def optimize_Model():
 
     model_results1
     # 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
+
     def plot_feature_importance(importance, names, model_type):
         feature_importance = np.array(importance)
         feature_names = np.array(names)
 
-        data={'feature_names':feature_names,'feature_importance':feature_importance}
+        data = {'feature_names': feature_names,
+                'feature_importance': feature_importance}
         fi_df = pd.DataFrame(data)
 
-        fi_df.sort_values(by=['feature_importance'], ascending=False,inplace=True)
+        fi_df.sort_values(by=['feature_importance'],
+                          ascending=False, inplace=True)
 
         plt.figure(figsize=(10, 8))
         sn.barplot(x=fi_df['feature_importance'], y=fi_df['feature_names'])
@@ -345,7 +342,7 @@ def optimize_Model():
         plt.ylabel('FEATURE NAMES')
         from pylab import mpl
         mpl.rcParams['font.sans-serif'] = ['SimHei']
-    ## Xgboost 模型参数优化-初步
+    # Xgboost 模型参数优化-初步
     # 参考: https://juejin.im/post/6844903661013827598
     # 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）
 
@@ -387,7 +384,8 @@ def optimize_Model():
     try:
         results = model_results1.append(model_results2, ignore_index=False)
     except:
-        results = pd.concat([model_results1,model_results2],ignore_index=True)
+        results = pd.concat(
+            [model_results1, model_results2], ignore_index=True)
     import pickle
 
     Pkl_Filename = "日度价格预测_液化气最佳模型.pkl"
@@ -395,6 +393,7 @@ def optimize_Model():
     with open(Pkl_Filename, 'wb') as file:
         pickle.dump(grid_search_XGB, file)
 
+
 def read_xls_data():
     """获取特征项ID"""
     global one_cols, two_cols
@@ -425,7 +424,8 @@ def start(date=''):
             print(data_value)
             dataItemNo_dataValue[data_value["dataItemNo"]] = ""
         else:
-            dataItemNo_dataValue[data_value["dataItemNo"]] = data_value["dataValue"]
+            dataItemNo_dataValue[data_value["dataItemNo"]
+                                 ] = data_value["dataValue"]
 
     for value in one_cols:
         if value in dataItemNo_dataValue:
@@ -472,6 +472,7 @@ def getNow(date='', offset=0):
     compact_date = date_str.replace("-", "")
     return compact_date, date_str
 
+
 def start_1(date=''):
     """补充昨日数据"""
     read_xls_data()
@@ -493,7 +494,8 @@ def start_1(date=''):
             print(data_value)
             dataItemNo_dataValue[data_value["dataItemNo"]] = ""
         else:
-            dataItemNo_dataValue[data_value["dataItemNo"]] = data_value["dataValue"]
+            dataItemNo_dataValue[data_value["dataItemNo"]
+                                 ] = data_value["dataValue"]
 
     for value in one_cols:
         if value in dataItemNo_dataValue:
@@ -537,10 +539,12 @@ def save_xls_2(append_rows):
 
     except FileNotFoundError:
         # 如果文件不存在则创建新文件
-        pd.DataFrame([append_rows]).to_excel('液化气数据.xlsx', index=False, engine='openpyxl')
+        pd.DataFrame([append_rows]).to_excel(
+            '液化气数据.xlsx', index=False, engine='openpyxl')
     except Exception as e:
         print(f"保存数据时发生错误: {str(e)}")
 
+
 def check_data(dataItemNo):
     token = get_head_auth()
     if not token:
@@ -550,6 +554,7 @@ def check_data(dataItemNo):
     if not datas:
         return
 
+
 def get_queryDataListItemNos_value(token, url, dataItemNoList, dateStart, dateEnd):
 
     search_data = {
@@ -563,13 +568,15 @@ def get_queryDataListItemNos_value(token, url, dataItemNoList, dateStart, dateEn
     }
 
     headers = {"Authorization": token}
-    search_res = requests.post(url=url, headers=headers, json=search_data, timeout=(3, 5))
+    search_res = requests.post(
+        url=url, headers=headers, json=search_data, timeout=(3, 5))
     search_value = json.loads(search_res.text)["data"]
     if search_value:
         return search_value
     else:
         return None
 
+
 def save_queryDataListItemNos_xls(data_df, dataItemNoList):
     from datetime import datetime, timedelta
     current_year_month = datetime.now().strftime('%Y-%m')
@@ -624,7 +631,9 @@ def queryDataListItemNos(date=None,token=None):
     # 格式化为 YYYYMMDD 格式
     dateEnd = current_date.strftime('%Y%m%d')
     dateStart = first_day_of_month.strftime('%Y%m%d')
-    search_value = get_queryDataListItemNos_value(token, queryDataListItemNos_url, dataItemNoList, dateStart, dateEnd)
+    # dateStart = '20250604'
+    search_value = get_queryDataListItemNos_value(
+        token, queryDataListItemNos_url, dataItemNoList, dateStart, dateEnd)
     data_df = pd.DataFrame(search_value)
     data_df["dataDate"] = pd.to_datetime(data_df["dataDate"])
     data_df["dataDate"] = data_df["dataDate"].dt.strftime('%Y-%m-%d')
@@ -632,8 +641,6 @@ def queryDataListItemNos(date=None,token=None):
     print('当月数据更新完成')
 
 
-
-
 def main(start_date=None, token=None, token_push=None):
     from datetime import datetime, timedelta
     if start_date is None:
@@ -654,10 +661,18 @@ def main(start_date=None,token=None,token_push=None):
     # start(date)
     # 训练模型
     optimize_Model()
-    # # 预测&上传预测结果
+    # 预测&上传预测结果
     upload_data_to_system(token_push, start_date)
+    # forecast_price()
 
 
 if __name__ == "__main__":
     print("运行中ing...")
+    # 遍历2024-11-25 到 2024-12-3 之间的工作日日期
+    # for i_time in pd.date_range('2025-7-1', '2025-7-8', freq='D'):
+    #     # try:
+    #     print(i_time)
+    #     main(start_date=i_time)
+    # except Exception as e:
+    #     continue
     main()