liurui/PriceForecast
Template
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

丙烯py添加当月数据维护功能

Browse Source
This commit is contained in:
workpc 2025-07-08 11:25:31 +08:00
parent 91387a7241
commit d529d0cee6
3 changed files with 244 additions and 159 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
aisenzhecode/聚合级丙烯/丙烯基础数据收集表.xlsx Normal file
View File

Binary file not shown.

403
aisenzhecode/聚合级丙烯/丙烯每日价格预测.py
View File

@ -1,3 +1,31 @@
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
from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator
import statsmodels.api as sm
import datetime
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 random
import seaborn as sn
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import requests import requests
import json import json
import xlrd import xlrd
@ -7,6 +35,7 @@ import time
# 变量定义 # 变量定义
login_url = "http://10.200.32.39/jingbo-api/api/server/login" login_url = "http://10.200.32.39/jingbo-api/api/server/login"
search_url = "http://10.200.32.39/jingbo-api/api/warehouse/dwDataItem/queryByItemNos" search_url = "http://10.200.32.39/jingbo-api/api/warehouse/dwDataItem/queryByItemNos"
queryDataListItemNos_url = "http://10.200.32.39/jingbo-api//api/warehouse/dwDataItem/queryDataListItemNos"
login_push_url = "http://10.200.32.39/jingbo-api/api/server/login" login_push_url = "http://10.200.32.39/jingbo-api/api/server/login"
upload_url = "http://10.200.32.39/jingbo-api/api/dw/dataValue/pushDataValueList" upload_url = "http://10.200.32.39/jingbo-api/api/dw/dataValue/pushDataValueList"
@ -37,67 +66,24 @@ read_file_path_name = "丙烯基础数据收集表.xls"
one_cols = [] one_cols = []
two_cols = [] two_cols = []
import pandas as pd
import numpy as np # 导入机器学习算法模型
import matplotlib.pyplot as plt
import seaborn as sn
import random
import time
# 切割训练数据和样本数据
# 用于模型评分
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 datetime
import statsmodels.api as sm
from 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() le = preprocessing.LabelEncoder()
# print(__version__) # requires version >= 1.9.0 # print(__version__) # requires version >= 1.9.0
import cufflinks as cf
cf.go_offline() cf.go_offline()
random.seed(100) random.seed(100)
# 数据获取 # 数据获取
def get_head_auth(): def get_head_auth():
@ -121,7 +107,8 @@ def get_data_value(token, dataItemNoList):
"funcOperation": "查询" "funcOperation": "查询"
} }
headers = {"Authorization": token} 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))
search_value = json.loads(search_res.text)["data"] search_value = json.loads(search_res.text)["data"]
if search_value: if search_value:
return search_value return search_value
@ -166,7 +153,8 @@ def get_cur_time():
def get_head_push_auth(): 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) text = json.loads(login_res.text)
if text["status"]: if text["status"]:
token = text["data"]["accessToken"] token = text["data"]["accessToken"]
@ -176,7 +164,6 @@ def get_head_push_auth():
return None return None
def upload_data_to_system(token_push): def upload_data_to_system(token_push):
data = { data = {
"funcModule": "数据表信息列表", "funcModule": "数据表信息列表",
@ -185,17 +172,18 @@ def upload_data_to_system(token_push):
{"dataItemNo": "C01100007|Forecast_Price|ACN", {"dataItemNo": "C01100007|Forecast_Price|ACN",
"dataDate": get_cur_time()[0], "dataDate": get_cur_time()[0],
"dataStatus": "add", "dataStatus": "add",
# "dataValue": 7100 # "dataValue": 7100
"dataValue": forecast_price() "dataValue": forecast_price()
} }
] ]
} }
headers = {"Authorization": token_push} 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(res.text)
# def upload_data_to_system(token): # def upload_data_to_system(token):
# data = { # data = {
# "funcModule": "数据表信息列表", # "funcModule": "数据表信息列表",
@ -213,92 +201,95 @@ def upload_data_to_system(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(res.text)
def forecast_price(): def forecast_price():
# df_test = pd.read_csv('定价模型数据收集0212.csv') # df_test = pd.read_csv('定价模型数据收集0212.csv')
df_test = pd.read_excel('丙烯基础数据收集表.xls') df_test = pd.read_excel('丙烯基础数据收集表.xlsx')
df_test.drop([0],inplace=True) df_test.drop([0], inplace=True)
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='%Y-%m-%d', infer_datetime_format=True)
#将缺失值补为前一个或者后一个数值 # 将缺失值补为前一个或者后一个数值
df_test_1 = df_test df_test_1 = df_test
df_test_1=df_test_1.fillna(df_test.ffill()) df_test_1 = df_test_1.fillna(df_test.ffill())
df_test_1=df_test_1.fillna(df_test_1.bfill()) df_test_1 = df_test_1.fillna(df_test_1.bfill())
# 选择用于模型训练的列名称 # 选择用于模型训练的列名称
col_for_training = df_test_1.columns col_for_training = df_test_1.columns
import joblib import joblib
Best_model_DalyLGPrice = joblib.load("日度价格预测_丙烯最佳模型.pkl") Best_model_DalyLGPrice = joblib.load("日度价格预测_丙烯最佳模型.pkl")
# 最新的一天为最后一行的数据 # 最新的一天为最后一行的数据
df_test_1_Day = df_test_1.tail(1) df_test_1_Day = df_test_1.tail(1)
# 移除不需要的列 # 移除不需要的列
df_test_1_Day.index = df_test_1_Day["Date"] df_test_1_Day.index = df_test_1_Day["Date"]
df_test_1_Day = df_test_1_Day.drop(["Date"], axis= 1) df_test_1_Day = df_test_1_Day.drop(["Date"], axis=1)
df_test_1_Day=df_test_1_Day.drop('Price',axis=1) df_test_1_Day = df_test_1_Day.drop('Price', axis=1)
df_test_1_Day=df_test_1_Day.dropna() df_test_1_Day = df_test_1_Day.dropna()
# 转换数据类型
df_test_1_Day = df_test_1_Day.astype(float)
# df_test_1_Day # df_test_1_Day
#预测今日价格，显示至小数点后两位 # 预测今日价格，显示至小数点后两位
Ypredict_Today=Best_model_DalyLGPrice.predict(df_test_1_Day) Ypredict_Today = Best_model_DalyLGPrice.predict(df_test_1_Day)
df_test_1_Day['日度预测价格']=Ypredict_Today df_test_1_Day['日度预测价格'] = Ypredict_Today
print(df_test_1_Day['日度预测价格']) print(df_test_1_Day['日度预测价格'])
a = df_test_1_Day['日度预测价格'] a = df_test_1_Day['日度预测价格']
a = a[0] a = a[0]
a = float(a) a = float(a)
a = round(a,2) a = round(a, 2)
return a return a
def optimize_Model(): def optimize_Model():
from sklearn.model_selection import train_test_split from sklearn.model_selection import train_test_split
from sklearn.impute import SimpleImputer from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OrdinalEncoder from sklearn.preprocessing import OrdinalEncoder
from sklearn.feature_selection import SelectFromModel from sklearn.feature_selection import SelectFromModel
from sklearn.metrics import mean_squared_error, r2_score from sklearn.metrics import mean_squared_error, r2_score
import pandas as pd import pandas as pd
pd.set_option('display.max_rows',40) pd.set_option('display.max_rows', 40)
pd.set_option('display.max_columns',40) pd.set_option('display.max_columns', 40)
df_test = pd.read_excel('丙烯基础数据收集表.xls') df_test = pd.read_excel('丙烯基础数据收集表.xlsx')
df_test.drop([0],inplace=True) df_test.drop([0], inplace=True)
df_test['Date']=pd.to_datetime(df_test['Date'], format='%m/%d/%Y',infer_datetime_format=True) df_test['Date'] = pd.to_datetime(
#查看每个特征缺失值数量 df_test['Date'], format='%Y-%m-%d', infer_datetime_format=True)
MisVal_Check=df_test.isnull().sum().sort_values(ascending=False) # 查看每个特征缺失值数量
#去掉缺失值百分比>0.4的特征，去掉这些特征后的新表格命名为df_test_1 MisVal_Check = df_test.isnull().sum().sort_values(ascending=False)
df_MisVal_Check = pd.DataFrame(MisVal_Check,)# # 去掉缺失值百分比>0.4的特征，去掉这些特征后的新表格命名为df_test_1
df_MisVal_Check_1=df_MisVal_Check.reset_index() df_MisVal_Check = pd.DataFrame(MisVal_Check,)
df_MisVal_Check_1.columns=['Variable_Name','Missing_Number'] df_MisVal_Check_1 = df_MisVal_Check.reset_index()
df_MisVal_Check_1['Missing_Number']=df_MisVal_Check_1['Missing_Number']/len(df_test) df_MisVal_Check_1.columns = ['Variable_Name', 'Missing_Number']
df_test_1=df_test.drop(df_MisVal_Check_1[df_MisVal_Check_1['Missing_Number']>0.4].Variable_Name,axis = 1) df_MisVal_Check_1['Missing_Number'] = df_MisVal_Check_1['Missing_Number'] / \
#将缺失值补为前一个或者后一个数值 len(df_test)
df_test_1 = df_test.drop(
df_MisVal_Check_1[df_MisVal_Check_1['Missing_Number'] > 0.4].Variable_Name, axis=1)
# 将缺失值补为前一个或者后一个数值
df_test_1 = df_test df_test_1 = df_test
df_test_1=df_test_1.fillna(df_test.ffill()) df_test_1 = df_test_1.fillna(df_test.ffill())
df_test_1=df_test_1.fillna(df_test_1.bfill()) df_test_1 = df_test_1.fillna(df_test_1.bfill())
df_test_1["Date"] = pd.to_datetime(df_test_1["Date"]) df_test_1["Date"] = pd.to_datetime(df_test_1["Date"])
df_test_1.index = df_test_1["Date"] df_test_1.index = df_test_1["Date"]
df_test_1 = df_test_1.drop(["Date"], axis= 1) df_test_1 = df_test_1.drop(["Date"], axis=1)
df_test_1 = df_test_1.astype('float') df_test_1 = df_test_1.astype('float')
import numpy as np import numpy as np
import pandas as pd import pandas as pd
from pandas import Series,DataFrame from pandas import Series, DataFrame
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
import sklearn.datasets as datasets import sklearn.datasets as datasets
#导入机器学习算法模型 # 导入机器学习算法模型
from sklearn.linear_model import Lasso from sklearn.linear_model import Lasso
from xgboost import XGBRegressor from xgboost import XGBRegressor
from datetime import datetime from datetime import datetime
import statsmodels.api as sm import statsmodels.api as sm
from keras.preprocessing.sequence import TimeseriesGenerator from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator
import plotly.express as px import plotly.express as px
import plotly.graph_objects as go import plotly.graph_objects as go
@ -306,7 +297,7 @@ def optimize_Model():
import xgboost as xgb import xgboost as xgb
from xgboost import plot_importance, plot_tree from xgboost import plot_importance, plot_tree
from sklearn.metrics import mean_absolute_error from sklearn.metrics import mean_absolute_error
from statsmodels.tools.eval_measures import mse,rmse from statsmodels.tools.eval_measures import mse, rmse
from sklearn.model_selection import GridSearchCV from sklearn.model_selection import GridSearchCV
from xgboost import XGBRegressor from xgboost import XGBRegressor
import warnings import warnings
@ -314,63 +305,67 @@ def optimize_Model():
from sklearn.metrics import mean_squared_error from sklearn.metrics import mean_squared_error
#切割训练数据和样本数据 # 切割训练数据和样本数据
from sklearn.model_selection import train_test_split from sklearn.model_selection import train_test_split
#用于模型评分 # 用于模型评分
from sklearn.metrics import r2_score from sklearn.metrics import r2_score
dataset1=df_test_1.drop('Price',axis=1)#.astype(float) dataset1 = df_test_1.drop('Price', axis=1) # .astype(float)
y=df_test_1['Price'] y = df_test_1['Price']
x=dataset1 x = dataset1
train = x train = x
target = y target = y
#切割数据样本集合测试集 # 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 # 模型缩写
Lasso = Lasso(random_state=0) Lasso = Lasso(random_state=0)
XGBR = XGBRegressor(random_state=0) XGBR = XGBRegressor(random_state=0)
#训练模型 # 训练模型
Lasso.fit(X_train,y_train) Lasso.fit(X_train, y_train)
XGBR.fit(X_train,y_train) XGBR.fit(X_train, y_train)
#模型拟合 # 模型拟合
y_pre_Lasso = Lasso.predict(x_test) y_pre_Lasso = Lasso.predict(x_test)
y_pre_XGBR = XGBR.predict(x_test) y_pre_XGBR = XGBR.predict(x_test)
#计算Lasso、XGBR、RandomForestR、AdaBoostR、GradientBoostingR、BaggingRegressor各模型的R² # 计算Lasso、XGBR、RandomForestR、AdaBoostR、GradientBoostingR、BaggingRegressor各模型的R²
Lasso_score = r2_score(y_true,y_pre_Lasso) Lasso_score = r2_score(y_true, y_pre_Lasso)
XGBR_score=r2_score(y_true,y_pre_XGBR) XGBR_score = r2_score(y_true, y_pre_XGBR)
#计算Lasso、XGBR的MSE和RMSE # 计算Lasso、XGBR的MSE和RMSE
Lasso_MSE=mean_squared_error(y_true, y_pre_Lasso) Lasso_MSE = mean_squared_error(y_true, y_pre_Lasso)
XGBR_MSE=mean_squared_error(y_true, y_pre_XGBR) XGBR_MSE = mean_squared_error(y_true, y_pre_XGBR)
Lasso_RMSE=np.sqrt(Lasso_MSE) Lasso_RMSE = np.sqrt(Lasso_MSE)
XGBR_RMSE=np.sqrt(XGBR_MSE) XGBR_RMSE = np.sqrt(XGBR_MSE)
# 将不同模型的不同误差值整合成一个表格 # 将不同模型的不同误差值整合成一个表格
model_results = pd.DataFrame([['Lasso', Lasso_RMSE, Lasso_score], model_results = pd.DataFrame([['Lasso', Lasso_RMSE, Lasso_score],
['XgBoost', XGBR_RMSE, XGBR_score]], ['XgBoost', XGBR_RMSE, XGBR_score]],
columns = ['模型(Model)','均方根误差(RMSE)', 'R^2 score']) columns=['模型(Model)', '均方根误差(RMSE)', 'R^2 score'])
#将模型名称(Model)列设置为索引 # 将模型名称(Model)列设置为索引
model_results1=model_results.set_index('模型(Model)') model_results1 = model_results.set_index('模型(Model)')
model_results1 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 # 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):
def plot_feature_importance(importance, names, model_type):
feature_importance = np.array(importance) feature_importance = np.array(importance)
feature_names = np.array(names) 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 = 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)) plt.figure(figsize=(10, 8))
sn.barplot(x=fi_df['feature_importance'], y=fi_df['feature_names']) sn.barplot(x=fi_df['feature_importance'], y=fi_df['feature_names'])
plt.title(model_type + " "+'FEATURE IMPORTANCE') plt.title(model_type + " "+'FEATURE IMPORTANCE')
@ -378,55 +373,145 @@ def optimize_Model():
plt.ylabel('FEATURE NAMES') plt.ylabel('FEATURE NAMES')
from pylab import mpl from pylab import mpl
mpl.rcParams['font.sans-serif'] = ['SimHei'] 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 # 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） # 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）
from xgboost import XGBRegressor from xgboost import XGBRegressor
from sklearn.model_selection import GridSearchCV from sklearn.model_selection import GridSearchCV
estimator = XGBRegressor(random_state=0, estimator = XGBRegressor(random_state=0,
nthread=4, nthread=4,
seed=0 seed=0
) )
parameters = { parameters = {
'max_depth': range (2, 11, 2), # 树的最大深度 'max_depth': range(2, 11, 2), # 树的最大深度
'n_estimators': range (50, 101, 10), # 迭代次数 'n_estimators': range(50, 101, 10), # 迭代次数
'learning_rate': [0.01, 0.03, 0.1, 0.3, 0.5, 1] 'learning_rate': [0.01, 0.03, 0.1, 0.3, 0.5, 1]
} }
grid_search_XGB = GridSearchCV( grid_search_XGB = GridSearchCV(
estimator=estimator, estimator=estimator,
param_grid=parameters, param_grid=parameters,
# n_jobs = 10, # n_jobs = 10,
cv = 3, cv=3,
verbose=True verbose=True
) )
grid_search_XGB.fit(X_train, y_train) grid_search_XGB.fit(X_train, y_train)
#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 # 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
best_parameters = grid_search_XGB.best_estimator_.get_params() best_parameters = grid_search_XGB.best_estimator_.get_params()
y_pred = grid_search_XGB.predict(x_test) y_pred = grid_search_XGB.predict(x_test)
op_XGBR_score = r2_score(y_true,y_pred) op_XGBR_score = r2_score(y_true, y_pred)
op_XGBR_MSE= mean_squared_error(y_true, y_pred) op_XGBR_MSE = mean_squared_error(y_true, y_pred)
op_XGBR_RMSE= np.sqrt(op_XGBR_MSE) op_XGBR_RMSE = np.sqrt(op_XGBR_MSE)
model_results2 = pd.DataFrame([['Optimized_Xgboost', op_XGBR_RMSE, op_XGBR_score]], model_results2 = pd.DataFrame([['Optimized_Xgboost', op_XGBR_RMSE, op_XGBR_score]],
columns = ['模型(Model)', '均方根误差(RMSE)', 'R^2 score']) columns=['模型(Model)', '均方根误差(RMSE)', 'R^2 score'])
model_results2=model_results2.set_index('模型(Model)') model_results2 = model_results2.set_index('模型(Model)')
results = model_results1.append(model_results2, ignore_index = False) results = pd.concat([model_results1, model_results2], ignore_index=False)
import pickle import pickle
Pkl_Filename = "日度价格预测_丙烯最佳模型.pkl" Pkl_Filename = "日度价格预测_丙烯最佳模型.pkl"
with open(Pkl_Filename, 'wb') as file: with open(Pkl_Filename, 'wb') as file:
pickle.dump(grid_search_XGB, file) pickle.dump(grid_search_XGB, file)
def queryDataListItemNos(token=None):
df = pd.read_excel('丙烯基础数据收集表.xlsx')
dataItemNoList = df.iloc[0].tolist()[1:]
if token is None:
token = get_head_auth()
if not token:
print('token获取失败')
return
# 获取当前日期
from datetime import datetime, timedelta
current_date = datetime.now()
# 获取当月1日
first_day_of_month = current_date.replace(day=1)
# 格式化为 YYYYMMDD 格式
dateEnd = current_date.strftime('%Y%m%d')
dateStart = first_day_of_month.strftime('%Y%m%d')
# dateStart = '20241026'
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')
save_queryDataListItemNos_xls(data_df, dataItemNoList)
print('当月数据更新完成')
def save_queryDataListItemNos_xls(data_df, dataItemNoList):
from datetime import datetime, timedelta
current_year_month = datetime.now().strftime('%Y-%m')
grouped = data_df.groupby("dataDate")
# 使用openpyxl打开xlsx文件
from openpyxl import load_workbook
workbook = load_workbook('丙烯基础数据收集表.xlsx')
# 创建新工作簿
new_workbook = load_workbook('丙烯基础数据收集表.xlsx')
for sheetname in workbook.sheetnames:
sheet = workbook[sheetname]
new_sheet = new_workbook[sheetname]
current_year_month_row = 0
# 查找当前月份数据起始行
for row_idx, row in enumerate(sheet.iter_rows(values_only=True), 1):
if str(row[0]).startswith(current_year_month):
current_year_month_row += 1
# 追加新数据
if sheetname == workbook.sheetnames[0]:
start_row = sheet.max_row - current_year_month_row + 1
for row_idx, (date, group) in enumerate(grouped, start=start_row):
new_sheet.cell(row=row_idx, column=1, value=date)
for j, dataItemNo in enumerate(dataItemNoList, start=2):
if group[group["dataItemNo"] == dataItemNo]["dataValue"].values:
new_sheet.cell(row=row_idx, column=j,
value=group[group["dataItemNo"] == dataItemNo]["dataValue"].values[0])
# 保存修改后的xlsx文件
new_workbook.save("丙烯基础数据收集表.xlsx")
def get_queryDataListItemNos_value(token, url, dataItemNoList, dateStart, dateEnd):
search_data = {
"funcModule": "数据项",
"funcOperation": "查询",
"data": {
"dateStart": dateStart,
"dateEnd": dateEnd,
"dataItemNoList": dataItemNoList # 数据项编码,代表 brent最低价和最高价
}
}
headers = {"Authorization": token}
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 read_xls_data(): def read_xls_data():
global one_cols, two_cols global one_cols, two_cols
@ -456,8 +541,6 @@ def read_xls_data():
# workbook.close() # workbook.close()
def start(): def start():
read_xls_data() read_xls_data()
@ -480,8 +563,9 @@ def start():
print(data_value) print(data_value)
dataItemNo_dataValue[data_value["dataItemNo"]] = "" dataItemNo_dataValue[data_value["dataItemNo"]] = ""
else: else:
dataItemNo_dataValue[data_value["dataItemNo"]] = data_value["dataValue"] dataItemNo_dataValue[data_value["dataItemNo"]
] = data_value["dataValue"]
for value in one_cols[1:]: for value in one_cols[1:]:
if value in dataItemNo_dataValue: if value in dataItemNo_dataValue:
append_rows.append(dataItemNo_dataValue[value]) append_rows.append(dataItemNo_dataValue[value])
@ -500,7 +584,6 @@ def start_1():
token = get_head_auth() token = get_head_auth()
if not token: if not token:
return return
datas = get_data_value(token, one_cols[1:]) datas = get_data_value(token, one_cols[1:])
# if not datas: # if not datas:
@ -514,7 +597,8 @@ def start_1():
print(data_value) print(data_value)
dataItemNo_dataValue[data_value["dataItemNo"]] = "" dataItemNo_dataValue[data_value["dataItemNo"]] = ""
else: else:
dataItemNo_dataValue[data_value["dataItemNo"]] = data_value["dataValue"] dataItemNo_dataValue[data_value["dataItemNo"]
] = data_value["dataValue"]
for value in one_cols[1:]: for value in one_cols[1:]:
if value in dataItemNo_dataValue: if value in dataItemNo_dataValue:
@ -523,10 +607,10 @@ def start_1():
append_rows.append("") append_rows.append("")
save_xls_1(append_rows) save_xls_1(append_rows)
# data_list.append(three_cols) # data_list.append(three_cols)
# write_xls(data_list) # write_xls(data_list)
def save_xls_1(append_rows): def save_xls_1(append_rows):
# 打开xls文件 # 打开xls文件
@ -568,11 +652,9 @@ def save_xls_1(append_rows):
new_sheet.write(row_count, col, append_rows[col]) new_sheet.write(row_count, col, append_rows[col])
# 保存新的xls文件 # 保存新的xls文件
new_workbook.save("丙烯基础数据收集表.xls") new_workbook.save("丙烯基础数据收集表.xls")
def check_data(dataItemNo): def check_data(dataItemNo):
token = get_head_auth() token = get_head_auth()
if not token: if not token:
@ -628,5 +710,8 @@ def save_xls(append_rows):
if __name__ == "__main__": if __name__ == "__main__":
start() # start()
queryDataListItemNos()
optimize_Model()
forecast_price()
upload_data_to_system(token_push=get_head_push_auth())

BIN
aisenzhecode/聚合级丙烯/日度价格预测_丙烯最佳模型.pkl
View File

Binary file not shown.