更新入模数据

入模数据/1.py

@@ -1,120 +0,0 @@
-import xgboost as xgb
-import pandas as pd
-import os
-from sklearn.metrics import r2_score
-from sklearn.model_selection import train_test_split
-import matplotlib as mpl
-import matplotlib.pyplot as plt
-mpl.rcParams['font.sans-serif']=['kaiti']
-
-pd.set_option('display.width',None)
-
-def hf_season(x):
-    list1= []
-    for i in range(1,13):
-        if x.loc[f'2021-{i}'].mean() >= x.describe()['75%']:
-            list1.append(i)
-    return list1
-
-
-def season(x):
-    if str(x)[5:7] in ('06','07','08','12','01','02'):
-        return 1
-    else:
-        return 0
-def month(x):
-    if str(x)[5:7] in ('08','09','10','12','01','02'):
-        return 1
-    else:
-        return 0
-def normal(nd):
-    high = nd.describe()['75%'] + 1.5*(nd.describe()['75%']-nd.describe()['25%'])
-    low = nd.describe()['25%'] - 1.5*(nd.describe()['75%']-nd.describe()['25%'])
-    return nd[(nd<high)&(nd>low)]
-
-
-data = pd.read_excel(r'C:\python-project\pytorch3\入模数据\杭州数据.xlsx',index_col='dtdate')
-data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
-data = data.loc[normal(data['售电量']).index]
-# for i in range(1,13):
-# plt.plot(range(len(data['售电量'][f'2022-{i}'])),data['售电量'][f'2022-{i}'])
-# plt.show()
-print(data['售电量']['2022-9'])
-plt.plot(range(len(data['售电量']['2022-7'])),data['售电量']['2022-7'])
-plt.plot(range(len(data['售电量']['2022-7']),len(data['售电量']['2022-7'])+len(data['售电量']['2023-7'])),data['售电量']['2023-7'])
-# plt.plot(range(len(data['售电量'][['2022-9','2023-9']])),data['售电量'][['2022-9','2023-9']])
-plt.show()
-
-# print(hf_season(data.loc['2021']['售电量']))
-
-data['month'] = data.index.strftime('%Y-%m-%d').str[6]
-data['month'] = data['month'].astype('int')
-data['season'] = data.index.map(season)
-print(data.head(50))
-
-df_eval = data.loc['2023-7']
-df_train = data.loc['2021-1':'2023-6']
-# df_train = df[500:850]
-print(len(df_eval),len(df_train),len(data))
-
-print(data.drop(columns='city_name').corr(method='pearson')['售电量'])
-
-df_train = df_train[['tem_max','tem_min','24ST','rh','rh_max','prs','prs_max','prs_min','售电量','month','holiday','season']]
-
-
-# IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
-# high = df['售电量'].describe()['75%'] + 1.5*IQR
-# low = df['售电量'].describe()['25%'] - 1.5*IQR
-# print('异常值数量：',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)]))
-#
-# df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
-
-
-X = df_train[['tem_max','tem_min','24ST','holiday','season']]
-X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']]
-y = df_train['售电量']
-print(y.describe())
-# best_goal = 1
-# best_i = {}
-# for i in range(400):
-
-x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.15,random_state=42)
-model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
-model.fit(x_train,y_train)
-
-y_pred = model.predict(x_test)
-result_test = pd.DataFrame({'test':y_test,'pred':y_pred},index=y_test.index)
-
-# 指标打印
-print(abs(y_test - y_pred).mean() / y_test.mean())
-eval_pred = model.predict(X_eval)
-
-result_eval = pd.DataFrame({'eval':df_eval['售电量'],'pred':eval_pred},index=df_eval['售电量'].index)
-
-print((result_eval['eval'].sum()-result_eval['pred'].sum())/result_eval['eval'].sum())
-
-goal = (result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum()
-print('goal:',goal)
-
-goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
-
-print('goal2:',goal2)
-print(result_eval)
-print('r2:',r2_score(y_test,y_pred))
-    # if abs(goal) < best_goal:
-    #     best_goal = abs(goal)
-    #     best_i['best_i'] = i
-    #     x = goal2
-# print(best_i,best_goal,x)
-
-
-
-# result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\杭州.csv')
-# with open(r'C:\Users\user\Desktop\9月各地市日电量预测结果\偏差率.txt','a',encoding='utf-8') as f:
-#     f.write(f'杭州月末3天偏差率：{round(goal,5)},9号-月底偏差率：{round(goal2,5)}\n')
-# # 保存模型
-# model.save_model('hangzhou.bin')
-# loaded_model = xgb.XGBRegressor()
-# loaded_model.load_model('hangzhou.bin')
-# model.predict(X_eval)
-

入模数据/金华.csv

@@ -1,32 +0,0 @@
-dtdate,eval,pred
-2023-08-01,4781.72,4638.4565
-2023-08-02,5264.18,4224.5635
-2023-08-03,5308.39,5036.8037
-2023-08-04,5531.27,5441.4995
-2023-08-05,5989.36,6265.5225
-2023-08-06,6373.8,5753.8174
-2023-08-07,5688.18,4972.277
-2023-08-08,5287.83,4424.5815
-2023-08-09,5560.11,4310.7837
-2023-08-10,5706.55,4657.085
-2023-08-11,5923.97,5702.3916
-2023-08-12,6238.88,5897.044
-2023-08-13,5961.14,4939.6694
-2023-08-14,5316.45,3566.0615
-2023-08-15,4802.99,3005.286
-2023-08-16,4908.05,3805.3303
-2023-08-17,4792.48,3044.6094
-2023-08-18,4380.25,3086.1318
-2023-08-19,4490.53,4237.0283
-2023-08-20,4577.54,3911.61
-2023-08-21,4784.33,4044.5312
-2023-08-22,4517.86,3943.1465
-2023-08-23,4327.74,4588.3257
-2023-08-24,4736.04,4383.0825
-2023-08-25,4981.34,4765.4146
-2023-08-26,4967.04,4744.9272
-2023-08-27,5044.84,4771.1987
-2023-08-28,4919.99,4644.142
-2023-08-29,3611.24,3359.0356
-2023-08-30,3184.04,3217.3503
-2023-08-31,3026.0,3217.8718

区域电量19年至今数据.py

@@ -12,10 +12,6 @@ mpl.rcParams['font.sans-serif']=['kaiti']
 pd.set_option('display.width',None)
 
 
-
-
-
-
 def season(x):
     if str(x)[5:7] in ['07', '08']:
         return 2

浙江电压等级电量/电压等级_输出为5.py

@@ -17,8 +17,8 @@ class LSTM_Regression(nn.Module):
         self.fc = nn.Linear(hidden_size, output_size)
 
     def forward(self, _x):
-        x, _ = self.lstm(_x)  # _x is input, size (seq_len, batch, input_size)   一批多少条样本  多少批样本  每一个样本的输入特征大小（10）
-        s, b, h = x.shape  # x is output, size (seq_len, batch, hidden_size)        经过lstm计算后输出为隐藏层大小
+        x, _ = self.lstm(_x)  # _x is input, size (seq_len, batch, input_size)
+        s, b, h = x.shape  # x is output, size (seq_len, batch, hidden_size)
         x = x.view(s * b, h)
         x = self.fc(x)
         x = x.view(s, b, -1)  # 把形状改回来
@@ -52,20 +52,19 @@ def data_preprocessing(data):
     return data
 
 
-if __name__ == '__main__':
-    # 拼接数据集
-    file_dir = r'C:\Users\user\Desktop\浙江各地市分电压日电量数据'
-    excel = os.listdir(file_dir)[0]
+# 拼接数据集
+file_dir = r'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据'
+excel = os.listdir(file_dir)[0]
 
-    data = pd.read_excel(os.path.join(file_dir, excel), sheet_name=0, index_col=' stat_date  ')
+data = pd.read_excel(os.path.join(file_dir, excel), sheet_name=0, index_col=' stat_date  ')
 
-    data = data_preprocessing(data)
+data = data_preprocessing(data)
 
-    df = data[data.columns[0]]
-    df.dropna(inplace = True)
-    dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN)
+df = data[data.columns[0]]
+df.dropna(inplace = True)
+dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN)
 
-    for level in data.columns[1:]:
+for level in data.columns[1:]:
     df = data[level]
     df.dropna(inplace=True)
     x, y = create_dataset(df, DAYS_FOR_TRAIN)
@@ -73,7 +72,7 @@ if __name__ == '__main__':
     dataset_y = np.concatenate((dataset_y, y))
 
 
-    for excel in os.listdir(file_dir)[1:]:
+for excel in os.listdir(file_dir)[1:]:
     data = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col=' stat_date  ')
     data = data_preprocessing(data)
 
@@ -84,101 +83,79 @@ if __name__ == '__main__':
         dataset_x = np.concatenate((dataset_x,x))
         dataset_y = np.concatenate((dataset_y,y))
 
-    print(dataset_x,dataset_y,dataset_x.shape,dataset_y.shape)
-
-    # 训练
-    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-
-    # 标准化到0~1
-    max_value = np.max(dataset_x)
-    min_value = np.min(dataset_x)
-    dataset_x = (dataset_x - min_value) / (max_value - min_value)
-    dataset_y = (dataset_y - min_value) / (max_value - min_value)
-
-    # 划分训练集和测试集
-    train_size = int(len(dataset_x)*0.7)
-
-    train_x = dataset_x[:train_size]
-    train_y = dataset_y[:train_size]
-
-    # 将数据改变形状，RNN 读入的数据维度是 (seq_size, batch_size, feature_size)
-    train_x = train_x.reshape(-1, 1, DAYS_FOR_TRAIN)
-    train_y = train_y.reshape(-1, 1, 5)
-
-    # 转为pytorch的tensor对象
-    train_x = torch.from_numpy(train_x).to(device).type(torch.float32)
-    train_y = torch.from_numpy(train_y).to(device).type(torch.float32)
+print(dataset_x,dataset_y,dataset_x.shape,dataset_y.shape)
 
-    model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=5, num_layers=2).to(device)  # 导入模型并设置模型的参数输入输出层、隐藏层等
+# 训练
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 
+# 标准化到0~1
+max_value = np.max(dataset_x)
+min_value = np.min(dataset_x)
+dataset_x = (dataset_x - min_value) / (max_value - min_value)
+dataset_y = (dataset_y - min_value) / (max_value - min_value)
 
-    train_loss = []
-    loss_function = nn.MSELoss()
-    optimizer = torch.optim.Adam(model.parameters(), lr=0.005, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)
+# 划分训练集和测试集
+train_size = len(dataset_x)*0.7
+train_x = dataset_x[:train_size]
+train_y = dataset_y[:train_size]
 
-    # for i in range(1500):
-    #     out = model(train_x)
-    #     loss = loss_function(out, train_y)
-    #     loss.backward()
-    #     optimizer.step()
-    #     optimizer.zero_grad()
-    #     train_loss.append(loss.item())
-    #     # print(loss)
-    # # 保存模型
-    # torch.save(model.state_dict(),'dy5.pth')
+# 将数据改变形状，RNN 读入的数据维度是 (seq_size, batch_size, feature_size)
+train_x = train_x.reshape(-1, 1, DAYS_FOR_TRAIN)
+train_y = train_y.reshape(-1, 1, 5)
 
+# 转为pytorch的tensor对象
+train_x = torch.from_numpy(train_x).to(device)
+train_y = torch.from_numpy(train_y).to(device)
 
-    model.load_state_dict(torch.load('dy5.pth'))
+model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=3, num_layers=2).to(device)  # 导入模型并设置模型的参数输入输出层、隐藏层等
 
-    # for test
-    model = model.eval()  # 转换成测试模式
-    # model.load_state_dict(torch.load(os.path.join(model_save_dir,model_file)))  # 读取参数
-    dataset_x = dataset_x.reshape(-1, 1, DAYS_FOR_TRAIN)  # (seq_size, batch_size, feature_size)
-    dataset_x = torch.from_numpy(dataset_x).to(device).type(torch.float32)
-
-    pred_test = model(dataset_x)  # 全量训练集
-
-    # 模型输出 (seq_size, batch_size, output_size)
-    pred_test = pred_test.view(-1)
-    pred_test = np.concatenate((np.zeros(DAYS_FOR_TRAIN), pred_test.cpu().detach().numpy()))
-
-    # plt.plot(pred_test.reshape(-1), 'r', label='prediction')
-    # plt.plot(dataset_y.reshape(-1), 'b', label='real')
-    # plt.plot((train_size*5, train_size*5), (0, 1), 'g--')  # 分割线 左边是训练数据 右边是测试数据的输出
-    # plt.legend(loc='best')
-    # plt.show()
 
+train_loss = []
+loss_function = nn.MSELoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=0.005, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)
+for i in range(1500):
+    out = model(train_x)
+    loss = loss_function(out, train_y)
+    loss.backward()
+    optimizer.step()
+    optimizer.zero_grad()
+    train_loss.append(loss.item())
+    # print(loss)
+# 保存模型
+torch.save(model.state_dict(),'dy5.pth')
 
 
+# for test
+model = model.eval()  # 转换成测试模式
+# model.load_state_dict(torch.load(os.path.join(model_save_dir,model_file)))  # 读取参数
+dataset_x = dataset_x.reshape(-1, 1, DAYS_FOR_TRAIN)  # (seq_size, batch_size, feature_size)
+dataset_x = torch.from_numpy(dataset_x).to(device)
 
+pred_test = model(dataset_x)  # 全量训练集
+# 模型输出 (seq_size, batch_size, output_size)
+pred_test = pred_test.view(-1)
+pred_test = np.concatenate((np.zeros(DAYS_FOR_TRAIN), pred_test.cpu().detach().numpy()))
 
+plt.plot(pred_test, 'r', label='prediction')
+plt.plot(df, 'b', label='real')
+plt.plot((train_size, train_size), (0, 1), 'g--')  # 分割线 左边是训练数据 右边是测试数据的输出
+plt.legend(loc='best')
+plt.show()
 
 
 # 创建测试集
 # result_list = []
 # 以x为基础实际数据，滚动预测未来3天
-df_eval = pd.read_excel(r'C:\Users\user\Desktop\浙江各地市分电压日电量数据\杭州.xlsx',index_col=' stat_date  ')
-df_eval.columns = df_eval.columns.map(lambda x:x.strip())
-df_eval.index = pd.to_datetime(df_eval.index)
-
-x,y = create_dataset(df_eval.loc['2023-7']['10kv以下'],10)
-
-x = (x - min_value) / (max_value - min_value)
-x = x.reshape(-1,1,10)
-
-x = torch.from_numpy(x).type(torch.float32).to(device)
-pred = model(x)
+# x = torch.from_numpy(df[-14:-4]).to(device)
+# pred = model(x.reshape(-1,1,DAYS_FOR_TRAIN)).view(-1).detach().numpy()
 
 
 # 反归一化
-pred = pred * (max_value - min_value) + min_value
+# pred = pred * (max_value - min_value) + min_value
 # df = df * (max_value - min_value) + min_value
 
-print(pred,y)
-df = pd.DataFrame({'real':y.reshape(-1),'pred':pred.view(-1).cpu().detach().numpy()})
-df.to_csv('7月预测.csv',encoding='gbk')
-
-# 打印指标
+# print(pred)
+# # 打印指标
 # print(abs(pred - df[-3:]).mean() / df[-3:].mean())
 # result_eight = pd.DataFrame({'pred': np.round(pred,1),'real': df[-3:]})
 # target = (result_eight['pred'].sum() - result_eight['real'].sum()) / df[-31:].sum()