删除重复数据集

.idea/misc.xml

@@ -1,4 +1,4 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="C:\anaconda\envs\pytorch" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="pytorch_gpu" project-jdk-type="Python SDK" />
 </project>

.idea/pytorch2.iml

@@ -2,7 +2,7 @@
 <module type="PYTHON_MODULE" version="4">
   <component name="NewModuleRootManager">
     <content url="file://$MODULE_DIR$" />
-    <orderEntry type="jdk" jdkName="C:\anaconda\envs\pytorch" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="pytorch_gpu" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
 </module>

浙江行业电量/分类归一化.py

@@ -1,4 +1,3 @@
-import os
 import numpy as np
 import pandas as pd
 from sklearn.preprocessing import MinMaxScaler
@@ -7,6 +6,8 @@ from torch import nn
 from torch.utils.data import DataLoader, TensorDataset
 import matplotlib.pyplot as plt
 
+
+train_step = 10
 class LSTM(nn.Module):
     def __init__(self, input_size, hidden_size, output_size, num_layers):
         super().__init__()
@@ -14,13 +15,13 @@ class LSTM(nn.Module):
         self.fc1 = nn.Linear(hidden_size, 128)
         self.fc2 = nn.Linear(128, output_size)
         self.ReLu = nn.ReLU()
-        self.dropout = nn.Dropout(0.5)
+        self.dropout = nn.Dropout(0.8)
 
     def forward(self, x):
         x, _ = self.lstm(x)
         s, b, h = x.shape
         x = x.reshape(-1, h)
-        output = self.ReLU(self.dropout(self.fc1(x)))
+        output = self.ReLu(self.dropout(self.fc1(x)))
         output = self.fc2(output)
         return output
 
@@ -49,8 +50,7 @@ def normal(data):
 #
 # df.to_csv('11市行业数据(已处理异常).csv',index=False,encoding='GBK')
 df = pd.read_csv('11市行业数据(已处理异常).csv', encoding='gbk')
-print(sum(df.isnull().sum()))
-print(df.describe())
+
 # 对df每一行业进行归一化
 column_params = {}
 for column in df.columns[2:]:
@@ -63,12 +63,11 @@ for column in df.columns[2:]:
 print(column_params)
 print(df.head())
 
-
-def create_dataset(data, days_for_train=10) -> (np.array, np.array):
+def create_dataset(data, train_step=train_step) -> (np.array, np.array):
     dataset_x, dataset_y = [], []
-    for i in range(len(data) - days_for_train - 3):
-        dataset_x.append(data[i:(i + days_for_train)])
-        dataset_y.append(data[i + days_for_train:i + days_for_train + 3])
+    for i in range(len(data) - train_step - 3):
+        dataset_x.append(data[i:(i + train_step)])
+        dataset_y.append(data[i + train_step:i + train_step + 3])
 
     return (np.array(dataset_x), np.array(dataset_y))
 
@@ -76,75 +75,100 @@ def create_dataset(data, days_for_train=10) -> (np.array, np.array):
 # 切分x,y数据集，步长为10.最小单位为单个城市的单个行业。
 # 先从第一个行业切分，合并所有城市。
 
-industry = df.columns[2:][0]
-city = df['地市'].drop_duplicates()[0]
-df_city_industry = df[df['地市'] == city][industry]
-dataset_x, dataset_y = create_dataset(df_city_industry)
-
-for city in df['地市'].drop_duplicates()[1:]:
-    df_city_industry = df[df['地市'] == city][industry]
-    x, y = create_dataset(df_city_industry)
-    dataset_x, dataset_y = np.concatenate([dataset_x, x]), np.concatenate([dataset_y, y])
-
-for industry in df.columns[2:][1:]:
-    for city in df['地市'].drop_duplicates():
-        df_city_industry = df[df['地市'] == city][industry]
-        x, y = create_dataset(df_city_industry)
-        dataset_x, dataset_y = np.concatenate([dataset_x, x]), np.concatenate([dataset_y, y])
-
+# industry = df.columns[2:][0]
+# city = df['地市'].drop_duplicates()[0]
+# df_city_industry = df[df['地市'] == city][industry]
+# dataset_x, dataset_y = create_dataset(df_city_industry)
+#
+# for city in df['地市'].drop_duplicates()[1:]:
+#     df_city_industry = df[df['地市'] == city][industry]
+#     x, y = create_dataset(df_city_industry)
+#     dataset_x, dataset_y = np.concatenate([dataset_x, x]), np.concatenate([dataset_y, y])
+#
+# for industry in df.columns[2:][1:]:
+#     for city in df['地市'].drop_duplicates():
+#         df_city_industry = df[df['地市'] == city][industry]
+#         x, y = create_dataset(df_city_industry)
+#         dataset_x, dataset_y = np.concatenate([dataset_x, x]), np.concatenate([dataset_y, y])
+#
+# print(dataset_x.shape, dataset_y.shape)
+# df_x = pd.DataFrame(dataset_x)
+# df_y = pd.DataFrame(dataset_y)
+# df_x.to_csv('df_x_100.csv',index=False)
+# df_y.to_csv('df_y_100.csv',index=False)
+dataset_x = pd.read_csv('df_x.csv').values
+dataset_y = pd.read_csv('df_y.csv').values
 print(dataset_x.shape, dataset_y.shape)
 
 train_size = int(0.7 * len(dataset_x))
-x_train, y_train = dataset_x[:train_size].reshape(-1,1,10), dataset_y[:train_size].reshape(-1, 1, 3)
-x_eval, y_eval = dataset_x[train_size:].reshape(-1,1,10), dataset_y[train_size:].reshape(-1, 1, 3)
+x_train, y_train = dataset_x[:train_size].reshape(-1,1,train_step), dataset_y[:train_size].reshape(-1, 1, 3)
+x_eval, y_eval = dataset_x[train_size:].reshape(-1,1,train_step), dataset_y[train_size:].reshape(-1, 1, 3)
 x_train, y_train = torch.from_numpy(x_train).type(torch.float32), torch.from_numpy(y_train).type(torch.float32)
 x_eval, y_eval = torch.from_numpy(x_eval).type(torch.float32), torch.from_numpy(y_eval).type(torch.float32)
 
 ds = TensorDataset(x_train, y_train)
-dl = DataLoader(ds, batch_size=128, shuffle=True, drop_last=True)
+dl = DataLoader(ds, batch_size=32, drop_last=True)
 eval_ds = TensorDataset(x_eval, y_eval)
-eval_dl = DataLoader(eval_ds, batch_size=256, drop_last=True)
+eval_dl = DataLoader(eval_ds, batch_size=64, drop_last=True)
 
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-model = LSTM(10,64, 3, num_layers=2).to(device)
+model = LSTM(train_step,64, 3, num_layers=2).to(device)
 loss_fn = nn.MSELoss()
-optimizer = torch.optim.Adam(model.parameters(), lr=0.0001)
+optimizer = torch.optim.Adam(model.parameters(), lr=0.00005, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)
 
 min_loss = 1
-for epoch in range(10):
-    for step, (x, y) in enumerate(dl):
-        x, y = x.to(device), y.to(device)
-        pred = model(x)
-        loss = loss_fn(pred,y)
-        optimizer.zero_grad()
-        loss.backward()
-        optimizer.step()
-
-        if (step+1) % 1000 == 0:
-            print(f'epoch{epoch+1}: train_step{step}/{len(dl)} train_loss:{round(loss)}\n')
-
-    model.eval()
-    batch_loss = 0
-    with torch.no_grad():
-        for x,y in eval_dl:
-            x, y = x.to(device), y.to(device)
-            pred = model(x)
-            loss = loss_fn(pred, y)
-            batch_loss += loss
-    print(f'epoch{epoch+1}: eval_loss:{batch_loss/len(eval_dl)}')
-
-    if batch_loss/len(eval_dl) < min_loss:
-        min_loss = batch_loss/len(eval_dl)
-        best_parameters = model.state_dict()
+for i in range(500):
+    train_x,train_y = train_x.to(device),train_y.to(device)
+    out = model(train_x)
+    loss = loss_fn(out, train_y)
+    loss.backward()
+    optimizer.step()
+    optimizer.zero_grad()
+
+    if loss <= min_loss:
+        min_loss = loss
+        best_para = model.state_dict()
+    if i % 100 == 0:
+        print(f'epoch {i+1}: loss:{loss}')
+
+# for epoch in range(3):
+#     model.train()
+#     for step, (x, y) in enumerate(dl):
+#         x, y = x.to(device), y.to(device)
+#         pred = model(x)
+#         loss = loss_fn(pred,y)
+#         optimizer.zero_grad()
+#         loss.backward()
+#         optimizer.step()
+#
+#         if step % 1000 == 0:
+#             print(f'epoch{epoch+1}: train_step:{step}/{len(dl)} train_loss:{loss}\n')
+#
+#     model.eval()
+#     batch_loss = 0
+#     with torch.no_grad():
+#         for x,y in eval_dl:
+#             x, y = x.to(device), y.to(device)
+#             pred = model(x)
+#             loss = loss_fn(pred, y)
+#             batch_loss += loss
+#     print(f'epoch{epoch+1}: eval_loss:{batch_loss/len(eval_dl)}\n')
+#
+#     if batch_loss/len(eval_dl) < min_loss:
+#         min_loss = batch_loss/len(eval_dl)
+#         best_parameters = model.state_dict()
 
 torch.save(best_parameters,'best_3.pth')
 
-model = LSTM(10,64, 3, num_layers=2).to(device)
+model = LSTM(train_step,64, 3, num_layers=2).to(device)
 model.load_state_dict(torch.load('best_3.pth'))
-dataset_x = dataset_x.reshape(-1,1,10)
+params = sum(p.numel() for p in model.parameters() if p.requires_grad)
+print("LSTM参数总量:", params)
+
+dataset_x = dataset_x.reshape(-1,1,train_step)
 dataset_x = torch.from_numpy(dataset_x).type(torch.float32).to(device)
 pred = model(dataset_x).reshape(-1)
-pred = np.concatenate((np.zeros(10), pred.cpu().detach().numpy()))
+pred = np.concatenate((np.zeros(train_step), pred.cpu().detach().numpy()))
 
 
 plt.plot(pred, 'r', label='prediction')

浙江行业电量/行业分类.py

@@ -0,0 +1,128 @@
+import pandas as pd
+import datetime
+import os
+import numpy as np
+import torch
+from torch import nn
+
+def normalise(dataset_x,dataset_y):
+    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)
+    return dataset_x,dataset_y,max_value,min_value
+def create_data(df_industry, industry):
+    dataset_x = []
+    dataset_y = []
+    for i in df_industry['地市'].drop_duplicates():
+        data = df_industry[df_industry['地市'] == i]
+        grouped = data.groupby(data['stat_date'].dt.to_period('M'))
+
+        # 遍历每个月的数据
+        for name, group in grouped:
+            if len(group) == 31:
+                dataset_x.append(list(group[industry].values[1:28]))
+                dataset_y.append(list(group[industry].values[-3:]))
+            if len(group) == 30:
+                dataset_x.append(list(group[industry].values[:27]))
+                dataset_y.append(list(group[industry].values[-3:]))
+            if len(group) == 28:
+                fst = group[industry].values[0]
+
+                dataset_x.append([fst, fst, fst] + list(group[industry].values[1:25]))
+                dataset_y.append(list(group[industry].values[-3:]))
+            else:
+                fst = group[industry].values[0]
+                if len([fst, fst] + list(group[industry].values[1:26])) != 27:
+                    break
+                dataset_x.append([fst, fst] + list(group[industry].values[1:26]))
+                dataset_y.append(list(group[industry].values[-3:]))
+
+    return np.array(dataset_x), np.array(dataset_y)
+
+
+df = pd.read_csv('合并行业数据.csv')
+df[df.columns[2:]] /= 10000
+df['stat_date'] = df['stat_date'].map(lambda x:str(x).strip()[:10])
+df['stat_date'] = pd.to_datetime(df['stat_date'],format='%Y-%m-%d')
+list_1 = ['1.煤炭开采和洗选业']
+list_2 = ['2.石油和天然气开采业', '3.黑色金属矿采选业']
+list_3 = ['2.林业', '4.有色金属矿采选业', '4.烟草制品业', '31.金属制品、机械和设备修理业', '2.燃气生产和供应业', '3.建筑安装业', '4.航空运输业', '5.管道运输业', '6.多式联运和运输代理业', '8.邮政业']
+list_4 = ['第一产业', '一、农、林、牧、渔业', '1.农业', '3.畜牧业', '4.渔业', '5.农、林、牧、渔专业及辅助性活动', '（一）采矿业', '5.非金属矿采选业', '6.其他采矿业', '1.农副食品加工业', '2.食品制造业', '3.酒、饮料及精制茶制造业', '8.木材加工和木、竹、藤、棕、草制品业', '9.家具制造业', '11.印刷和记录媒介复制业', '25.铁路、船舶、航空航天和其他运输设备制造业', '28.仪器仪表制造业', '30.废弃资源综合利用业', '1.房屋建筑业', '4.建筑装饰、装修和其他建筑业', '1.铁路运输业', '2.道路运输业', '3.水上运输业', '7.装卸搬运和仓储业', '2.互联网和相关服务', '3.软件和信息技术服务业', '八、金融业', '1.科学研究和技术服务业', '3.居民服务、修理和其他服务业']
+list_5 = ['城镇居民', '6.纺织服装、服饰业', '7.皮革、毛皮、羽毛及其制品和制鞋业', '10.造纸和纸制品业', '12.文教、工美、体育和娱乐用品制造业', '13.石油、煤炭及其他燃料加工业', '14.化学原料和化学制品制造业', '15.医药制造业', '16.化学纤维制造业', '17.橡胶和塑料制品业', '18.非金属矿物制品业', '19.黑色金属冶炼和压延加工业', '20.有色金属冶炼和压延加工业', '21.金属制品业', '22.通用设备制造业', '23.专用设备制造业', '24.汽车制造业', '26.电气机械和器材制造业', '27.计算机、通信和其他电子设备制造业', '29.其他制造业', '（三）电力、热力、燃气及水的生产和供应业', '1.电力、热力生产和供应业', '3.水的生产和供应业', '三、建筑业', '2.土木工程建筑业', '四、交通运输、仓储和邮政业', '五、信息传输、软件和信息技术服务业', '1.电信、广播电视和卫星传输服务', '六、批发和零售业', '七、住宿和餐饮业', '九、房地产业', '十、租赁和商务服务业', '十一、公共服务及管理组织', '2.水利、环境和公共设施管理业', '4.教育、文化、体育和娱乐业', '5.卫生和社会工作', '6.公共管理和社会组织、国际组织']
+list_6 = ['全社会用电总计', 'a、全行业用电合计', '第二产业', '第三产业', 'b、城乡居民生活用电合计', '乡村居民', '二、工业', '（二）制造业', '5.纺织业']
+
+
+# list_1
+industry = '1.煤炭开采和洗选业'
+df_industry = df[['地市', 'stat_date', industry]]
+dataset_x1,dataset_y1 = create_data(df_industry,industry)
+print('list_1:',np.max(dataset_x1),np.min(dataset_x1))
+dataset_x1,dataset_y1 = normalise(dataset_x1,dataset_y1)[:2]
+
+# list_2
+industry = '2.石油和天然气开采业'
+df_industry = df[['地市', 'stat_date', industry]]
+dataset_x2,dataset_y2 = create_data(df_industry,industry)
+for i in list_2[1:]:
+    df_industry = df[['地市', 'stat_date', industry]]
+    x, y = create_data(df_industry, industry)
+    dataset_x2 = np.concatenate([dataset_x2, x])
+    dataset_y2 = np.concatenate([dataset_y2, y])
+print('list_2:',np.max(dataset_x2),np.min(dataset_x2))
+dataset_x2,dataset_y2 = normalise(dataset_x2,dataset_y2)[:2]
+
+# list_3
+industry = '2.林业'
+df_industry = df[['地市', 'stat_date', industry]]
+dataset_x3,dataset_y3 = create_data(df_industry,industry)
+for i in list_3[1:]:
+    df_industry = df[['地市', 'stat_date', industry]]
+    x, y = create_data(df_industry, industry)
+    dataset_x3 = np.concatenate([dataset_x3, x])
+    dataset_y3 = np.concatenate([dataset_y3, y])
+print('list_3:',np.max(dataset_x3),np.min(dataset_x3))
+dataset_x3,dataset_y3 = normalise(dataset_x3,dataset_y3)[:2]
+
+# list_4
+industry = list_4[0]
+df_industry = df[['地市', 'stat_date', industry]]
+dataset_x4,dataset_y4 = create_data(df_industry,industry)
+for i in list_4[1:]:
+    df_industry = df[['地市', 'stat_date', industry]]
+    x, y = create_data(df_industry, industry)
+    dataset_x4 = np.concatenate([dataset_x4, x])
+    dataset_y4 = np.concatenate([dataset_y4, y])
+print('list_4:',np.max(dataset_x4),np.min(dataset_x4))
+dataset_x4,dataset_y4 = normalise(dataset_x4,dataset_y4)[:2]
+
+# list_5
+industry = list_5[0]
+df_industry = df[['地市', 'stat_date', industry]]
+dataset_x5,dataset_y5 = create_data(df_industry,industry)
+for i in list_5[1:]:
+    df_industry = df[['地市', 'stat_date', industry]]
+    x, y = create_data(df_industry, industry)
+    dataset_x5 = np.concatenate([dataset_x5, x])
+    dataset_y5 = np.concatenate([dataset_y5, y])
+print('list_5:',np.max(dataset_x5),np.min(dataset_x5))
+dataset_x5,dataset_y5 = normalise(dataset_x5,dataset_y5)[:2]
+
+
+
+# list_6
+industry = list_6[0]
+df_industry = df[['地市', 'stat_date', industry]]
+dataset_x6,dataset_y6 = create_data(df_industry,industry)
+for i in list_6[1:]:
+    df_industry = df[['地市', 'stat_date', industry]]
+    x, y = create_data(df_industry, industry)
+    dataset_x6 = np.concatenate([dataset_x6, x])
+    dataset_y6 = np.concatenate([dataset_y6, y])
+print('list_6:',np.max(dataset_x6),np.min(dataset_x6))
+dataset_x6,dataset_y6 = normalise(dataset_x6,dataset_y6)[:2]
+
+dataset_x = np.concatenate([dataset_x1,dataset_x2,dataset_x3,dataset_x4,dataset_x5,dataset_x6])
+
+dataset_y = np.concatenate([dataset_y1,dataset_y2,dataset_y3,dataset_y4,dataset_y5,dataset_y6])
+print(dataset_y.shape,dataset_x.shape)

浙江行业电量/行业电量_输出为3_步长为10.py

@@ -4,6 +4,7 @@ import torch
 from torch import nn
 import os
 import time
+import matplotlib.pyplot as plt
 t1 = time.time()
 
 os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
@@ -50,7 +51,6 @@ def data_preprocessing(data):
     data = data.astype(float)
     for col in data.columns:
         data[col] = normal(data[col])
-
     return data
 
 # 拼接数据集
@@ -86,10 +86,16 @@ for excel in os.listdir(file_dir)[1:]:
         dataset_y = np.concatenate((dataset_y,y))
 
 
+df_x_10 = pd.DataFrame(dataset_x)
+df_y_10 = pd.DataFrame(dataset_y)
+df_x_10.to_csv('df_x_10.csv',index=False)
+df_y_10.to_csv('df_y_10.csv',index=False)
+dataset_x = pd.read_csv('df_x_10.csv').values
+dataset_y = pd.read_csv('df_y_10.csv').values
 print(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)
@@ -108,47 +114,52 @@ train_y = train_y.reshape(-1, 1, 3)
 # # 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('=====================================',train_x.shape)
+
 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
-#
+
 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):
+min_loss = 1
+for i in range(500):
+    train_x,train_y = train_x.to(device),train_y.to(device)
     out = model(train_x)
-    print(out.shape)
     loss = loss_function(out, train_y)
     loss.backward()
     optimizer.step()
     optimizer.zero_grad()
     train_loss.append(loss.item())
+
+    if loss <= min_loss:
+        min_loss = loss
+        best_para = model.state_dict()
     if i % 100 == 0:
         print(f'epoch {i+1}: loss:{loss}')
-#
-# # 保存/读取模型
-# torch.save(model.state_dict(),'hy5.pth')
-
-# model.load_state_dict(torch.load('hy5.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).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()
-
-model.load_state_dict(torch.load('hy3.pth',map_location=torch.device('cpu')))
-max_value = 354024930.8
-min_value = 0.0
+
+
+# 保存/读取模型
+torch.save(best_para,'hy3.pth')
+model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=3, num_layers=2).to(device)
+model.load_state_dict(torch.load('hy3.pth'))
+# 测试
+model = model.eval()
+
+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
+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*3, train_size*3), (0, 1), 'g--')
+plt.legend(loc='best')
+plt.show()
+
+# model.load_state_dict(torch.load('hy3.pth',map_location=torch.device('cpu')))
+# max_value = 354024930.8
+# min_value = 0.0
 
 # 创建测试集
 file_dir = './浙江各地市行业电量数据'
@@ -176,22 +187,22 @@ print(time.time()-t1)
 print(result_dict)
 
 # 反归一化
-# pred = pred * (max_value - min_value) + min_value
-# df = df * (max_value - min_value) + min_value
-
-
-# # 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()
-# result_eight['loss_rate'] = round(target, 5)
-# result_eight['level'] = level
-# list_app.append(result_eight)
-# print(target)
-# print(result_eight)
-# final_df = pd.concat(list_app,ignore_index=True)
-# final_df.to_csv('市行业电量.csv',encoding='gbk')
-# print(final_df)
+pred = pred * (max_value - min_value) + min_value
+df = df * (max_value - min_value) + min_value
+
+
+# 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()
+result_eight['loss_rate'] = round(target, 5)
+result_eight['level'] = level
+list_app.append(result_eight)
+print(target)
+print(result_eight)
+final_df = pd.concat(list_app,ignore_index=True)
+final_df.to_csv('市行业电量.csv',encoding='gbk')
+print(final_df)