删除重复数据集

浙江电压等级电量/电压等级_输出为3.py

@@ -10,19 +10,21 @@ torch.manual_seed(42)
 os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"  # 解决OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
 pd.set_option('display.width',None)
 class LSTM(nn.Module):
-    def __init__(self,input_size,hidden_size,output_size,num_layers=2):
+    def __init__(self,input_size,hidden_size,output_size,num_layers=3):
         super().__init__()
         self.lstm = nn.LSTM(input_size,hidden_size,num_layers)
-        self.fc1 = nn.Linear(hidden_size,output_size)
-        # self.ReLu = nn.ReLU()
-        # self.fc2 = nn.Linear(64,output_size)
+        self.fc1 = nn.Linear(hidden_size,64)
+        self.fc2 = nn.Linear(64,128)
+        self.fc3 = nn.Linear(128, output_size)
+        self.ReLu = nn.ReLU()
+        self.dropout = nn.Dropout()
     def forward(self,x):
         output,_ = self.lstm(x)
         s,b,h = output.shape
         output = output.reshape(-1,h)
-        output = self.fc1(output)
-        # output = self.ReLu(self.fc1(output))
-        # output = self.fc2(output)
+        output = self.ReLu(self.fc1(output))
+        output = self.ReLu(self.fc2(output))
+        output = self.fc3(output)
         return output
 
 
@@ -96,6 +98,7 @@ dataset_x = (dataset_x - min_value) / (max_value - min_value)
 dataset_y = (dataset_y - min_value) / (max_value - min_value)
 
 print(max_value,min_value)
+print(np.max(dataset_x),np.min(dataset_x),np.max(dataset_y),np.min(dataset_y))
 
 # 划分训练集和测试集
 train_size = int(len(dataset_x)*0.8)
@@ -117,12 +120,12 @@ eval_x = torch.from_numpy(eval_x).to(device).type(torch.float32)
 eval_y = torch.from_numpy(eval_y).to(device).type(torch.float32)
 
 train_ds = TensorDataset(train_x,train_y)
-train_dl = DataLoader(train_ds,batch_size=2,drop_last=True)
+train_dl = DataLoader(train_ds,batch_size=2,shuffle=True, drop_last=True)
 eval_ds = TensorDataset(eval_x,eval_y)
 eval_dl = DataLoader(eval_ds,batch_size=4,drop_last=True)
 
 
-model = LSTM(27, 16, 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
+model = LSTM(27, 16, output_size=3, num_layers=3).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()
@@ -155,11 +158,13 @@ for i in range(200):
         best_model_weight = model.state_dict()
     print(f'epoch {i+1} test_loss:{test_loss}')
 
+total_params = sum(p.numel() for p in model.parameters() if p.requires_grad)
+print(f"Total parameters in the LSTM model: {total_params}")
 # 保存模型
 torch.save(best_model_weight,'dy3.pth')
 
 # 读取模型
-model = LSTM(27, 16, output_size=3, num_layers=2).to(device)
+model = LSTM(27, 16, output_size=3, num_layers=3).to(device)
 model.load_state_dict(torch.load('dy3.pth'))
 # for test
 

浙江行业电量/行业电量_输出为3.py

@@ -0,0 +1,197 @@
+import torch
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from torch import nn
+import os
+from torch.utils.data import TensorDataset, DataLoader
+import datetime
+
+torch.manual_seed(42)
+os.environ[
+    "KMP_DUPLICATE_LIB_OK"] = "TRUE"  # 解决OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
+pd.set_option('display.width', None)
+
+
+class LSTM(nn.Module):
+    def __init__(self, input_size, hidden_size, output_size, num_layers=3):
+        super().__init__()
+        self.lstm = nn.LSTM(input_size, hidden_size, num_layers)
+        self.fc1 = nn.Linear(hidden_size, 64)
+        self.fc2 = nn.Linear(64, 128)
+        self.fc3 = nn.Linear(128, output_size)
+        self.ReLu = nn.ReLU()
+        self.dropout = nn.Dropout()
+
+    def forward(self, x):
+        output, _ = self.lstm(x)
+        s, b, h = output.shape
+        output = output.reshape(-1, h)
+        output = self.ReLu(self.fc1(output))
+        output = self.ReLu(self.fc2(output))
+        output = self.fc3(output)
+        return output
+
+
+def normal(df):
+    for col in df.columns:
+        try:
+            high = df[col].describe()['75%'] + 1.5 * (df[col].describe()['75%'] - df[col].describe()['25%'])
+            low = df[col].describe()['25%'] - 1.5 * (df[col].describe()['75%'] - df[col].describe()['25%'])
+            df[col] = df[col].map(lambda x: np.nan if (x >= high) | (x <= low) else x)
+            df[col] = df[col].fillna(method='ffill')
+        except:
+            pass
+
+
+def create_data(df_industry, industry):
+    dataset_x = []
+    dataset_y = []
+    # 按月份分组
+    grouped = df_industry.groupby(df_industry['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)
+
+
+# 创建数据集
+file_dir = './浙江各地市行业电量数据'
+city1 = os.listdir(file_dir)[0]
+df_city = pd.read_excel(os.path.join(file_dir, city1))
+df_city = normal(df_city)
+df_city = df_city.drop(columns='地市')
+df_city[df_city.columns[1:]] /= 10000
+df_city['stat_date'] = df_city['stat_date'].map(lambda x: str(x).strip()[:10])
+df_city.stat_date = pd.to_datetime(df_city.stat_date)
+
+industry = '全社会用电总计'
+df_industry = df_city[['stat_date', industry]]
+dataset_x, dataset_y = create_data(df_industry, industry)
+
+for industry in df_city.columns[2:]:
+    df_level = df_city[['stat_date', industry]]
+    x, y = create_data(df_level, industry)
+    dataset_x = np.concatenate([dataset_x, x])
+    dataset_y = np.concatenate([dataset_y, y])
+
+for excel in os.listdir(file_dir)[1:]:
+    df_city = pd.read_excel(os.path.join(file_dir, excel)).drop(columns='地市')
+    df_city[df_city.columns[1:]] /= 10000
+    df_city['stat_date'] = df_city['stat_date'].map(lambda x: str(x).strip()[:10])
+    df_city.stat_date = pd.to_datetime(df_city.stat_date)
+    for industry in df_city.columns[1:]:
+        df_level = df_city[['stat_date', industry]]
+        x, y = create_data(df_level, industry)
+        dataset_x = np.concatenate([dataset_x, x])
+        dataset_y = np.concatenate([dataset_y, y])
+
+print(dataset_x.shape, dataset_y.shape)
+
+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)
+
+print(max_value, min_value)
+print(np.max(dataset_x), np.min(dataset_x), np.max(dataset_y), np.min(dataset_y))
+
+# 划分训练集和测试集
+train_size = int(len(dataset_x) * 0.8)
+train_x = dataset_x[:train_size]
+train_y = dataset_y[:train_size]
+eval_x = dataset_x[train_size:]
+eval_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, 27)
+train_y = train_y.reshape(-1, 1, 3)
+eval_x = eval_x.reshape(-1, 1, 27)
+eval_y = eval_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)
+eval_x = torch.from_numpy(eval_x).to(device).type(torch.float32)
+eval_y = torch.from_numpy(eval_y).to(device).type(torch.float32)
+
+train_ds = TensorDataset(train_x, train_y)
+train_dl = DataLoader(train_ds, batch_size=32, shuffle=True, drop_last=True)
+eval_ds = TensorDataset(eval_x, eval_y)
+eval_dl = DataLoader(eval_ds, batch_size=64, drop_last=True)
+
+model = LSTM(27, 16, output_size=3, num_layers=3).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)
+min_loss = 1
+for i in range(10):
+    model.train()
+    for j, (x, y) in enumerate(train_dl):
+        x, y = x.to(device), y.to(device)
+        out = model(x)
+        loss = loss_function(out, y)
+        loss.backward()
+        optimizer.step()
+        optimizer.zero_grad()
+        train_loss.append(loss.item())
+        # if (i+1) % 100 == 0:
+        #     print(f'epoch {i+1}/1500 loss:{round(loss.item(),5)}')
+        if (j + 1) % 10 == 0:
+            print(f'epoch {i + 1}/200 step {j + 1}/{len(train_dl)} loss:{loss}')
+    test_running_loss = 0
+    model.eval()
+    with torch.no_grad():
+        for x, y in eval_dl:
+            pred = model(eval_x)
+            loss = loss_function(pred, y)
+            test_running_loss += loss.item()
+    test_loss = test_running_loss / len(eval_dl)
+    if test_loss < min_loss:
+        min_loss = test_loss
+        best_model_weight = model.state_dict()
+    print(f'epoch {i + 1} test_loss:{test_loss}')
+
+total_params = sum(p.numel() for p in model.parameters() if p.requires_grad)
+print(f"Total parameters in the LSTM model: {total_params}")
+# 保存模型
+torch.save(best_model_weight, 'dy3.pth')
+
+# 读取模型
+model = LSTM(27, 16, output_size=3, num_layers=3).to(device)
+model.load_state_dict(torch.load('dy3.pth'))
+# for test
+
+dataset_x = dataset_x.reshape(-1, 1, 27)  # (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).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--')  # 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()