电压等级输出为5lstm

.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="pytorch_gpu" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="C:\anaconda\envs\pytorch" 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="pytorch_gpu" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="C:\anaconda\envs\pytorch" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
 </module>

bp神经网络.py

@@ -3,33 +3,37 @@ import pandas as pd
 import matplotlib.pyplot as plt
 import torch
 from sklearn import preprocessing
+from torch.utils.data import DataLoader,TensorDataset
 
-data = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\杭州数据.xlsx',index_col='dtdate')
+
+
+data = pd.read_excel(r'C:\python-project\pytorch3\入模数据\杭州数据.xlsx',index_col='dtdate')
 print(data.columns)
 
 
-y = np.array(data['售电量'])  # 制作标签，用于比对训练结果
-x = data.drop(columns=['售电量','city_name'])  # 在特征数据集中去掉label
-# df.drop(label, axis=0)
-# label：要删除的列或者行，如果要删除多个，传入列表
-# axis:轴的方向，0为行，1为列，默认为0
-fea_train = np.array(x)  # 转换为ndarray格式
+x = np.array(data.drop(columns=['售电量','city_name']).loc['2021-1':'2023-6'])
+y = np.array(data['售电量'].loc['2021-1':'2023-6'])
 
 # 数据标准化操作：(x-均值μ) / 标准差σ ，使数据关于原点对称，提升训练效率
-input_features = preprocessing.StandardScaler().fit_transform(fea_train)  # fit：求出均值和标准差 transform：求解
+input_features = preprocessing.StandardScaler().fit_transform(np.array(x))  # fit：求出均值和标准差 transform：求解
+
+# y归一化
+min = np.min(y)
+max = np.max(y)
+y = (y - min)/(max - min)
+
+x_eval = torch.from_numpy(data.drop(columns=['售电量','city_name']).loc['2023-7'].values).type(torch.float32)
+y_eval = torch.from_numpy(data['售电量'].loc['2023-7'].values).type(torch.float32)
+
+ds = TensorDataset(torch.from_numpy(x),torch.from_numpy(y))
+dl = DataLoader(ds,batch_size=12,shuffle=True,drop_last=True)
 
-# y归一化 防止梯度爆炸
-y = (y - np.min(y))/(np.max(y) - np.min(y))
-print(y)
 
 # 设定神经网络的输入参数、隐藏层神经元、输出参数的个数
 input_size = input_features.shape[1]  # 设定输入特征个数
-# np.shape[1]
-# 0为行，1为列，默认为0
-# 在此表格中因为每行为各样本的值，每列为不同的特征分类，所以此处0表示样本数，1表示特征数
-hidden_size = 64  # 设定隐藏层包含64个神经元
-output_size = 1  # 设定输出特征个数为1
-batch_size = 32  # 每一批迭代的特征数量
+
+hidden_size = 64
+output_size =1
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")  # 选择使用GPU训练
 
@@ -40,24 +44,21 @@ my_nn = torch.nn.Sequential(
     torch.nn.ReLU().to(device),
     torch.nn.Linear(hidden_size, hidden_size).to(device),  # 第二层 → 第三层
     torch.nn.ReLU().to(device),
-    torch.nn.Linear(hidden_size, hidden_size).to(device),  # 第三层 → 第四层
-    torch.nn.ReLU().to(device),
-    torch.nn.Linear(hidden_size, output_size).to(device)  # 第四层 → 输出层
+    torch.nn.Linear(hidden_size, output_size)
 ).to(device)
 cost = torch.nn.MSELoss().to(device)
-optimizer = torch.optim.Adam(my_nn.parameters(), lr=0.001)
+optimizer = torch.optim.Adam(my_nn.parameters(), lr=0.0001)
 
 # 训练网络
 losses = []
-for i in range(300):
+for i in range(1000):
     batch_loss = []
     # 采用MINI-Batch的方法进行训练
-    for start in range(0, len(input_features), batch_size):
-        end = start + batch_size if start + batch_size < len(input_features) else len(input_features)
-        x_train = torch.tensor(input_features[start:end], dtype=torch.float32, requires_grad=True).to(device)
-        y_train = torch.tensor(y[start:end], dtype=torch.float32, requires_grad=True).to(device)
-        prediction = my_nn(x_train)
-        loss = cost(y_train, prediction)
+    for X,y in dl:
+        X,y = X.to(device).type(torch.float32),y.to(device).type(torch.float32)
+
+        prediction = my_nn(X)
+        loss = cost(y, prediction)
         optimizer.zero_grad()
         loss.backward(retain_graph=True)
         optimizer.step()
@@ -65,17 +66,16 @@ for i in range(300):
 
     if i % 10 == 0:
         losses.append(np.mean(batch_loss))
-        print(losses)
         print(i, np.mean(batch_loss))
 
 # 保存模型
 # torch.save(my_nn, 'BP.pt')
 
 # 绘制图像
-dev_x = [i * 10 for i in range(20)]
-plt.xlabel('step count')
-plt.ylabel('loss')
-plt.xlim((0, 200))
-plt.ylim((0, 1000))
-plt.plot(dev_x, losses)
-plt.show()
+# dev_x = [i * 10 for i in range(20)]
+# plt.xlabel('step count')
+# plt.ylabel('loss')
+# plt.xlim((0, 200))
+# plt.ylim((0, 1000))
+# plt.plot(dev_x, losses)
+# plt.show()

入模数据/1.py

@@ -17,7 +17,6 @@ def hf_season(x):
     return list1
 
 
-
 def season(x):
     if str(x)[5:7] in ('06','07','08','12','01','02'):
         return 1

浙江电压等级电量/test1.py

@@ -0,0 +1,7 @@
+import numpy as np
+n1 = np.array([[1,1,1]])
+n2 = np.array([1,1,1]).reshape(1,-1)
+print(n2)
+n2 = np.array([]).reshape(3,-1)
+
+print(np.max([[1,2,3],[4,5,6]]))

浙江电压等级电量/电压等级_输出为3.py

@@ -1,176 +0,0 @@
-import numpy as np
-import pandas as pd
-import torch
-from torch import nn
-from multiprocessing import Pool
-import matplotlib.pyplot as plt
-import os
-os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
-DAYS_FOR_TRAIN = 10
-torch.manual_seed(42)
-class LSTM_Regression(nn.Module):
-
-    def __init__(self, input_size, hidden_size, output_size=1, num_layers=2):
-        super().__init__()
-
-        self.lstm = nn.LSTM(input_size, hidden_size, num_layers)
-        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)
-        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
-        return x
-
-
-def create_dataset(data, days_for_train=5) -> (np.array, np.array):
-    dataset_x, dataset_y = [], []
-    for i in range(len(data) - days_for_train-3):
-        _x = data[i:(i + days_for_train)]
-        dataset_x.append(_x)
-        dataset_y.append(data[i + days_for_train:i + days_for_train+3])
-    return (np.array(dataset_x), np.array(dataset_y))
-
-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)]
-
-
-
-# def get_data():
-file_dir = r'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据'
-dataset_x = []
-for excel in os.listdir(file_dir):
-    data = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col=' stat_date ')
-    data.columns = data.columns.map(lambda x: x.strip())
-
-    data.index = pd.to_datetime(data.index,format='%Y%m%d')
-    data.sort_index(inplace=True)
-
-    data = data.loc['2021-01':'2023-08']
-    data.drop(columns=[i for i in data.columns if (data[i] == 0).sum() / len(data) >= 0.5], inplace=True)  # 去除0值列
-    print('len(data):', len(data))
-    list_app = []
-    for level in data.columns:
-        df = data[level]
-        df = df[df.values != 0]  # 去除0值行
-        df = normal(df)
-        df = df.astype('float32').values  # 转换数据类型
-        dataset_x create_dataset(df,DAYS_FOR_TRAIN)
-
-
-def run(file_dir,excel):
-    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-
-    data = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col=' stat_date ')
-
-    data.columns = data.columns.map(lambda x: x.strip())
-
-    data.index = pd.to_datetime(data.index,format='%Y%m%d')
-    data.sort_index(inplace=True)
-    print(data.head())
-    data = data.loc['2021-01':'2023-09']
-
-    data.drop(columns=[i for i in data.columns if (data[i] == 0).sum() / len(data) >= 0.5], inplace=True)  # 去除0值列
-    print('len(data):', len(data))
-    list_app = []
-    for level in data.columns:
-        df = data[level]
-        df = df[df.values != 0]  # 去除0值行
-        df = normal(df)
-        df = df.astype('float32').values  # 转换数据类型
-
-
-        # 标准化到0~1
-        max_value = np.max(df)
-        min_value = np.min(df)
-        df = (df - min_value) / (max_value - min_value)
-
-        dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN)
-        print('len(dataset_x:)', len(dataset_x))
-
-        # 划分训练集和测试集
-        train_size = len(dataset_x) - 3
-        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, 3)
-
-        # 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 = 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):
-            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(),save_filename)
-        # torch.save(model.state_dict(),os.path.join(model_save_dir,model_file))
-
-        # 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
-        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
-        df = df * (max_value - min_value) + min_value
-
-        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()
-        result_eight['loss_rate'] = round(target, 5)
-        result_eight['industry'] = industry
-        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)
-
-        # result_eight.to_csv(f'./月底预测结果/9月{excel[:2]}.txt', sep='\t', mode='a')
-        # with open(fr'./偏差/9月底偏差率.txt', 'a', encoding='utf-8') as f:
-        #     f.write(f'{excel[:2]}{industry}:{round(target, 5)}\n')
-
-if __name__ == '__main__':
-    file_dir = r'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据'
-
-    run(file_dir,'杭州.xlsx')

浙江电压等级电量/电压等级_输出为5.py

@@ -0,0 +1,172 @@
+import numpy as np
+import pandas as pd
+import torch
+from torch import nn
+from multiprocessing import Pool
+import matplotlib.pyplot as plt
+import os
+os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
+DAYS_FOR_TRAIN = 10
+torch.manual_seed(42)
+class LSTM_Regression(nn.Module):
+
+    def __init__(self, input_size, hidden_size, output_size=1, num_layers=2):
+        super().__init__()
+
+        self.lstm = nn.LSTM(input_size, hidden_size, num_layers)
+        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)
+        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
+        return x
+
+
+def create_dataset(data, days_for_train=5) -> (np.array, np.array):
+    dataset_x, dataset_y = [], []
+    for i in range(len(data) - days_for_train-5):
+        dataset_x.append(data[i:(i + days_for_train)])
+        dataset_y.append(data[i + days_for_train:i + days_for_train+5])
+        # print(dataset_x,dataset_y)
+    return (np.array(dataset_x), np.array(dataset_y))
+
+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)]
+
+def data_preprocessing(data):
+    data.columns = data.columns.map(lambda x: x.strip())
+    data.index = pd.to_datetime(data.index)
+    data.sort_index(inplace=True)
+    data = data.loc['2021-01':'2023-08']
+    data.drop(columns=[i for i in data.columns if (data[i] == 0).sum() / len(data) >= 0.5], inplace=True)  # 去除0值列
+    data = data[data.values != 0]
+    data = data.astype(float)
+    for col in data.columns:
+        data[col] = normal(data[col])
+
+    return data
+
+
+# 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 = data_preprocessing(data)
+
+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:]:
+    df = data[level]
+    df.dropna(inplace=True)
+    x, y = create_dataset(df, DAYS_FOR_TRAIN)
+    dataset_x = np.concatenate((dataset_x, x))
+    dataset_y = np.concatenate((dataset_y, y))
+
+
+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)
+
+    for level in data.columns:
+        df = data[level]
+        df.dropna(inplace=True)
+        x,y = create_dataset(df,DAYS_FOR_TRAIN)
+        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 = 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)
+train_y = torch.from_numpy(train_y).to(device)
+
+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):
+    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
+# 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
+# df = df * (max_value - min_value) + min_value
+
+# 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()
+# 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)
+
+
+