,

浙江行业电量/行业电量_输出为5.py

@@ -0,0 +1,176 @@
+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 = data.index.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
+
+    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\user\Desktop\浙江各地市行业电量数据'
+excel = os.listdir(file_dir)[0]
+data = pd.read_excel(os.path.join(file_dir, excel), sheet_name=0, index_col='stat_date')
+data.drop(columns='地市',inplace=True)
+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.drop(columns='地市', inplace=True)
+    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))
+
+
+
+# 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)
+
+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
+
+
+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())
+    if i % 100 == 0:
+        print(f'epoch {i+1}: loss:{loss}')
+
+# 保存模型
+torch.save(model.state_dict(),'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()
+
+
+# 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)
+
+
+
+