get
/
pytorch
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

,

Browse Source
main
get 1 year ago
parent 8a2d8f2a9a
commit 6e775ae4d9
1 changed files with 96 additions and 85 deletions
Show Stats Download Patch File Download Diff File

181
浙江行业电量/行业电量_输出为5.py
Unescape Escape View File

@ -54,91 +54,91 @@ def data_preprocessing(data):
return data return data
# 拼接数据集 # 拼接数据集
file_dir = r'C:\Users\user\Desktop\浙江各地市行业电量数据' # file_dir = r'C:\Users\user\Desktop\浙江各地市行业电量数据'
excel = os.listdir(file_dir)[0] # 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.drop(columns='地市',inplace=True) # data.drop(columns='地市',inplace=True)
data = data_preprocessing(data) # data = data_preprocessing(data)
#
df = data[data.columns[0]] # df = data[data.columns[0]]
df.dropna(inplace = True) # df.dropna(inplace = True)
dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN) # 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 = data[level]
df.dropna(inplace=True) # df.dropna(inplace=True)
x, y = create_dataset(df, DAYS_FOR_TRAIN) # x, y = create_dataset(df, DAYS_FOR_TRAIN)
dataset_x = np.concatenate((dataset_x, x)) # dataset_x = np.concatenate((dataset_x, x))
dataset_y = np.concatenate((dataset_y, y)) # 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 = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col='stat_date')
data.drop(columns='地市', inplace=True) # data.drop(columns='地市', inplace=True)
data = data_preprocessing(data) # data = data_preprocessing(data)
#
for level in data.columns: # for level in data.columns:
df = data[level] # df = data[level]
df.dropna(inplace=True) # df.dropna(inplace=True)
x,y = create_dataset(df,DAYS_FOR_TRAIN) # x,y = create_dataset(df,DAYS_FOR_TRAIN)
dataset_x = np.concatenate((dataset_x,x)) # dataset_x = np.concatenate((dataset_x,x))
dataset_y = np.concatenate((dataset_y,y)) # dataset_y = np.concatenate((dataset_y,y))
#
#
print(dataset_x.shape,dataset_y.shape) # print(dataset_x.shape,dataset_y.shape)
# 训练 # # 训练
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
#
# 标准化到0~1 # # 标准化到0~1
max_value = np.max(dataset_x) # max_value = np.max(dataset_x)
min_value = np.min(dataset_x) # min_value = np.min(dataset_x)
dataset_x = (dataset_x - min_value) / (max_value - min_value) # dataset_x = (dataset_x - min_value) / (max_value - min_value)
dataset_y = (dataset_y - min_value) / (max_value - min_value) # dataset_y = (dataset_y - min_value) / (max_value - min_value)
# print('max_value:',max_value,'min_value:',min_value)
# 划分训练集和测试集 # # 划分训练集和测试集
train_size = int(len(dataset_x)*0.7) # train_size = int(len(dataset_x)*0.7)
train_x = dataset_x[:train_size] # train_x = dataset_x[:train_size]
train_y = dataset_y[: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) # # 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_x = train_x.reshape(-1, 1, DAYS_FOR_TRAIN)
train_y = train_y.reshape(-1, 1, 5) # train_y = train_y.reshape(-1, 1, 5)
#
# 转为pytorch的tensor对象 # # 转为pytorch的tensor对象
train_x = torch.from_numpy(train_x).to(device).type(torch.float32) # train_x = torch.from_numpy(train_x).to(device).type(torch.float32)
train_y = torch.from_numpy(train_y).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 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 = [] # # train_loss = []
# loss_function = nn.MSELoss() # # loss_function = nn.MSELoss()
# optimizer = torch.optim.Adam(model.parameters(), lr=0.005, betas=(0.9, 0.999), eps=1e-08, weight_decay=0) # # 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): # # for i in range(1500):
# out = model(train_x) # # out = model(train_x)
# loss = loss_function(out, train_y) # # loss = loss_function(out, train_y)
# loss.backward() # # loss.backward()
# optimizer.step() # # optimizer.step()
# optimizer.zero_grad() # # optimizer.zero_grad()
# train_loss.append(loss.item()) # # train_loss.append(loss.item())
# if i % 100 == 0: # # if i % 100 == 0:
# print(f'epoch {i+1}: loss:{loss}') # # print(f'epoch {i+1}: loss:{loss}')
#
# 保存/读取模型 # # 保存/读取模型
# torch.save(model.state_dict(),'hy5.pth') # # torch.save(model.state_dict(),'hy5.pth')
#
model.load_state_dict(torch.load('hy5.pth')) # model.load_state_dict(torch.load('hy5.pth'))
# for test # # for test
model = model.eval() # 转换成测试模式 # 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 # # 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 = 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) # dataset_x = torch.from_numpy(dataset_x).to(device).type(torch.float32)
#
pred_test = model(dataset_x) # 全量训练集 # pred_test = model(dataset_x) # 全量训练集
# 模型输出 (seq_size, batch_size, output_size) # # 模型输出 (seq_size, batch_size, output_size)
pred_test = pred_test.view(-1) # pred_test = pred_test.view(-1)
pred_test = np.concatenate((np.zeros(DAYS_FOR_TRAIN), pred_test.cpu().detach().numpy())) # 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(pred_test.reshape(-1), 'r', label='prediction')
# plt.plot(dataset_y.reshape(-1), 'b', label='real') # plt.plot(dataset_y.reshape(-1), 'b', label='real')
@ -146,6 +146,9 @@ pred_test = np.concatenate((np.zeros(DAYS_FOR_TRAIN), pred_test.cpu().detach().n
# plt.legend(loc='best') # plt.legend(loc='best')
# plt.show() # plt.show()
model.load_state_dict(torch.load('hy5.pth'))
max_value = 354024930.8
min_value = 0.0
# 创建测试集 # 创建测试集
@ -153,7 +156,7 @@ df_eval = pd.read_excel(r'C:\Users\user\Desktop\浙江各地市行业电量数
df_eval.columns = df_eval.columns.map(lambda x:x.strip()) df_eval.columns = df_eval.columns.map(lambda x:x.strip())
df_eval.index = pd.to_datetime(df_eval.index) df_eval.index = pd.to_datetime(df_eval.index)
x,y = create_dataset(df_eval.loc['2023-7']['第三产业'],10) x,y = create_dataset(df_eval.loc['2023-7']['第二产业'],10)
x = (x - min_value) / (max_value - min_value) x = (x - min_value) / (max_value - min_value)
x = x.reshape(-1,1,10) x = x.reshape(-1,1,10)
@ -161,13 +164,21 @@ x = x.reshape(-1,1,10)
x = torch.from_numpy(x).type(torch.float32).to(device) x = torch.from_numpy(x).type(torch.float32).to(device)
pred = model(x) pred = model(x)
x2 = np.array([227964890.1,220189256.2,220189256.2,220189256.2,220189256.2,220189256.2,220189256.2,220189256.2,220189256.2,220189256.2])
x2 = (x2 - min_value) / (max_value - min_value)
x2 = x2.reshape(-1,1,10)
print(x2)
x2 = torch.from_numpy(x2).type(torch.float32).to(device)
pred2 = model(x2)
# 反归一化 # 反归一化
pred = pred * (max_value - min_value) + min_value pred = pred * (max_value - min_value) + min_value
pred2 = pred2 * (max_value - min_value) + min_value
print('pred2:',pred2.view(-1).cpu().detach().numpy())
# df = df * (max_value - min_value) + min_value # df = df * (max_value - min_value) + min_value
df = pd.DataFrame({'real':y.reshape(-1),'pred':pred.view(-1).cpu().detach().numpy()}) df = pd.DataFrame({'real':y.reshape(-1),'pred':pred.view(-1).cpu().detach().numpy()})
print(df) print(df)
df.to_csv('7月第三产业.csv',encoding='gbk') df.to_csv('7月第二产业.csv',encoding='gbk')
# 反归一化 # 反归一化
# pred = pred * (max_value - min_value) + min_value # pred = pred * (max_value - min_value) + min_value

Write Preview
Loading…
Cancel
Save