|
|
@ -44,20 +44,18 @@ def data_preprocessing(data):
|
|
|
|
data.sort_index(inplace=True)
|
|
|
|
data.sort_index(inplace=True)
|
|
|
|
data = data.loc['2021-01':'2023-08']
|
|
|
|
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.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)
|
|
|
|
data = data.astype(float)
|
|
|
|
for col in data.columns:
|
|
|
|
for col in data.columns:
|
|
|
|
data[col] = normal(data[col])
|
|
|
|
data[col] = normal(data[col])
|
|
|
|
|
|
|
|
|
|
|
|
return data
|
|
|
|
return data
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# 拼接数据集
|
|
|
|
# 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'
|
|
|
|
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]
|
|
|
|
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 = data_preprocessing(data)
|
|
|
|
data = data_preprocessing(data)
|
|
|
|
|
|
|
|
|
|
|
|
df = data[data.columns[0]]
|
|
|
|
df = data[data.columns[0]]
|
|
|
@ -73,7 +71,9 @@ for level in data.columns[1:]:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 = data_preprocessing(data)
|
|
|
|
data = data_preprocessing(data)
|
|
|
|
|
|
|
|
|
|
|
|
for level in data.columns:
|
|
|
|
for level in data.columns:
|
|
|
@ -95,7 +95,7 @@ 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)
|
|
|
|
|
|
|
|
|
|
|
|
# 划分训练集和测试集
|
|
|
|
# 划分训练集和测试集
|
|
|
|
train_size = 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]
|
|
|
|
|
|
|
|
|
|
|
@ -104,10 +104,10 @@ 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)
|
|
|
|
train_x = torch.from_numpy(train_x).to(device).type(torch.float32)
|
|
|
|
train_y = torch.from_numpy(train_y).to(device)
|
|
|
|
train_y = torch.from_numpy(train_y).to(device).type(torch.float32)
|
|
|
|
|
|
|
|
|
|
|
|
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
|
|
|
|
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 = []
|
|
|
@ -120,11 +120,10 @@ for i in range(1500):
|
|
|
|
optimizer.step()
|
|
|
|
optimizer.step()
|
|
|
|
optimizer.zero_grad()
|
|
|
|
optimizer.zero_grad()
|
|
|
|
train_loss.append(loss.item())
|
|
|
|
train_loss.append(loss.item())
|
|
|
|
# print(loss)
|
|
|
|
print(loss)
|
|
|
|
# 保存模型
|
|
|
|
# 保存模型
|
|
|
|
torch.save(model.state_dict(),'dy5.pth')
|
|
|
|
torch.save(model.state_dict(),'dy5.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
|
|
|
|