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

更新电压lstm模型

Browse Source
main
get 11 months ago
parent 7f387ebb78
commit f8969d4f06
2 changed files with 106 additions and 106 deletions
Show Stats Download Patch File Download Diff File

1
浙江电压等级电量/test1.py
Unescape Escape View File

@ -17,6 +17,7 @@ for city in df['地市'].drop_duplicates():
df_city['stat_date'] = df_city['stat_date'].map(lambda x:x.strip())
df_city['stat_date'] = pd.to_datetime(df_city['stat_date'],format='%Y-%m-%d')
df_city = df_city[df_city.columns[:-1]]
df_city.sort_values(by='stat_date',ascending=True,inplace=True)
df_city['stat_date'] = df_city['stat_date'].astype('str')
df_city.to_excel(fr'C:\Users\user\Desktop\浙江各地市分电压日电量数据\{city}.xlsx',index=False)
# file_Dir = r'C:\Users\鸽子\Desktop\浙江各地市行业电量数据'

211
浙江电压等级电量/电压等级_输出为5.py
Unescape Escape View File

@ -52,120 +52,119 @@ def data_preprocessing(data):
return data
# 拼接数据集
file_dir = r'C:\Users\user\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.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
# file_dir = r'C:\Users\user\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.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)
print(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)
#
# # 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)
# # 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())
# 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).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()
# 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())
#
# # 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).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
# max_value,min_value = 192751288.47,0.0
# model.load_state_dict(torch.load('dy5.pth',map_location=torch.device('cpu')))
# file_dir = r'C:\Users\user\Desktop\浙江各地市分电压日电量数据'
# for excel in os.listdir(file_dir):
# df_city = pd.read_excel(os.path.join(file_dir,excel))
# df_city.drop(columns=[i for i in df_city.columns if (df_city[i] == 0).sum() / len(df_city) >= 0.5], inplace=True)
#
# city = df_city['地市'].iloc[0]
# result_dict = {}
# for level in df_city.columns[2:]:
# x, y = create_dataset(df_city[level], 10)
# x = (x - min_value) / (max_value - min_value)
# x = x.reshape(-1, 1, 10)
# x = torch.from_numpy(x).type(torch.float32).to(device)
# pred = model(x).view(-1)
# pred = pred * (max_value - min_value) + min_value
# result = pred.detach().numpy()[-5:-2]
# result_dict[level] = list(result)
# df = pd.DataFrame(result_dict,index=['2023-10-29','2023-10-30','2023-10-31'])
# df.to_excel(fr'C:\Users\鸽子\Desktop\分压电量预测29-31\{city}.xlsx')
# print(result_dict)
max_value,min_value = 192751288.47,0.0
model.load_state_dict(torch.load('dy5.pth',map_location=torch.device('cpu')))
file_dir = r'C:\Users\user\Desktop\浙江各地市分电压日电量数据'
for excel in os.listdir(file_dir):
df_city = pd.read_excel(os.path.join(file_dir,excel))
df_city.drop(columns=[i for i in df_city.columns if (df_city[i] == 0).sum() / len(df_city) >= 0.5], inplace=True)
city = df_city['地市'].iloc[0]
result_dict = {}
for level in df_city.columns[2:]:
x, y = create_dataset(df_city[level], 10)
x = (x - min_value) / (max_value - min_value)
x = x.reshape(-1, 1, 10)
x = torch.from_numpy(x).type(torch.float32).to(device)
pred = model(x).view(-1)
pred = pred * (max_value - min_value) + min_value
result = pred.cpu().detach().numpy()[-5:-2]
result_dict[level] = list(result)
df = pd.DataFrame(result_dict,index=['2023-10-29','2023-10-30','2023-10-31'])
df.to_excel(fr'C:\Users\user\Desktop\分压电量预测29-31\{city} .xlsx')
print(result_dict)

Write Preview
Loading…
Cancel
Save