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 1 year ago
parent 08f1129750
commit 7f387ebb78
5 changed files with 123 additions and 122 deletions
Show Stats Download Patch File Download Diff File

2
.idea/misc.xml
Unescape Escape View File

@ -1,4 +1,4 @@
<?xml version="1.0" encoding="UTF-8"?> <?xml version="1.0" encoding="UTF-8"?>
<project version="4"> <project version="4">
<component name="ProjectRootManager" version="2" project-jdk-name="C:\anaconda\envs\pytorch" project-jdk-type="Python SDK" /> <component name="ProjectRootManager" version="2" project-jdk-name="pytorch_gpu" project-jdk-type="Python SDK" />
</project> </project>

2
.idea/pytorch2.iml
Unescape Escape View File

@ -2,7 +2,7 @@
<module type="PYTHON_MODULE" version="4"> <module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager"> <component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$" /> <content url="file://$MODULE_DIR$" />
<orderEntry type="jdk" jdkName="C:\anaconda\envs\pytorch" jdkType="Python SDK" /> <orderEntry type="jdk" jdkName="pytorch_gpu" jdkType="Python SDK" />
<orderEntry type="sourceFolder" forTests="false" /> <orderEntry type="sourceFolder" forTests="false" />
</component> </component>
</module> </module>

BIN
浙江电压等级电量/dy5.pth
View File

Binary file not shown.

45
浙江电压等级电量/test1.py
Unescape Escape View File

@ -9,26 +9,27 @@ n2 = np.array([]).reshape(3,-1)
print(np.max([[1,2,3],[4,5,6]])) print(np.max([[1,2,3],[4,5,6]]))
# 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\user\Desktop\浙江各地市分电压日电量数据'
# df = pd.read_csv(r'C:\Users\鸽子\Desktop\浙江省各地市日电量数据21-23年 .csv',encoding='gbk') df = pd.read_excel(r'C:\Users\user\Desktop\浙江省各地市日电量及分压数据21-23年.xlsx',sheet_name=1)
# df.columns = df.columns.map(lambda x:x.strip()) df.columns = df.columns.map(lambda x:x.strip())
# for city in df['地市'].drop_duplicates(): for city in df['地市'].drop_duplicates():
# df_city = df[df['地市']== city] df_city = df[df['地市']== city]
# df_city['stat_date'] = pd.to_datetime(df_city['stat_date'],format='%Y/%m/%d') df_city['stat_date'] = df_city['stat_date'].map(lambda x:x.strip())
# df_city = df_city[df_city.columns[:-1]] df_city['stat_date'] = pd.to_datetime(df_city['stat_date'],format='%Y-%m-%d')
# df_city['stat_date'] = df_city['stat_date'].astype('str') df_city = df_city[df_city.columns[:-1]]
# df_city.to_excel(fr'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据\{city}.xlsx',index=False) df_city['stat_date'] = df_city['stat_date'].astype('str')
file_Dir = r'C:\Users\鸽子\Desktop\浙江各地市行业电量数据' 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)
for excel in os.listdir(file_Dir): # file_Dir = r'C:\Users\鸽子\Desktop\浙江各地市行业电量数据'
df1 = pd.read_excel(r'C:\Users\鸽子\Desktop\浙江各地市日电量数据-27-28).xlsx',sheet_name=1) # for excel in os.listdir(file_Dir):
df1.columns = df1.columns.map(lambda x:x.strip()) # df1 = pd.read_excel(r'C:\Users\鸽子\Desktop\浙江各地市日电量数据-27-28).xlsx',sheet_name=1)
df2 = pd.read_excel(os.path.join(file_Dir,excel)) # df1.columns = df1.columns.map(lambda x:x.strip())
df2['地市'] = df2['地市'].map(lambda x:x.strip()) # df2 = pd.read_excel(os.path.join(file_Dir,excel))
city = df2['地市'].iloc[0] # df2['地市'] = df2['地市'].map(lambda x:x.strip())
col_list = df2.columns # city = df2['地市'].iloc[0]
df1 = df1[col_list] # col_list = df2.columns
df1 = df1[(df1['stat_date']==20231028)&(df1['地市']==city)] # df1 = df1[col_list]
df1['stat_date'] = pd.to_datetime(df1['stat_date'],format='%Y%m%d') # df1 = df1[(df1['stat_date']==20231028)&(df1['地市']==city)]
df2 = pd.concat((df2,df1),ignore_index=True) # df1['stat_date'] = pd.to_datetime(df1['stat_date'],format='%Y%m%d')
df2.to_excel(fr'C:\Users\鸽子\Desktop\浙江各地市行业电量数据\{city}.xlsx') # df2 = pd.concat((df2,df1),ignore_index=True)
# df2.to_excel(fr'C:\Users\鸽子\Desktop\浙江各地市行业电量数据\{city}.xlsx')

196
浙江电压等级电量/电压等级_输出为5.py
Unescape Escape View File

@ -5,7 +5,7 @@ from torch import nn
from multiprocessing import Pool from multiprocessing import Pool
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
import os import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE" os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE" # 解决OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
DAYS_FOR_TRAIN = 10 DAYS_FOR_TRAIN = 10
torch.manual_seed(42) torch.manual_seed(42)
class LSTM_Regression(nn.Module): class LSTM_Regression(nn.Module):
@ -52,120 +52,120 @@ def data_preprocessing(data):
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\user\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.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))
# 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,min_value) print(max_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())
# 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
# 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')
# 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.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.legend(loc='best')
# plt.show() plt.show()
# 创建测试集 # 创建测试集
max_value,min_value = 199482558.1,0.0 # max_value,min_value = 192751288.47,0.0
model.load_state_dict(torch.load('dy5.pth',map_location=torch.device('cpu'))) # model.load_state_dict(torch.load('dy5.pth',map_location=torch.device('cpu')))
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\user\Desktop\浙江各地市分电压日电量数据'
for excel in os.listdir(file_dir): # for excel in os.listdir(file_dir):
df_city = pd.read_excel(os.path.join(file_dir,excel)) # 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) # 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] # city = df_city['地市'].iloc[0]
result_dict = {} # result_dict = {}
for level in df_city.columns[2:]: # for level in df_city.columns[2:]:
x, y = create_dataset(df_city[level], 10) # x, y = create_dataset(df_city[level], 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)
x = torch.from_numpy(x).type(torch.float32).to(device) # x = torch.from_numpy(x).type(torch.float32).to(device)
pred = model(x).view(-1) # pred = model(x).view(-1)
pred = pred * (max_value - min_value) + min_value # pred = pred * (max_value - min_value) + min_value
result = pred.detach().numpy()[-5:-2] # result = pred.detach().numpy()[-5:-2]
result_dict[level] = list(result) # result_dict[level] = list(result)
df = pd.DataFrame(result_dict,index=['2023-10-29','2023-10-30','2023-10-31']) # 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') # df.to_excel(fr'C:\Users\鸽子\Desktop\分压电量预测29-31\{city}.xlsx')
print(result_dict) # print(result_dict)

Write Preview
Loading…
Cancel
Save