You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

186 lines
6.7 KiB
Python

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

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" # 解决OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
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 = pd.to_datetime(data.index)
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)
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()
# 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.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)
# # 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)