第12周：LSTM（火灾温度）

1.库以及数据的导入

1.1库的导入

import torch.nn.functional as F
import numpy  as np
import pandas as pd
import torch
from torch import nn

1.2数据集的导入

data = pd.read_csv("woodpine2.csv")

data

5948 rows × 4 columns

1.3数据集可视化

import matplotlib.pyplot as plt
import seaborn as sns
 
plt.rcParams['savefig.dpi'] = 500 #图片像素
plt.rcParams['figure.dpi']  = 500 #分辨率
 
fig, ax =plt.subplots(1,3,constrained_layout=True, figsize=(14, 3))
 
sns.lineplot(data=data["Tem1"], ax=ax[0])
sns.lineplot(data=data["CO 1"], ax=ax[1])
sns.lineplot(data=data["Soot 1"], ax=ax[2])
plt.show()

​

dataFrame = data.iloc[:,1:]
dataFrame

5948 rows × 3 columns

2.数据集的构建

2.1数据的预处理

from sklearn.preprocessing import MinMaxScaler

dataFrame = data.iloc[:,1:].copy()
sc  = MinMaxScaler(feature_range=(0, 1)) #将数据归一化，范围是0到1

for i in ['CO 1', 'Soot 1', 'Tem1']:
    dataFrame[i] = sc.fit_transform(dataFrame[i].values.reshape(-1, 1))

dataFrame.shape

(5948, 3)

2.设置X，y

width_X = 8
width_y = 1

##取前8个时间段的Tem1、CO 1、Soot 1为X，第9个时间段的Tem1为y。
X = []
y = []

in_start = 0

for _, _ in data.iterrows():
    in_end  = in_start + width_X
    out_end = in_end   + width_y
    
    if out_end < len(dataFrame):
        X_ = np.array(dataFrame.iloc[in_start:in_end , ])
        y_ = np.array(dataFrame.iloc[in_end  :out_end, 0])

        X.append(X_)
        y.append(y_)
    
    in_start += 1

X = np.array(X)
y = np.array(y).reshape(-1,1,1)

X.shape, y.shape

((5939, 8, 3), (5939, 1, 1))

#检查数据集中是否有空值
print(np.any(np.isnan(X)))
print(np.any(np.isnan(y)))

False
False

2.3划分数据集

X_train = torch.tensor(np.array(X[:5000]), dtype=torch.float32)
y_train = torch.tensor(np.array(y[:5000]), dtype=torch.float32)

X_test  = torch.tensor(np.array(X[5000:]), dtype=torch.float32)
y_test  = torch.tensor(np.array(y[5000:]), dtype=torch.float32)
X_train.shape, y_train.shape

(torch.Size([5000, 8, 3]), torch.Size([5000, 1, 1]))

from torch.utils.data import TensorDataset, DataLoader

train_dl = DataLoader(TensorDataset(X_train, y_train),
                      batch_size=64, 
                      shuffle=False)

test_dl  = DataLoader(TensorDataset(X_test, y_test),
                      batch_size=64, 
                      shuffle=False)

3.模型训练

3.1模型构建

class model_lstm(nn.Module):
    def __init__(self):
        super(model_lstm, self).__init__()
        self.lstm0 = nn.LSTM(input_size=3 ,hidden_size=320, 
                             num_layers=1, batch_first=True)
        
        self.lstm1 = nn.LSTM(input_size=320 ,hidden_size=320, 
                             num_layers=1, batch_first=True)
        self.fc0   = nn.Linear(320, 1)
 
    def forward(self, x):
 
        out, hidden1 = self.lstm0(x) 
        out, _ = self.lstm1(out, hidden1) 
        out    = self.fc0(out) 
        return out[:, -1:, :]   #取2个预测值,否则经过lstm会得到8*2个预测

model = model_lstm()
model

model_lstm(
  (lstm0): LSTM(3, 320, batch_first=True)
  (lstm1): LSTM(320, 320, batch_first=True)
  (fc0): Linear(in_features=320, out_features=1, bias=True)
)

model(torch.rand(30,8,3)).shape

torch.Size([30, 1, 1])

3.2定义训练函数

# 训练循环
import copy
def train(train_dl, model, loss_fn, opt, lr_scheduler=None):
    size        = len(train_dl.dataset)  
    num_batches = len(train_dl)   
    train_loss  = 0  # 初始化训练损失和正确率
    
    for x, y in train_dl:  
        x, y = x.to(device), y.to(device)
        
        # 计算预测误差
        pred = model(x)          # 网络输出
        loss = loss_fn(pred, y)  # 计算网络输出和真实值之间的差距
        
        # 反向传播
        opt.zero_grad()  # grad属性归零
        loss.backward()  # 反向传播
        opt.step()       # 每一步自动更新
        
        # 记录loss
        train_loss += loss.item()
        
    if lr_scheduler is not None:
        lr_scheduler.step()
        print("learning rate = {:.5f}".format(opt.param_groups[0]['lr']), end="  ")
    train_loss /= num_batches
    return train_loss

3.3定义测试函数

def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset)  # 测试集的大小
    num_batches = len(dataloader)          # 批次数目
    test_loss   = 0
    
    # 当不进行训练时，停止梯度更新，节省计算内存消耗
    with torch.no_grad():
        for x, y in dataloader:
            
            x, y = x.to(device), y.to(device)
            
            # 计算loss
            y_pred = model(x)
            loss        = loss_fn(y_pred, y)
            test_loss += loss.item()
        
    test_loss /= num_batches
    return test_loss

#设置GPU训练
device=torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

device(type='cpu')

3.4正式训练模型

#训练模型
model = model_lstm()
model = model.to(device)
loss_fn    = nn.MSELoss() # 创建损失函数
learn_rate = 1e-1   # 学习率
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate,weight_decay=1e-4)
epochs     = 50
train_loss = []
test_loss  = []
lr_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(opt,epochs, last_epoch=-1) 

for epoch in range(epochs):
    model.train()
    epoch_train_loss = train(train_dl, model, loss_fn, opt, lr_scheduler)
 
    model.eval()
    epoch_test_loss = test(test_dl, model, loss_fn)

    train_loss.append(epoch_train_loss)
    test_loss.append(epoch_test_loss)
    
    template = ('Epoch:{:2d}, Train_loss:{:.5f}, Test_loss:{:.5f}')
    print(template.format(epoch+1, epoch_train_loss,  epoch_test_loss))
    
print("="*20, 'Done', "="*20)

learning rate = 0.09990  Epoch: 1, Train_loss:0.00131, Test_loss:0.01243
learning rate = 0.09961  Epoch: 2, Train_loss:0.01428, Test_loss:0.01208
learning rate = 0.09911  Epoch: 3, Train_loss:0.01401, Test_loss:0.01172
learning rate = 0.09843  Epoch: 4, Train_loss:0.01369, Test_loss:0.01132
learning rate = 0.09755  Epoch: 5, Train_loss:0.01333, Test_loss:0.01088
learning rate = 0.09649  Epoch: 6, Train_loss:0.01289, Test_loss:0.01039
learning rate = 0.09524  Epoch: 7, Train_loss:0.01237, Test_loss:0.00983
learning rate = 0.09382  Epoch: 8, Train_loss:0.01174, Test_loss:0.00919
learning rate = 0.09222  Epoch: 9, Train_loss:0.01100, Test_loss:0.00849
learning rate = 0.09045  Epoch:10, Train_loss:0.01015, Test_loss:0.00772
learning rate = 0.08853  Epoch:11, Train_loss:0.00918, Test_loss:0.00689
learning rate = 0.08645  Epoch:12, Train_loss:0.00812, Test_loss:0.00604
learning rate = 0.08423  Epoch:13, Train_loss:0.00701, Test_loss:0.00520
learning rate = 0.08187  Epoch:14, Train_loss:0.00588, Test_loss:0.00438
learning rate = 0.07939  Epoch:15, Train_loss:0.00479, Test_loss:0.00363
learning rate = 0.07679  Epoch:16, Train_loss:0.00379, Test_loss:0.00297
learning rate = 0.07409  Epoch:17, Train_loss:0.00291, Test_loss:0.00241
learning rate = 0.07129  Epoch:18, Train_loss:0.00219, Test_loss:0.00196
learning rate = 0.06841  Epoch:19, Train_loss:0.00161, Test_loss:0.00160
learning rate = 0.06545  Epoch:20, Train_loss:0.00117, Test_loss:0.00133
learning rate = 0.06243  Epoch:21, Train_loss:0.00084, Test_loss:0.00112
learning rate = 0.05937  Epoch:22, Train_loss:0.00061, Test_loss:0.00098
learning rate = 0.05627  Epoch:23, Train_loss:0.00045, Test_loss:0.00087
learning rate = 0.05314  Epoch:24, Train_loss:0.00034, Test_loss:0.00079
learning rate = 0.05000  Epoch:25, Train_loss:0.00027, Test_loss:0.00073
learning rate = 0.04686  Epoch:26, Train_loss:0.00021, Test_loss:0.00069
learning rate = 0.04373  Epoch:27, Train_loss:0.00018, Test_loss:0.00066
learning rate = 0.04063  Epoch:28, Train_loss:0.00016, Test_loss:0.00063
learning rate = 0.03757  Epoch:29, Train_loss:0.00014, Test_loss:0.00061
learning rate = 0.03455  Epoch:30, Train_loss:0.00013, Test_loss:0.00060
learning rate = 0.03159  Epoch:31, Train_loss:0.00012, Test_loss:0.00058
learning rate = 0.02871  Epoch:32, Train_loss:0.00012, Test_loss:0.00058
learning rate = 0.02591  Epoch:33, Train_loss:0.00012, Test_loss:0.00057
learning rate = 0.02321  Epoch:34, Train_loss:0.00012, Test_loss:0.00057
learning rate = 0.02061  Epoch:35, Train_loss:0.00012, Test_loss:0.00057
learning rate = 0.01813  Epoch:36, Train_loss:0.00012, Test_loss:0.00057
learning rate = 0.01577  Epoch:37, Train_loss:0.00012, Test_loss:0.00057
learning rate = 0.01355  Epoch:38, Train_loss:0.00012, Test_loss:0.00057
learning rate = 0.01147  Epoch:39, Train_loss:0.00013, Test_loss:0.00058
learning rate = 0.00955  Epoch:40, Train_loss:0.00013, Test_loss:0.00059
learning rate = 0.00778  Epoch:41, Train_loss:0.00013, Test_loss:0.00060
learning rate = 0.00618  Epoch:42, Train_loss:0.00014, Test_loss:0.00061
learning rate = 0.00476  Epoch:43, Train_loss:0.00014, Test_loss:0.00061
learning rate = 0.00351  Epoch:44, Train_loss:0.00014, Test_loss:0.00062
learning rate = 0.00245  Epoch:45, Train_loss:0.00014, Test_loss:0.00062
learning rate = 0.00157  Epoch:46, Train_loss:0.00014, Test_loss:0.00062
learning rate = 0.00089  Epoch:47, Train_loss:0.00014, Test_loss:0.00062
learning rate = 0.00039  Epoch:48, Train_loss:0.00014, Test_loss:0.00062
learning rate = 0.00010  Epoch:49, Train_loss:0.00014, Test_loss:0.00062
learning rate = 0.00000  Epoch:50, Train_loss:0.00014, Test_loss:0.00062
==================== Done ====================

4.模型评估

4.1loss

import matplotlib.pyplot as plt
from datetime import datetime
current_time = datetime.now() # 获取当前时间

plt.figure(figsize=(5, 3),dpi=120)
 
plt.plot(train_loss    , label='LSTM Training Loss')
plt.plot(test_loss, label='LSTM Validation Loss')
 
plt.title('Training and Validation Loss')
plt.xlabel(current_time) # 打卡请带上时间戳，否则代码截图无效
plt.legend()
plt.show()

​

​

4.2模型调用及预测

predicted_y_lstm = sc.inverse_transform(model(X_test).detach().numpy().reshape(-1,1))                    # 测试集输入模型进行预测
y_test_1         = sc.inverse_transform(y_test.reshape(-1,1))
y_test_one       = [i[0] for i in y_test_1]
predicted_y_lstm_one = [i[0] for i in predicted_y_lstm]
 
plt.figure(figsize=(5, 3),dpi=120)
# 画出真实数据和预测数据的对比曲线
plt.plot(y_test_one[:2000], color='red', label='real_temp')
plt.plot(predicted_y_lstm_one[:2000], color='blue', label='prediction')
 
plt.title('Title')
plt.xlabel('X')
plt.ylabel('Y')
plt.legend()
plt.show()

​

4.3R2值评估

from sklearn import metrics
"""
RMSE ：均方根误差  ----->  对均方误差开方
R2   ：决定系数，可以简单理解为反映模型拟合优度的重要的统计量
"""
RMSE_lstm  = metrics.mean_squared_error(predicted_y_lstm_one, y_test_1)**0.5
R2_lstm    = metrics.r2_score(predicted_y_lstm_one, y_test_1)
 
print('均方根误差: %.5f' % RMSE_lstm)
print('R2: %.5f' % R2_lstm)

均方根误差: 7.07942
R2: 0.82427

• 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
• *🍖 原作者：K同学啊