第R7周：糖尿病预测模型优化探索

• 🍨 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

1. 数据预处理

1.1 设置GPU

import torch.nn as nn
import torch.nn.functional as F
import torchvision,torch

# 设置硬件设备，如果有GPU则使用，没有则使用cpu
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

1.2 数据导入

import numpy             as np
import pandas            as pd
import seaborn           as sns
from sklearn.model_selection   import train_test_split
import matplotlib.pyplot as plt
plt.rcParams['savefig.dpi'] = 500 #图片像素
plt.rcParams['figure.dpi']  = 500 #分辨率

plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签

import warnings 
warnings.filterwarnings("ignore")

DataFrame=pd.read_excel('/home/aiusers/space_yjl/深度学习训练营/进阶/第R6周：LSTM实现糖尿病探索与预测/dia.xls')
DataFrame.head()

DataFrame.shape

1.3 数据检查

# 查看数据是否有缺失值
print('数据缺失值---------------------------------')
print(DataFrame.isnull().sum())

# 查看数据是否有重复值
print('数据重复值---------------------------------')
print('数据集的重复值为:'f'{DataFrame.duplicated().sum()}')

2. 数据分析

2.1 数据分布分析

feature_map = {
    '年龄': '年龄',
    '高密度脂蛋白胆固醇': '高密度脂蛋白胆固醇',
    '低密度脂蛋白胆固醇': '低密度脂蛋白胆固醇',
    '极低密度脂蛋白胆固醇': '极低密度脂蛋白胆固醇',
    '甘油三酯': '甘油三酯',
    '总胆固醇': '总胆固醇',
    '脉搏': '脉搏',
    '舒张压':'舒张压',
    '高血压史':'高血压史',
    '尿素氮':'尿素氮',
    '尿酸':'尿酸',
    '肌酐':'肌酐',
    '体重检查结果':'体重检查结果'
}
plt.figure(figsize=(15, 10))

for i, (col, col_name) in enumerate(feature_map.items(), 1):
    plt.subplot(3, 5, i)
    sns.boxplot(x=DataFrame['是否糖尿病'], y=DataFrame[col])
    plt.title(f'{col_name}的箱线图', fontsize=14)
    plt.ylabel('数值', fontsize=12)
    plt.grid(axis='y', linestyle='--', alpha=0.7)

plt.tight_layout()
plt.show()

2.2 相关性分析

import plotly
import plotly.express as px

# 删除列 '卡号'
DataFrame.drop(columns=['卡号'], inplace=True)
# 计算各列之间的相关系数
df_corr = DataFrame.corr()

# 相关矩阵生成函数
def corr_generate(df):
    fig = px.imshow(df,text_auto=True,aspect="auto",color_continuous_scale='RdBu_r')
    fig.show()

# 生成相关矩阵
corr_generate(df_corr)

3. LSTM 模型

3.1 划分数据集

from sklearn.preprocessing import StandardScaler

# '高密度脂蛋白胆固醇'字段与糖尿病负相关，故而在 X 中去掉该字段
X = DataFrame.drop(['是否糖尿病','高密度脂蛋白胆固醇'],axis=1)
y = DataFrame['是否糖尿病']

# 数据集标准化处理
sc_X    = StandardScaler()
X = sc_X.fit_transform(X)

X = torch.tensor(np.array(X), dtype=torch.float32)
y = torch.tensor(np.array(y), dtype=torch.int64)

train_X, test_X, train_y, test_y = train_test_split(X, y, 
                                                    test_size=0.2,
                                                    random_state=1)
train_X.shape, train_y.shape

3.2 数据集构建

from torch.utils.data import TensorDataset, DataLoader

train_dl = DataLoader(TensorDataset(train_X, train_y),
                      batch_size=64, 
                      shuffle=False)

test_dl  = DataLoader(TensorDataset(test_X, test_y),
                      batch_size=64, 
                      shuffle=False)

3.3 定义模型

class model_lstm(nn.Module):
    def __init__(self):
        super(model_lstm, self).__init__()
        self.lstm0 = nn.LSTM(input_size=13 ,hidden_size=200, 
                             num_layers=1, batch_first=True)
        
        self.lstm1 = nn.LSTM(input_size=200 ,hidden_size=200, 
                             num_layers=1, batch_first=True)
        self.fc0   = nn.Linear(200, 2)
 
    def forward(self, x):
 
        out, hidden1 = self.lstm0(x) 
        out, _ = self.lstm1(out, hidden1) 
        out    = self.fc0(out) 
        return out   

model = model_lstm().to(device)
model

4. 训练模型

4.1 定义训练函数

# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小
    num_batches = len(dataloader)   # 批次数目, (size/batch_size，向上取整)

    train_loss, train_acc = 0, 0  # 初始化训练损失和正确率
    
    for X, y in dataloader:  # 获取图片及其标签
        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，targets为真实值，计算二者差值即为损失
        
        # 反向传播
        optimizer.zero_grad()  # grad属性归零
        loss.backward()        # 反向传播
        optimizer.step()       # 每一步自动更新
        
        # 记录acc与loss
        train_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()
        train_loss += loss.item()
            
    train_acc  /= size
    train_loss /= num_batches

    return train_acc, train_loss

4.2 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, (size/batch_size，向上取整)
    test_loss, test_acc = 0, 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 imgs, target in dataloader:
            imgs, target = imgs.to(device), target.to(device)
            
            # 计算loss
            target_pred = model(imgs)
            loss        = loss_fn(target_pred, target)
            
            test_loss += loss.item()
            test_acc  += (target_pred.argmax(1) == target).type(torch.float).sum().item()

    test_acc  /= size
    test_loss /= num_batches

    return test_acc, test_loss

4.3 训练模型

loss_fn    = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-4   # 学习率
opt        = torch.optim.Adam(model.parameters(),lr=learn_rate)
epochs     = 30

train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []

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

    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)
    
    # 获取当前的学习率
    lr = opt.state_dict()['param_groups'][0]['lr']
    
    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, 
                          epoch_test_acc*100, epoch_test_loss, lr))
    
print("="*20, 'Done', "="*20)

5. 模型评估

5.1 Loss与Accuracy图

import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings("ignore")               #忽略警告信息
plt.rcParams['font.sans-serif']    = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False      # 用来正常显示负号
plt.rcParams['figure.dpi']         = 100        #分辨率

from datetime import datetime
current_time = datetime.now() # 获取当前时间

epochs_range = range(epochs)

plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)

plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.xlabel(current_time) # 打卡请带上时间戳，否则代码截图无效

plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

六、总结

LSTM模型优化：

增加Dropout层以防止过拟合。

使用双向LSTM（bidirectional=True）以捕捉更多特征。

self.lstm0 = nn.LSTM(input_size=13, hidden_size=200, num_layers=1, batch_first=True, bidirectional=True)
self.dropout = nn.Dropout(0.5)  # 添加Dropout层