LSTM 实现糖尿病探索与预测-CSDN博客

- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/rnFa-IeY93EpjVu0yzzjkw) 中的学习记录博客**
- **🍖 原作者：[K同学啊](https://mtyjkh.blog.csdn.net/)**

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

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
plt.rcParams['figure.dpi'] = 500
plt.rcParams['font.sans-serif'] = ['SimHei']

import warnings
warnings.filterwarnings('ignore')

DataFrame = pd.read_excel('/content/drive/MyDrive/dia.xls')
DataFrame.head()

DataFrame.shape

1.3 数据检查

print('数据缺失值----------------------')
print(DataFrame.isnull().sum())

print('数据重复值----------------------')
print('数据集的重复值为：'f'{DataFrame.duplicated().sum()}')

1.4 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('树脂',fontsize=12)
  plt.grid(axis='y',linestyle='--',alpha=0.7)

plt.tight_layout()
plt.show()

2.LSTM 模型

2.1 数据集构建

from sklearn.preprocessing import StandardScaler

X = DataFrame.drop(['卡号','是否糖尿病','高密度脂蛋白胆固醇'],axis=1)
y = DataFrame['是否糖尿病']

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

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)

2.2 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

3.训练模型

3.1 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pred和真实值y之间的差距，y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

3.2 定义测试函数

def test(dataloader, model, loss_fn):
    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)
    test_loss, test_acc = 0, 0  # 初始化测试损失和正确率

    # 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:  # 获取图片及其标签
        with torch.no_grad():
            imgs, target = imgs.to(device), target.to(device)

            # 计算误差
            tartget_pred = model(imgs)          # 网络输出
            loss = loss_fn(tartget_pred, target)  # 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

            # 记录acc与loss
            test_loss += loss.item()
            test_acc  += (tartget_pred.argmax(1) == target).type(torch.float).sum().item()

    test_acc  /= size
    test_loss /= num_batches

    return test_acc, test_loss

3.3 训练模型

loss_fn = nn.CrossEntropyLoss()
opt = torch.optim.Adam(model.parameters(),lr=1e-4)
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)

    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)

4.模型评估

4.1 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()