当前位置：首页 > ds >正文

第35周—————糖尿病预测模型优化探索

ds 2025/7/13 9:55:49

目录

目录

前言

1.检查GPU

2.查看数据

编辑 3.划分数据集

4.创建模型与编译训练

5.编译及训练模型

6.结果可视化

7.总结

前言

🍨 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.检查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

2.查看数据

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('data/dia.xls')
DataFrame.head()# 查看数据是否有缺失值
print('数据缺失值---------------------------------')
print(DataFrame.isnull().sum())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))import matplotlib.pyplot as plt
import seaborn as sns# 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):plt.figure(figsize=(10, 8))sns.heatmap(df, annot=True,          # 显示数值fmt=".2f",           # 保留两位小数cmap='RdBu_r',       # 使用相同颜色方案annot_kws={"size": 8}, # 调整注释字号linewidths=0.5)      # 单元格间线 宽plt.xticks(rotation=45, ha='right')  # 调整x轴标签角度plt.yticks(rotation=0)           # 保持y轴标签水平plt.tight_layout()               # 自动调整布局plt.show()# 生成相关矩阵
corr_generate(df_corr)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()

3.划分数据集

from sklearn.preprocessing import StandardScaler
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)
# 维度扩增使其符合LSTM模型可接受shape
train_X = train_X.unsqueeze(1)
test_X = test_X.unsqueeze(1)
train_X.shape, train_y.shapefrom torch.utils.data import TensorDataset, DataLoadertrain_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)

4.创建模型与编译训练

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 = out[:, -1, :] # 只取最后一个时间步的输出out = self.fc0(out) return out model = model_lstm().to(device)
model

5.编译及训练模型

# 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losstrain_acc += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc /= sizetrain_loss /= num_batchesreturn train_acc, train_lossdef 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losstarget_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 /= sizetest_loss /= num_batchesreturn test_acc, test_lossloss_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 = 30train_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)

6.结果可视化

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()