RNN心脏病预测

Zzzzzzzz1013

164人浏览 · 2026-07-24 14:51:24

Zzzzzzzz1013 · 2026-07-24 14:51:24 发布

🍨 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

一、前期准备工作

1.设置硬件设备

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

# 设置GPU训练，也可以使用CPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

2.导入数据

import pandas as pd

df = pd.read_csv(r"D:\Code\R1.csv")

df

二、构建数据集

1.标准化

from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split

X = df.iloc[:, :-1]
y = df.iloc[:, -1]

# 将每一列特征标准化为标准正态分布，注意，标准化是针对每一列而言的
sc = StandardScaler()
X = sc.fit_transform(X)

2.划分数据集

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

X_train, X_test, y_train, y_test = train_test_split(
    X,
    y,
    test_size=0.1,
    random_state=1
)

# 维度扩增使其符合RNN模型可接受的shape
X_train = X_train.unsqueeze(1)
X_test = X_test.unsqueeze(1)

X_train.shape, y_train.shape

3.构建数据加载器

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
)

三、模型训练

1.构建模型

class model_rnn(nn.Module):
    def __init__(self):
        super(model_rnn, self).__init__()

        self.rnn0 = nn.RNN(
            input_size=13,
            hidden_size=200,
            num_layers=1,
            batch_first=True
        )

        self.fc0 = nn.Linear(200, 50)
        self.fc1 = nn.Linear(50, 2)

    def forward(self, x):
        out, _ = self.rnn0(x)
        out = out[:, -1, :]  # 只取最后一个时间步的输出
        out = self.fc0(out)
        out = self.fc1(out)

        return out


model = model_rnn().to(device)
model

model(torch.rand(30, 1, 13).to(device)).shape

2.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:  # 获取数据及其标签
        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

        # 反向传播
        optimizer.zero_grad()  # 梯度归零
        loss.backward()        # 反向传播
        optimizer.step()       # 更新模型参数

        # 记录准确率与损失
        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.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.正式训练模型

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 = 50

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)

四、模型评估

1.Loss与Accuracy图

import matplotlib.pyplot as plt
from datetime import datetime

# 隐藏警告
import warnings
warnings.filterwarnings("ignore")  # 忽略警告信息

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

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"] = 200              # 分辨率

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()

2.混淆矩阵

print("=============输入数据Shape为============")
print("X_test.shape: ", X_test.shape)
print("y_test.shape: ", y_test.shape)

pred = model(X_test.to(device)).argmax(1).cpu().numpy()

print("\n=============输出数据Shape为============")
print("pred.shape: ", pred.shape)

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay

# 计算混淆矩阵
cm = confusion_matrix(y_test, pred)

plt.figure(figsize=(6, 5))
plt.suptitle("")
sns.heatmap(cm, annot=True, fmt="d", cmap="Blues")

# 修改字体大小
plt.xticks(fontsize=10)
plt.yticks(fontsize=10)
plt.title("Confusion Matrix", fontsize=12)
plt.xlabel("Predicted Label", fontsize=10)
plt.ylabel("True Label", fontsize=10)

# 显示图
plt.tight_layout()  # 调整布局防止重叠
plt.show()

3.调用模型进行预测

test_X = X_test[0].unsqueeze(1)  # X_test[0]即我们的输入数据

pred = model(test_X.to(device)).argmax(1).item()

print("模型预测结果为：", pred)
print("==" * 20)
print("0：不会患心脏病")
print("1：可能患心脏病")