从0开始搞机器学习

第一个demo

安装基础包

pip3 install torch torchvision torchaudio
pip3 install scikit-learn

基础pytorch代码

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import TensorDataset, DataLoader
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_auc_score
import matplotlib.pyplot as plt

# 设置随机种子以复现结果
torch.manual_seed(42)

# 生成模拟数据
X, y = make_classification(n_samples=100, n_features=10, n_informative=10, n_redundant=0, random_state=42)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 将数据转换为PyTorch张量
X_train_tensor = torch.tensor(X_train, dtype=torch.float32)
y_train_tensor = torch.tensor(y_train, dtype=torch.float32).view(-1, 1)
X_test_tensor = torch.tensor(X_test, dtype=torch.float32)
y_test_tensor = torch.tensor(y_test, dtype=torch.float32).view(-1, 1)

# 创建数据加载器
train_dataset = TensorDataset(X_train_tensor, y_train_tensor)
train_loader = DataLoader(dataset=train_dataset, batch_size=8, shuffle=True)

# 定义模型
class SimpleDNN(nn.Module):
    def __init__(self):
        super(SimpleDNN, self).__init__()
        self.fc1 = nn.Linear(10, 64)
        self.fc2 = nn.Linear(64, 32)
        self.fc3 = nn.Linear(32, 1)
        self.sigmoid = nn.Sigmoid()
        
    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.sigmoid(self.fc3(x))
        return x

# 实例化模型
model = SimpleDNN()

# 定义损失函数和优化器
criterion = nn.BCELoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 训练模型
num_epochs = 100
for epoch in range(num_epochs):
    for inputs, labels in train_loader:
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

# 测试模型
with torch.no_grad():
    y_pred = model(X_test_tensor).numpy()

# 计算AUC值
auc_score = roc_auc_score(y_test, y_pred)
print(f'AUC: {auc_score:.2f}')

# 绘制ROC曲线
from sklearn.metrics import roc_curve
fpr, tpr, _ = roc_curve(y_test, y_pred)
plt.plot(fpr, tpr, label=f'ROC Curve (AUC = {auc_score:.2f})')
plt.plot([0, 1], [0, 1], 'k--')
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC Curve')
plt.legend(loc='lower right')
plt.show()