Pytorch专题实战——逻辑回归(Logistic Regression)

1.计算流程

 1)设计模型： Design model (input, output, forward pass with different layers)   
 2) 构建损失函数与优化器：Construct loss and optimizer
 3) 循环：Training loop
      - Forward = compute prediction and loss
      - Backward = compute gradients
       - Update weights

2.Pytorch搭建线性逻辑模型

2.1.导入必要模块

import torch
import torch.nn as nn
import numpy as np
from sklearn import datasets
from sklearn.preprocessing import StandardScaler   #数据标准化模块
from sklearn.model_selection import train_test_split

2.2.数据准备

bc = datasets.load_breast_cancer()      #加载数据集
X, y = bc.data, bc.target       #取数据和标签

n_samples, n_features = X.shape    #样本数量、特征数
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

sc = StandardScaler()
X_train = sc.fit_transform(X_train)    #求得训练集X的均值，方差，最大值，最小值并进行标准化
X_test = sc.transform(X_test)         #对标签标准化

#将数据转化为torch形式
X_train = torch.from_numpy(X_train.astype(np.float32))    
X_test = torch.from_numpy(X_test.astype(np.float32))
y_train = torch.from_numpy(y_train.astype(np.float32))
y_test = torch.from_numpy(y_test.astype(np.float32))

y_train = y_train.view(y_train.shape[0], 1)   #将标签多行1列
y_test = y_test.view(y_test.shape[0], 1)

2.3.构建模型

class Model(nn.Module):
    def __init__(self, n_input_features):
        super(Model, self).__init__()
        self.linear = nn.Linear(n_input_features, 1)
        
    def forward(self, x):
        y_pred = torch.sigmoid(self.linear(x))
        return y_pred

2.4.训练+计算准确率

model = Model(n_features)

num_epochs = 100
learning_rate = 0.01
criterion = nn.BCELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

for epoch in range(num_epochs):
    y_pred = model(X_train)
    loss = criterion(y_pred, y_train)
    loss.backward()
    optimizer.step()
    optimizer.zero_grad()
    if (epoch+1)%10 == 0:
        print(f'epoch:{epoch+1}, loss={loss.item():.4f}')
        
with torch.no_grad():
    y_predicted = model(X_test)
    y_predicted_cls = y_predicted.round()  #四舍五入
    acc = y_predicted_cls.eq(y_test).sum()/float(y_test.shape[0])
    print(f'accuracy:{acc.item():.4f}')