Python实现Logistic回归：代码示例和应用

以下是一个简单的实现Logistic回归的Python代码：

import numpy as np

class LogisticRegression:
    def __init__(self, lr=0.01, num_iter=100000, fit_intercept=True, verbose=False):
        self.lr = lr
        self.num_iter = num_iter
        self.fit_intercept = fit_intercept
        self.verbose = verbose
        
    def __add_intercept(self, X):
        intercept = np.ones((X.shape[0], 1))
        return np.concatenate((intercept, X), axis=1)
    
    def __sigmoid(self, z):
        return 1 / (1 + np.exp(-z))
    
    def __loss(self, h, y):
        return (-y * np.log(h) - (1 - y) * np.log(1 - h)).mean()
    
    def fit(self, X, y):
        if self.fit_intercept:
            X = self.__add_intercept(X)
        
        self.theta = np.zeros(X.shape[1])
        
        for i in range(self.num_iter):
            z = np.dot(X, self.theta)
            h = self.__sigmoid(z)
            gradient = np.dot(X.T, (h - y)) / y.size
            self.theta -= self.lr * gradient
            
            if self.verbose and i % 10000 == 0:
                z = np.dot(X, self.theta)
                h = self.__sigmoid(z)
                print(f'Loss: {self.__loss(h, y)}\t')
    
    def predict_prob(self, X):
        if self.fit_intercept:
            X = self.__add_intercept(X)
    
        return self.__sigmoid(np.dot(X, self.theta))
    
    def predict(self, X, threshold):
        return self.predict_prob(X) >= threshold

使用方法：

from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split

X, y = make_classification(n_samples=1000, n_features=10, n_classes=2, random_state=42)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

model = LogisticRegression(lr=0.1, num_iter=300000)
model.fit(X_train, y_train)
predictions = model.predict(X_test, 0.5)

print(f'Accuracy: {(predictions == y_test).mean()}')

该代码使用梯度下降算法实现Logistic回归，并在训练数据上进行了拟合。在测试数据上进行了预测，并计算了准确率。