机器学习系列（八） 逻辑回归和多分类问题 2020.6.9

前言

本节学习逻辑回归

• 解决分类问题
• 样本特征和发生概率联系在一起

最后涉及多分类的OvR和OvO

1、逻辑回归

将样本的特征和样本发生的概率联系在一起

用到了sigmoid函数

通过训练得到θ
然后可以进行预测

损失函数是

进行演化和代入如下



由于这个损失函数没有解析解
所以用梯度下降法来求解
梯度是

实现如下

import numpy as np
from sklearn.metrics import accuracy_score

class LogisticRegression:
    def __init__(self):
        """初始化Logistic Regression模型"""
        self.coef_ = None
        self.intercept_ = None
        self._theta = None
   
    def _sigmoid(self, t):
        return 1. / (1. + np.exp(-t))
    
    def fit(self, X_train, y_train, eta=0.01, n_iters=1e4):
        """根据训练数据集X_train, y_train, 使用梯度下降法训练Logistic Regression模型"""
        assert X_train.shape[0] == y_train.shape[0], \
            "the size of X_train must be equal to the size of y_train"
        # 损失函数
        def J(theta, X_b, y):
            y_hat = self._sigmoid(X_b.dot(theta))
            try:
                return - np.sum(y*np.log(y_hat) + (1-y)*np.log(1-y_hat)) / len(y)
            except:
                return float('inf')
        # 梯度
        def dJ(theta, X_b, y):
            return X_b.T.dot(self._sigmoid(X_b.dot(theta)) - y) / len(y)
        # 梯度下降
        def gradient_descent(X_b, y, initial_theta, eta, n_iters=1e4, epsilon=1e-8):
            theta = initial_theta
            cur_iter = 0
            while cur_iter < n_iters:
                gradient = dJ(theta, X_b, y)
                last_theta = theta
                theta = theta - eta * gradient
                if (abs(J(theta, X_b, y) - J(last_theta, X_b, y)) < epsilon):
                    break
                cur_iter += 1
            return theta
        X_b = np.hstack([np.ones((len(X_train), 1)), X_train])
        initial_theta = np.zeros(X_b.shape[1])
        self._theta = gradient_descent(X_b, y_train, initial_theta, eta, n_iters)
        self.intercept_ = self._theta[0]
        self.coef_ = self._theta