逻辑回归(logistic regression)

基本概念

逻辑回归是一种概率型非线性回归模型。虽然名字里面有回归，但是他其实是一种分类的方法，通常是用来研究在某些条件下某个结果会不会发生，例如：已知病人身体里的肿瘤的情况，然后判断这个肿瘤是良性还是恶性。

逻辑回归与线性回归

逻辑回归同线性回归一样都需要有一个假设函数$h_\theta(x)$,代价函数$J(\theta)$,在大体上基本相同。
在线性回归中：

$$h_\theta(x)=\theta_0+\theta_1*x_1+...+..\theta_n*x_n$$
但是我们引入了一个 $Sigmoid$函数，将结果给映射到区间 $(0,1)$.
$Sigmoid$函数：
$$\pi(x)= \frac{1}{1+e^{-x}}$$
因此在逻辑回归中的假设函数就是
$$h_\theta(x)=\pi(\theta^\tau x)\\ =\frac{1}{1+e^{-\theta^\tau x}}$$
$\pi(x)$的定义域为 $(-\infty,+\infty)$,值域为 $(0,1)$。因此就将最后的结果映射到了 $(0,1)$中。
$$P(y=1|x,\theta)=\pi(\theta^\tau x) P(y=0|x,\theta)=1-\pi(\theta^\tau x)$$
当 $h_\theta(x)\geq 0.5$时, $y=1$
当 $h_\theta(x)< 0.5$时, $y=0$

代价函数$J(\theta)$

在求解参数$\theta$的时候我们用用极大似然估计来求解。设$pi=P(y_i=1|xi;\theta)$表示在给定条件下$y_i=1$的概率，则$pi=P(y_i=0|xi;\theta)=1-pi$,所以可以得到一个观测值的概率$P(y_i)=p_i^{y_i}(1-p_i)^{1-y_i}$,各样本间相互独立就可以得到似然函数为：

$$L(\theta)=\Pi_{i=1}^m[h_\theta(x_i)]^{y_i}[1-h_\theta(x_i)]^{1-y_i}$$
目标就是求这个函数的值最大的时候的参数 $\theta$,推导过程如下：

$$lnL(\theta)=\Sigma_{i=1}^m[y^{(i)}ln(h_\theta(x^{(i)}))+(1-y^{(i)})ln(1-h_\theta(x^{(i)}))]$$
$$lnL(\theta)=\Sigma_{i=1}^m(y^{(i)}ln(\frac{1}{1+e^{-x^{(i)}}})+(1-y^{(i)})ln(1-\frac{1}{1+e^{-x^{(i)}}}))$$
$$lnL(\theta)=\Sigma_{i=1}^m(y^{(i)}ln(\frac{e^{x^{(i)}}}{e^{x^{(i)}}+1})+(1-y^{(i)})ln(\frac{1}{e^{x^{(i)}}+1}))$$
$$lnL(\theta)=\Sigma_{i=1}^m(y^{(i)}*lne^{x^{(i)}}-y^{(i)}*ln(1+e^{x^{(i)}})-(1-y^{(i)})*ln(1+e^{x^{(i)}}))$$
$$lnL(\theta)=\Sigma_{i=1}^m(x^{(i)}y^{(i)}-ln(1+e^{x^{(i)}}))$$

我们要求得$\theta$，使得$L(\theta)$最大，那么我们的代价函数就可以这样表示：

$$J(\theta)=-\frac{1}{ m}lnL(\theta)=-\frac{1}{ m}\Sigma_{i=1}^m(x^{(i)}y^{(i)}-ln(1+e^{x^{(i)}}))$$
为了求得 $\theta$我们可以用梯度下降法:
对 $J(\theta)$求偏导：
$$\frac{\partial J(\theta)}{\partial \theta_j}=-\Sigma_{i=1}^m[y^{(i)}-h_\theta(x^{(i)})]*x_j^{(i)}=\Sigma_{i=1}^m[h_\theta(x^{(i)})-y^{(i)}]*x_j^{(i)}$$
因此完整的梯度下降应该为：
$$\theta_j=\theta_j+\alpha\frac{\partial J(\theta)}{\partial \theta_j}=\theta_j+\alpha\Sigma_{i=1}^m[h_\theta(x^{(i)})-y^{(i)}]*x_j^{(i)}$$

Matlab code

$cost function$

function [J, grad] = costFunction(theta, X, y)
%COSTFUNCTION Compute cost and gradient for logistic regression
%   J = COSTFUNCTION(theta, X, y) computes the cost of using theta as the
%   parameter for logistic regression and the gradient of the cost
%   w.r.t. to the parameters.

% Initialize some useful values
m = length(y); % number of training examples

% You need to return the following variables correctly 
J = 0;
grad = zeros(size(theta));

% ====================== YOUR CODE HERE ======================
% Instructions: Compute the cost of a particular choice of theta.
%               You should set J to the cost.
%               Compute the partial derivatives and set grad to the partial
%               derivatives of the cost w.r.t. each parameter in theta
%
% Note: grad should have the same dimensions as theta
%

z = X*theta;
hx = 1 ./ (1 + exp(-z));
J = -1/m *sum([y'*log(hx) + (1-y)'*log(1-hx)]);
%J = 1/m * sum([-y' * log(hx) - (1 - y)' * log(1 - hx)]);
for j = 1:length(theta)
    grad(j)=1/m*sum((hx-y)'*X(:,j));
end;






% =============================================================

end

$Sigmoid$

function g = sigmoid(z)
%SIGMOID Compute sigmoid functoon
%   J = SIGMOID(z) computes the sigmoid of z.

% You need to return the following variables correctly 
g = zeros(size(z));

% ====================== YOUR CODE HERE ======================
% Instructions: Compute the sigmoid of each value of z (z can be a matrix,
%               vector or scalar).

sz = size(z);

for i = 1:sz(1),
    for j = 1:sz(2),
        g(i,j) = 1./(1+exp(-z(i,j)));
    end;
end;
% =============================================================

end

$predict$

function p = predict(theta, X)
%PREDICT Predict whether the label is 0 or 1 using learned logistic 
%regression parameters theta
%   p = PREDICT(theta, X) computes the predictions for X using a 
%   threshold at 0.5 (i.e., if sigmoid(theta'*x) >= 0.5, predict 1)

m = size(X, 1); % Number of training examples

% You need to return the following variables correctly
p = zeros(m, 1);

% ====================== YOUR CODE HERE ======================
% Instructions: Complete the following code to make predictions using
%               your learned logistic regression parameters. 
%               You should set p to a vector of 0's and 1's
%


pp = sigmoid(X*theta);

pos = find(pp>=0.5);

p(pos,1)=1;




% =========================================================================


end