机器学习作业 之 logistic regression（programming exercise week 3 ）

1 plotDate

pos = find(y==1);neg =find(y == 0); 15 h1=plot(X(pos,1),X(pos,2),'*','MarkerFaceColor','b'); 16 h2=plot(X(neg,1),X(neg,2),'o','MarkerfaceColor','r');

2 sigmoid

g = 1./(1+exp(-z));

ps: 這個除號前面一定要加點，之前沒有的時候一直報錯

3 cost function && gradient descent

 h = sigmoid(X*theta); J = sum((-y)'*log(h) - (1-y)'*log(1-h))/m; grad =(h-y)'*X/m;

4 predict

 f = sigmoid(X*theta); p = (f>=0.5);

5 cost function reg

 h = sigmoid(X*theta); 22  23  J = sum((-y)'*log(h) - (1-y)'*log(1-h))/m +(lambda/(2*m)) * sum(theta(2:end ).^2) 24  25  grad(1) =(h-y)'*X(:,1)/m; 26   grad(2:end) = (h-y)'*X(:,2:end)/m+lambda/m*theta(2:end)'; 27