Machine Learning 5 Basic Operations

5-4 Plotting data

• T = [0:0.1:1]
• Y1 = sin(2*pi*4*t)
• Plot(t,y1) //绘图程序
• Hold on 在原图基础上绘制
• Xlabel(‘time’)
• Ylabel(‘value’)
• Legend(‘sin’,’cos’) 为线进行标注
• Title(‘my plot’) 标题
• Print -dpng ‘myplot.png’ 保存
• Close 关闭图像
• Figure(1); plot(t,y1);
• Figute(2);plot(t,y2);
• Subplot(1,2,1); %Divides plot a 1x2 grid
• Axis([0.5 1 -1 1])
• Clf 干掉所有的图片
• Imagesc(A) 可视化矩阵
• Imagesc(A), colorbar, colormap gray; 为图片添加bar，设置颜色为灰色

5-5 Control Statements for, while, if statements

语法上不对缩进有要求

• for

for i = 1:10,    v(i) =  2^i;    end;indices = 1:10;for i = indices.    disp(i);end;

• while

while i <= 5,    v(i) = 100;    i = i+1;end;

• break

while true,    v(i) = 999;    i = i + 1;    if(i == 6),        break;    end;end;

• if else

if v(1) == 1,    disp('The value is one');    elseif v(1) == 2,        disp('The value is two');    else        disp('end');end;

• exit/quit 退出octave
• function 使用时，要把函数放在当前空间

function y = squareThisNumber(x)y = x^2;

function [y1, y2] = squareAndCubeThisNumber(x); % 返回多个值y1 = x^2;y2 = x^3;

function J = costFunctionJ(X, y, theta)% X is the "design matrix" containing our training examples.% y i the class labelsm = size(X, 1); % number of training examplespredictions = X*theta; % predictions of hypothesis on all m examplessqrErrors = (predictions - y).^2; % squared errorsJ = 1/(2*m) * sum(sqrErrors);

• addpath 添加搜索路径

addpath('C:\users\ang\Desktop')

Vectorization

• 向量化可以降低计算时间，提升编程效率

Working on and submitting programming exercises

cd '作业所在目录'submit()