【吴恩达】机器学习第14章k-Means以及ex7-k-means编程练习

1.K-means方法是什么?

1.首先K-meas方法是一种无监督的聚类问题。

2.方法内容:首先需要确定聚类中心u和聚类数量K:我们可以随机选择中心u;当K<m(m是样本数),我们可以随机选择K个样本作为聚类中心,这个方法一般效果会好一些。聚类数量K我们可以通过最小化K-means的优化目标函数J来实现,得到“肘部规则”的拐点,即可找到合适的聚类数量。但是往往很多时候,通过这种方法并不能得到具有拐点的变化曲线,因此我们也可以尝试借助后续目标来确定聚类数量。比如卖衣服:有S、M、L三个号码,那我们可以将聚类数量K=3,但是号码也是是xs、s、M、L、xL,我们也可以将聚类数目定为5,如何确定3还是5呢,我们可以根据两种分类方法后续的销量和利润进行对比,选择最佳聚类数目。

3.方法步骤:

step1:首先我们随机确定K个聚类中心u_{1} ;u_{2};....u_{k},这里的u_{i}表示的是坐标。

step2:分类:在这里我们根据每个样本点到K个聚类中心的欧式距离来测算相似度。我们将每个样本点划分到与它距离最短的聚类中。用c^{(i)}来记录每个样本点所属的聚类。比如:x^{(1)};x^{(3)};x^{(5)}都距离聚类2最近,那么c^{(1)}=2;c^{(3)}=2;c^{(5)}=2;

step3:计算各个聚类中心的新位置:使用每个聚类中样本坐标的平均值。比如:聚类2中有x^{(1)};x^{(3)};x^{(5)}三个样本,那么u_{2}=\frac{x^{(1)}+x^{(3)}+x^{(5)}}{3}为聚类2的新坐标。

step4:不断重复2,3直到聚类不再变化。

notes:假如没有点聚类到某一个聚类中,那么直接将这个聚类删除。

2.使用优化目标函数的K-means

step1:首先进行不加入优化目标函数的k-means第2,3步,计算出c^{(i)},其中u_{c^{(i)}}已经进行过聚类的x^{(i)}所属聚类的中心坐标。

step2:固定u_{1} ;u_{2};....u_{k}不变,最小化J,也就是对所用点重新进行聚类操作。计算c^{(i)}.

step3:最小化J,计算u_{1} ;u_{2};....u_{k}。(???不太清楚 利用2更新的聚类划分)

note:wrt:with respect to 着眼于

3.编程作业

function idx = findClosestCentroids(X, centroids)
%FINDCLOSESTCENTROIDS computes the centroid memberships for every example
%   idx = FINDCLOSESTCENTROIDS (X, centroids) returns the closest centroids
%   in idx for a dataset X where each row is a single example. idx = m x 1 
%   vector of centroid assignments (i.e. each entry in range [1..K])
%

% Set K
K = size(centroids, 1);
nums=size(centroids,1);
% You need to return the following variables correctly.
idx = zeros(size(X,1), 1);

% ====================== YOUR CODE HERE ======================
% Instructions: Go over every example, find its closest centroid, and store
%               the index inside idx at the appropriate location.
%               Concretely, idx(i) should contain the index of the centroid
%               closest to example i. Hence, it should be a value in the 
%               range 1..K
%
% Note: You can use a for-loop over the examples to compute this.
%

for i=1:size(X,1),
    temp=1000000;
	tempidx=0;
    for j=1:size(centroids,1),
	      nums(j)=sum((X(i,:)-centroids(j,:)).^2);
		  if nums(j)<=temp,
		      temp=nums(j);
			  tempidx=j;
	end
	idx(i)=tempidx;
end     

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

end





function centroids = computeCentroids(X, idx, K)
%COMPUTECENTROIDS returns the new centroids by computing the means of the 
%data points assigned to each centroid.
%   centroids = COMPUTECENTROIDS(X, idx, K) returns the new centroids by 
%   computing the means of the data points assigned to each centroid. It is
%   given a dataset X where each row is a single data point, a vector
%   idx of centroid assignments (i.e. each entry in range [1..K]) for each
%   example, and K, the number of centroids. You should return a matrix
%   centroids, where each row of centroids is the mean of the data points
%   assigned to it.
%

% Useful variables
[m n] = size(X);

% You need to return the following variables correctly.
centroids = zeros(K, n);
centroids_temp = zeros(K, n);

% ====================== YOUR CODE HERE ======================
% Instructions: Go over every centroid and compute mean of all points that
%               belong to it. Concretely, the row vector centroids(i, :)
%               should contain the mean of the data points assigned to
%               centroid i.
%
% Note: You can use a for-loop over the centroids to compute this.
%
for i=1:size(centroids,1),
   temp=0;
   for j=1:size(idx,1),
       if idx(j)==i,
	      centroids_temp(i,:)=centroids_temp(i,:)+X(j,:);
		  temp=temp+1;
	end
	centroids(i,:)=centroids_temp(i,:)/temp;
end

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


end



猜你喜欢

转载自blog.csdn.net/BRAVE_NO1/article/details/82930002
今日推荐