MATLAB使用pdist处理时间序列Clustering

Question

我在使用 MATLAB 进行时间序列数据聚类方面遇到问题

我正在尝试使用下面的 DTW 库作为我的距离测量方法 http://www.mathworks.com/matlabcentral/fileexchange/16350-continuous-dynamic-time-warping

TimeData = csvread('testData10.csv',1,0)
Y = pdist(TimeData,@dtw_dist)
Z = linkage(Y,'complete')
dendrogram(Z)

我做了一个函数来适应'pdist'距离函数

的格式

function d2 = dtw_dist(XI,XJ)
    [dist,D,k,w,rw,tw] = dtw2(XI,XJ,0)
    d2 = dist
end

但我收到错误消息

Error using pdist (line 373)
Error evaluating distance function 'dtw_dist'.

Caused by:
    Error using  - 
    Matrix dimensions must agree.

如果有人帮助我，我会很开心

谢谢！

---2015.1.5更新---

我改变了我的功能来调用 dtw 以适应格式并且有效

function d2 = dtw_dist(XI,XJ)
    result =[];
    [m1,n1] = size(XI);
    [m2,n2] = size(XJ);
    for j=1:m2
        result = horzcat(result,dtw(XI,XJ(j,:)));
    end
    d2=result;    
end

Answer 1

如果不知道 dtw2 是什么，就很难分辨。但这里有一个可能的原因：当您使用自定义距离函数调用 pdist2 时，它应该满足以下条件：

A distance function must be of the form
     function D2 = DISTFUN(ZI,ZJ)
taking as arguments a 1-by-N vector ZI containing a single observation from X or Y, an M2-by-N matrix ZJ containing multiple observations from X or Y, and returning an M2-by-1 vector of distances D2, whose Jth element is the distance between the observations ZI and ZJ(J,:).

检查 dtw2 是否满足，如果不满足，相应地修改它（或使用循环而不是 pdist2）。

MATLAB使用pdist处理时间序列Clustering

MATLAB using pdist to deal with Time series Clustering

matlab

cluster-analysis

time-series