Questions on the cluster analysis functions of Mathematica, including the Hierarchical Clustering Package.

learn more… | top users | synonyms (1)

6
votes
3answers
206 views

How to speed up computation of medoids?

I need to compute medoids (based on SquaredEuclideanDistance for large lists of k-vectors (k = 14). My implementations so far are impractically slow. Here is a ...
2
votes
1answer
26 views

What is the default `SignificanceTest` setting for `FindClusters` with `Optimize` method?

According to the documentation, the default value of FindCluster's Method option is ...
0
votes
0answers
44 views

Can parallelization speed up FindClusters?

I have a clustering task that would take FindClusters 2-3 months1 to complete. Can this calculation be sped up with parallelization? (FWIW, the data to be ...
3
votes
1answer
93 views

How to automatically label the cluster distances in a DendrogramPlot?

I have a distance matrix data, and want to visualize it as below: The current codes I am using is: ...
5
votes
0answers
53 views

How many clusters does DominantColors return?

Is there any documentation on how it automatically chooses the number of colors - does it use X-means or some other heuristic to determine the number of clusters it automatically returns?
0
votes
0answers
43 views

Number of clusters varies rapidly

I'm having some trouble with FindClusters. I've got a list of 7,598 vectors, each with 10 real numbers generally between 0 and 1. The number of clusters for the ...
3
votes
0answers
47 views

Clustering with restrictions

I have this dataset of a ranking of roughly 32.5k players in increasing order. The third column contains the number of players which have the corresponding score, whilst the second is the number ...
7
votes
1answer
187 views

Clustered heatmaps with dendrograms

In biology it's common to cluster both dimensions of a matrix, display it as a heatmap (MatrixPlot, ArrayPlot) and show ...
2
votes
0answers
74 views

How can I access the Criterion function of KI method in `FindThreshold` for a dataset?

I want to find a threshold for some data set, using Kittler-Illingworth minimum error thresholding method (KI method). To do so, I use the Mathematica built-in function ...
0
votes
0answers
28 views

Cluto functionality in Mathematica

Hi is there a function or library that is available in Mathematica that will enable Cluto-like cluster analysis
5
votes
1answer
96 views

How to get `FindCurvePath` to return only one list

As you can see below, FindCurvePath returns only a part of the list, resulting in a partial interpolation. I would like to interpolate all the points. Complete ...
12
votes
1answer
166 views

User-defined distance functions in FindClusters

I am trying to use FindClusters to segment data points into two special parts data ...
8
votes
4answers
164 views

Cluster numbers into n partitions so that each partitions sum is closest to total/n

For example having data data = {16, 4, 17, 10, 15, 4, 4, 6, 7, 14, 9, 17, 27, 6, 1, 9, 0, 12, 20, 8, 0, 3, 4, 0, 3, 4} I want to cluster them int 4 partitions ...
1
vote
0answers
46 views

Question on ClusteringComponents [duplicate]

I am fairly new to Mathematica. I've been playing around with ClusteringComponents. Assume we are clustering points in the plane using k-means clustering and ...
0
votes
0answers
70 views

Statistical significance test of FindCluster

I have a list of vectors which could be roughly divided into two clusters. The list is huge so I have to use RandomChoice[list, 20000] to speed up the calculation. ...
-1
votes
1answer
87 views

How can I cluster a continuous percentage? [closed]

I've got a table with 3 columns. 1 is descriptive A 1 is a percentage B 1 is a decimal number C I would like to investigate for the clusters (ie. B is high ad C is low, or viceversa). How can I ...
8
votes
2answers
403 views

Creating Identification/Classification trees

I have data given in following format; from which I need to create identification/classification trees (three different trees from three different criterion, that is average disorder, gain ratio and ...
5
votes
2answers
422 views

Code elegance and compactness. Help needed with Map, Apply

I need some help with code optimization and compactness. I have a set of two-dimensional points and I can use the Mathematica function FindClusters to find 4 clusters. I'd like to plot the points ...
2
votes
0answers
134 views

How to get the SIFT features of an image?

According to the documentation, the function KeyPoints[] computes features only using SURF, but what about SIFT or FAST features?
2
votes
1answer
75 views

Partitioning a list in n sublists with constrains in their sums

Is there a way to put cluster level limits on clusters? For example, if I run: FindClusters[{1, 2, 3, 4, 4, 6, 7, 10}] I get back two lists, ...
2
votes
1answer
316 views

Cluster entities by a combination of values

I can plot the population of zip codes in NY with something like ...
3
votes
1answer
217 views

Clustering image data by intensity and position

I'd like to apply FindClusters or ClusteringComponents to image data of an indistinct edge, with the goal of segmenting the ...
2
votes
0answers
227 views

Max iterations in K-means clustering algorithm

I want to use k-means for clustering. I have used the ClusteringComponents function but I said how can I control the max-iteration for k-means ?
1
vote
1answer
121 views

Cluster a time series by labels

I have a time series, tab delimited dataset with the following format ...
2
votes
0answers
110 views

Matrix clustering in Mathematica?

Suppose I have a square matrix $M$, which you can think of as the weighted adjacency matrix of a graph $G$. I want to order the vertices of $G$ in such a way that the entries of the matrix $M$ are ...
1
vote
1answer
77 views

ClusteringComponents returning only ones

I am trying to use ClusteringComponents without having to specify the number of clusters initially... so the algorithm can find itself the optimal number of clusters... My data is of the form: ...
1
vote
1answer
80 views

Bug in ClusteringComponents yielding different results on practically same input?

I am using the image below. I want to run a simple ClusteringComponents, using the KMeans method and ...
6
votes
2answers
272 views

How to get the centroids of the ClusterComponents function

I use the ClusterComponent function to get the k-means clustering: ...
3
votes
0answers
83 views

k-means clustering in parallel

How can the k-means algorithm for some given distance function be implemented using ParallelMap or other parallel processing program constructs in Mathematica?
2
votes
0answers
72 views

k-means clustering using squared correlation in Mathematica

I am trying to cluster data using the squared correlation coefficient since in the case of my data, -1 correlation is equivalent to 1 correlation (polarities do not matter). How can this be done in ...
5
votes
1answer
165 views

FindClusters giving wrong groupings

I am having trouble getting FindClusters to find the right clustering for this set of data (and many other sets of data similar to it): ...
3
votes
1answer
289 views

Spectral Clustering

I am attempting to implement a spectral clustering routine using Mathematica, but I am encountering difficulties. Using the standard Gaussian similarity function found in section 2.2 of this paper ...
1
vote
1answer
117 views

Using FindGraphCommunities, write community membership for each vertex to CSV

I have a network that I've loaded into Mathematica, and I've used FindGraphCommunitites[network,Method->"Hierarchical"] to identify the communities in the ...
4
votes
1answer
156 views

Agglomerate output to Graph

I'm using the HierarchicalClustering package to cluster some data. So let's say I have this: ...
2
votes
3answers
443 views

Clustering data sets with multiple variables

I am learning how to cluster large datasets and this maybe a newbie question, but I haven’t found a suitable answer in the Documentation or on this board. My question is best illustrated by an ...
2
votes
1answer
255 views

Hierarchical clustering: convert Mathematica cluster hierarchy to NEWICK format

Can anyone tell me a clever way to convert the hierarchical clustering object, created, say, by Agglomerate or DirectAgglomerate ...
1
vote
1answer
87 views

What does the VertexMoving method for FindGraphCommunities do?

I've been applying the VertexMoving method to some graph data, and it's producing very useful results. However, I've got no clue as to what this method actually is, and the documentation is ...
12
votes
0answers
235 views

Strategies to find curves on messy data using FindCurvePath

I have a set of data points that correspond to roots of a transcendental equation with respect to a parameter (the abscissa) which, by the properties of the system, define continuous curves (might be ...
1
vote
1answer
218 views

How to efficiently distinguish the rewired edges in WattsStrogatzGraphDistribution?

The WattsStrogatzGraphDistribution function is a way to construct random graphs based on Watts and Strogatz small world model. The ...
7
votes
3answers
351 views

Morphological Components with periodic boundary conditions

I would like to find the connected(with periodic boundary conditions) components in a large binary matrix. What I've tried, and it does a fair job is: ...
3
votes
1answer
221 views

Clustering of 2D map, based on similarity in spectra

I have experimental 2D-spectroscopy data, in a format similar to this: ...
6
votes
3answers
528 views

Finding connected components in an array

I have an $w\times h$ array with non-negative integers. I wish to partition the set of coordinates $(c,r)$ with $1\leq c \leq w$ and $1\leq r \leq h$, in subsets, so that each subset corresponds to a ...
3
votes
1answer
166 views

Setting label in DendrogramPlot

I want to create a dendrogram with the labels being a visual representation of the data. Something like this: How can I do that in Mathematica? My attempt so far hasn't been very successful. The ...
0
votes
1answer
340 views

Mean path length of randomly generated graphs

I am looking to find the the average path length of 1000 random graphs with the following degree distribution, a few of the vertex degrees are included below ...
5
votes
2answers
359 views

Provided an array of 2D point clouds, can we quickly replace distance- and index-based cliques of points with their median or mean values?

Imagine I have $N \approx 10^5$ clouds of points in an array of the form: UPDATED ...
5
votes
1answer
928 views

Clustering 3D Data Points on a Periodic Cubic Grid

I have a set of 3D data points on a cubic grid. The data can be downloaded from here https://skydrive.live.com/redir?resid=F96524B72DCD75FB!14240 and read into a variable ...
2
votes
1answer
148 views

DirectAgglomerate not working for Large Matrices

I am trying to graphically display a distance matrix with similar elements visually clustered into groups. My original matrix has the elements in a random order so the first thing I do is to change ...
4
votes
3answers
288 views

make specific cluster

I have set of coordinates. I want to make clusters in which every point is within 1.5 distance unit of it's neighbor. ex of point coordinates: ...
23
votes
4answers
1k views

Generating an “average curve” from a dense set of “semicontinuous curves” which clear trends

This question is related to a previous one of mine: Partitioning a superset of coordinates into subsets that generate continuous curves, where the challenge was to partition a data set into two ...