Questions tagged [cluster-analysis]
Questions on the cluster analysis functions of Mathematica, including the Hierarchical Clustering Package.
143
questions
1
vote
1answer
44 views
Nearest returning s different length of output with same input data [closed]
I am trying to classify a list of 2D data points into different clusters based on the Euclidean distance between the points and the clusters' centroids, i.e. the point will be classify into the ...
0
votes
0answers
20 views
What's the default setting of “NeighborhoodRadius” in “MeanShift” method of FindClusters"?
I'm using the FindClusters option Method -> "MeanShift". It works without an input of the sub-option "NeighborhoodRadius". In ...
1
vote
1answer
39 views
Building a nine - region cluster chart but, getting inaccurate plot-legend when empty subregions are present
This is a follow up question to the one submitted at the following:
Stack exchange Link
I quickly get to the subject:
...
3
votes
2answers
152 views
Building a nine - region cluster chart with Tooltip to display labels associated with 2D points
I'm attempting to build a nine-region cluster chart using Tooltip to display labels associated with 2-D points also displayed on it. I do NOT want to use "FindClusters". I want to design my own ...
2
votes
0answers
74 views
FindClusters giving complete wrong groups from very simple array
Bug introduced in 8.0.4 or earlier and later fixed in 11.3 or earlier.
I've been trying to use FindClusters function in Mathematica and it wasn't working well when ...
0
votes
0answers
39 views
Image and Data Clustering
I have a series of 2D array data measured at different time and would like to trace the development cluster-by-cluster.
For example, the data at the time T can be plotted as follows:
I would like to ...
1
vote
0answers
59 views
How can I parametrically generate a hierarchically clustered network? [closed]
I'm trying to create an image to illustrate what a large, hierarchically clustered network looks like. The details of the network don't matter, as long as, when plotted, it clearly shows at least a ...
1
vote
0answers
36 views
How to ensure that FindClusters and ClusterClassify have the same cluster name?
I am trying to ensure that both the FindCluster and ClusterClassify function provide the same cluster name.
To explain this ...
1
vote
1answer
46 views
Clustering with different variables
I've created a list of associations composed of userId's and average times for different sessions:
...
2
votes
1answer
77 views
Gap Statistic Significance Testing with KMeans / KMedoids
Relatively basic question here about FindClusters / ClusteringComponents. So I have noticed that Mathematica has an option for ...
0
votes
3answers
125 views
TF-IDF matrix question [closed]
I am looking to weight the words (TF-IDF) of a random text by his occurence and showing that on a matrix.
I saw there is a project on it but would like to know if it possible to change the ...
1
vote
0answers
67 views
Cluster analysis with constraints on number of clusters and their abundance
How to perform cluster analysis in a set:
With the number of clusters bounded but not specified, e.g. $k\in[3,5]$
With a bounded abundance of clusters (the number of elements in each of the clusters),...
0
votes
0answers
65 views
6
votes
1answer
95 views
Determining the Method option that FindClusters uses with AbsoluteOptions
I am trying to determine which method mathematica chooses when using FindClusters. The documentation says that it chooses the best one for the data. I have tried to use ...
1
vote
0answers
83 views
K-medians clustering computation
Is there a built-in function for data clustering using k-medians algorithm? I found out about the ClusterDissimilarityFunction of the ...
0
votes
1answer
128 views
map cellular automaton to planar surface
Im exploring possibility to apply a CA to a portion of a region in an image.
Think that I can process an image to identify a region, as an example, a green area.
I would like to confine that area, ...
1
vote
0answers
112 views
Programming a DBSCAN in Mathematica
FindClusters has a built-in Method called "DBSCAN". You can find it on this page:
https://...
2
votes
1answer
152 views
Adjacency Matrix to Clusters of Equal Sizes
I have a system with 72 nodes.
I have a binary adjacency matrix $S$ of size $72\times 72$. If $S_{i,j}=1$, then node $i$ is adjacent to node $j$. So, we also have $S_{i,j}=S{j,i}$. So, $S$ is a ...
0
votes
1answer
114 views
How to find clusters with same cluster sizes?
I have a set of 71 data points. Each data point is represented by its latitude and longitude. I want to divide them into 12 clusters. The first 11 cluster will have exactly 6 points each and 12th ...
2
votes
2answers
149 views
How to form multiple clusters of given size from a set of points?
Let us consider a 2 dimensional space. There are 100 points in it. So, each point has its $x$ and $y$ coordinates. I want to form 10 clusters. Each cluster has 10 points.
How can I form such ...
1
vote
1answer
90 views
Using Density Histogram on FindCluster
I have some data which I want to put in a DensityHistogram after i have clustered
it. The different clusters should have different colors and based on how many are ...
6
votes
1answer
138 views
How do we cluster separate curves in a set of data?
Below, I have included some data. (It is long, but I don't like to host data elsewhere and provide links that might some day be broken.)
Plotting this set of data,...
5
votes
1answer
87 views
ClusteringComponent and FindClusters are returning the wrong number of clusters and are inconsistent
I am trying to find the optimum number of clusters in a correlation matrix.
To do this I run a clustering algorithm that loops through 3 variables ( number of clusters, ...
0
votes
0answers
39 views
clustering data on a spectrum with a custom distance function
I have recently been faced with a problem on spectral analysis which may find a solution with data clustering techniques. I have an energy spectrum with around 200 energy levels: many of them ...
1
vote
0answers
37 views
How to ask FindClusters to return the loss function value in the output?
I have some data points pts as below:-
pts = BlockRandom[SeedRandom[123]; RandomReal[1, {100, 2}]];
Now I want to separate ...
4
votes
0answers
77 views
What is the default method of FindClusters?
I used Method -> Automatic on FindClusters and obtain a cluster autoCts as below:-
...
5
votes
0answers
60 views
How to make the clustering result of version 11.2 and 11.3 same?
I was doing clustering analysis in version 11.2, with codes like below, and then got 12 clusters as the output:
...
1
vote
2answers
71 views
Number of contiguous ones of an element in a 2d binary array
I have a 2d binary array of 0s and 1s. I select an element and would like to know how many 1s are in the contiguous cluster that includes the selected point. If the selected element is 0, the answer ...
7
votes
2answers
248 views
How to Wrap the Points of a 3D Clustering Plot?
I am doing clustering and have a plot as below:-
...
6
votes
1answer
119 views
Why does FindClusters put closer points into different clusters?
Bug introduced in 11.3 or earlier and persisting through 12.0
Bug isn't present in version 8.0.4
I am trying to do clustering and then obtained a plot as below:-
...
1
vote
0answers
63 views
6
votes
3answers
149 views
How to know the layout about these points
I have such points
pts=Uncompress[FromCharacterCode[
Flatten[ImageData[Import["http://i.stack.imgur.com/hkAK8.png"],"Byte"]]]];
...
1
vote
2answers
102 views
How to cluster the elements of a list based on connectivity?
Consider a list (coordpairs) of coordinate pairs as
...
3
votes
1answer
99 views
Finding the size of connected clusters with specific patterns in an array
I have a $w \times h$ array with either $-1$ or $+1$.
I wish to monitor the size of the largest connected clusters with specific patterns that occur during a Monte Carlo simulation, i.e.,
a ...
1
vote
0answers
54 views
How does DominantColors work?
I'm trying to understand the algorithms behind DominantColors[]. Unfortunately Trace[] and ...
4
votes
1answer
76 views
How to specify radius for “MeanShift” Method of FindClusters
I would like to specify the radius used for the "MeanShift" Method of FindClusters. Where ...
0
votes
1answer
128 views
How to segment an image based on MeanEuclideanDistance?
Consider an image (img) as
Now I have partitioned the image using the following command
parts = ImagePartition[img, 32];
...
6
votes
0answers
59 views
What method does FindGraphCommunities use with Method -> “Centrality”?
Cross-posted to W Community
I would like to know what method FindGraphCommunities uses with the option Method -> "Centrality"...
3
votes
0answers
58 views
“Optimize” find clustering by local optimization
There is a method of clustering in Mathematica named "Optimize" which find clustering by local optimization. Here is the ref http://reference.wolfram.com/language/tutorial/PartitioningDataIntoClusters....
2
votes
0answers
81 views
ClusterClassify and FeatureTypes
I have a dataset that I want to classify in clusters. All values are numbers.
For some variables, the values can represent a real measure (a distance, a weight...) but for some other variables, the ...
0
votes
1answer
147 views
How to visualize several groups of points?
I have generated a dataset that clustered some of data points into three groups, the output was three -column data like this:
there are some points with X,Y coordinates and I already labeled each of ...
2
votes
0answers
136 views
1
vote
0answers
141 views
How can I rotate labels in a Dendrogram when using pre-clustered data?
I have some pre-clustered data that I want to visualize with Dendrogram. I am using Dendrogram purely for visualization in this ...
7
votes
2answers
143 views
Impact of Linkage and DistanceFunction on Agglomerate clustering
I'm using Agglomerate function to find clusters of my experimental points. I have about 20 points with 10 parameters each. It seems it works fine, but there are plenty of Linkage and DistanceFunction ...
7
votes
0answers
124 views
FindCluster only finds cluster “with a little help”
Currently I made some slides to illustrate clustering. As an example I made a point set of two clusters:
...
1
vote
0answers
72 views
How can I improve effect of Clustering of MNIST?
Limit us with Clustering technology, like FindClusters, ClusteringComponents,ClusterClassify,...
5
votes
2answers
120 views
How to detect the frequency of gene pairings in lists of genetic profiles
We have a list of >1000 gene profiles each consisting typically of 4 genes. Many profiles share pairs of identical genes. Can we derive clusters of profiles which share pairs or even trios of genes? ...
14
votes
4answers
646 views
How to split data into clusters based on fitting to function
I have data which looks somewhat like this:
On the picture, you can see that the data can be described by 2 linear functions - if you manage to split it into 2 groups, each can easily be fitted with <...
0
votes
0answers
63 views
FindCluster gives same grouping each time in Mathematica 9 and different in 11.1
This is my dataset:
...
3
votes
2answers
780 views
Plot density of discrete data
I have some discrete data in the form {{x1,y1},{x2,y2},...} and when I produce a ListLogLogPlot they look like this:
I would ...
