Partitioning data into subsets of objects according to their mutual "similarity," without using preexisting knowledge such as class labels. Clustered-standard-errors and/or cluster-samples should be tagged as such; do not use the "clustering" tag for them.

learn more… | top users | synonyms (1)

0
votes
0answers
28 views

mean square distortion of quantization data set

I am using the matlab function lloyds to cluster a 1-dimensional timeseries. [partition,codebook,distor] = lloyds(training_set,initcodebook); and I get that the ...
0
votes
0answers
12 views

Representing clustered sequences in PCoA

I'd like to represent a set of clustered dna sequences (at a 0.0049 threshold) under a PCoA. But I have to calculate a distance matrix once the clustering done. How could I do that since the result ...
-1
votes
0answers
13 views

Clustering timestamped data

hi I have data timestamped based on entry and exit of several people in the same house the problem is not to classify these people but to actually make a clustering on the variables input / output to ...
1
vote
0answers
14 views

Unsupervised clustering with Pearson correlation as measure of similarity

I have data from the cell lineage as samples: Cell1 -> Cell2 -> Cell3 Then for each of the above samples I obtained the expression for 'coding' and ...
0
votes
1answer
31 views

Analysing the spread of data of a variable

In my data set there are repeated measures where each subject is measured at three time points.I want to see how the data of a single variable is spread.That is to find groups so that I can categorize ...
4
votes
3answers
270 views

Text Mining: how to cluster texts (e.g. news articles) with artificial intelligence?

I have built some neural networks (MLP (fully-connected), Elman (recurrent)) for different tasks, like playing Pong, classifying handwritten digits and stuff...additionally I tried to build some first ...
1
vote
2answers
33 views

Cluster analysis missing data

I have a question about cluster analysis. Normally when there is less than 10% missing data and its missing at random, then it can be ignored. But how should I handle the missing data for a cluster ...
-1
votes
1answer
17 views

How to statistically categorize a list of reasons?

I am working with call center data, one of the variables available is "Reason" which is a description of the reason the customer called. There is 40 different reasons that the agent can choose from. ...
1
vote
0answers
7 views

Affinity Propagation with missing data

I'm using Affinity Propagation to cluster some data, and I have to deal with missing values, so for points that I have the data, I can use it to change similarity between them, but for those that I ...
0
votes
1answer
21 views

Clustering matrices with “2d interpretation”

I am not sure if I can formulate this such that it is clear. :) I have around 700 80x80 matrices, where each matrix shows some weather event (a matrix has continuous entries from 0 to 60). Now I ...
0
votes
0answers
17 views

Streaming K-medoids

Mahout, Hadoop machine learning library, contains an implementation of Streaming K-means algorithm that is based on the following paperworks The Effectiveness of Lloyd-Type Methods for the k-Means ...
0
votes
0answers
8 views

What is the best practice to deal with NA values when calculating a dissimilarity matrix?

I need to calculate a matrix of distances between sites where different variables were measured. I will use it in a cluster analysis. The following is a sample of the matrix I am dealing with: ...
0
votes
0answers
37 views

Using SVD or PCA for reducing dimensionality [duplicate]

I have always heard that I can reduce dimensionality of a matrix using SVD. So, I'd like to ask something hypothetically. Suppose that the following matrix A has a high dimensionality and I want to ...
0
votes
0answers
8 views

Can / should I use country fixed effects AND cluster at country level at the same time?

I have a survey data set from more than 200k subjects, from 37 countries. Trying to estimate the relationship between various socio-economic factors in the probability of certain experiences. The ...
2
votes
2answers
57 views

Performing k-means clustering on a set of lines

I have a set of lines (y = numbers between 1 and 100, x= discrete) that I am trying to cluster to group similarly-shaped profiles. I have found that the profiles seem to cluster the cleanest when ...
0
votes
0answers
7 views

locality sensitive hashing for infinite feature space

I'm trying to wrap my head around locality-senstive hashing in the case when you can not enumerate all possible features (e.g. Facebook likes when comparing users). Are there solutions adressing this ...
0
votes
0answers
26 views

fuzzy clustering and multi-label classification

I’m working on a clustering problem that I would like to extend to multi-label classification. Basically, I want to generate a number (x) of clusters using something like fuzzy c-means and using the ...
1
vote
0answers
7 views

watershedding vs mean shift clustering

I'm working on a clustering problem, and I was trying to understand the difference between the watershed algorithm and mean shift clustering. It seems that these algorithms are popular for image ...
2
votes
0answers
18 views

Clustering stream of new customers based on future potential

I need to cluster new customer according to their future potential, but I have only information about their first transaction. I have access to all transactions for the other customers. So I can do ...
2
votes
1answer
54 views

Clustering by fitting many linear SVMs and clustering their weight vectors?

Let’s say I have a bunch of discrete sequence data, with each sequence belonging to some individual (there are ~1000 individuals and many more sequences). With a great deal of success, one can train a ...
0
votes
2answers
29 views

Clustering methods based off set membership

So most of the clustering algorithms I've looked at are based on the distance between points. I was wondering if anyone knows any simple clustering algorithms based off points making up a set. ...
0
votes
1answer
82 views

How is survey respondent segmentation based on market opportunity score done in practice?

As per instructions, I have administered a survey to a sample population that for several different "jobs-to-be-done" asks the survey participants to rate the importance of the "job-tobe-done" and the ...
0
votes
0answers
21 views

Clustering where intra-row sign matters but inter-row sign doesn't

I'm not sure how best to express this question except through an example. I have some data, let's say it represents the inputs from 2 partners on a task. From that, we can create a set of difference ...
0
votes
0answers
14 views

A Binary Classification to Distinguish two Different Models?

I have two functions, a step function $f(x)$ and an inverse exponential function $g(x)$. Together, they explain virtually all the data when combined as a piecewise function. Some of the data points ...
2
votes
1answer
44 views

Variational Inference: good inference but ELBO decreases instead of increasing

I am playing with Variational Inference for clustering within a mixture of Gaussians. My first implementation seems to work fine (this is for the geyser dataset): ...
0
votes
0answers
29 views

How to compare clustering algorithms of numerical and nominal data

I have a dataset for clustering including numerical and nominal variables. I would like to compare the k-means and k-medoids clustering algorithms and I would also like to find the optimal k-value ...
2
votes
1answer
24 views

How to specify K cluster in Hierarchical clustering with noisy data?

I'm new in Mining and Clustering and I wonder how to cut off the hierarchical clustering Dendrogram to obtain a specific number of clusters. The problem is here that the data is noisy and the ...
2
votes
0answers
26 views

Observations get in a line in a PCA score plot. Something wrong with the data?

I ran a clustering and in the resultant PCA score plot some observations getting in a line drew my attention (I marked them with a red line) . How come they distribute like that? I doubt there is ...
1
vote
0answers
20 views

Different Methods for clustering skills in text

Consider a talent pool in which each member has some set of skills. Some of these talent are submitted to orders as potential candidates of which one is selected. It is reasonable to assume that the ...
0
votes
0answers
38 views

Feature extraction based on correlations

I have a small problem regarding feature extraction with correlation. I have divided my question in four parts hoping that somebody can help me. I have a dataset consisting of fMRI images. Each image ...
0
votes
1answer
31 views

Correlation / clustering over lognormal data

I'm working with some financial data and it turns out my data is pretty much lognormal distributed. The question I have is, which produces "better" results: using plain data to find correlation / ...
1
vote
1answer
23 views

Is there a version of Latent Class Analysis with unspecified # of clusters

I understand that you can use the elbow method to plot LCA solutions vs log likelihood to figure out, at which k, it is no longer worth it to add more clusters. And I will resort to this if need be. ...
2
votes
1answer
73 views

Unknown writing system: different letters or variants of the same letter?

In a fictitious language, there are 4 graphic variants of what is commonly believed to be the same letter "a": a1, a2, a3, a4. In a corpus of texts, any word containing "a" (Xa, Ya, Za, etc.) can be ...
0
votes
0answers
8 views

Disadvantages of cluster randomised controlled trials

Can anyone explain some of the disadvantages of a cluster randomized controlled trial? I read something about data being more correlation between partiticipnts in each condition/group but I don't ...
-2
votes
1answer
29 views

How to do text clustering for a set of around 10000 messages?

I have around 10000 messages in a variable, i want to form clusters of them based on similarity, so that I can assign some class say 1-10, if 10 clusters are formed and run analysis on them. How can ...
0
votes
0answers
27 views

Trying to understand xmeans (using R, RWeka)

In a project I want to use XMeans to estimate the 'optimal' number of clusters that are distinguishable in different datasets. The numbers I got seemed too low, so I experimented a bit with generated ...
0
votes
0answers
38 views

R: How to choose the height parameter in cutree, or: how to find the optimal number of clusters in UPGMA clustering?

I am using hclust() to carry out a UPGMA clustering (method="average") in R. Then, I'm using ...
4
votes
1answer
103 views

Incorporate new unlabeled data into classifier trained on a small set of labeled data

I have a set of 400 labeled samples (8 numeric features) on which I trained a binary classifier. The problem I am facing is that once the classifier is shipped to the users, I will get additional ...
0
votes
0answers
36 views

Which unsupervised learning method should I use on classification on many point cloud datasets?

I have a few abstract and high dimensional point clouds in the form of distance matrices. I want to do unsupervised learning on this dataset. The problem is, I am not using one distance matrix, but ...
5
votes
2answers
354 views

Do I need to remove duplicates for cluster analysis?

I am doing a cluster analyis and I was wondering whether it is possible to remove duplicates from the data set - in order to increase performance. I work on tables where objects are in rows and ...
0
votes
0answers
23 views

Integrated Classification Likelihood computation for R package HDclassif

I'm in the process of fitting some mixture models to some data I have. As this data is high-dimensional, I used the subspace clustering package HDclassif. As the package has no option for the Akaike ...
3
votes
3answers
70 views

Any easy way to cluster GPS trajectories?

Can anyone recommend an easy way to cluster hundreds of GPS trajectories to find out their common paths? The GPS data is coming from different vehicles that have traveled thousands of miles.
1
vote
2answers
71 views

Simple way for histograms Clustering

I'm trying to cluster set of histograms. The histograms represent the frequencies of the distribution for a numbers from 1 to 5. The following figure shows two samples of my data. I have 10,000 ...
0
votes
0answers
49 views

Rescaling Features for ML

I have data that is collected every month and I want to perform K-means clustering on each month (both on historical data and on future data). However, it isn't clear to me how best to rescale my data ...
1
vote
0answers
22 views

Standard deviation comparison for splitting clusters in ISODATA

I am currently implementing the ISODATA algorithm and I am new to cluster analysis as I just learnt about it. I got stuck at the step which I need to compute the standard deviation of each cluster, ...
0
votes
0answers
34 views

How to evaluate and compare two clustering algorithms in R for text mining

I am doing research in R language for text mining. I would like to know how to evaluate and compare two clustering algorithms in R for text mining?
0
votes
1answer
39 views

Hierarchical clustering with categorical variables - what distance/similarity to use in R? [duplicate]

I have only categorical variables in my database. What distance/similarity to use? I´m using the function simil() (library(proxy) in R.
1
vote
1answer
72 views

The most popular hierarchical clustering algorithm (divisive scheme)

My question: what is a "standard divisive hierarchical clustering algorithm". I have a well-defined similarity matrix, and have already carried out a clustering (with spectral + genetic clustering ...
0
votes
2answers
41 views

Clustering based on distance matrices

Given a pre-computed distance matrix, obtained from arbitrary samples, such as graphs, I am currently looking for efficient clustering algorithms to deal with distance matrices, so that the algorithm ...
1
vote
1answer
43 views

Observations from two distribution functions mixed, how to separate them?

Assume I have 100 observations, I know they are from two distribution functions, they are mixed together. Is this possible to find out which distribution they are coming from? Here is an example in ...