This question already has answers here:
Cluster analysis in R: determine the optimal number of clusters
(8 answers)
Closed 3 years ago.
I am going to build a K-means clustering model for outlier detection. For that, I need to identify the best number of clusters needs to be selected.
For now, I have tried to do this using Elbow Method. I plotted the sum of squared error vs. the number of clusters(k) but, I got a graph like below which makes confusion to identify the elbow point.
I need to know, why do I get a graph like this and how do I identify the optimal number of clusters.
K-means is not suitable for outlier detection. This keeps popping up here all the time.
K-means is conceptualized for "pure" data, with no false points. All measurements are supposed to come from the data, and only vary by some Gaussian measurement error. Occasionally this may yield some more extreme values, but even these are real measurements, from the real clusters, and should be explained not removed.
K-means itself is known to not work well on noisy data where data points do not belong to the clusters
It tends to split large real clusters in two, and then points right in the middle of the real cluster will have a large distance to the k-means centers
It tends to put outliers into their own clusters (because that reduces SSQ), and then the actual outliers will have a small distance, even 0.
Rather use an actual outlier detection algorithm such as Local Outlier Factor, kNN, LOOP etc. instead that were conceptualized with noisy data in mind.
Remember that the Elbow Method doesn't just 'give' the best value of k, since the best value of k is up to interpretation.
The theory behind the Elbow Method is that we in tandem both want to minimize some error function (i.e. sum of squared errors) while also picking a low value of k.
The Elbow Method thus suggests that a good value of k would lie in a point on the plot that resembles an elbow. That is the error is small, but doesn't decrease drastically when k increases locally.
In your plot you could argue that both k=3 and k=6 resembles elbows. By picking k=3 you'd have picked a small k, and we see that k=4, and k=5 doesn't do much better in minimizing the error. Same goes with k=6.
Related
I did clustering on spatial datasets using DBSCAN algorithm and generating a lot of noise 193000 of 250000 data. is that a reasonable amount?
Depends on your data and problem.
If I generate random coordinates, 100% noise would be appropriate because the data is random noise.
First, to address the question in your title. By making eps
very large, it is easy to get no noise points and all the points are
in one big cluster. By making eps very small, you can easily
make all points be noise points. In general, somewhere in between
is what you are looking for. Your job is to find a value that produces
a meaningful clustering. That is where the remark of
#Anony-Mousse comes into play.
Depends on your data and problem
As he suggested, if you have uniform random data, maybe all
noise is the best answer. If you have Gaussian random data,
maybe one big cluster with a few outliers is good. But this is
supposed to help you understand the structure of your data.
What happens as you change eps? From your current clustering
with many noise points, what happens as you gradually increase eps?
Does it gradually add a few noise points into the existing clusters?
Is there some place where two clusters get merged into one? Is there
someplace that there is a sudden change in the number of clusters?
Also, can you interpret the clusters in terms of your variables?
Perhaps the difference between two clusters is that in one all the
values of some variable are low and in another cluster they are high. Considering whatever problem you are trying to solve,
do the clusters divide the data into meaningful groups? Try to use
the clusterings to find meaning in your data.
I am implementing k means clustering in tensorflow and have successfully made the function where we randomly select centroids from the sample points. Then these centroids are to be updated based on distance from sample points.
Is it always guaranteed that the more i iterate the better I get the cluster prediction or there is some point after which the predictions start getting wrong/anomalous??
Usually, K-means solving algorithm behaves as expected, in that it converges to a local minimum always. (I assume you're talking about the Lloyd/Florgy method) This is a statistical method used to find a local minima. It may stall at a saddle point where one of the dimensions is optimized but the others is not.
To abbreviate the rigorousness of the proof, it will always converge, albeit slowly due to many saddle points in your function.
There is no point in which your prediction gets more "wrong". It will be closer to the minima that you wanted, but the minima may not be the global. This may be your source of concern, because random initializations of K-means does not guarrantee this to happen.
One way to alleviate this is to actually run K-means on subgroups of your data, and then take those final points and average them to find a good initializer for your final clustering on the whole dataset.
Hope this helps.
I have a large dataset of around 20 million points (x,y,z) in a 3-dimensional space. I know these points are organized in dense regions, but that these regions vary in size. I think a standard unsupervised 3D clustering should solve my problem.
Since I can't estimate the number of clusters a priori, I tried using k-means with a wide range for k, but it is slow and also, I would have to estimate how significant each k-partition is.
Basically, my question is: how can I extract the most significant partition of my points into clusters?
k-means is probably not the best alhorithm for such data.
DBSCAN should be closer to your intuition of dense regions.
Try on a sample first, then figure out how to scale up.
It is not clear to me from the above if you're going to use k-means or not, but if you are, you should be following the responses from the post below which shows how to measure variance of the clusters.
Calculating the percentage of variance measure for k-means?
Additionally, you can get a good fit using 'the elbow method' by trying 2 to 15 k sized clusters. See the answer from Amro for the process on this.
One simple idea in this case is to use 3 different clusterings, along each dimension. That might speed things up.
So you find clusters along X axis (project all the points down to X axis) and then continue to form sub clusters along the Y axis and then along the Z axis.
I think 1-D k-means can be solved very efficiently using dynamic programming http://www.sciencedirect.com/science/article/pii/0025556473900072.
Let me explain what I'm trying to do.
I have plot of an Image's points/pixels in the RGB space.
What I am trying to do is find elongated clusters in this space. I'm fairly new to clustering techniques and maybe I'm not doing things correctly, I'm trying to cluster using MATLAB's inbuilt k-means clustering but it appears as if that is not the best approach in this case.
What I need to do is find "color clusters".
This is what I get after applying K-means on an image.
This is how it should look like:
for an image like this:
Can someone tell me where I'm going wrong, and what I can to do improve my results?
Note: Sorry for the low-res images, these are the best I have.
Are you trying to replicate the results of this paper? I would say just do what they did.
However, I will add since there are some issues with the current answers.
1) Yes, your clusters are not spherical- which is an assumption k-means makes. DBSCAN and MeanShift are two more common methods for handling such data, as they can handle non spherical data. However, your data appears to have one large central clump that spreads outwards in a few finite directions.
For DBSCAN, this means it will put everything into one cluster, or everything is its own cluster. As DBSCAN has the assumption of uniform density and requires that clusters be separated by some margin.
MeanShift will likely have difficulty because everything seems to be coming from one central lump - so that will be the area of highest density that the points will shift toward, and converge to one large cluster.
My advice would be to change color spaces. RGB has issues, and it the assumptions most algorithms make will probably not hold up well under it. What clustering algorithm you should be using will then likely change in the different feature space, but hopefully it will make the problem easier to handle.
k-means basically assumes clusters are approximately spherical. In your case they are definitely NOT. Try fit a Gaussian to each cluster with non-spherical covariance matrix.
Basically, you will be following the same expectation-maximization (EM) steps as in k-means with the only exception that you will be modeling and fitting the covariance matrix as well.
Here's an outline for the algorithm
init: assign each point at random to one of k clusters.
For each cluster estimate mean and covariance
For each point estimate its likelihood to belong to each cluster
note that this likelihood is based not only on the distance to the center (mean) but also on the shape of the cluster as it is encoded by the covariance matrix
repeat stages 2 and 3 until convergence or until exceeded pre-defined number of iterations
Take a look at density-based clustering algorithms, such as DBSCAN and MeanShift. If you are doing this for segmentation, you might want to add pixel coordinates to your vectors.
I running kmeans in matlab on a 400x1000 matrix and for some reason whenever I run the algorithm I get different results. Below is a code example:
[idx, ~, ~, ~] = kmeans(factor_matrix, 10, 'dist','sqeuclidean','replicates',20);
For some reason, each time I run this code I get different results? any ideas?
I am using it to identify multicollinearity issues.
Thanks for the help!
The k-means implementation in MATLAB has a randomized component: the selection of initial centers. This causes different outcomes. Practically however, MATLAB runs k-means a number of times and returns you the clustering with the lowest distortion. If you're seeing wildly different clusterings each time, it may mean that your data is not amenable to the kind of clusters (spherical) that k-means looks for, and is an indication toward trying other clustering algorithms (e.g. spectral ones).
You can get deterministic behavior by passing it an initial set of centers as one of the function arguments (the start parameter). This will give you the same output clustering each time. There are several heuristics to choose the initial set of centers (e.g. K-means++).
As you can read on the wiki, k-means algorithms are generally heuristic and partially probabilistic, the one in Matlab being no exception.
This means that there is a certain random part to the algorithm (in Matlab's case, repeatedly using random starting points to find the global solution). This makes kmeans output clusters that are of good-quality-on-average. But: given the pseudo-random nature of the algorithm, you will get slightly different clusters each time -- this is normal behavior.
This is called initialization problem, as kmeans starts with random iniinital points to cluster your data. matlab selects k random points and calculates the distance of points in your data to these locations and finds new centroids to further minimize the distance. so you might get different results for centroid locations, but the answer is similar.