Problem: It appears to me that a fundamental property of a clustering method c() is whether we can combine the results c(A) and c(B) by some function f() of two clusterings in a way that we do not have to apply the full clustering c(A+B) again but instead do f(c(A),c(B)) and still end up with the same result:
c(A+B) == f(c(A),c(B))
I suppose that a necessary condition for some c() to have this property is that it is determistic, that is the order of its internal processing is irrelevant for the result. However, this might not be sufficient.
It would be really nice to have some reference where to look up which cluster methods support this and what a good f() looks like in the respective case.
Example: At the moment I am thinking about DBSCAN which should be deterministic if I allow border points to belong to multiple clusters at the same time (without connecting them):
One point is reachable from another point if it is in its eps-neighborhood
A core point is a point with at least minPts reachable
An edge goes from every core point to all points reachable from it
Every point with incoming edge from a core point is in the same cluster as the latter
If you miss the noise points then assume that each core node reaches itself (reflexivity) and afterwards we define noise points to be clusters of size one. Border points are non-core points. Afterwards if we want a partitioning, we can assign randomly the border points that are in multiple clusters to one of them. I do not consider this relevant for the method itself.
Supposedly the only clustering where this is efficiently possible is single linkage hierarchical clustering, because edges removed from A x A and B x B are not necessary for finding the MST of the joined set.
For DBSCAN precisely, you have the problem that the core point property can change when you add data. So c(A+B) likely has core points that were not core in either A not B. This can cause clusters to merge. f() supposedly needs to re-check all data points, i.e., rerun DBSCAN. While you can exploit that core points of the subset must be core of the entire set, you'll still need to find neighbors and missing core points.
Related
I have the following graph with 2 different parameters called p and t.
Their relationship is experimentally found. Manually by knowing (t,p), you can simply find the area number (group) of the point based on where it is located. For example, point M(t,p), locates in area 3 and belongs to group number 3. However, I would like to write a code/logical approach which automatically finds the group numbers. therefore when it reads (t,p) it will find the location of the point and give the group/Area number it belongs.
Is there any solution in Matlab for this scope? Graph
If you have the Image Processing Toolbox and your contours are closed, you can use imfill to fill them up (a bit like the bucket tool in Paint) and assign different values to each filled up region. Does this make sense to you? Let me know if you would like more detail.
Marta
I am trying to cluster some geospatial data, and I previously tried the WEKA library.
I found this benchmarking, and decided to try ELKI.
Despite the advice to not use ELKI as a Java library (which is suppose to be less maintained than the UI), I incorporated it in my application, and I can say that I am quite happy about the results. The structures that it uses to store data, are far more efficient than the ones used by Weka, and the fact that it has the option of using a spatial index is definetly a plus.
However, when I compare the results of Weka's DBSCAN, with the ones from ELKI's DBSCAN, I get a little bit puzzled. I would accept different implementations can give origin to slightly different results, but these magnitude of difference makes me think there is something wrong with the algorithm (probably with my code). The number of clusters and their geometry is very different in the two algorithms.
For the record, I am using the latest version of ELKI (0.6.0), and the parameters I used for my simulations were:
minpts=50
epsilon=0.008
I coded two DBSCAN functions (for Weka and ELKI), where the "entry point" is a csv with points, and the "output" for both of them is also identical: a function that calculates the concave hull of a set of points (one for each cluster). Since the function that reads the csv file into an ELKI "database" is relatively simple, I think my problem could be:
a) in the parametrization of the algorithm;
b) reading the results (most likely).
Parametrizing DBSCAN does not pose any challenges, and I use the two compulsory parameters, which I previously tested through the UI:
ListParameterization params2 = new ListParameterization();
params2.addParameter(de.lmu.ifi.dbs.elki.algorithm.clustering.DBSCAN.Parameterizer.MINPTS_ID, minPoints);
params2.addParameter(de.lmu.ifi.dbs.elki.algorithm.clustering.DBSCAN.Parameterizer.EPSILON_ID, epsilon);
Reading the result is a bit more challenging, as I don't completely understand the organization of the structure that stores the clusters; My idea is to iterate over each cluster, get the list of points, and pass it to the function that calculates the concave hull, in order to generate a polygon.
ArrayList<Clustering<?>> cs = ResultUtil.filterResults(result, Clustering.class);
for (Clustering<?> c : cs) {
System.out.println("clusters: " + c.getAllClusters().size());
for (de.lmu.ifi.dbs.elki.data.Cluster<?> cluster : c.getAllClusters()) {
if (!cluster.isNoise()){
Coordinate[] ptList=new Coordinate[cluster.size()];
int ct=0;
for (DBIDIter iter = cluster.getIDs().iter(); iter.valid(); iter.advance()) {
ptList[ct]=dataMap.get(DBIDUtil.toString(iter));
++ct;
}
//there are no "empty" clusters
assertTrue(ptList.length>0);
GeoPolygon poly=getBoundaryFromCoordinates(ptList);
if (poly.getCoordinates().getGeometryType()==
"Polygon"){
try {
out.write(poly.coordinates.toText()+"\n");
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}else
System.out.println(
poly.getCoordinates().getGeometryType());
}//!noise
}
}
I notice that the "noise" was coming up as a cluster, so I ignored this cluster (I don't want to draw it).
I am not sure if this is the right way of reading the clusters, as I don't find many examples. I also have some questions, for which I did not found answers yet:
What is the difference between getAllClusters() and
getTopLevelClusters()?
Are the DBSCAN clusters "nested", i.e.: can we have points that
belong to many clusters at the same time? Why?
I read somewhere that we should not use the database IDs to identify
the points, as they are for ELKI's internal use, but what other way
there is to get the list of points in each cluster? I read that you
can use a relation for the labels, but I am not sure how to actually
implement this...
Any comments that could point me in the right direction, or any code suggestions to iterate over the result set of ELKI's DBSCAN would be really welcome! I also used ELKI's OPTICSxi in my code, and I have even more questions regarding those results, but I guess I'll save that for another post.
This is mostly a follow-up to #Anony-Mousse, who gave a pretty complete answer.
getTopLevelClusters() and getAllClusters() do the same for DBSCAN, as DBSCAN does not produce hierarchical clusters.
DBSCAN clusters are disjoint. Treating clusters with isNoise()==true as singleton objects is likely the best way to handling noise. Clusters returned by our OPTICSXi implementation are also disjoint, but you should consider the members of all child clusters to be part of the outer cluster. For convex hulls, an efficient approach is to first compute the convex hull of the child clusters; then for the parent compute the convex hull on the additional objects + the convex hull points of all childs.
The RangeDBIDs approach mentioned by #Anony-Mousse is pretty clean for static databases. A clean approach that also works with dynamic databases is to have an additional relation that identifies the objects. When using a CSV file as input, instead of relying on the line numbering to be consistent, you would just add a non-numeric column, containing labels e.g. object123. This is the best approach from a logical point of view - if you want to be able to identify objects, give them a unique identifier. ;-)
We use ELKI for teaching, and we have verified its DBSCAN algorithm very very carefully (you can find a DBSCAN step by step demonstration here, and ELKI results exactly match this). The DBSCAN and OPTICS code in Weka was contributed by a student a long time ago, and has never been verified to the same extend. From a quick check, Weka does not produce the correct results on our class exercise data set.
Because the exercise data set has the same extend of 10 in each dimension, we can adjust the epsilon parameter by 1/10, and then the Weka result seems to match the solution; so #Anony-Mousses finding appears to be correct: Weka's implementation enforces a [0;1] scaling on the data.
Accessing the DBIDs of ELKI works, if you pay attention to how they are assigned.
For a static database, getDBIDs() will return a RangeDBIDs object, and it can give you an offset into the database. This is very reliable. But if you always restart your process, the DBIDs will be assigned deterministically anyway (only when using the MiniGUI, they will differ if you rerun a job!)
This will also be more efficient than DBIDUtil.toString.
DBSCAN results are not hierarchical, so every cluster should be a top level cluster.
As for Weka, it sometimes does automatic normalization. Then the epsilon value will be distorted. For geographic data, I would prefer geodetic distance anyway, Euclidean distance on latitude and longitude does not make sense.
Check this part of Wekas code: "norm" function, used by EuclideanDataObject. This does look to me as if Wekas DBSCAN enforces a normalization on the data set! Try scaling your data to [0:1] (I'm pretty sure there is a filter for this in ELKI), if the results are identical afterwards?
Judging from this code snippet, I would blame Weka. The code above also looks a bit inefficient to me. The filter approach makes IMHO more sense than this enforced filtering in the data objects.
I experience a strange situation when running Mahout K-means:
Using the a pre-selected set of initial centroids, I run K-means on a SequenceFile generated by lucene.vector. The run is for testing purposes, so the file is small (around 10MB~10000 vectors).
When K-means is executed with a single mapper (the default considering the Hadoop split size which in my cluster is 128MB), it reaches a given clustering result in 2 iterations (Case A).
However, I wanted to test if there would be any improvement/deterioration in the algorithm's execution speed by firing more mapping tasks (the Hadoop cluster has in total 6 nodes).
I therefore set the -Dmapred.max.split.size parameter to 5242880 bytes, in order to make mahout fire 2 mapping tasks (Case B).
I indeed succeeded in starting two mappers, but the strange thing was that the job finished after 5 iterations instead of 2, and that even at the first assignment of points to clusters, the mappers made different choices compared to the single-map execution . What I mean is that after close inspection of the clusterDump for the first iteration for both two cases, I found that in case B some points were not assigned to their closest cluster.
Could this behavior be justified by the existing K-means Mahout implementation?
From a quick look at the sources, I see two problems with the Mahout k-means implementation.
First of all, the way the S0, S1, S2 statistics are kept is probably not numerically stable for large data sets. Oh, and since k-means actually does not even use S2, it is also unnecessary slow. I bet a good implementation can beat this version of k-means by a factor of 2-5 at least.
For small data sets split onto multiple machines, there seems to be an error in the way they compute their means. Ouch. This will amplify if the reducer is applied to more than one input, in particular when the partitions are small. To be more verbose, the cluster mean apparently is initialized with the previous mean instead of the 0 vector. Now if you if you reduce 't' copies of it, the resulting vector will be off by 't' times the previous mean.
Initialization of AbstractCluster:
setS1(center.like());
Update of the mean:
getS1().assign(x, Functions.PLUS);
Merge of multiple copies of a cluster:
setS1(getS1().plus(cl.getS1()));
Finalization to new center:
setCenter(getS1().divide(getS0()));
So with this approach, the center will be offset from the proper value by the previous center times t / n where t is the number of splits, and n the number of objects.
To fix the numerical instability (which arises whenever the data set is not centered on the 0 vector), I recommend replacing the S1 statistic by the true mean, not S0*mean. Both S1 and S2 can be incrementally updated at little cost using the incremental mean formula which AFAICT was used in the original "k-means" publication by MacQueen (which actually is an online kmeans, while this is Lloyd style batch iterations). Well, for an incremental k-means you obviously need the updatable mean vector anyway... I believe the formula was also discussed by Knuth in his essential books. I'm surprised that Mahout does not seem to use it. It's fairly cheap (just a few CPU instructions more, no additional data, so it all happens in the CPU cache line) and gives you extra precision when you are dealing with large data sets.
I have a rather large(not too large but possibly 50+) set of conditions that must be placed on a set of data(or rather the data should be manipulated to fit the conditions).
For example, Suppose I have the a sequence of binary numbers of length n,
if n = 5 then a element in the data might be {0,1,1,0,0} or {0,0,0,1,1}, etc...
BUT there might be a set of conditions such as
x_3 + x_4 = 2
sum(x_even) <= 2
x_2*x_3 = x_4 mod 2
etc...
Because the conditions are quite complex in that they come from experiment(although they can be written down in logic form) and are hard to diagnose I would like instead to use a large sample set of valid data. i.e., Data I know satisfies the conditions and is a pretty large set. i.e., it is easier to collect the data then it is to deduce the conditions that the data must abide by.
Having said that, basically what I'm doing is very similar to neural networks. The difference is, I would like an actual algorithm, in some sense optimal, in some form of code that I can run instead of the network.
It might not be clear what I'm actually trying to do. What I have is a set of data in some raw format that is unique and unambiguous but not appropriate for my needs(in a sense the amount of data is too large).
I need to map the data into another set that actually is ambiguous to some degree but also has certain specific set of constraints that all the data follows(certain things just cannot happen while others are preferred).
The unique constraints and preferences are hard to figure out. That is, the mapping from the non-ambiguous set to the ambiguous set is hard to describe(which is why it is ambiguous). The goal, actually, is to have an unambiguous map by supplying the right constraints if at all possible.
So, on the vein of my initial example, I'm given(or supply) a set of elements and need some way to derive a list of constraints similar to what I've listed.
In a sense, I simply have a set of valid data and train it very similar to neural networks.
Then, after this "Training" I'm given the mapping function I can then use on any element in my dataset and it will produce a new element satisfying the constraint's, or if it can't, will give as close as possible an unambiguous result.
The main difference between neural networks and what I'm trying to achieve is I'd like to be able to use have an algorithm to code to be used instead of having to run a neural network. The difference here is the algorithm would probably be a lot less complex, not need potential retraining, and a lot faster.
Here is a simple example.
Suppose my "training set" are the binary sequences and mappings
01000 => 10000
00001 => 00010
01010 => 10100
00111 => 01110
then from the "Magical Algorithm Finder"(tm) I would get a mapping out like
f(x) = x rol 1 (rol = rotate left)
or whatever way one would want to express it.
Then I could simply apply f(x) to any other element, such as x = 011100 and could apply f to generate a hopefully unambiguous output.
Of course there are many such functions that will work on this example but the goal is to supply enough of the dataset to narrow it down to hopefully a few functions that make the most sense(at the very least will always map the training set correctly).
In my specific case I could easily convert my problem into mapping the set of binary digits of length m to the set of base B digits of length n. The constraints prevents some numbers from having an inverse. e.g., the mapping is injective but not surjective.
My algorithm could be a simple collection if statements acting on the digits if need be.
I think what you are looking for here is an application of Learning Classifier Systems, LCS -wiki. There are actually quite a few LCS open-source applications available, but you may need to experiment with the parameters in order to get a good result.
LCS/XCS/ZCS have the features that you are looking for including individual rules that could be heavily optimized, pressure to reduce the rule-set, and of course a human-readable/understandable set of rules. (Unlike a neural-net)
I am clustering a large set of points. Throughout the iterations, I want to avoid re-computing cluster properties if the assigned points are the same as the previous iteration. Each cluster keeps the IDs of its points. I don't want to compare them element wise, comparing the sum of the ID vector is risky (a small ID can be compensated with a large one), may be I should compare the sum of squares? Is there a hashing method in Matlab which I can use with confidence?
Example data:
a=[2,13,14,18,19,21,23,24,25,27]
b=[6,79,82,85,89,111,113,123,127,129]
c=[3,9,59,91,99,101,110,119,120,682]
d=[11,57,74,83,86,90,92,102,103,104]
So the problem is that if I just check the sum, it could be that cluster d for example, looses points 11,103 and gets 9,105. Then I would mistakenly think that there has been no change in the cluster.
This is one of those (very common) situations where the more we know about your data and application the better we are able to help. In the absence of better information than you provide, and in the spirit of exposing the weakness of answers such as this in that absence, here are a couple of suggestions you might reject.
One appropriate data structure for set operations is a bit-set, that is a set of length equal to the cardinality of the underlying universe of things in which each bit is set on or off according to the things membership of the (sub-set). You could implement this in Matlab in at least two ways:
a) (easy, but possibly consuming too much space): define a matrix with as many columns as there are points in your data, and one row for each cluster. Set the (cluster, point) value to true if point is a member of cluster. Set operations are then defined by vector operations. I don't have a clue about the relative (time) efficiency of setdiff versus rowA==rowB.
b) (more difficult): actually represent the clusters by bit sets. You'll have to use Matlab's bit-twiddling capabilities of course, but the pain might be worth the gain. Suppose that your universe comprises 1024 points, then you'll need an array of 16 uint64 values to represent the bit set for each cluster. The presence of, say, point 563 in a cluster requires that you set, for the bit set representing that cluster, bit 563 (which is probably bit 51 in the 9th element of the set) to 1.
And perhaps I should have started by writing that I don't think that this is a hashing sort of a problem, it's a set sort of a problem. Yeah, you could use a hash but then you'll have to program around the limitations of using a screwdriver on a nail (choose your preferred analogy).
If I understand correctly, to hash the ID's I would recommend using the matlab Java interface to use the Java hashing algorithms
http://docs.oracle.com/javase/1.4.2/docs/api/java/security/MessageDigest.html
You'll do something like:
hash = java.security.MessageDigest.getInstance('SHA');
Hope this helps.
I found the function
DataHash on FEX it is quiet fast for vectors and the strcmp on the keys is a lot faster than I expected.