I have given a Cluster. How can i decide splitting the Cluster in two parts is better than the original Cluster?
I have tried using K-Mean with k = 2 and again stuck.. Is it better to spilt or not to spilt?
EDit: Well i dont get the downvotes... A little explanation would be helpful to improve the question :D
The literature proposes different metrics, e.g,
Bayesiqan Information Criterion
Alaine Information Criterion
I want to use clustering techniques for binary data analysis. I have collected the data through survey in which i asked the users to select exactly 20 features out of list of 94 product features. The columns in my data represents the 94 product features and the rows represents the participants. I am trying to cluster the similar users in different user groups based on the product features they selected. Each user cluster should also tell me the product features associated with each cluster. I am using some open source clustering tools like NCSS and JMP. I was trying to use fuzzy clustering technique for achieveing my goal but unfortunately these tools do not deal with binary data. Can you please suggest me which technique would really be appropriate for my tasks , also which online tool i can use for using the cluster analysis on my data? As beacuse of the time limitation, I am not looking to code myself and i am only looking for some open source tools that have all the functionality available in them which i can use as it is.
Clustering for binary data is not really well defined.
Rather than looking for some tool/function that may or may not work by trial and error, you should first try to answer a 'simple" question:
What is a good cluster, mathematically?
Vague terms not allowed. The next questions to answer then are: I) when is clustering A better than clustering B (I.e. how does the computer compute quality), and ii) how can this be found efficiently.
You won't get far if you don't understand what you are doing just by calling random functions...
Also, is clustering actually what you are looking for? Most of the time with binary data e.g. frequent itemset mining is the better choice.
I'm fairly new to clustering and related topics so please forgive my questions.
I'm trying to get introduced into this area by doing some tests, and as a first experiment I'd like to create clusters on tweets based on content similarity. The basic idea for the experiment would be storing tweets on a database and periodically calculate the clustering (ie. using a cron job). Please note that the database would obtain new tweets from time to time.
Being ignorant in this field, my idea (probably naive) would be to do something like this:
1. For each new tweet in the db, extract N-grams (N=3 for example) into a set
2. Perform Jaccard similarity and compare with each of the existing clusters. If result > threshold then it would be assigned to that cluster
3. Once finished I'd get M clusters containing similar tweets
Now I see some problems with this basic approach. Let's put aside computational cost, how would the comparison between a tweet and a cluster be done? Assuming I have a tweet Tn and a cluster C1 containing T1, T4, T10 which one should I compare it to? Given that we're talking about similarity, it could well happen that sim(Tn,T1) > threshold but sim(Tn,T4) < threshold. My gut feeling tells me that something like an average should be used for the cluster, in order to avoid this problem.
Also, it could happen that sim(Tn, C1) and sim(Tn, C2) are both > threshold but similarity with C1 would be higher. In that case Tn should go to C1. This could be done brute force as well to assign the tweet to the cluster with maximum similarity.
And last of all, it's the computational issue. I've been reading a bit about minhash and it seems to be the answer to this problem, although I need to do some more research on it.
Anyway, my main question would be: could someone with experience in the area recommend me which approach should I aim to? I read some mentions about LSA and other methods, but trying to cope with everything is getting a bit overwhelming, so I'd appreciate some guiding.
From what I'm reading a tool for this would be hierarchical clustering, as it would allow regrouping of clusters whenever new data enters. Is this correct?
Please note that I'm not looking for any complicated case. My use case idea would be being able to cluster similar tweets into groups without any previous information. For example, tweets from Foursquare ("I'm checking in ..." which are similar to each other would be one case, or "My klout score is ..."). Also note that I'd like this to be language independent, so I'm not interested in having to deal with specific language issues.
It looks like to me that you are trying to address two different problems in one, i.e. "syntactic" and "semantic" clustering. They are quite different problems, expecially if you are in the realm of short-text analysis (and Twitter is the king of short-text analysis, of course).
"Syntactic" clustering means aggregating tweets that come, most likely, from the same source. Your example of Foursquare fits perfectly, but it is also common for retweets, people sharing online newspaper articles or blog posts, and many other cases. For this type of problem, using a N-gram model is almost mandatory, as you said (my experience suggests that N=2 is good for tweets, since you can find significant tweets that have as low as 3-4 features). Normalization is also an important factor here, removing RT tag, mentions, hashtags might help.
"Semantic" clustering means aggregating tweets that share the same topic. This is a much more difficult problem, and it won't likely work if you try to aggregate random sample of tweets, due to the fact that they, usually, carry too little information. These techniques might work, though, if you restrict your domain to a specific subset of tweets (i.e. the one matching a keyword, or an hashtag). LSA could be useful here, while it is useless for syntactic clusters.
Based on your observation, I think what you want is syntactic clustering. Your biggest issue, though, is the fact that you need online clustering, and not static clustering. The classical clustering algorithms that would work well in the static case (like hierarchical clustering, or union find) aren't really suited for online clustering , unless you redo the clustering from scratch every time a new tweet gets added to your database. "Averaging" the clusters to add new elements isn't a great solution according to my experience, because you need to retain all the information of every cluster member to update the "average" every time new data gets in. Also, algorithms like hierarchical clustering and union find work well because they can join pre-existant clusters if a link of similarity is found between them, and they don't simply assign a new element to the "closest" cluster, which is what you suggested to do in your post.
Algorithms like MinHash (or SimHash) are indeed more suited to online clustering, because they support the idea of "querying" for similar documents. MinHash is essentially a way to obtain pairs of documents that exceed a certain threshold of similarity (in particular, MinHash can be considered an estimator of Jaccard similarity) without having to rely on a quadratic algorithm like pairwise comparison (it is, in fact, O(nlog(n)) in time). It is, though, quadratic in space, therefore a memory-only implementation of MinHash is useful for small collections only (say 10000 tweets). In your case, though, it can be useful to save "sketches" (i.e., the set of hashes you obtain by min-hashing a tweet) of your tweets in a database to form an "index", and query the new ones against that index. You can then form a similarity graph, by adding edges between vertices (tweets) that matched the similarity query. The connected components of your graph will be your clusters.
This sounds a lot like canopy pre-clustering to me.
Essentially, each cluster is represented by the first object that started the cluster.
Objects within the outer radius join the cluster. Objects that are not within the inner radius of at least one cluster start a new cluster. This way, you get an overlapping (non-disjoint!) quantization of your dataset. Since this can drastically reduce the data size, it can be used to speed up various algorithms.
However don't expect useful results from clustering tweets. Tweet data is just to much noise. Most tweets have just a few words, too little to define a good similarity. On the other hand, you have the various retweets that are near duplicates - but trivial to detect.
So what would be a good cluster of tweets? Can this n-gram similarity actually capture this?
I have to check performance of various clustering algos using different performance operators in rapidminer. For that I want to know the following things:
what does cluster number index value shows which is output of cluster count performance operator?
what does small and large value of avg within cluster distance and avg. within centroid distance mean in terms of good and bad clustering?
I also want to check other indexes value like Dunn index,Jaccard index, Fowlkes–Mallows for various clustering algos. but rapidminer don't have any operator for this, what to do for that. I don't have experience with R.
I have copied part of the answer I gave on the Rapid-I forum
The cluster number index is the count of clusters - pointless you might say but when used with DBSCAN, it can be quite interesting http://rapidminernotes.blogspot.co.uk/2010/12/counting-clusters.html
The avg within cluster and centroid distances are hard to interpret - one thing to search for is "elbow criterion" in this context. As the number of clusters varies, note how the validity measure changes and look for an "elbow" that marks the point where the natural progression of the measure dominates the structure.
R has many validity measures and it's worth investing some time because you can always call the R process from RapidMiner which makes it easier to work out what is going on.
I'm doing a little research on how to cluster articles into 'news stories' ala Google News.
Looking at previous questions here on the subject, I often see it recommended to simply pull out a vector of words from an article, weight some of the words more if they're in certain parts of the article (e.g. the headline), and then to use something like a k-means algorithm to cluster the articles.
But this leads to a couple of questions:
With k-means, how do you know in advance how much k should be? In a dynamic news environment you may have a very variable number of stories, and you won't know in advance how many stories a collection of articles represents.
With hierarchal clustering algorithms, how do you decide which clusters to use as your stories? You'll have clusters at the bottom of the tree that are just single articles, which you obviously won't want to use, and a cluster at the root of the tree which has all of the articles, which again you won't want...but how do you know which clusters in between should be used to represent stories?
Finally, with either k-means or hierarchal algorithms, most literature I have read seems to assume you have a preset collection of documents you want to cluster, and it clusters them all at once. But what of a situation where you have new articles coming in every so often. What happens? Do you have to cluster all the articles from scratch, now that there's an additional one? This is why I'm wondering if there are approaches that let you 'add' articles as you go without re-clustering from scratch. I can't imagine that's very efficient.
I worked on a start-up that built exactly this: an incremental clustering engine for news articles. We based our algorithm on this paper: Web Document Clustering Using Document Index Graph (http://ieeexplore.ieee.org/xpl/articleDetails.jsp?reload=true&arnumber=4289851). Worked well for us for 10K articles / day.
It has two main advantages:
1) It's incremental, which addresses the problem you have with having to deal with a stream of incoming articles (rather than clustering all at once)
2) It uses phrase-based modeling, as opposed to just "bag of words", which results in much higher accuracy.
A Google search pops up http://www.similetrix.com, they might have what you're looking for.
I would do a search for adaptive K-means clustering algorithms. There is a good section of research devoted to the problems you describe. Here is one such paper (pdf)