Hi all, I have added a new page to the SPMF website listing some unofficial wrappers for calling SPMF from Python, Spark, R and Weka... http://www.philippe-fournier-viger.com/spmf/index.php?link=spmfwrappers.php Those are unofficial wrappers, so I cannot provide support them, and note that some do not support all features of SPMF. But this can be very useful if you want to use SPMF from o
Forum: The Data Mining / Big Data Forum

Still about 1 week to submit your chapter If some of you need more time, you may let me know!
Forum: The Data Mining / Big Data Forum

Hi all, Hope you are doing well. This year, I am the special session chair of the upcoming IEA AIE 2021 conference on applied intelligent systems and data mining. The IEA AIE conference is a well-known conference, organized for over 30 years, and published by Springer in the LNAI series. I am glad to announce that this year, beside the main track for submitting paper, we will have many special
Forum: The Data Mining / Big Data Forum

Hi, Welcome to the forum. The short answer is: A transaction database has two dimensions: transactions and items In an horizontal transaction database, each row represents a transaction. Thus, a row contains a set of items purchased by a customer. In a vertical transaction database, each row represents an item. Thus a row contains the set of transactions where the item was purchased.
Forum: The Data Mining / Big Data Forum

Thanks for using SPMF and joining the forum. I have answered your e-mail ;-) Philippe
Forum: The Data Mining / Big Data Forum

Hi all, I would like to remind you that I am co-organizing a book about tracking and preventing diseases with AI: http://www.philippe-fournier-viger.com/books/ai_disease_book/index.php If you are working in this area or have some research related to healthcare, you may consider submitting your work to the book. The deadline is coming soon but if you would need extra time, let me know and
Forum: The Data Mining / Big Data Forum

Hi all, The forum has been down for more than 1 week. I am sorry about that. After investigating the problem several days ago I found that it was due to a technical problem from the 1and1 IONOS webhosting service that I use for hosting all my websites. The database powering this forum was completely disconnected. After contacting with the customer support service a few days ago, they have f
Forum: The Data Mining / Big Data Forum

Dear Madiha, Thanks for using SPMF, and I am sorry for not answering earlier. Usually, I receive an e-mail for each message poster on the forum and I try to answer quickly to each message. But somehow, I did not see the notification. I think the problem is likely due to some issue in the input file. It could be a bug... but since this algorithm has been used by many people, I think it is mor
Forum: The Data Mining / Big Data Forum

==================================================================== Call for Special Sessions (IEA AIE 2021) The 34th International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA AIE 2021) invites proposals for special sessions on specific research sub-areas related to artificial intelligence and applications. Each special session will b
Forum: The Data Mining / Big Data Forum

Hi, One possibility for visualizing sequential patterns is to use GraphViz like this: https://data-mining.philippe-fournier-viger.com/discovering-visualizing-sequential-patterns-web-log-data-using-spmf/ Best regards, Philippe
Forum: The Data Mining / Big Data Forum

Hi, Thanks a lot for reporting this problem in the documentation:-) It is indeed because the code has changed and it is no longer necessary to indicate that there is no input file. I somehow forgot to update the documentation. Now it is done! Thanks! Philippe
Forum: The Data Mining / Big Data Forum

Hi! I am happy that you like the software. Thanks for using it :-) Yes, I indeed prefer the unordered rules, as you have noticed. But I think that for some applications, ordered can also be interesting. If you want to try the ordered rules, you can use the RuleGen algorithm in SPMF. The idea of that algorithm is very simple: (1) it first finds the sequential patterns (sequences of s
Forum: The Data Mining / Big Data Forum

My pleasure. Happy that SPMF is useful ;-) Thanks for using it :-) Philippe
Forum: The Data Mining / Big Data Forum

Hi, The answer is no. There are some algorithm like Rulegen by Zaki (2001) who will first mine sequential patterns in a sequence database and then use them to create some sequential rules: http://www.philippe-fournier-viger.com/spmf/Zaki2001.pdf But some other algorithms like RuleGrowth and some others will directly find the rules: http://www.philippe-fournier-viger.com/spmf/TKDE20
Forum: The Data Mining / Big Data Forum

Good evening, Sorry for the delay to answer. I have read the message a while ago, but I did not find much time recently to answer messages on the forum. As the semester starts and many projects happen at the same time, I had to wait a little to answer. That is a very interesting topic. I understand now the reason for a single item per transaction. Since there is a single item per transa
Forum: The Data Mining / Big Data Forum

Hi, I see. How many lines is there in your data? Maybe you can also send me your data to my e-mail: philfv8@yahoo.com and I can also try it if you want. Best regards, Philippe
Forum: The Data Mining / Big Data Forum

Hi, Yes, it is indeed written as you said in the paper. And I am checking the code and it seems that the paper and the code are the same. So it is my example above that contains error, and BETA should have the same support as Z Good that you found it.
Forum: The Data Mining / Big Data Forum

Hi all, Just to let you know that there is less than one week to submit a paper to the UDML 2020 workshop at ICDM 2020! Hope to see your papers. Best regards, Philippe
Forum: The Data Mining / Big Data Forum

Good evening, Welcome to the forum. Happy that the software is useful, and thanks for using it! I will try to give some comments/suggestions below. > I am aware the association rules are applied > mainly to Transactional Databases, however I was > wondering if I could use it to find association or > patterns among features of a database. Yes. Indeed. A transaction d
Forum: The Data Mining / Big Data Forum

Hi again, The local utility pruning would be different from both pictures on Page 22. Let me explain with a simple example. Let say that the order between items is a < b < c < d < e ... We will look at the picture of the tree on page 22. Let's say that we want to apply the local utility pruning for the itemset {b} containing a single item, then ALPHA = {} empty set z = b
Forum: The Data Mining / Big Data Forum

>>Dear Sir >>i think local utility and remaining utility are the same in mathematically why we introduce local utility ? and when WE use local utility pruning if utility a<minutil we prune only the child of itemset a or we prune itemset a with the child of item set a . Thank you for your help Good evening, Just to make sure, I think that your question is about the EFIM algor
Forum: The Data Mining / Big Data Forum

Hi! Interesting question. I think it depends on the application. For some applications, it makes sense to use the length constraint. For example, if we analyze customer transactions for the purpose of marketing, maybe we don't want to find itemsets containing five or more items because it would be difficult to promote all these items together. For example, if we find that {juice, milk, bread
Forum: The Data Mining / Big Data Forum

Hi, These two strategies have different goals. EUCP will let you eliminate some candidates. For example, using EUCP you can know that combining {A} and {B} together to make {A,B} is useless. Thus, you don't need to create the utility list of {A,B}. So in other words, EUCP is applied before you build the utility-list of an itemset to decide if you should build that list, and also if all exte
Forum: The Data Mining / Big Data Forum

Hi, Welcome to the forum and thanks for using SPMF. Yes, example #213 explains how to use the text file from the source code. But if you use the GUI or the command line to call SPMF, then it will all be done automatically. So you can just call the algorithm that you want to use from the command line with a file with .text as extension, and it should work! For example, if you want to a
Forum: The Data Mining / Big Data Forum

Happy it is clear;-) Best regards, Philippe
Forum: The Data Mining / Big Data Forum

Hi again, But rare means infrequent... It means something that has a low frequency. It depends on how you set the parameter. If you set maxsup very low, you will find infrequent (rare) rules. For example, if you set maxsup = 25 %, the algorithm should not give you rule more frequent than 25%.. If you set maxsup = 0.01 %, the algorithm will not give you rules more frequent than 0.01% and so o
Forum: The Data Mining / Big Data Forum

Hi Irfan, I would like to understand more clearly. You said "maxconf" but rare rule is not about confidence but about the support. The parameter is "maxsup" not "maxconf". I have implemented a parameter "maxsup" for TopKClassRules in the version that you have downloaded. Do you mean that you would like to have a parameter "maxconf?"
Forum: The Data Mining / Big Data Forum

Hi Irfan, I have added the "maxsup" parameter: You can try it by downloading the spmf.jar file again from the website. For the source code version of SPMF, I will upload spmf.zip maybe in a few hours because I want to also update another algorithm. Best, Philippe
Forum: The Data Mining / Big Data Forum

Thanks for sharing
Forum: The Data Mining / Big Data Forum

Hi, Just saw your message. I will try to explain in a simple way. In the algorithm EFIM-Closed we use some processing order to process items. To make my example simple, let's say that this order is A < B < C < D < E < F. And let's say that we have a transaction database with three transactions: T1: A B C D T2: A B D T3: A C D E F Now, all the itemsets an
Forum: The Data Mining / Big Data Forum