class working

[mathematiciseverywhere]

Hello, I can not understand class what they do, if you have a time , can you write explanation of class? have a nice weekend.

[procheta]

Hi,

I will let you know by this weekend.

Thanks Procheta

On Fri, 7 Dec 2018 at 13:25, mathematiciseverywhere < notifications@github.com> wrote:

Hello, I can not understand class what they do, if you have a time , can you write explanation of class? have a nice weekend.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/procheta/AOLTaskExtraction/issues/2, or mute the thread https://github.com/notifications/unsubscribe-auth/AQCR2JtauRiGBTd8CK1opRD93NIxg_FAks5u2mwugaJpZM4ZIcEN .

[mathematiciseverywhere]

thank you.

[procheta]

Hi,

At this moment I have the following explanation of different classes in the project:

LucheseImplementation Package -> Luchese task extraction method implemented

preprocessing https://github.com/procheta/AOLTaskExtraction/tree/master/AOLTaskExtraction/src/preprocessing /ClustEval.java -> evaluation of cluster assignments done by task extraction method.

src https://github.com/procheta/AOLTaskExtraction/tree/master/AOLTaskExtraction/src /aoltaskextraction https://github.com/procheta/AOLTaskExtraction/tree/master/AOLTaskExtraction/src/aoltaskextraction /FeatureExtraction.java -> To extract character ngram feature given a query log as input.

AOLTaskExtraction https://github.com/procheta/AOLTaskExtraction/tree/master/AOLTaskExtraction /src https://github.com/procheta/AOLTaskExtraction/tree/master/AOLTaskExtraction/src /dbscanClustering https://github.com/procheta/AOLTaskExtraction/tree/master/AOLTaskExtraction/src/dbscanClustering /DBSCAN.java -> java implementation of clustering query vectors using dbscan algorithm

src https://github.com/procheta/AOLTaskExtraction/tree/master/AOLTaskExtraction/src /LucheseImplementation https://github.com/procheta/AOLTaskExtraction/tree/master/AOLTaskExtraction/src/LucheseImplementation /QueryVecFormulator.java -> Computes similarity between any query pair based on their ngram feature, cosine similarity and top K documents returned by CLueweb for each query.

src https://github.com/procheta/AOLTaskExtraction/tree/master/AOLTaskExtraction/src /LucheseImplementation https://github.com/procheta/AOLTaskExtraction/tree/master/AOLTaskExtraction/src/LucheseImplementation /SimScoreCalCulationTfIdf.java -> Calculates different similarity scores between query pairs . (e.g. lexical, tfidf score)

src https://github.com/procheta/AOLTaskExtraction/tree/master/AOLTaskExtraction/src /LucheseImplementation https://github.com/procheta/AOLTaskExtraction/tree/master/AOLTaskExtraction/src/LucheseImplementation /WeightedClustering.java -> Computes graph based weighted clustering on a set of queries. The output of clustering is a task id assigned to each query.

Best Procheta

On Fri, 7 Dec 2018 at 14:40, mathematiciseverywhere < notifications@github.com> wrote:

thank you.

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/procheta/AOLTaskExtraction/issues/2#issuecomment-445252249, or mute the thread https://github.com/notifications/unsubscribe-auth/AQCR2LuirTIxIsUc2v4sTPbFf1rvwkJMks5u2n3EgaJpZM4ZIcEN .

[mathematiciseverywhere]

Thanks for your reply but I can understand which class what can do. Bu I cannot your input files. For example I used this path: aolLogPath =/home/nurullah/Downloads/processedLog.txt and then I get this file: writeFile=/home/nurullah/Downloads/newLog.txt this file include sessions of queries. But you didint use newLog.txt file anywhere. what is the meaning of queryFile.txt. Where did you get this file queryFile.txt . Please help me?

[mathematiciseverywhere]

sorry again. What is the "new.txt" file.