2
$\begingroup$

I am newbie to NLP. I have a excel sheet with following columns: Server_SNo, Owner, Hosting Dept, Bus owner, Applications hosted, Functionality, comments

a. Except the Server_SNo, other columns may or may not have data.
b. For some records there is no data except Server_SNo which is the first column. c. One business owner can own more than 1 Server.

So, out of 4000 records, about 50% of data contain direct mapping for a server with owner. Remaining 50% of data have combination of other columns (Owner, Hosting Dept, Bus owner, Applications hosted, Functionality and comments)

Here is my problem, I need to find the owner for the given Server_Sno for 50% of data which have combination of other columns (Owner, Hosting Dept, Bus owner, Applications hosted, Functionality and comments).

I have just started to build the code using Python and NLTK.

Is this an NLP problem? Am I going in right direction using Python and NLTK for NLP?

Any insights is appreciated.

-Mani

$\endgroup$
1
$\begingroup$

I don't think this classify as an NLP problem, there is almost no semantic analysis needed, it is more like a classification problem using categorical features.

NLTK is surely valuable if you want to perform some text 'cleaning' or preprocessing before encoding the variables. The only NLP application that I think you could apply here is some sentiment analysis on the comments to extract extra features (like a number expressing the negativeness or positiveness of each comment). Nevertheless you might want to do that using some pre-trained models cause your dataset is pretty small.

| improve this answer | |
$\endgroup$
  • $\begingroup$ Hello Eodardo, Thanks for your reply, I was able to do this in python using dataframe itself. I am currently adding some more enhancements to it. I will post the completed code sometime soon. $\endgroup$ – Mani Mar 18 at 6:13

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.