Hi Mahesh,

Actually, IMO, there should be an output for trained model, which is the
evaluation metric; for linear regression, MSE and for logistic regression,
accuracy. For clustering, it could be cluster centers.
That way, it's possible to examine how model behaves with data.

Best regards.

On Mon, May 23, 2016 at 3:06 PM, Mahesh Dananjaya <dananjayamah...@gmail.com
> wrote:

> Hi suho,
> in my project machine learning models are incrementally being trained.
> Therefore real time data is taken into my design as mini batches of data
> sample points. Since we are developing this models for cep siddhi
> processor,we want to get the mini batch of data points into my algorithms
> from siddhi processor. In my case there is a input stream of K-size
> (Batch/Window Size) of sample points bundles together. In linear regrassion
> case all the independent and dependent data, In K-mean case whole feature
> vector (data sample). Not only as single sample points (Window size=1), but
> also as mini-batch (Window size=N)of sample points (Stream data). In my
> case there wont be an output stream. The modeled will be there so even
> predict can be used with that models.I looked into the [1] also.thank you.
> regards,
> Mahesh.
> [1]
> https://docs.wso2.com/display/CEP400/Writing+a+Custom+Stream+Processor+Extension
>
> On Mon, May 23, 2016 at 2:48 PM, Sriskandarajah Suhothayan <s...@wso2.com>
> wrote:
>
>> Hi Mahesh
>>
>> Can you explain the expected input to your extension and the expected
>> output. Then we can help you to find the proper Siddhi extension to use.
>>
>> Regards
>> Suho
>>
>> On Sat, May 21, 2016 at 11:44 AM, Mahesh Dananjaya <
>> dananjayamah...@gmail.com> wrote:
>>
>>> Hi all,
>>> i am currenl working on the gsoc project "Predictive analytics with
>>> online data for WSO2 Machine Learner
>>> <https://docs.wso2.com/display/GSoC/Project+Proposals+for+2016#ProjectProposalsfor2016-Proposal6:[ML]PredictiveanalyticswithonlinedataforWSO2MachineLearner>"
>>> with wso2 ML and cep extention for acquiring stream of events (sample data
>>> points interms of ml) from cep siddhi porocessor. I am trying to write a
>>> cep extention to get the stream of events as windows with a "Specified
>>> window size". Then i am using those data sets to incrementally and
>>> periodically learn the ML model which store the specific ml model
>>> information to use with the current window of event data samples. I am
>>> facing problem of writing a siddhi extention for my purpose to get stream
>>> of data windows from cep siddhi rpocessor. Please help me with followings.
>>> 1. I have been referring to [1] [2] [3] for writing siddhi extention. In
>>> my case,what can be the most suitable option for this among the set of
>>> siddhi extensions given?
>>>
>>> 2. I am currently working on carbon-ml and product-ml and ml cep
>>> extentions currently built [6]. In case what is the best way to write
>>> simple cep extention to check the functionality.?
>>>
>>> 3. I have gone through the [5] [4] for cep inbuilt windows. How can i
>>> effectivey aggregate those features into my case?
>>>
>>> In case, if i need to look into other areas of cep for this purpose
>>> please let me know. Thank you very much.
>>> regards,
>>> Mahesh.
>>> [1]https://docs.wso2.com/display/CEP310/Writing+Extensions+to+Siddhi
>>> https://docs.wso2.com/display/CEP310/Writing+Extensions+to+Siddhi
>>> [2]https://docs.wso2.com/display/CEP400/Writing+Extensions+to+Siddhi
>>> https://docs.wso2.com/display/CEP400/Writing+Extensions+to+Siddhi
>>> [3]https://docs.wso2.com/display/CEP310/Writing+a+Custom+Function
>>> https://docs.wso2.com/display/CEP310/Writing+a+Custom+Function
>>> [4]
>>> https://docs.wso2.com/display/CEP400/Inbuilt+Windows#InbuiltWindows-lengthlength
>>> https://docs.wso2.com/display/CEP400/Inbuilt+Windows#InbuiltWindows-lengthlength
>>> [5]
>>> https://docs.wso2.com/display/CEP400/Writing+a+Custom+Aggregate+Function
>>> https://docs.wso2.com/display/CEP400/Writing+a+Custom+Aggregate+Function
>>> [6]
>>> https://docs.wso2.com/display/ML110/WSO2+CEP+Extension+for+ML+Predictions#WSO2CEPExtensionforMLPredictions-Siddhisyntaxfortheextension
>>> https://docs.wso2.com/display/ML110/WSO2+CEP+Extension+for+ML+Predictions#WSO2CEPExtensionforMLPredictions-Siddhisyntaxfortheextension
>>>
>>
>>
>>
>> --
>>
>> *S. Suhothayan*
>> Technical Lead & Team Lead of WSO2 Complex Event Processor
>> *WSO2 Inc. *http://wso2.com
>> * <http://wso2.com/>*
>> lean . enterprise . middleware
>>
>>
>> *cell: (+94) 779 756 757 <%28%2B94%29%20779%20756%20757> | blog:
>> http://suhothayan.blogspot.com/ <http://suhothayan.blogspot.com/>twitter:
>> http://twitter.com/suhothayan <http://twitter.com/suhothayan> | linked-in:
>> http://lk.linkedin.com/in/suhothayan <http://lk.linkedin.com/in/suhothayan>*
>>
>
>


-- 
Pruthuvi Maheshakya Wijewardena
mahesha...@wso2.com
+94711228855
_______________________________________________
Dev mailing list
Dev@wso2.org
http://wso2.org/cgi-bin/mailman/listinfo/dev

Reply via email to