Learn how easy it is to sync an existing GitHub or Google Code repo to a SourceForge project!

## [rm-sig-information-extraction] Analysing on boston housing data

 [rm-sig-information-extraction] Analysing on boston housing data From: Annawar soul - 2011-09-12 09:19:18 Attachments: Message as HTML ```Hi, I am doing analysis on the Boston Housing data and firstly I am starting to analysisThe sensitivity and specifity of applying K-NN under two setups. In the first setup, apply K-NN to the unprocessed data. In the second setup, apply K-NN after normalising the data. Secondly, The correlation matrix of all the predictors to compute the correlation matrix to the training set only. Explain why you should use the training set only. Based on the correlation matrix, decide on a new set of predictors and apply Naive Bayes on the new set. And I want to include ROC charts to decide what is the best system overall and choose the threshold that gives optimal results. I am a beginner and I have problems to use Rapidminer. I just can only use " opeartors" to analyse. Could you please explain step by step of doing this? Regards, MMT ```

 [rm-sig-information-extraction] Analysing on boston housing data From: Annawar soul - 2011-09-12 09:19:18 Attachments: Message as HTML ```Hi, I am doing analysis on the Boston Housing data and firstly I am starting to analysisThe sensitivity and specifity of applying K-NN under two setups. In the first setup, apply K-NN to the unprocessed data. In the second setup, apply K-NN after normalising the data. Secondly, The correlation matrix of all the predictors to compute the correlation matrix to the training set only. Explain why you should use the training set only. Based on the correlation matrix, decide on a new set of predictors and apply Naive Bayes on the new set. And I want to include ROC charts to decide what is the best system overall and choose the threshold that gives optimal results. I am a beginner and I have problems to use Rapidminer. I just can only use " opeartors" to analyse. Could you please explain step by step of doing this? Regards, MMT ```
 Re: [rm-sig-information-extraction] Analysing on boston housing data From: Sebastian Land - 2011-09-12 09:24:19 ```Hi, I would suggest the following steps: Please register as a member in our community forum and then ask there. This list is meant to deal with Information Extraction only, your request refers to general data mining problems. With kind regards, Sebastian Land > Hi, I am doing analysis on the Boston Housing data and firstly I am starting to > analysisThe sensitivity and specifity of applying K-NN under two setups. In the > first setup, apply K-NN to the unprocessed data. In the second setup, apply K-NN > after normalising the data. > > Secondly,The correlation matrix of all the predictors to compute the correlation > matrix to the training set only. Explain why you should use the training set > only.Based on the correlation matrix, decide on a new set of predictors and > apply Naive Bayes on the new set. And I want to include ROC charts to decide > what is the best system overall and choose the threshold that gives optimal results. > > > I am a beginner and I have problems to use Rapidminer. I just can only use " > opeartors" to analyse. Could you please explain step by step of doing this? > > Regards, > > MMT > > > > ------------------------------------------------------------------------------ > Doing More with Less: The Next Generation Virtual Desktop > What are the key obstacles that have prevented many mid-market businesses > from deploying virtual desktops? How do next-generation virtual desktops > provide companies an easier-to-deploy, easier-to-manage and more affordable > virtual desktop model.http://www.accelacomm.com/jaw/sfnl/114/51426474/ > > > > _______________________________________________ > Rapidminer-sig-information-extraction mailing list > Rapidminer-sig-information-extraction@... > https://lists.sourceforge.net/lists/listinfo/rapidminer-sig-information-extraction -- Sebastian Land Rapid-I GmbH Stockumer Str. 475 44227 Dortmund, Germany Phone: +49 (0)231 425 786 90 Fax: +49 (0)231 425 786 99 E-Mail: land@... Sitz: Dortmund HRB 20720, Amtsgericht Dortmund Geschäftsführer: Dr. Ingo Mierswa, Ralf Klinkenberg www: http://rapid-i.com/ ```