Building KXEN Models on Ubuntu

Doing analytics on Linux sometimes seems user unfriendly but the reality is itis not so- and it is actually cheaper for you as you can focus on the analytical software rather than the Operating System licensing costs.

virtualization-kvm-ubuntu
kxen2

virtualization-kvm-ubuntu

Note: The software used in this were KXEN Linux version 2.4 and Ubuntu Hardy Heron.

Using KXEN on an Ubuntu Linux proved surprisingly even more easy. Thanks to some excellent help provided by the KXEN support team and some discussions with KXEN’s head of Research,Bertrand the following 5 step procedure should help you start building models in KXEN right away.

Using Ubuntu has the added advantages of security, low costs as well as all the ease of a Graphical User Interface-

1)Backward Compatibility

$ sudo apt-get install libstdc++5

(it will then ask the password).

2)Installing Java

$ sudo apt-get install sun-java6-jre

3) Download and Unzipping the Software
Download the zipped folder from the KXEN Download Site.
Unzip  the Linux Version of KXEN system from the Download Site- This creates the master folder (example Kxen_X86-Linux-2.4.21-4.Elsmp_v5_0_3 )

4)Licensing
Run the KXEN Node Generator in KxNodeCodeGenerator folder within the master folder above.
The new file KXEN Node.txt is then sent back to support team and they send the License_nl.cfg

5)Installation ( for stand alone client)

Install a JVM 1.4.2 and export the java/bin directory in the $PATH environment variable.

The exe is located in the folder KJWizardJNI- The following commands

$ cd KJWizardJNI
$ PATH=/opt/j2sdk1.4.2_10/bin:$PATH ; export PATH
$ ./KJWizardJNI.sh

Run KXEN Models Happily ever after !!!

Note KXEN offers the ability to export models in a variety of formats including PMML, SAS, SQL and other languages

Disclaimer- I am a consultant on social media to KXEN

ROC Curve

ROC Curve is a nice modeling concept to know as it will used practically in nearly all models

irrespective of spoefic technique and irrespective of statistical software.

We use the Wikipedia for referring to easy to implement statistics rather than crusty

thick books which seem prohibitely dense and opaque to outsiders

-This is how you define the ROC Curve.

actual value
p n total
prediction
outcome
p’ True
Positive
False
Positive
P’
n’ False
Negative
True
Negative
N’
total P N

true positive (TP)

eqv. with hit
true negative (TN)
eqv. with correct rejection
false positive (FP)
eqv. with false alarm, Type I error
false negative (FN)
eqv. with miss, Type II error
true positive rate (TPR)
eqv. with hit rate, recall, sensitivity
TPR = TP / P = TP / (TP + FN)
false positive rate (FPR)
eqv. with false alarm rate, fall-out
FPR = FP / N = FP / (FP + TN)
accuracy (ACC)
ACC = (TP + TN) / (P + N)
specificity (SPC)
SPC = TN / (FP + TN) = 1 ? FPR
positive predictive value (PPV)
eqv. with precision
PPV = TP / (TP + FP)

Here is a good java enabled page to calculate the ROC Curve.

http://www.rad.jhmi.edu/jeng/javarad/roc/JROCFITi.html

And in case any one asks, ROC stands for Receiver Operating Characteristic. ……