negative values with density plot
when using auto model i got this density plot.
I do not have negative values. How do i remove negative values and what operator is used to plot density
plots
I do not have negative values. How do i remove negative values and what operator is used to plot density
plotsFind more posts tagged with
Sort by:
1 - 8 of
81
Hi again @msacs09,
After reflection, I think you have to keep these curves like that (although you have no negative values) : With Naive Bayes, when dealing with continuous data, a typical assumption is that the continuous values associated with each class are distributed according to a Gaussian distribution :
Regards,
Lionel
After reflection, I think you have to keep these curves like that (although you have no negative values) : With Naive Bayes, when dealing with continuous data, a typical assumption is that the continuous values associated with each class are distributed according to a Gaussian distribution :
Regards,
Lionel
Thank you. Is there a way i can a do a density chart without negative values?? what operator should i use to get this graph with in Rapidminer?
Hi @msacs09,
I would like to second that from a modeling perspective the function is what it is and even if no negative values are part of your data, still the used distribution will cover both sides of the average value equally. If you want to avoid this, you may want to try Kernel Naive Bayes instead.
However, if you simply would like to get a distribution curve like yours, the upcoming RapidMiner release will offer a new (and very cool!) new visualization framework where you can easily create such a chart yourself (see below). You can try it yourself already with the public beta version available here: http://static.rapidminer.com/rnd/html/rapidminer-9.2-preview.html
Hope this helps,
Ingo
Ingo
Waoow thank you. wanted to try this right away
Also, I used "Kernel Naive Bayes" and still i get the same negative values.. further is there a way we can reduce the x axis values.. for better clarity
What is being explained is that while there may not be negative values in your data (and negative values may in fact be impossible based on the quantity being measured), the NB algorthim models your numerical data as though they are continuous functions based on the Gaussian distribution, which means it will show the full possible range of values in the built-in charts. This is a simplification, of course, of reality, but one that allows the NB algorithm to produce its estimates with minimal computational complexity. If you want to customize the axis of the graphs to omit the negative range or cut off the long right tail, you'll have to do that manually (as Ingo showed above) by setting the min and max values for the X axis, which is pretty easy to do in the new charting interface in RapidMiner 9.2.
Thank you all
Sort by:
1 - 1 of
11
Hi @msacs09,
I would like to second that from a modeling perspective the function is what it is and even if no negative values are part of your data, still the used distribution will cover both sides of the average value equally. If you want to avoid this, you may want to try Kernel Naive Bayes instead.
However, if you simply would like to get a distribution curve like yours, the upcoming RapidMiner release will offer a new (and very cool!) new visualization framework where you can easily create such a chart yourself (see below). You can try it yourself already with the public beta version available here: http://static.rapidminer.com/rnd/html/rapidminer-9.2-preview.html
Hope this helps,
Ingo
Ingo
Can you share your dataset in order to understand ?
Regards,
Lionel