MartinLiebigAdministrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University ProfessorPosts:3,404RM Data Scientist
Hi,
a similar chart is possbile. Marius did this once and told me how to do it. Sadly i forgot it
Cheers, Martin
- Sr. Director Data Solutions, Altair RapidMiner - Dortmund, Germany
0
MartinLiebigAdministrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University ProfessorPosts:3,404RM Data Scientist
Hi Sven! If you need this plot for your paper, i might programm a quick python snippet for it. Even though it might feel like code club:https://www.youtube.com/watch?v=a6FhAQsjRuk
- Sr. Director Data Solutions, Altair RapidMiner - Dortmund, Germany
Dear Martin, This wound be very kind of you. I looked at:https://plot.ly/python/heatmaps/but had to admit that I am only a anesthesiologist which means a human being with less brain volume compared to real data scientists! Cheers Sven
0
MartinLiebigAdministrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University ProfessorPosts:3,404RM Data Scientist
Hi,
attached is a process doing it on iris. I do not know how to get rid of the blue background color... Might need to think about it. It is a bit strange for me to write this kind of code again.
一定要有python扩展和matplotlib installed. I personally use Anaconda which is available for windows and mac. Please be careful running this on server, because it opens a dialogue and the process ends only if you close the dialogue
You can also save yourself the Python by using Advanced Charts.
Set the Domain to : C Set the Numerical Axis to : gamma Set the Color dimension to : Performance
Click on domain dimension & set it to Logarithmic Click on numerical axis & set it to Logarithmic
This will now give you little coloured dots, but really bigger dots would be nicer. Click on Numerical Axis -> Series: gamma & then click on Format -> Configure In this setting you can change from circle to square and then update the size of the square to whatever size looks good.
Hi, Without the background if you define the number of bins : for iris number of bins = 5 plt.hist2d(x,y,bins=5,weights=z,vmin=z.min(),vmax=z.max()) Information from:http://matplotlib.org/api/pyplot_api.html
Cheers Sven
0
MartinLiebigAdministrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University ProfessorPosts:3,404RM Data Scientist
So much regarding the
I amonlya anesthesiologist
thing.
Well done, thanks for sharing. Since you can pass macros to python, you might automate it by counting the number of different C/gamma values
- Sr. Director Data Solutions, Altair RapidMiner - Dortmund, Germany
0
MartinLiebigAdministrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University ProfessorPosts:3,404RM Data Scientist
Hi,
the process attached extracts the xbins and ybins automatically from the process. Might be useful The result is this:
Hi, The axis in this chart might be the number of bins, not the log10 c or log 10 gamma? I provide a link with the 2 charts I get using two processes provided by Martin. Although I prefer the the smoothing of colors, I think the values are not the log10 c and log10 gamma values. Any suggestions Cheers Sven https://www.dropbox.com/s/knrrummnwztsxlu/SVMCgammacompare.docx?dl=0
0
MartinLiebigAdministrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University ProfessorPosts:3,404RM Data Scientist
Oh,
you are completly right. Sorry for that. The python script below exports the correct min and max values. For a scientific publication i would not use the gaussian interpolation. It simply adds information which might not be there.
Unicorn
Answers
you can use a log operator and log C,gamma and performance. Than you can use standard charts on the log (in results view).
attached is a process on Iris. I use this optimize also as a building block.
Cheers,
Martin
<运营商激活= " true "类= compati“过程”bility="6.4.000" expanded="true" name="Process">
<连接from_op = "VM" from_port="model" to_port="model"/>
Dortmund, Germany
as usual, a clear and perfect solution.
Thanks, Have a nice weekend
Cheers
Sven
I suppose the following chart is impossible to generate in RM?
http://scikit-learn.org/0.10/_images/plot_svm_parameters_selection_1.png
Cheers
Sven
a similar chart is possbile. Marius did this once and told me how to do it. Sadly i forgot it
Cheers,
Martin
Dortmund, Germany
If you need this plot for your paper, i might programm a quick python snippet for it. Even though it might feel like code club:https://www.youtube.com/watch?v=a6FhAQsjRuk
Dortmund, Germany
This wound be very kind of you. I looked at:https://plot.ly/python/heatmaps/but had to admit that I am only a anesthesiologist which means a human being with less brain volume compared to real data scientists!
Cheers
Sven
attached is a process doing it on iris. I do not know how to get rid of the blue background color... Might need to think about it. It is a bit strange for me to write this kind of code again.
一定要有python扩展和matplotlib installed. I personally use Anaconda which is available for windows and mac.
Please be careful running this on server, because it opens a dialogue and the process ends only if you close the dialogue
Cheers,
Martin
<运营商激活= " true "类= compati“过程”bility="6.4.000" expanded="true" name="Process">
<连接from_op = "VM" from_port="model" to_port="model"/>
Dortmund, Germany
Martin,
Works perfect with Iris. Now try my own log file.
You made my day!
Thanks
Sven
You can also save yourself the Python by using Advanced Charts.
Set the Domain to : C
Set the Numerical Axis to : gamma
Set the Color dimension to : Performance
Click on domain dimension & set it to Logarithmic
Click on numerical axis & set it to Logarithmic
This will now give you little coloured dots, but really bigger dots would be nicer.
Click on Numerical Axis -> Series: gamma & then click on Format -> Configure
In this setting you can change from circle to square and then update the size of the square to whatever size looks good.
I have a look. Nice to give alternatives!
Have nice day.
Sven
Without the background if you define the number of bins : for iris number of bins = 5 plt.hist2d(x,y,bins=5,weights=z,vmin=z.min(),vmax=z.max())
Information from:http://matplotlib.org/api/pyplot_api.html
Cheers
Sven
Well done, thanks for sharing. Since you can pass macros to python, you might automate it by counting the number of different C/gamma values
Dortmund, Germany
the process attached extracts the xbins and ybins automatically from the process. Might be useful
The result is this:
<运营商激活= " true "类= compati“过程”bility="6.4.000" expanded="true" name="Process">
<连接from_op = "VM" from_port="model" to_port="model"/>
Dortmund, Germany
Thanks Martin, worked excellent for me!
Cheers
Sven
The axis in this chart might be the number of bins, not the log10 c or log 10 gamma?
I provide a link with the 2 charts I get using two processes provided by Martin.
Although I prefer the the smoothing of colors, I think the values are not the log10 c and log10 gamma values.
Any suggestions
Cheers
Sven
https://www.dropbox.com/s/knrrummnwztsxlu/SVMCgammacompare.docx?dl=0
you are completly right. Sorry for that. The python script below exports the correct min and max values. For a scientific publication i would not use the gaussian interpolation. It simply adds information which might not be there.
Cheers,
Martin
<运营商激活= " true "类= compati“过程”bility="6.4.000" expanded="true" name="Process">
<连接from_op = "VM" from_port="model" to_port="model"/>
Dortmund, Germany