Please, did anyone try to run CHAID algorithm on continuous predictors ??
At first, I used SPSS Modeler and it worked fine.
but when I tried it on Python 3.6, it didn't work for me.
Thanks :)
P.S. CHAID package could be found here :
https://github.com/Rambatino/CHAID
I'm the author of that library.
It's usually better to post on the issues tab on the github repo as questions have more visibility there.
Unfortunately, with regards to continuous predictors, they need to be binned first before they can be run using CHAID. We haven't implemented a binning strategy as it's very subjective (SPSS makes a lot of decisions under the hood).
Related
I've found online the toolbox bumps (https://pypi.org/project/bumps/) which looks like a well-rounded and easy to use approach to fit data.
I'm interested to fit data described by two coupled ODEs, but, unfortunately, I haven't found any information regarding this procedure on the docs (https://bumps.readthedocs.io/en/latest/index.html).
Does anyone know how to do it?
Thanks in advance
I've ask to the developer on GitHub and he provided two complete examples.
Here the link: https://github.com/bumps/bumps/issues/26
I would like to know how post hoc tests are performed with Python
(I have estimated a parameter by different independent experiments, obtaining a value with uncertainty from each fit).
Thanks in advance
Have you looking into the statsmodels package? Something like statsmodels.stats.multicomp.pairwise_tukeyhsd (https://www.statsmodels.org/dev/generated/statsmodels.stats.multicomp.pairwise_tukeyhsd.html) might be what you need
Does anyone know a python library which has online PCA estimations (something similar to what is described in this paper online PCA)
Does it make sense to use the sklearn.decomposition.IncrementalPCA method with batch_size =1.
You can check this out:
https://github.com/flatironinstitute/online_psp
It is not exactly PCA since components might be not orthogonal (you can easily orthogonalize them at need, there is also an object method to do so)
Cheers
DISCLAIMER: I am one of the developers of this project.
So mixed-effects regression model is used when I believe that there is dependency with a particular group of a feature. I've attached the Wiki link because it explains better than me. (https://en.wikipedia.org/wiki/Mixed_model)
Although I believe that there are many occasions in which we need to consider the mixed-effects, there aren't too many modules that support this.
R has lme4 and Python seems to have a similar module, but they are both statistic driven; they do not use the cost function algorithm such as gradient boosting.
In Machine Learning setting, how would you handle the situation that you need to consider mixed-effects? Are there any other models that can handle longitudinal data with mixed-effects(random-effects)?
(R seems to have a package that supports mixed-effects: https://rd.springer.com/article/10.1007%2Fs10994-011-5258-3
But I am looking for a Python solution.
There are, at least, two ways to handle longitudinal data with mixed-effects in Python:
StatsModel for linear mixed effects;
MERF for mixed effects random forest.
If you go for StatsModel, I'd recommend you to do some of the examples provided here. If you go for MERF, I'd say that the best starting point is here.
I hope it helps!
Is there anyone that has some ideas on how to implement the AdaBoost (Boostexter) algorithm in python?
Cheers!
It looks as if the sdpy project has an AdaBoost implementation. Specifically look at the sdpy/cs/ml/cla/boosting.py file.
Perhaps you can get some motivation from there.
Thanks a million Steve! In fact, your suggestion had some compatibility issues with MacOSX (a particular library was incompatible with the system) BUT it helped me find out a more interesting package : icsi.boost.macosx. I am just denoting that in case any Mac-eter finds it interesting!
Thank you again!
Tim