Randy Olson
Randy Olson
We plan to add it eventually, but we have many more high-priority issues to resolve before we touch this one. We are happy for you to start working on this...
Did anything ever come of this issue/PR? I notice that the hardcoded example is still in the code, and I also ran into it as a bug.
IMO the proposed solution to use a fixed query from the test split makes a lot of sense.
One of the scikit-MDR algorithms uses scikit-learn's [BaggingClassifier](http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.BaggingClassifier.html), which should be available in your installation of scikit-learn. What version of scikit-learn is installed? ```Python import sklearn print sklearn.__version__ ```
That explains it. The latest version of scikit-learn is 0.19, and the BaggingClassifier was probably added after 0.14.1. If you use the [Anaconda distribution](https://www.continuum.io/downloads), I believe they have scikit-learn up-to-date...
Hi @avilella, MDR can perform feature construction to compress some number of features down to a single feature. Theoretically, MDR could do so with thousands of features; practically, MDR works...
Great. I should note that scikit-rebate may take a while to run on a dataset with 200k features, but there is a `n_jobs` parameter that will allow it to use...
Good idea. Not sure if we have the bandwidth to get around to doing that anytime soon, but we'll keep it filed here in case anyone wants to take this...
I believe that's captured in #3.
Oh, I see. How would we accomplish that? Scrape from the README?