2012/2/27 Mathieu Blondel <[email protected]>:
> Hi Jake,
>
> The section on bias / variance is great! I'm gonna read the rest of
> the materials later but this looks really interesting.

The section on bias / variance trade off is indeed great. However I am
not sure whether the attendee of the pydata workshop would like to
learn about those (important concepts) or would rather like see
scikit-learn in action.

Also the manifold section might be a bit too mathematical for a
general programmer audience that might have forgotten the math classes
from college.

2 improvements:

- in the section on General concepts: drop the useless header for
http://jakevdp.github.com/tutorial/astronomy/general_concepts.html#general-concepts
  that will make the general toc tree more balanced / informative:
  http://jakevdp.github.com/tutorial/astronomy/index.html

- in this chart: http://jakevdp.github.com/_images/plot_ML_flow_chart_2.png

  the API called on the test set should be X_new =
vec.transform(input) instead of fit_transform

Very interesting red by the way.

# Unlocked achievement: Quasar Recognition #

-- 
Olivier
http://twitter.com/ogrisel - http://github.com/ogrisel

------------------------------------------------------------------------------
Try before you buy = See our experts in action!
The most comprehensive online learning library for Microsoft developers
is just $99.99! Visual Studio, SharePoint, SQL - plus HTML5, CSS3, MVC3,
Metro Style Apps, more. Free future releases when you subscribe now!
http://p.sf.net/sfu/learndevnow-dev2
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general

Reply via email to