Sebastian Raschka
Sebastian Raschka
Hi there. As far as I know, the `early_stopping` parameter was added in scikit-learn 0.20. So, my possible explanation for this error could be that the pickle file of the...
hm, that's weird. Sounds like it's a bug in Chrome!? Don't have Chrome installed, but it's not an issue on Safari, Firefox, and Opera. Also, have you tried force reloading...
Ah, good catch! Thanks a lot!
> also the RL chapter is still great, but feels rushed in comparison with whole book, maybe a bit more love to it on 4th ed? xx Oh yeah for...
Good catch. Sorry about that and thanks for the feedback. We will fix that in the next edition
> (p159) In first Eq., \Sigma_i = \frac{1}{n_i} S_W should be \Sigma_i = \frac{1}{n_i} S_i Hm, in my version this already looks correct. I think we fixed that in a...
Thanks! Will update in the next edition!
Thanks for the note. It's been a few years ago, but I vaguely remember this issue. I believe we had fixed that in the 3rd edition: https://github.com/rasbt/python-machine-learning-book-3rd-edition/blob/master/ch15/ch15_part1.ipynb
You are right. Arg, yeah, the /s shouldn't be there. Probably didn't notice due to setting `s=1`. Need to check this more thoroughly and update it. I will add a...
Thanks for the note! In my version, it's not ```python indices = np.argsort(importances[::-1]) ``` but ```python indices = np.argsort(importances)[::-1] ``` which would be similar to what you suggested with `indices...