Alessandro Mariani

yep - would be greatly appreciated, I have no idea how to configure scrapy!

unfortunately not :(

@lopuhin in regards of the BIAS, I wanted to comment [here](https://github.com/TeamHG-Memex/eli5/issues/166#issuecomment-343076325) but then noticed the issue is closed. Reading the [post](http://blog.datadive.net/interpreting-random-forests/) in the blog you've linked that comment my understanding...

I've just tried with the new push and indeed the nan problem is solved. the clock still remain though .. my C experience is very close to zero, so once...

I've tried with **APPLE**, **APPLE_CC**, **OSX** ... nothing :(

hehe, they all have the underscores... that's why is bold! I don't know the markup to prevent going bold, sorry :) I've tried adding #define **MACH** (with the underscores) but...

yey - I now got other error, I'll see if I can fix it by myself - thanks heaps Tianqi!!!

``` import pandas as pd import numpy as np import itertools def search_sorted_subsets_field(df, field, keywords): subsets = [] for keyword in keywords: left_bound = df[field].searchsorted(keyword,'left')[0] right_bound = df[field].searchsorted(keyword,'right')[0] if (right_bound-left_bound)...

Sorry - I was in rush yesterday so I couldn't explain in detail. If you increase the size of the DataFrame you'll start noticing significant change in performance. ``` In...

I wasn't aware of the slicer and how to use them - thanks! Although even using slicer and taking advantages of using sorted columns, is not as fast using "precompute...