<div dir="ltr">From my own casual benchmarks, the new scipy cKDTree is much faster than any of the scikit-learn options, though it still only supports axis-aligned euclidean-like metrics (where sklearn's BallTree supports dozens of additional metrics). The cKDTree also has a limited range of query types compared to scikit-learn's trees,<div>   Jake</div></div><div class="gmail_extra"><br clear="all"><div><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"> <font size="1">Jake VanderPlas</font></div><div dir="ltr"><font size="1"> Senior Data Science Fellow<br></font><div><div><font size="1"> Director of Research in Physical Sciences</font></div><div><font size="1"> </font><span style="font-size:x-small">University of Washington </span><span style="font-size:x-small">eScience Institute</span></div></div></div></div></div></div></div>
<br><div class="gmail_quote">On Mon, Sep 5, 2016 at 12:46 AM, Daπid <span dir="ltr"><<a href="mailto:davidmenhur@gmail.com" target="_blank">davidmenhur@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">On 4 September 2016 at 23:00, Robert Lucente <<a href="mailto:rlucente@pipeline.com">rlucente@pipeline.com</a>> wrote:<br>
> Please note that I am a newbie and just a lurker.<br>
><br>
> I noticed in a recent email that cKDTree was mentioned.<br>
><br>
> Q: What is the relationship if any between SciPy an scikit-learn when it comes to cKDTree?<br>
><br>
> The reason that I ask are the following 2 links<br>
><br>
> <a href="https://jakevdp.github.io/blog/2013/04/29/benchmarking-nearest-neighbor-searches-in-python/" rel="noreferrer" target="_blank">https://jakevdp.github.io/<wbr>blog/2013/04/29/benchmarking-<wbr>nearest-neighbor-searches-in-<wbr>python/</a><br>
><br>
> <a href="https://github.com/scikit-learn/scikit-learn/issues/3682" rel="noreferrer" target="_blank">https://github.com/scikit-<wbr>learn/scikit-learn/issues/3682</a><br>
<br>
</span>Note that these benchmarks are from 2013 and 2014. Scipy's KDTree has<br>
seen its performance recently improved, twice. Scikit's last update to<br>
its KDTree was in 2015. So, we need to run the benchmarks again.<br>
<br>
/David.<br>
<div class="HOEnZb"><div class="h5">______________________________<wbr>_________________<br>
SciPy-Dev mailing list<br>
<a href="mailto:SciPy-Dev@scipy.org">SciPy-Dev@scipy.org</a><br>
<a href="https://mail.scipy.org/mailman/listinfo/scipy-dev" rel="noreferrer" target="_blank">https://mail.scipy.org/<wbr>mailman/listinfo/scipy-dev</a><br>
</div></div></blockquote></div><br></div>