<div dir="ltr">OK, thanks, that looks interesting. I really should get into Python.. would be great if this could work with raster data as input, e.g., for species distribution modelling. I can imagine that this might be a (faster) alternative to modelling in R (especially the model projection part, which can be a bit problematic in R for large data sets).<br>
</div><div class="gmail_extra"><br><br><div class="gmail_quote">On Wed, May 14, 2014 at 9:55 AM, Moritz Lennert <span dir="ltr"><<a href="mailto:mlennert@club.worldonline.be" target="_blank">mlennert@club.worldonline.be</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div class="HOEnZb"><div class="h5">On 13/05/14 22:27, Paulo van Breugel wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Does anybody have experience with the scikit-learn toolkit? It seems<br>
like a very extensive tool set for machine learning in Python. I have no<br>
experience in programming in Python, so I cannot really judge how<br>
difficult it would be to call functions from this tool set in GRASS, but<br>
if possible, that would be great.<br>
</blockquote>
<br></div></div>
Pietro used scikit-learn for object-based classification:<br>
<br>
<a href="https://svn.osgeo.org/grass/grass-addons/grass7/vector/v.class.ml/" target="_blank">https://svn.osgeo.org/grass/<u></u>grass-addons/grass7/vector/v.<u></u>class.ml/</a><br>
<br>
See it mentioned here:<br>
<br>
<a href="http://lists.osgeo.org/pipermail/grass-dev/2014-January/066804.html" target="_blank">http://lists.osgeo.org/<u></u>pipermail/grass-dev/2014-<u></u>January/066804.html</a><span class="HOEnZb"><font color="#888888"><br>
<br>
Moritz<br>
</font></span></blockquote></div><br></div>