Here's a hacky way that worked for me to get started with scikits.learning under Mac OS X:<div>1. Install Sage <<a href="http://www.sagemath.org/">http://www.sagemath.org/</a>>. (I dropped it in /Applications as suggested in the docs.) This brings with it its own custom Python system with all of the dependencies present already -- numpy, scipy, matplotlib and associated libraries.</div>
<div><br></div><div>2. Download the source for scikits.learn <<a href="http://sourceforge.net/projects/scikit-learn/files/">http://sourceforge.net/projects/scikit-learn/files/</a>> and unpack them:</div><div>$ tar zxvf scikits.learn-0.5.tar.gz</div>
<div><br></div><div>3. Set PYTHONPATH to point to Sage's local directory: (I think this may not be necessary.)</div><div>$ export PYTHONPATH=/Applications/sage/local/lib/python/site-packages/</div><div><br></div><div>
4. Change into scikits.learn source directory and build, using the sage frontend (which I guess is just a souped up Python interpreter):</div><div>$ cd scikits.learn-0.5</div><div>$ /Applications/sage/sage setup.py install</div>
<div><br></div><div>5. Try it out</div><div><meta charset="utf-8">$ /Applications/sage/sage</div><div>Despite having the "sage:" prompt, you still have a Python interpreter there to play with. The logistic regression example here <<a href="http://scikit-learn.sourceforge.net/auto_examples/logistic_l1_l2_coef.html">http://scikit-learn.sourceforge.net/auto_examples/logistic_l1_l2_coef.html</a>> worked for me with no modification. (I haven't gotten a chance to go through the actual examples for our class, but I'm hopeful that if this works so will probably most other stuff.)</div>
<div><br><div class="gmail_quote">On Wed, Oct 27, 2010 at 6:12 PM, Mike Schachter <span dir="ltr"><<a href="mailto:mike@mindmech.com">mike@mindmech.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
I posted the code to ml-noisebridge's sourceforge git repository. It<br>probably needs some more work, but you can find it in the scikits.linear<br>subdirectory of this repo:<br><br><code>git clone git://<a href="http://ml-noisebridge.git.sourceforge.net/gitroot/ml-noisebridge/ml-noisebridge" target="_blank">ml-noisebridge.git.sourceforge.net/gitroot/ml-noisebridge/ml-noisebridge</a><br>
<br><br></code><div><div></div><div class="h5"><br><div class="gmail_quote">On Wed, Oct 27, 2010 at 5:06 PM, Mike Schachter <span dir="ltr"><<a href="mailto:mike@mindmech.com" target="_blank">mike@mindmech.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0pt 0pt 0pt 0.8ex;border-left:1px solid rgb(204, 204, 204);padding-left:1ex">
Two more things:<br><br>Don't forget to install scipy:<br><br><a href="http://www.scipy.org/" target="_blank">http://www.scipy.org/</a><br><br>And by "linear classification" i actually meant "comparing<br>
support vector machines and k-nearest neighbors"<div><div></div><div><br>
<br><br><br><br><br><div class="gmail_quote">On Wed, Oct 27, 2010 at 12:14 PM, Mike Schachter <span dir="ltr"><<a href="mailto:mike@mindmech.com" target="_blank">mike@mindmech.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0pt 0pt 0pt 0.8ex;border-left:1px solid rgb(204, 204, 204);padding-left:1ex">
There are some prerequisites:<br><br>Python 2.5+<br><br>Numpy: <a href="http://numpy.scipy.org/" target="_blank">http://numpy.scipy.org/</a><br><br>Matplotlib: <a href="http://matplotlib.sourceforge.net/" target="_blank">http://matplotlib.sourceforge.net/</a><br>
<br>scikits.learn: <a href="http://scikit-learn.sourceforge.net/" target="_blank">http://scikit-learn.sourceforge.net/</a><br><br>Try to have these installed before we get started.<br><font color="#888888"> <br> mike</font><div>
<div></div><div><br><br><br><br><br><div class="gmail_quote">
On Tue, Oct 26, 2010 at 2:08 PM, Mike Schachter <span dir="ltr"><<a href="mailto:mike@mindmech.com" target="_blank">mike@mindmech.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0pt 0pt 0pt 0.8ex;border-left:1px solid rgb(204, 204, 204);padding-left:1ex">
Hey everyone,<br><br>Tomorrow I'll be guiding an impromptu workshop with<br>scikits.learn. We'll use a sample dataset and try our<br>hands at classifying it with linear classifiers and perhaps<br>even support vector machines. See you there!<br>
<br><a href="http://scikit-learn.sourceforge.net/" target="_blank">http://scikit-learn.sourceforge.net/</a><br><font color="#888888"><br> mike<br><br>
</font></blockquote></div><br>
</div></div></blockquote></div><br>
</div></div></blockquote></div><br>
</div></div><br>_______________________________________________<br>
ml mailing list<br>
<a href="mailto:ml@lists.noisebridge.net">ml@lists.noisebridge.net</a><br>
<a href="https://www.noisebridge.net/mailman/listinfo/ml" target="_blank">https://www.noisebridge.net/mailman/listinfo/ml</a><br>
<br></blockquote></div><br></div>