<div dir="ltr">So there is no possibility to reach a consistency?</div><div class="gmail_extra"><br><div class="gmail_quote">2016-08-27 15:36 GMT+03:00 olologin <span dir="ltr"><<a href="mailto:olologin@gmail.com" target="_blank">olologin@gmail.com</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div bgcolor="#FFFFFF" text="#000000"><div><div class="h5">
<div>On 08/27/2016 02:19 PM,
<a href="mailto:elgesto@gmail.com" target="_blank">elgesto@gmail.com</a> wrote:<br>
</div>
<blockquote type="cite">
<div dir="ltr">Can I update the libsvm version by myself?</div>
<div class="gmail_extra"><br>
<div class="gmail_quote">2016-08-27 12:49 GMT+03:00 olologin <span dir="ltr"><<a href="mailto:olologin@gmail.com" target="_blank">olologin@gmail.com</a>></span>:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div bgcolor="#FFFFFF" text="#000000">
<div>
<div>
<div>On 08/27/2016 12:33 PM, <a href="mailto:elgesto@gmail.com" target="_blank">elgesto@gmail.com</a>
wrote:<br>
</div>
</div>
</div>
<blockquote type="cite">
<div>
<div>
<div dir="ltr">
<div class="gmail_quote">
<div dir="ltr">
<p>I have a project that is based on SVM
algorithm implemented by <a href="https://www.csie.ntu.edu.tw/%7Ecjlin/libsvm/" rel="nofollow" style="margin:0px;padding:0px;border:0px;color:rgb(0,89,153);text-decoration:none" target="_blank">libsvm</a>. Recently I
decided to try several other classification
algorithm, this is where <a href="http://scikit-learn.org/" rel="nofollow" style="margin:0px;padding:0px;border:0px;color:rgb(0,89,153);text-decoration:none" target="_blank">scikit-learn</a> comes to
the picture.</p>
<p>The connection to the scikit was pretty
straightforward, it supports libsvm format
by <code style="margin:0px;padding:1px 5px;border:0px;font-size:13px;font-family:Consolas,Menlo,Monaco,"Lucida Console","Liberation Mono","DejaVu Sans Mono","Bitstream Vera Sans Mono","Courier New",monospace,sans-serif;white-space:pre-wrap;background-color:rgb(239,240,241)">load_svmlight_file</code> routine.
Ans it's svm implementation is based on the
same libsvm.</p>
<p>When everything was done, I decided to the
check the consistence of the results by
directly running libsvm and via
scikit-learn, and the results were
different. Among 18 measures in learning
curves, 7 were different, and the difference
is located at the small steps of the
learning curve. The libsvm results seems
much more stable, but scikit-learn results
have some drastic fluctuation.</p>
<p>The classifiers have exactly the same
parameters of course. I tried to check the
version of libsvm in scikit-learn
implementation, but I din't find it, the
only thing I found was libsvm.so file.</p>
<p>Currently I am using libsvm 3.21 version,
and scikit-learn 0.17.1 version.</p>
<p>I wound appreciate any help in addressing
this issue.</p>
<p><br>
</p>
<pre style="margin-top:0px;margin-bottom:1em;padding:5px;border:0px;font-size:13px;width:auto;max-height:600px;overflow:auto;font-family:Consolas,Menlo,Monaco,"Lucida Console","Liberation Mono","DejaVu Sans Mono","Bitstream Vera Sans Mono","Courier New",monospace,sans-serif;word-wrap:normal;color:rgb(36,39,41);background-color:rgb(239,240,241)"><code style="margin:0px;padding:0px;border:0px;font-family:Consolas,Menlo,Monaco,"Lucida Console","Liberation Mono","DejaVu Sans Mono","Bitstream Vera Sans Mono","Courier New",monospace,sans-serif;white-space:inherit">size libsvm scikit-learn
1 0.1336239435355727 0.1336239435355727
2 0.08699516468193455 0.08699516468193455
3 0.32928301642777424 0.2117238289550198 #different
4 0.2835688734876902 0.2835688734876902
5 0.27846766962743097 0.26651875338163966 #different
6 0.2853854654662907 0.18898048915599963 #different
7 0.28196058132165136 0.28196058132165136
8 0.31473956032575623 0.1958710201604552 #different
9 0.33588303670653136 0.2101641630182972 #different
10 0.4075242509025311 0.2997807499800962 #different
15 0.4391771087975972 0.4391771087975972
20 0.3837789445609818 0.2713167833345173 #different
25 0.4252154334940311 0.4252154334940311
30 0.4256407777477492 0.4256407777477492
35 0.45314944605858387 0.45314944605858387
40 0.4278633233755064 0.4278633233755064
45 0.46174762022239796 0.46174762022239796
50 0.45370452524846866 0.45370452524846866</code></pre>
</div>
</div>
<br>
</div>
<br>
<fieldset></fieldset>
<br>
</div>
</div>
<pre>______________________________<wbr>_________________
scikit-learn mailing list
<a href="mailto:scikit-learn@python.org" target="_blank">scikit-learn@python.org</a>
<a href="https://mail.python.org/mailman/listinfo/scikit-learn" target="_blank">https://mail.python.org/mailma<wbr>n/listinfo/scikit-learn</a>
</pre>
</blockquote>
<p>This might be because current version of libsvm used in scikit is
3.10 from 2011. With some patch imported from upstream.
</p>
</div>
______________________________<wbr>_________________
scikit-learn mailing list
<a href="mailto:scikit-learn@python.org" target="_blank">scikit-learn@python.org</a>
<a href="https://mail.python.org/mailman/listinfo/scikit-learn" rel="noreferrer" target="_blank">https://mail.python.org/mailma<wbr>n/listinfo/scikit-learn</a>
</blockquote></div>
</div>
<fieldset></fieldset>
<pre>______________________________<wbr>_________________
scikit-learn mailing list
<a href="mailto:scikit-learn@python.org" target="_blank">scikit-learn@python.org</a>
<a href="https://mail.python.org/mailman/listinfo/scikit-learn" target="_blank">https://mail.python.org/<wbr>mailman/listinfo/scikit-learn</a>
</pre>
</blockquote></div></div><p>I don't think it is so easy, version which is used in scikit-learn has many additional modifications.</p><p>from header of svm.cpp:
/*
Modified 2010:
- Support for dense data by Ming-Fang Weng
- Return indices for support vectors, Fabian Pedregosa
<a href="mailto:fabian.pedregosa@inria.fr" target="_blank"><fabian.pedregosa@inria.fr></a>
- Fixes to avoid name collision, Fabian Pedregosa
- Add support for instance weights, Fabian Pedregosa based on work
by Ming-Wei Chang, Hsuan-Tien Lin, Ming-Hen Tsai, Chia-Hua Ho and
Hsiang-Fu Yu,
<a href="http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/#weights_for_data_instances" target="_blank"><http://www.csie.ntu.edu.tw/~<wbr>cjlin/libsvmtools/#weights_<wbr>for_data_instances></a>.
- Make labels sorted in svm_group_classes, Fabian Pedregosa.
*/
</p></div><br>______________________________<wbr>_________________<br>
scikit-learn mailing list<br>
<a href="mailto:scikit-learn@python.org">scikit-learn@python.org</a><br>
<a href="https://mail.python.org/mailman/listinfo/scikit-learn" rel="noreferrer" target="_blank">https://mail.python.org/<wbr>mailman/listinfo/scikit-learn</a><br>
<br></blockquote></div><br></div>