<div dir="ltr"><div><div>SubSample would remove a lot of information from the negative class.<br></div>I have more than 500 samples of negative class and just 5 samples of positive class.<br><br></div>Amita<br></div><div class="gmail_extra"><br><div class="gmail_quote">On Thu, Aug 4, 2016 at 4:43 PM, Nicolas Goix <span dir="ltr"><<a href="mailto:goix.nicolas@gmail.com" target="_blank">goix.nicolas@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div>Hi,</div><div><br></div>Yes you can use your labeled data (you will need to sub-sample your normal class to have similar proportion normal-abnormal) to learn your hyper-parameters through CV.<div><br></div><div>You can also try to use supervised classification algorithms on `not too highly unbalanced' sub-samples.</div><div><br></div><div>Nicolas</div></div><div class="gmail_extra"><br><div class="gmail_quote"><div><div class="h5">On Thu, Aug 4, 2016 at 5:17 PM, Amita Misra <span dir="ltr"><<a href="mailto:amisra2@ucsc.edu" target="_blank">amisra2@ucsc.edu</a>></span> wrote:<br></div></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div><div class="h5"><div dir="ltr">Hi,<br><div class="gmail_quote"><div dir="ltr"><div><div><div><div><div><div><div><br></div><div>I am currently exploring the problem of speed bump detection using accelerometer time series data.<br></div>I have extracted some features based on mean, std deviation etc within a time window.<br><br></div>Since the dataset is highly skewed ( I have just 5 positive samples for every > 300 samples)<br></div>I was looking into <br><br>One ClassSVM <br>covariance.EllipticEnvelope<br>sklearn.ensemble.IsolationFore<wbr>st<br><p>but I am not sure how to use them. <br></p><p>What I get from docs<br></p>separate the positive examples and train using only negative examples<br><pre><span>clf</span><span>.</span><span>fit</span><span>(</span><span>X_train</span><span>)</span></pre>and then<br>predict the positive examples using<br>clf.predict(X_test)<br><br></div><br>I am not sure what is then the role of positive examples in my training dataset or how can I use them to improve my classifier so that I can predict better on new samples.<br><br><br></div><div>Can we do something like Cross validation to learn the parameters as in normal binary SVM classification<br></div><br></div>Thanks,?<br></div>Amita<span><font color="#888888"><br><div><div><div><br><div><div><div><div><div><div data-smartmail="gmail_signature"><div dir="ltr"><div>Amita Misra<div><div>Graduate Student Researcher</div><div>Natural Language and Dialogue Systems Lab</div><div>Baskin School of Engineering</div><div>University of California Santa Cruz</div></div></div><div><br></div></div></div>
</div></div></div></div></div></div></div></div></font></span></div><span><font color="#888888">
<br></font></span></div><span><font color="#888888"><br><br clear="all"><br>-- <br><div data-smartmail="gmail_signature"><div dir="ltr"><div>Amita Misra<div><div>Graduate Student Researcher</div><div>Natural Language and Dialogue Systems Lab</div><div>Baskin School of Engineering</div><div>University of California Santa Cruz</div></div></div><div><br></div></div></div>
</font></span></div>
<br></div></div>______________________________<wbr>_________________<br>
scikit-learn mailing list<br>
<a href="mailto:scikit-learn@python.org" target="_blank">scikit-learn@python.org</a><br>
<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><br>
<br></blockquote></div><br></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><br clear="all"><br>-- <br><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div>Amita Misra<div><div>Graduate Student Researcher</div><div>Natural Language and Dialogue Systems Lab</div><div>Baskin School of Engineering</div><div>University of California Santa Cruz</div></div></div><div><br></div></div></div>
</div>