<html><head></head><body><div style="font-family:Helvetica Neue, Helvetica, Arial, sans-serif;font-size:16px;"><div style="font-family:Helvetica Neue, Helvetica, Arial, sans-serif;font-size:16px;"><div><div>Hi Stuart</div><div><br></div><div>Thanks ;-)</div><div><br></div><div><span><span style="font-family: "Helvetica Neue", Helvetica, Arial, sans-serif;">Activation threshold is in our plan and will be added in next release (in the <span>next few weeks</span>)</span></span><br></div><div><br></div><div><br></div><div class="ydpcb212fd8signature">Best Regards</div><div class="ydpcb212fd8signature">Sepand Haghighi</div></div>
<div><br></div><div><br></div>
</div><div id="ydp1f6c6b2eyahoo_quoted_8179037584" class="ydp1f6c6b2eyahoo_quoted">
<div style="font-family:'Helvetica Neue', Helvetica, Arial, sans-serif;font-size:13px;color:#26282a;">
<div>
On Thursday, May 31, 2018, 9:56:43 PM GMT+4:30, Stuart Reynolds <stuart@stuartreynolds.net> wrote:
</div>
<div><br></div>
<div><br></div>
<div><div dir="ltr">Hi Sepand,<br clear="none"><br clear="none">Thanks for this -- looks useful. I had to write something similar (for<br clear="none">the binary case) and wish scikit had something like this.<br clear="none"><br clear="none">I wonder if there's something similar for the binary class case where,<br clear="none">the prediction is a real value (activation) and from this we can also<br clear="none">derive<br clear="none"> - CMs for all prediction cutoff (or set of cutoffs?)<br clear="none"> - scores over all cutoffs (AUC, AP, ...)<br clear="none"><br clear="none">For me, in analyzing (binary class) performance, reporting scores for<br clear="none">a single cutoff is less useful than seeing how the many scores (tpr,<br clear="none">ppv, mcc, relative risk, chi^2, ...) vary at various false positive<br clear="none">rates, or prediction quantiles.<br clear="none">Does your library provide any tools for the binary case where we add<br clear="none">an activation threshold?<br clear="none"><br clear="none">Thanks again for releasing this and providing pip packaging.<br clear="none">- Stuart<br clear="none"><br clear="none"><div class="ydp1f6c6b2eyqt0308824405" id="ydp1f6c6b2eyqtfd84665"><br clear="none">On Thu, May 31, 2018 at 6:05 AM, Sepand Haghighi via scikit-learn<br clear="none"><<a shape="rect" href="mailto:scikit-learn@python.org" rel="nofollow" target="_blank">scikit-learn@python.org</a>> wrote:<br clear="none">> PyCM is a multi-class confusion matrix library written in Python that<br clear="none">> supports both input data vectors and direct matrix, and a proper tool for<br clear="none">> post-classification model evaluation that supports most classes and overall<br clear="none">> statistics parameters. PyCM is the swiss-army knife of confusion matrices,<br clear="none">> targeted mainly at data scientists that need a broad array of metrics for<br clear="none">> predictive models and an accurate evaluation of large variety of<br clear="none">> classifiers.<br clear="none">><br clear="none">> Github Repo : <a shape="rect" href="https://github.com/sepandhaghighi/pycm" rel="nofollow" target="_blank">https://github.com/sepandhaghighi/pycm</a><br clear="none">><br clear="none">> Webpage : <a shape="rect" href="http://pycm.shaghighi.ir/" rel="nofollow" target="_blank">http://pycm.shaghighi.ir/</a><br clear="none">><br clear="none">> JOSS Paper : <a shape="rect" href="https://doi.org/10.21105/joss.00729" rel="nofollow" target="_blank">https://doi.org/10.21105/joss.00729</a></div><br clear="none">><br clear="none">><br clear="none">><br clear="none">><br clear="none">><br clear="none">><br clear="none">><br clear="none">><br clear="none">><br clear="none">> _______________________________________________<br clear="none">> scikit-learn mailing list<br clear="none">> <a shape="rect" href="mailto:scikit-learn@python.org" rel="nofollow" target="_blank">scikit-learn@python.org</a><br clear="none">> <a shape="rect" href="https://mail.python.org/mailman/listinfo/scikit-learn" rel="nofollow" target="_blank">https://mail.python.org/mailman/listinfo/scikit-learn</a><div class="ydp1f6c6b2eyqt0308824405" id="ydp1f6c6b2eyqtfd84282"><br clear="none">><br clear="none"></div></div></div>
</div>
</div></div></body></html>