<div dir="auto">I have been using both in time-series classification. I put a exponential decay in sample_weights AND class weights as a dictionary. </div><div dir="auto"><br></div><div dir="auto">BR/Schots </div><div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">Em sex., 4 de dez. de 2020 às 12:01, Nicolas Hug <<a href="mailto:niourf@gmail.com">niourf@gmail.com</a>> escreveu:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div>
<p>Basically passing class weights should be equivalent to passing
per-class-constant sample weights.</p>
<p>> why do some estimators allow to pass weights both as a dict
in the init or as sample weights in fit? what's the logic?</p>
<p>SW is a per-sample property (aligned with X and y) so we avoid
passing those to init because the data isn't known when
initializing the estimator. It's only known when calling fit. In
general we avoid passing data-related info into init so that the
same instance can be fitted on any data (with different number of
samples, different classes, etc.).<br>
</p>
<p>We allow to pass class_weight in init because the 'balanced'
option is data-agnostic. Arguably, allowing a dict with actual
class values violates the above argument (of not having
data-related stuff in init), so I guess that's where the logic
ends ;)</p>
<p>As to why one would use both, I'm not so sure honestly.</p></div><div><p><br>
</p>
<p>Nicolas<br>
</p>
<p><br>
</p>
<div>On 12/4/20 10:40 AM, Sole Galli via
scikit-learn wrote:<br>
</div>
<blockquote type="cite">
<div>Actually, I found the answer. Both seem to be optimising the
loss function for the various algorithms, below I include some
links.<br>
</div>
<div><br>
</div>
<div> If, we pass <b>class_weight</b> and <b>sample_weight,</b>
then the final cost / weight is a combination of both.<br>
</div>
<div><br>
</div>
<div>I have a follow up question: in which scenario would we use
both? why do some estimators allow to pass weights both as a
dict in the init or as sample weights in fit? what's the logic?
I found it a bit confusing at the beginning.<br>
</div>
<div><br>
</div>
<div>Thank you!<br>
</div>
<div><br>
</div>
<div><a href="https://stackoverflow.com/questions/30805192/scikit-learn-random-forest-class-weight-and-sample-weight-parameters" target="_blank">https://stackoverflow.com/questions/30805192/scikit-learn-random-forest-class-weight-and-sample-weight-parameters</a><br>
</div>
<div><br>
</div>
<div><a href="https://stackoverflow.com/questions/30972029/how-does-the-class-weight-parameter-in-scikit-learn-work/30982811#30982811" target="_blank">https://stackoverflow.com/questions/30972029/how-does-the-class-weight-parameter-in-scikit-learn-work/30982811#30982811</a><br>
</div>
<div><br>
</div>
<div>
<div>
<div>Soledad Galli<br>
</div>
<div><a href="https://www.trainindata.com/" target="_blank">https://www.trainindata.com/</a><br>
</div>
</div>
<div><br>
</div>
</div>
<div><br>
</div>
<div>‐‐‐‐‐‐‐ Original Message ‐‐‐‐‐‐‐<br>
</div>
<div> On Thursday, December 3, 2020 11:55 AM, Sole Galli via
scikit-learn <a href="mailto:scikit-learn@python.org" target="_blank"><scikit-learn@python.org></a> wrote:<br>
</div>
<div> <br>
</div>
<blockquote type="cite">
<div>Hello team,<br>
</div>
<div><br>
</div>
<div>What is the difference in the implementation of
class_weight and sample_weight in those algorithms that
support both? like random forest or logistic regression?<br>
</div>
<div><br>
</div>
<div>Are both modifying the loss function? in a similar way?<br>
</div>
<div><br>
</div>
<div>Thank you!<br>
</div>
<div><br>
</div>
<div>Sole<br>
</div>
<div>
<div><br>
</div>
</div>
<div><br>
</div>
</blockquote>
<div><br>
</div>
<br>
<fieldset></fieldset>
<pre>_______________________________________________
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/mailman/listinfo/scikit-learn</a>
</pre>
</blockquote>
</div>
_______________________________________________<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/mailman/listinfo/scikit-learn</a><br>
</blockquote></div></div>-- <br><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature">Schots</div>