<html><head></head><body><div dir="auto">I think that the vocabulary mismatch comes from the fact that you are looking at these terms thinking about in sample statistics, while they are used here in the context of prediction. I think that in the context of prediction, these are the right terms. <br><br></div>
<div dir="auto">Cheers,<br><br></div>
<div dir="auto">Gaël<br><br></div>
<div dir="auto"><!-- tmjah_g_1299s -->Sent from my phone. Please forgive typos and briefness.<!-- tmjah_g_1299e --></div>
<div class="gmail_quote" >On Aug 7, 2018, at 10:40, Fellype via scikit-learn <<a href="mailto:scikit-learn@python.org" target="_blank">scikit-learn@python.org</a>> wrote:<blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
<div style="font-family:times new roman, new york, times, serif;font-size:16px;"><div style="font-family:times new roman, new york, times, serif;font-size:16px;">Dear maintainers,</div><div style="font-family:times new roman, new york, times, serif;font-size:16px;">I've just known scikit-learn and found it very useful. Congratulations for this library.</div><div style="font-family:times new roman, new york, times, serif;font-size:16px;"><br></div><div style="font-family:times new roman, new york, times, serif;font-size:16px;">I found some confuse terms to describe r2_score parameters in documentation [1]. For me, the meanings of<span> <span>y_true and <span><span>y_pred</span></span></span></span> are not clear. From [1]:</div><div style="font-family:times new roman, new york, times, serif;font-size:16px;">- <span><span><span>y_true</span></span>: ... Ground truth (correct) target values</span></div><div style="font-family:times new roman, new york, times, serif;font-size:16px;">- <span></span><span><span><span><span>y_pred: ... <span>Estimated target values</span></span></span></span></span></div><div style="font-family:times new roman, new york, times, serif;font-size:16px;"><span><span><span><span><span><br></span></span></span></span></span></div><div style="font-family:times new roman, new york, times, serif;font-size:16px;"><span><span><span><span><span>Since the R^2 value is usually used to compare the behavior of experimental data (observed) with a theoretical model or standard data (expected), I guess that it would be better to change the description of<span> <span>y_true and <span><span>y_pred</span></span></span></span> to something like:<span><div style="font-family:times new roman, new york, times, serif;font-size:16px;">- <span><span><span>y_true</span></span>: ... Observed (or measured) target values</span></div></span></span></span></span></span></span><div><span><span><span><span><span><span><div style="font-family:times new roman, new york, times, serif;font-size:16px;">- <span></span><span><span><span><span>y_pred: ... Expected<span> (or theoretical) target values</span></span></span></span></span></div></span></span></span></span></span></span></div><div><br></div><div> <span><span id="ydpbdd6ad67result_box" class="ydpbdd6ad67short_text" lang="en"><span>I also think that</span></span></span> the same should be done in documentation of other <span>scikit-learn</span> functions that use the <span><span><span>y_true and <span><span>y_pred</span></span></span></span></span> terms with the same meaning.<br></div><div><br></div><div>Thanks for your attention and best wishes.</div><div><br></div><div>Fellype<br></div><br></div><div style="font-family:times new roman, new york, times, serif;font-size:16px;">[1] <a href="http://scikit-learn.org/stable/modules/generated/sklearn.metrics.r2_score.html" rel="nofollow" target="_blank">http://scikit-learn.org/stable/modules/generated/sklearn.metrics.r2_score.html</a></div></div><pre class="blue"><hr><br>scikit-learn mailing list<br>scikit-learn@python.org<br><a href="https://mail.python.org/mailman/listinfo/scikit-learn">https://mail.python.org/mailman/listinfo/scikit-learn</a><br></pre></blockquote></div></body></html>