You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In the precision-recall curve plot, place recall on the x-axis and precision on the y-axis.
Motivation
In my experience, precision-recall curves with precision on the y-axis (ordinate) and recall on the x-axis (abscissa) are much more common than the other way around (i.e., how the plot is generated at the moment). A quick Google image search confirms this. And it is also the case in the sklearn implementation.
Pitch
Place recall on the x-axis and precision on the y-axis in PrecisionRecallCurve.plot()
Alternatives
Add an option to choose between both variants.
Additional context
Furthermore, an option for plotting the chance value similar to sklearn's plot_chance_level argument would be a welcome addition to the precision-recall curve plot.
The text was updated successfully, but these errors were encountered:
🚀 Feature
In the precision-recall curve plot, place recall on the x-axis and precision on the y-axis.
Motivation
In my experience, precision-recall curves with precision on the y-axis (ordinate) and recall on the x-axis (abscissa) are much more common than the other way around (i.e., how the plot is generated at the moment). A quick Google image search confirms this. And it is also the case in the sklearn implementation.
Pitch
Place recall on the x-axis and precision on the y-axis in
PrecisionRecallCurve.plot()
Alternatives
Add an option to choose between both variants.
Additional context
Furthermore, an option for plotting the chance value similar to sklearn's
plot_chance_level
argument would be a welcome addition to the precision-recall curve plot.The text was updated successfully, but these errors were encountered: