attribench.plot.ConvergencePlot

class attribench.plot.ConvergencePlot(df)[source]

Bases: Plot

Line plot of the median values of a given metric vs the number of samples. Error bars are computed using bootstrapping. Allows the user to inspect if metric values have converged, i.e. if the benchmark has been run on enough samples.

Parameters:
dfpd.DataFrame

Pandas dataframe containing the metric values. The columns are the names of the methods.

Methods

render

Render the plot.

render(title=None, figsize=(20, 20), fontsize=None, bs_samples=1000, interval=5)[source]

Render the plot.

Parameters:
titlestr | None, optional

Title of the figure, by default None

figsizeTuple[int, int], optional

Figure size, by default (20, 20)

fontsizeint | None, optional

Font size of x and y axis ticks, by default None

bs_samplesint, optional

Number of bootstrap samples for estimating the median value of the metric using a given sample size. By default 1000

intervalint, optional

Interval between sample sizes, by default 5

Returns:
Figure

The rendered Matplotlib figure.

Return type:

Figure