skopt.plots.plot_evaluations

skopt.plots.plot_evaluations(result, bins=20, dimensions=None, plot_dims=None, size=2, wspace=0.35, hspace=0.35, cmap='viridis', ax=None)

Visualize the order in which points were sampled during optimization.

This creates a 2-d matrix plot where the diagonal plots are histograms that show the distribution of samples for each search-space dimension.

The plots below the diagonal are scatter-plots of the samples for all combinations of search-space dimensions.

The order in which samples were evaluated is encoded in each point’s color.

A red star shows the best found parameters.

Parameters:

resultOptimizeResult

The optimization results from calling e.g. gp_minimize().

binsint, bins=20

Number of bins to use for histograms on the diagonal.

dimensionslist of str, default=None

Labels of the dimension variables. None defaults to space.dimensions[i].name, or if also None to ['X_0', 'X_1', ..].

plot_dimslist of str and int, default=None

List of dimension names or dimension indices from the search-space dimensions to be included in the plot. If None then use all dimensions except constant ones from the search-space.

sizefloat, default=2

Height (in inches) of each facet.

wspacefloat, default=0.35

The width of the padding between subplots, as a fraction of the average Axes width. Ignored if ax is provided.

hspacefloat, default=0.35

The height of the padding between subplots, as a fraction of the average Axes height. Ignored if ax is provided.

sizefloat, default=2

Height (in inches) of each facet.

cmap: str or Colormap, default = ‘viridis’

Color map for scatter plots. Passed directly to plt.scatter()

ax: `Matplotlib.Axes`, default= None

An axis object in which to plot the dependence plot.

Returns:

axMatplotlib.Axes

Matplotlib axis the plto was drawn in