Generates figure of the bootstrap distribution of aRT.
The main method in this module generates figures of Empirical
Cumulative Distribution Functions of the bootstrap distribution of
the Average Running Time (aRT) divided by the dimension for many
algorithms.
The outputs show the ECDFs of the running times of the simulated runs
divided by dimension for 50 different targets logarithmically uniformly
distributed in [1e−8, 1e2]. The crosses (×) give the median number of
function evaluations of unsuccessful runs divided by dimension.
**Example**
.. plot::
:width: 50%
import cocopp
# Empirical cumulative distribution function of bootstrapped aRT figure
ds = cocopp.load(cocopp.bbob.get('2009/BIPOP-CMA-ES'))
figure()
cocopp.compall.pprldmany.plot(ds) # must rather call main instead of plot?
cocopp.compall.pprldmany.beautify()
| Function | plt_plot | Undocumented |
| Function | beautify | Customize figure presentation. |
| Function | plotdata | Draw a normalized ECDF. What means normalized? |
| Function | plotLegend | Display right-side legend. |
| Function | plot | This function is obsolete? Generates a graph of the run length distribution of an algorithm. |
| Function | all_single_functions | Undocumented |
| Function | main | Generates a figure showing the performance of algorithms. |
| Parameters | seq data | data set, a 1-D ndarray of runlengths |
| float maxval | right-most value to be displayed, will use the largest non-inf, non-nan value in data if not provided | |
| seq maxevals | if provided, will plot the median of this sequence as a single cross marker | |
| float CrE | Crafting effort the data will be multiplied by the exponential of this value. | |
| kwargs | optional arguments provided to plot function. |
Display right-side legend.
The figure is stopped at maxval (upper x-bound), and the graphs in the figure are prolonged with straight lines to the right to connect with labels of the graphs (uniformly spread out vertically). The order of the graphs at the upper x-bound line give the order of the labels, in case of ties, the best is the graph for which the x-value of the first step (from the right) is smallest.
The annotation string is stripped from preceeding pathnames.
| Parameters | float maxval | rightmost x boundary |
| Returns | list of (ordered) labels and handles. | |
This function is obsolete?
Generates a graph of the run length distribution of an algorithm.
We display the empirical cumulative distribution function ECDF of
the bootstrapped distribution of the runlength for an algorithm
(in number of function evaluations) to reach the target functions
value :py:data:`targets`.
:param DataSetList dsList: data set for one algorithm
:param seq targets: target function values
:param float crafting effort: the data will be multiplied by the
exponential of this value
:param dict kwargs: additional parameters provided to plot function.
:returns: handles
Generates a figure showing the performance of algorithms.
From a dictionary of :py:class:`DataSetList` sorted by algorithms,
generates the cumulative distribution function of the bootstrap
distribution of aRT for algorithms on multiple functions for
multiple targets altogether.
:param dict dictAlg: dictionary of :py:class:`DataSetList` instances
one instance is equivalent to one algorithm,
:param list targets: target function values
:param list order: sorted list of keys to dictAlg for plotting order
:param str outputdir: output directory
:param str info: output file name suffix
:param str parentHtmlFileName: defines the parent html page