For generating performance profiles. This module is not in use (anymore or not yet?). **Example** .. plot:: :width: 75% import urllib import tarfile import glob from pylab import * import pickle import cocopp import cocopp.compall.ppperfprof import cocopp.bestalg # Collect and unarchive data dsets = {} for alg in cocopp.compall.ppperfprof.best: for date in ('2010', '2009'): try: dataurl = 'http://coco.lri.fr/BBOB'+date+'/pythondata/' + alg + '.tar.gz' filename, headers = urllib.urlretrieve(dataurl) archivefile = tarfile.open(filename) archivefile.extractall() # write to disc dsets[alg] = cocopp.load(glob.glob('BBOB'+date+'pythondata/' + alg + '/ppdata_f0*_20.pickle')) except: pass # plot the profiles figure() # cocopp.compall.ppperfprof.plotmultiple(dsets, dsref=cocopp.bestalg.bestAlgorithmEntries)
Function | beautify | Customize figure presentation. |
Function | plotmultiple | Generate performance profile figure. |
Function | plot | Generates a graph showing the performance profile of an algorithm. |
Function | main | Generates image files of the performance profiles of algorithms |
Generate performance profile figure. :param dict dictAlg: dictionary of :py:class:`DataSetList` instances one instance = one algorithm :param DataSetList dsref: reference data set :param seq targets: target function values :param bool istoolsstats: if True, uses bootstrapped distribution :param bool rhleg: if True, displays the right-hand legend
Generates a graph showing the performance profile of an algorithm. We display the empirical cumulative distribution function ECDF of the bootstrapped distribution of the average running time (aRT) for an algorithm to reach the function value :py:data:`targets` normalized by the aRT of the reference algorithm for these targets. :param DataSetList dsList: data set for one algorithm :param DataSetList dsref: reference data set for normalization :param seq targets: target function values :param dict kwargs: additional parameters provided to plot function. :returns: handles
Generates image files of the performance profiles of algorithms From a dictionary of :py:class:`DataSetList` sorted by algorithms, generates the performance profile (Moré:2008) on multiple functions for multiple targets altogether. :param dict dictAlg: dictionary of :py:class:`DataSetList` instances, one dataSetList :param list targets: target function values :param list order: sorted list of keys to dictAlg for plotting order