def test_aes(self): gp = ggplot2.ggplot(mtcars) gp += ggplot2.aes(x='wt', y='mpg') gp += ggplot2.geom_point() assert isinstance(gp, ggplot2.GGPlot) gp = ggplot2.ggplot(mtcars) gp += ggplot2.aes('wt', 'mpg') gp += ggplot2.geom_point() assert isinstance(gp, ggplot2.GGPlot)
def bargraph_language(cfg, values): r = robjects.r for lang in cfg.languages: times = [] varss = [] probs = [] ses = [] for prob in cfg.problems: for var in cfg.variations: # we use the pretty names to make the varss.append(pretty_varis[var]) probs.append(prob) data = FloatVector(values[prob][var][lang][0]) times.append(r['mean'](data)[0]) t_result = r['t.test'](data, **{ " conf.level": 0.999 }).rx('conf.int')[0] ses.append((t_result[1] - t_result[0]) / 2) r.pdf('bargraph-executiontime-lang-' + lang + '.pdf', height=pdf_height(), width=pdf_width()) df = robjects.DataFrame({ 'Variation': StrVector(varss), 'Problem': StrVector(probs), 'Time': FloatVector(times), 'SE': FloatVector(ses) }) limits = ggplot2.aes(ymax='Time + SE', ymin='Time - SE') dodge = ggplot2.position_dodge(width=0.9) gp = ggplot2.ggplot(df) pp = gp + \ ggplot2.aes_string (x='Problem', y='Time', fill='Variation') + \ ggplot2.geom_bar (position='dodge', stat='identity') + \ ggplot2.geom_errorbar (limits, position=dodge, width=0.25) + \ ggplot2_options () + \ ggplot2_colors () + \ robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\ robjects.r('ylab("Execution time (in seconds)")') pp.plot() r['dev.off']()
def bargraph_language (cfg, values): r = robjects.r for lang in cfg.languages: times = [] varss = [] probs = [] ses = [] for prob in cfg.problems: for var in cfg.variations: # we use the pretty names to make the varss.append (pretty_varis [var]) probs.append (prob) data = FloatVector (values[prob][var][lang][0]) times.append (r['mean'] (data)[0]) t_result = r['t.test'] (data, **{" conf.level": 0.999}).rx ('conf.int')[0] ses.append ((t_result[1] - t_result[0])/2) r.pdf ('bargraph-executiontime-lang-' + lang + '.pdf', height=pdf_height (), width=pdf_width ()) df = robjects.DataFrame({'Variation': StrVector (varss), 'Problem': StrVector (probs), 'Time' : FloatVector (times), 'SE' : FloatVector (ses) }) limits = ggplot2.aes (ymax = 'Time + SE', ymin = 'Time - SE') dodge = ggplot2.position_dodge (width=0.9) gp = ggplot2.ggplot (df) pp = gp + \ ggplot2.aes_string (x='Problem', y='Time', fill='Variation') + \ ggplot2.geom_bar (position='dodge', stat='identity') + \ ggplot2.geom_errorbar (limits, position=dodge, width=0.25) + \ ggplot2_options () + \ ggplot2_colors () + \ robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\ robjects.r('ylab("Execution time (in seconds)")') pp.plot () r['dev.off']()
# #-- ggplot2coordtransreverse-end # grdevices.dev_off() grdevices.png('../../_static/graphics_ggplot2map_polygon.png', width=612, height=612, antialias="subpixel", type="cairo") #-- ggplot2mappolygon-begin map = importr('maps') fr = ggplot2.map_data('france') # add a column indicating which region names have an "o". fr = fr.cbind(fr, has_o=base.grepl('o', fr.rx2("region"), ignore_case=True)) p = ggplot2.ggplot(fr) + \ ggplot2.geom_polygon(ggplot2.aes(x = 'long', y = 'lat', group = 'group', fill = 'has_o'), col="black") p.plot() #-- ggplot2mappolygon-end grdevices.dev_off() grdevices.png('../../_static/graphics_ggplot2mtcars_coordtrans.png', width=936, height=624, antialias="subpixel", type="cairo") #-- ggplot2mtcarscoordtrans-begin from rpy2.robjects.lib import grid grid.newpage() grid.viewport(layout=grid.layout(2, 3)).push()
def test_vars(self): gp = (ggplot2.ggplot(mtcars) + ggplot2.aes(x='wt', y='mpg') + ggplot2.geom_point() + ggplot2.facet_wrap(ggplot2.vars('gears'))) assert isinstance(gp, ggplot2.GGPlot)
## loaded data sets can now be accessed through R handle ## note that different from R dot . is not valid for Python variable names! IL_railroads = robjects.r('IL.railroads') IL_final = robjects.r('IL.final') ## import device driver from R with importr to plot to PNG ## we can then call any function in the grdevices package grdevices = importr('grDevices') grdevices.png(file='/Users/user/Downloads/data/mapplot.png', width=1300, height=1000) ## plot the map ## note that the order matters when we add another layer in ggplot (here IL_railroads): first aes, then data, that's different from R ## (see http://permalink.gmane.org/gmane.comp.python.rpy/2349) ## note that we use dictionary to set the opts to be able to set options as keywords, for example legend.key.size p_map = ggplot2.ggplot(IL_final) + \ ggplot2.geom_polygon(ggplot2.aes(x = 'long', y = 'lat', group = 'group', color = 'ObamaShare', fill = 'ObamaShare')) + \ ggplot2.scale_fill_gradient(high = 'blue', low = 'red') + \ ggplot2.scale_fill_continuous(name = "Obama Vote Share") + \ ggplot2.scale_colour_continuous(name = "Obama Vote Share") + \ ggplot2.opts(**{'legend.position': 'left', 'legend.key.size': robjects.r.unit(2, 'lines'), 'legend.title' : ggplot2.theme_text(size = 14, hjust=0), \ 'legend.text': ggplot2.theme_text(size = 12), 'title' : "Obama Vote Share and Distance to Railroads in IL", \ 'plot.title': ggplot2.theme_text(size = 24), 'plot.margin': robjects.r.unit(robjects.r.rep(0,4),'lines'), \ 'panel.background': ggplot2.theme_blank(), 'panel.grid.minor': ggplot2.theme_blank(), 'panel.grid.major': ggplot2.theme_blank(), \ 'axis.ticks': ggplot2.theme_blank(), 'axis.title.x': ggplot2.theme_blank(), 'axis.title.y': ggplot2.theme_blank(), \ 'axis.title.x': ggplot2.theme_blank(), 'axis.title.x': ggplot2.theme_blank(), 'axis.text.x': ggplot2.theme_blank(), \ 'axis.text.y': ggplot2.theme_blank()} ) + \ ggplot2.geom_line(ggplot2.aes(x='long', y='lat', group='group'), data=IL_railroads, color='grey', size=0.2) + \ ggplot2.coord_equal() p_map.plot()
def line_plot (cfg, var, control, change_name, changing, selector, base_selector, basis): speedups = [] thrds = [] changes = [] lowers = [] uppers = [] for n in cfg.threads: probs.append ('ideal') langs.append ('ideal') speedups.append (n) thrds.append (n) changes.append ('ideal') lowers.append (n) uppers.append (n) for c in changing: sel = selector (c) # sequential base base = FloatVector (base_selector(c)) # base with p = 1 base_p1 = FloatVector (sel(1)) # use fastest sequential program if basis == 'fastest' and mean (base_p1) < mean(base): base = base_p1 elif basis == 'seq': pass elif basis == 'p1': base = base_p1 for n in cfg.threads: ntimes = FloatVector (sel(n)) # ratio confidence interval labels = ['Base'] * r.length(base)[0] + ['N']*r.length (ntimes)[0] df = DataFrame ({'Times': base + ntimes, 'Type': StrVector(labels)}) ratio_test = r['pairwiseCI'] (r('Times ~ Type'), data=df, control='N', method='Param.ratio', **{'var.equal': False, 'conf.level': 0.999})[0][0] lowers.append (ratio_test[1][0]) uppers.append (ratio_test[2][0]) mn = mean (ntimes) speedups.append (mean(base) / mn) # plot slowdowns #speedups.append (-mn/base)#(base / mn) thrds.append (n) if change_name == 'Language': changes.append (pretty_langs [c]) else: changes.append (c) df = DataFrame ({'Speedup': FloatVector (speedups), 'Threads': IntVector (thrds), change_name: StrVector (changes), 'Lower': FloatVector (lowers), 'Upper': FloatVector (uppers) }) ideal_changing = ['ideal'] if change_name == 'Language': ideal_changing.extend ([pretty_langs [c] for c in changing]) else: ideal_changing.extend (changing) legendVec = IntVector (range (len (ideal_changing))) legendVec.names = StrVector (ideal_changing) gg = ggplot2.ggplot (df) limits = ggplot2.aes (ymax = 'Upper', ymin = 'Lower') dodge = ggplot2.position_dodge (width=0.9) pp = gg + \ ggplot2.geom_line() + ggplot2.geom_point(size=3) +\ ggplot2.aes_string(x='Threads', y='Speedup', group=change_name, color=change_name, shape=change_name) + \ ggplot2.scale_shape_manual(values=legendVec) + \ ggplot2.geom_errorbar (limits, width=0.25) + \ ggplot2_options () + \ ggplot2_colors () + \ ggplot2.opts (**{'axis.title.x' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 15, vjust=-0.2)}) + \ robjects.r('ylab("Speedup")') + \ robjects.r('xlab("Cores")') # ggplot2.xlim (min(threads), max(threads)) + ggplot2.ylim(min(threads), max(threads)) +\ pp.plot() r['dev.off']()
def as_dataframe (cfg, results, basis): r = robjects.r varis = [] langs = [] probs = [] times = [] threads = [] # speedups, with upper and lower bounds below speedups = [] speedup_lowers = [] speedup_uppers = [] ses = [] # standard errors mems = [] # memory usage langs_ideal = list (cfg.languages) langs_ideal.append ('ideal') probs_ideal = list (cfg.problems) probs_ideal.append ('ideal') for var in cfg.variations: for lang in langs_ideal: # cfg.languages: for prob in probs_ideal: # cfg.problems: for thread in cfg.threads: if lang == 'ideal' and prob == 'ideal': continue elif lang == 'ideal' or prob == 'ideal': varis.append (var) langs.append (pretty_langs[lang]) probs.append (prob) threads.append (thread) speedups.append (thread) speedup_lowers.append (thread) speedup_uppers.append (thread) times.append (0) ses.append(0) mems.append (0) continue varis.append (var) # pretty_varis [var]) langs.append (pretty_langs [lang]) probs.append (prob) threads.append (thread) if var.find('seq') >= 0: thread = cfg.threads[-1] vals = FloatVector (results[thread][prob][var][lang][0]) time = mean (vals) times.append (time) # # time confidence interval # t_result = r['t.test'] (FloatVector(vals), **{" conf.level": 0.999}).rx ('conf.int')[0] ses.append ((t_result[1] - t_result[0])/2) # # memory usage # mem_filename = get_mem_output (lang, prob, var) with open (mem_filename, 'r') as mem_file: mem = mem_file.readline() mems.append (float (mem)) # we include dummy data for the sequential case to avoid the # speedup calculation below if var.find('seq') >= 0: speedups.append (1) speedup_lowers.append (1) speedup_uppers.append (1) continue # # speedup values and confidence intervals # seq_vals = results[cfg.threads[-1]][prob][var.replace ('par', 'seq')][lang][0] # sequential base base = FloatVector (seq_vals) # base with p = 1 base_p1 = FloatVector (results[1][prob][var][lang][0]) # use fastest sequential program if basis == 'fastest' and mean (base_p1) < mean(base): base = base_p1 elif basis == 'seq': pass elif basis == 'p1': base = base_p1 labels = ['Base'] * r.length(base)[0] + ['N']*r.length (vals)[0] df = DataFrame ({'Times': base + vals, 'Type': StrVector(labels)}) ratio_test = r['pairwiseCI'] (r('Times ~ Type'), data=df, control='N', method='Param.ratio', **{'var.equal': False})[0][0] speedups.append (mean(base) / time) speedup_lowers.append (ratio_test[1][0]) speedup_uppers.append (ratio_test[2][0]) df = robjects.DataFrame({'Language': StrVector (langs), 'Problem': StrVector (probs), 'Variation' : StrVector (varis), 'Threads': IntVector (threads), 'Time': FloatVector (times), 'SE': FloatVector (ses), 'Speedup': FloatVector (speedups), 'SpeedupLower': FloatVector (speedup_lowers), 'SpeedupUpper': FloatVector (speedup_uppers), 'Mem' : FloatVector (mems) }) r.assign ('df', df) r ('save (df, file="performance.Rda")') # reshape the data to make variation not a column itself, but a part of # the other columns describe ie, time, speedup, etc. # # also, remove the 'ideal' problem as we don't want it in this plot. df = r(''' redf = reshape (df, timevar="Variation", idvar = c("Language","Problem","Threads"), direction="wide") redf$Problem <- factor(redf$Problem, levels = c("randmat","thresh","winnow","outer","product","chain")) redf[which(redf$Problem != "ideal"),] ''') r.pdf ('speedup-expertpar-all.pdf', height=6.5, width=10) change_name = 'Language' legendVec = IntVector (range (len (langs_ideal))) legendVec.names = StrVector (langs_ideal) gg = ggplot2.ggplot (df) limits = ggplot2.aes (ymax = 'SpeedupUpper.expertpar', ymin = 'SpeedupLower.expertpar') dodge = ggplot2.position_dodge (width=0.9) pp = gg + \ ggplot2.geom_line() + ggplot2.geom_point(size=2.5) +\ robjects.r('scale_color_manual(values = c("#ffcb7e", "#1da06b", "#b94646", "#00368a", "#CCCCCC"))') +\ ggplot2.aes_string(x='Threads', y='Speedup.expertpar', group=change_name, color=change_name, shape=change_name) + \ ggplot2.geom_errorbar (limits, width=0.25) + \ ggplot2.opts (**{'axis.title.x' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 10, vjust=-0.2), 'axis.title.y' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 10, angle=90, vjust=0.2), 'axis.text.x' : ggplot2.theme_text(family = 'serif', size = 10), 'axis.text.y' : ggplot2.theme_text(family = 'serif', size = 10), 'legend.title' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 10), 'legend.text' : ggplot2.theme_text(family = 'serif', size = 10), 'strip.text.x' : ggplot2.theme_text(family = 'serif', size = 10), 'aspect.ratio' : 1, }) + \ robjects.r('ylab("Speedup")') + \ robjects.r('xlab("Number of cores")') + \ ggplot2.facet_wrap ('Problem', nrow = 2) pp.plot() r['dev.off']()
def bargraph_variation (cfg, values): r = robjects.r for var in cfg.variations: # each variation gets plot avgs = [] ses = [] # normalized values navgs = [] nses = [] langs = [] probs = [] for prob in cfg.problems: # aggregate by problems lavgs = [] lses = [] for lang in cfg.languages: # each problem displays a list of language times for that problem data = FloatVector (values[prob][var][lang][0]) langs.append (pretty_langs [lang]) probs.append (prob) mean = r['mean'] (data)[0] lavgs.append (mean) t_result = r['t.test'] (data, **{"conf.level": 0.999}).rx ('conf.int')[0] lses.append ((t_result[1] - t_result[0])/2) avgs.extend (lavgs) ses.extend (lses) lmin = min (lavgs) navgs.extend ([la/lmin for la in lavgs]) nses.extend ([ls/lmin for ls in lses]) df = robjects.DataFrame({'Language': StrVector (langs), 'Problem': StrVector (probs), 'Time' : FloatVector (avgs), 'SE' : FloatVector (ses), 'NormTime' : FloatVector (navgs), 'NormSE' : FloatVector (nses), 'TimeLabel' : StrVector ([str(round(time, 1)) + "s" for time in avgs]) }) # plot histogram of actual times r.pdf ('bargraph-executiontime-var-' + var + '.pdf', height=pdf_height (), width=pdf_width ()) limits = ggplot2.aes (ymax = 'Time + SE', ymin = 'Time - SE') dodge = ggplot2.position_dodge (width=0.9) gp = ggplot2.ggplot (df) pp = gp + \ ggplot2.aes_string (x='Problem', y='Time', fill='Language') + \ ggplot2.geom_bar (position='dodge', stat='identity') + \ ggplot2.geom_errorbar (limits, position=dodge, width=0.25) + \ ggplot2_options () + \ ggplot2_colors () + \ robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\ robjects.r('ylab("Execution time (in seconds)")') pp.plot () # plot histogram of times normalized with respect to fastest time for a problem r.pdf ('bargraph-executiontime-var-norm-' + var + '.pdf', height=pdf_height (), width=pdf_width ()) limits = ggplot2.aes (ymax = 'NormTime + NormSE', ymin = 'NormTime - NormSE') dodge = ggplot2.position_dodge (width=0.9) gp = ggplot2.ggplot (df) pp = gp + \ ggplot2.aes_string (x='Problem', y='NormTime', fill='Language') + \ ggplot2.geom_bar (position='dodge', stat='identity') + \ ggplot2.geom_errorbar (limits, position=dodge, width=0.25) +\ ggplot2_options () + \ ggplot2_colors () + \ robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\ robjects.r('ylab("Execution time (normalized to fastest)")') #ggplot2.geom_text(data=df, # mapping = ggplot2.aes_string (x='Problem', # y='NormTime + NormSE + 0.1', # label='TimeLabel') pp.plot () r['dev.off']()
# pp.plot() # #-- ggplot2coordtransreverse-end # grdevices.dev_off() grdevices.png('../../_static/graphics_ggplot2map_polygon.png', width = 612, height = 612, antialias="subpixel", type="cairo") #-- ggplot2mappolygon-begin map = importr('maps') fr = ggplot2.map_data('france') # add a column indicating which region names have an "o". fr = fr.cbind(fr, has_o = base.grepl('o', fr.rx2("region"), ignore_case = True)) p = ggplot2.ggplot(fr) + \ ggplot2.geom_polygon(ggplot2.aes(x = 'long', y = 'lat', group = 'group', fill = 'has_o'), col="black") p.plot() #-- ggplot2mappolygon-end grdevices.dev_off() grdevices.png('../../_static/graphics_grid.png', width = 612, height = 612, antialias="subpixel", type="cairo") #-- grid-begin grid.newpage() # create a rows/columns layout lt = grid.layout(2, 3) vp = grid.viewport(layout = lt)
## import device driver from R with importr to plot to PNG ## we can then call any function in the grdevices package grdevices = R.packages.importr('grDevices') grdevices.png(file='mapplot.png', width=1300, height=1000) ## plot the map ## note that the order matters when we add another layer in ggplot ## (here IL_railroads): first aes, then data, that's different from R ## (see http://permalink.gmane.org/gmane.comp.python.rpy/2349) ## note that we use dictionary to set the opts to be able to set options as ## keywords, for example legend.key.size p_map = ggplot2.ggplot(IL_final) + \ ggplot2.geom_polygon(ggplot2.aes(x = 'long', \ y = 'lat', \ group = 'group', \ color = 'ObamaShare', \ fill = 'ObamaShare')) + \ ggplot2.scale_fill_gradient(high = 'blue', \ low = 'red') + \ ggplot2.scale_fill_continuous(name = "Obama Vote Share") + \ ggplot2.scale_colour_continuous(name = "Obama Vote Share") + \ ggplot2.theme(**{ 'legend.position': 'left', \ 'legend.key.size': R.r.unit(2, 'lines'), \ 'legend.title' : ggplot2.element_text(size = 14, hjust=0), \ 'legend.text': ggplot2.element_text(size = 12), \ 'title' : ggplot2.element_text('Obama Vote Share and Distance to Railroads in IL'), \ 'plot.title': ggplot2.element_text(size = 24), 'plot.margin': R.r.unit(R.r.rep(0,4),'lines'), \ 'panel.background': ggplot2.element_blank(), \ 'panel.grid.minor': ggplot2.element_blank(), \
IL_railroads = robjects.r('IL.railroads') IL_final = robjects.r('IL.final') ## import device driver from R with importr to plot to PNG ## we can then call any function in the grdevices package grdevices = importr('grDevices') grdevices.png(file='/Users/user/Downloads/data/mapplot.png', width=1300, height=1000) ## plot the map ## note that the order matters when we add another layer in ggplot (here IL_railroads): first aes, then data, that's different from R ## (see http://permalink.gmane.org/gmane.comp.python.rpy/2349) ## note that we use dictionary to set the opts to be able to set options as keywords, for example legend.key.size p_map = ggplot2.ggplot(IL_final) + \ ggplot2.geom_polygon(ggplot2.aes(x = 'long', y = 'lat', group = 'group', color = 'ObamaShare', fill = 'ObamaShare')) + \ ggplot2.scale_fill_gradient(high = 'blue', low = 'red') + \ ggplot2.scale_fill_continuous(name = "Obama Vote Share") + \ ggplot2.scale_colour_continuous(name = "Obama Vote Share") + \ ggplot2.opts(**{'legend.position': 'left', 'legend.key.size': robjects.r.unit(2, 'lines'), 'legend.title' : ggplot2.theme_text(size = 14, hjust=0), \ 'legend.text': ggplot2.theme_text(size = 12), 'title' : "Obama Vote Share and Distance to Railroads in IL", \ 'plot.title': ggplot2.theme_text(size = 24), 'plot.margin': robjects.r.unit(robjects.r.rep(0,4),'lines'), \ 'panel.background': ggplot2.theme_blank(), 'panel.grid.minor': ggplot2.theme_blank(), 'panel.grid.major': ggplot2.theme_blank(), \ 'axis.ticks': ggplot2.theme_blank(), 'axis.title.x': ggplot2.theme_blank(), 'axis.title.y': ggplot2.theme_blank(), \ 'axis.title.x': ggplot2.theme_blank(), 'axis.title.x': ggplot2.theme_blank(), 'axis.text.x': ggplot2.theme_blank(), \ 'axis.text.y': ggplot2.theme_blank()} ) + \ ggplot2.geom_line(ggplot2.aes(x='long', y='lat', group='group'), data=IL_railroads, color='grey', size=0.2) + \ ggplot2.coord_equal() p_map.plot()
def line_plot(cfg, var, control, change_name, changing, selector, base_selector, basis): speedups = [] thrds = [] changes = [] lowers = [] uppers = [] for n in cfg.threads: probs.append('ideal') langs.append('ideal') speedups.append(n) thrds.append(n) changes.append('ideal') lowers.append(n) uppers.append(n) for c in changing: sel = selector(c) # sequential base base = FloatVector(base_selector(c)) # base with p = 1 base_p1 = FloatVector(sel(1)) # use fastest sequential program if basis == 'fastest' and mean(base_p1) < mean(base): base = base_p1 elif basis == 'seq': pass elif basis == 'p1': base = base_p1 for n in cfg.threads: ntimes = FloatVector(sel(n)) # ratio confidence interval labels = ['Base'] * r.length(base)[0] + ['N'] * r.length(ntimes)[0] df = DataFrame({'Times': base + ntimes, 'Type': StrVector(labels)}) ratio_test = r['pairwiseCI'](r('Times ~ Type'), data=df, control='N', method='Param.ratio', **{ 'var.equal': False, 'conf.level': 0.999 })[0][0] lowers.append(ratio_test[1][0]) uppers.append(ratio_test[2][0]) mn = mean(ntimes) speedups.append(mean(base) / mn) # plot slowdowns #speedups.append (-mn/base)#(base / mn) thrds.append(n) if change_name == 'Language': changes.append(pretty_langs[c]) else: changes.append(c) df = DataFrame({ 'Speedup': FloatVector(speedups), 'Threads': IntVector(thrds), change_name: StrVector(changes), 'Lower': FloatVector(lowers), 'Upper': FloatVector(uppers) }) ideal_changing = ['ideal'] if change_name == 'Language': ideal_changing.extend([pretty_langs[c] for c in changing]) else: ideal_changing.extend(changing) legendVec = IntVector(range(len(ideal_changing))) legendVec.names = StrVector(ideal_changing) gg = ggplot2.ggplot(df) limits = ggplot2.aes(ymax='Upper', ymin='Lower') dodge = ggplot2.position_dodge(width=0.9) pp = gg + \ ggplot2.geom_line() + ggplot2.geom_point(size=3) +\ ggplot2.aes_string(x='Threads', y='Speedup', group=change_name, color=change_name, shape=change_name) + \ ggplot2.scale_shape_manual(values=legendVec) + \ ggplot2.geom_errorbar (limits, width=0.25) + \ ggplot2_options () + \ ggplot2_colors () + \ ggplot2.opts (**{'axis.title.x' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 15, vjust=-0.2)}) + \ robjects.r('ylab("Speedup")') + \ robjects.r('xlab("Cores")') # ggplot2.xlim (min(threads), max(threads)) + ggplot2.ylim(min(threads), max(threads)) +\ pp.plot() r['dev.off']()
def as_dataframe(cfg, results, basis): r = robjects.r varis = [] langs = [] probs = [] times = [] threads = [] # speedups, with upper and lower bounds below speedups = [] speedup_lowers = [] speedup_uppers = [] ses = [] # standard errors mems = [] # memory usage langs_ideal = list(cfg.languages) langs_ideal.append('ideal') probs_ideal = list(cfg.problems) probs_ideal.append('ideal') for var in cfg.variations: for lang in langs_ideal: # cfg.languages: for prob in probs_ideal: # cfg.problems: for thread in cfg.threads: if lang == 'ideal' and prob == 'ideal': continue elif lang == 'ideal' or prob == 'ideal': varis.append(var) langs.append(pretty_langs[lang]) probs.append(prob) threads.append(thread) speedups.append(thread) speedup_lowers.append(thread) speedup_uppers.append(thread) times.append(0) ses.append(0) mems.append(0) continue varis.append(var) # pretty_varis [var]) langs.append(pretty_langs[lang]) probs.append(prob) threads.append(thread) if var.find('seq') >= 0: thread = cfg.threads[-1] vals = FloatVector(results[thread][prob][var][lang][0]) time = mean(vals) times.append(time) # # time confidence interval # t_result = r['t.test'](FloatVector(vals), **{ " conf.level": 0.999 }).rx('conf.int')[0] ses.append((t_result[1] - t_result[0]) / 2) # # memory usage # mem_filename = get_mem_output(lang, prob, var) with open(mem_filename, 'r') as mem_file: mem = mem_file.readline() mems.append(float(mem)) # we include dummy data for the sequential case to avoid the # speedup calculation below if var.find('seq') >= 0: speedups.append(1) speedup_lowers.append(1) speedup_uppers.append(1) continue # # speedup values and confidence intervals # seq_vals = results[cfg.threads[-1]][prob][var.replace( 'par', 'seq')][lang][0] # sequential base base = FloatVector(seq_vals) # base with p = 1 base_p1 = FloatVector(results[1][prob][var][lang][0]) # use fastest sequential program if basis == 'fastest' and mean(base_p1) < mean(base): base = base_p1 elif basis == 'seq': pass elif basis == 'p1': base = base_p1 labels = ['Base' ] * r.length(base)[0] + ['N'] * r.length(vals)[0] df = DataFrame({ 'Times': base + vals, 'Type': StrVector(labels) }) ratio_test = r['pairwiseCI'](r('Times ~ Type'), data=df, control='N', method='Param.ratio', **{ 'var.equal': False })[0][0] speedups.append(mean(base) / time) speedup_lowers.append(ratio_test[1][0]) speedup_uppers.append(ratio_test[2][0]) df = robjects.DataFrame({ 'Language': StrVector(langs), 'Problem': StrVector(probs), 'Variation': StrVector(varis), 'Threads': IntVector(threads), 'Time': FloatVector(times), 'SE': FloatVector(ses), 'Speedup': FloatVector(speedups), 'SpeedupLower': FloatVector(speedup_lowers), 'SpeedupUpper': FloatVector(speedup_uppers), 'Mem': FloatVector(mems) }) r.assign('df', df) r('save (df, file="performance.Rda")') # reshape the data to make variation not a column itself, but a part of # the other columns describe ie, time, speedup, etc. # # also, remove the 'ideal' problem as we don't want it in this plot. df = r(''' redf = reshape (df, timevar="Variation", idvar = c("Language","Problem","Threads"), direction="wide") redf$Problem <- factor(redf$Problem, levels = c("randmat","thresh","winnow","outer","product","chain")) redf[which(redf$Problem != "ideal"),] ''') r.pdf('speedup-expertpar-all.pdf', height=6.5, width=10) change_name = 'Language' legendVec = IntVector(range(len(langs_ideal))) legendVec.names = StrVector(langs_ideal) gg = ggplot2.ggplot(df) limits = ggplot2.aes(ymax='SpeedupUpper.expertpar', ymin='SpeedupLower.expertpar') dodge = ggplot2.position_dodge(width=0.9) pp = gg + \ ggplot2.geom_line() + ggplot2.geom_point(size=2.5) +\ robjects.r('scale_color_manual(values = c("#ffcb7e", "#1da06b", "#b94646", "#00368a", "#CCCCCC"))') +\ ggplot2.aes_string(x='Threads', y='Speedup.expertpar', group=change_name, color=change_name, shape=change_name) + \ ggplot2.geom_errorbar (limits, width=0.25) + \ ggplot2.opts (**{'axis.title.x' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 10, vjust=-0.2), 'axis.title.y' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 10, angle=90, vjust=0.2), 'axis.text.x' : ggplot2.theme_text(family = 'serif', size = 10), 'axis.text.y' : ggplot2.theme_text(family = 'serif', size = 10), 'legend.title' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 10), 'legend.text' : ggplot2.theme_text(family = 'serif', size = 10), 'strip.text.x' : ggplot2.theme_text(family = 'serif', size = 10), 'aspect.ratio' : 1, }) + \ robjects.r('ylab("Speedup")') + \ robjects.r('xlab("Number of cores")') + \ ggplot2.facet_wrap ('Problem', nrow = 2) pp.plot() r['dev.off']()
def bargraph_variation(cfg, values): r = robjects.r for var in cfg.variations: # each variation gets plot avgs = [] ses = [] # normalized values navgs = [] nses = [] langs = [] probs = [] for prob in cfg.problems: # aggregate by problems lavgs = [] lses = [] for lang in cfg.languages: # each problem displays a list of language times for that problem data = FloatVector(values[prob][var][lang][0]) langs.append(pretty_langs[lang]) probs.append(prob) mean = r['mean'](data)[0] lavgs.append(mean) t_result = r['t.test'](data, **{ "conf.level": 0.999 }).rx('conf.int')[0] lses.append((t_result[1] - t_result[0]) / 2) avgs.extend(lavgs) ses.extend(lses) lmin = min(lavgs) navgs.extend([la / lmin for la in lavgs]) nses.extend([ls / lmin for ls in lses]) df = robjects.DataFrame({ 'Language': StrVector(langs), 'Problem': StrVector(probs), 'Time': FloatVector(avgs), 'SE': FloatVector(ses), 'NormTime': FloatVector(navgs), 'NormSE': FloatVector(nses), 'TimeLabel': StrVector([str(round(time, 1)) + "s" for time in avgs]) }) # plot histogram of actual times r.pdf('bargraph-executiontime-var-' + var + '.pdf', height=pdf_height(), width=pdf_width()) limits = ggplot2.aes(ymax='Time + SE', ymin='Time - SE') dodge = ggplot2.position_dodge(width=0.9) gp = ggplot2.ggplot(df) pp = gp + \ ggplot2.aes_string (x='Problem', y='Time', fill='Language') + \ ggplot2.geom_bar (position='dodge', stat='identity') + \ ggplot2.geom_errorbar (limits, position=dodge, width=0.25) + \ ggplot2_options () + \ ggplot2_colors () + \ robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\ robjects.r('ylab("Execution time (in seconds)")') pp.plot() # plot histogram of times normalized with respect to fastest time for a problem r.pdf('bargraph-executiontime-var-norm-' + var + '.pdf', height=pdf_height(), width=pdf_width()) limits = ggplot2.aes(ymax='NormTime + NormSE', ymin='NormTime - NormSE') dodge = ggplot2.position_dodge(width=0.9) gp = ggplot2.ggplot(df) pp = gp + \ ggplot2.aes_string (x='Problem', y='NormTime', fill='Language') + \ ggplot2.geom_bar (position='dodge', stat='identity') + \ ggplot2.geom_errorbar (limits, position=dodge, width=0.25) +\ ggplot2_options () + \ ggplot2_colors () + \ robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\ robjects.r('ylab("Execution time (normalized to fastest)")') #ggplot2.geom_text(data=df, # mapping = ggplot2.aes_string (x='Problem', # y='NormTime + NormSE + 0.1', # label='TimeLabel') pp.plot() r['dev.off']()