Python pylab.boxplot函数代码示例

def prob_dispersion(target, result, prob, nclasses=5, save_as=''):
  classprob = [[] for i in 2 * range(nclasses)]
  for i in xrange(len(result)):
    p = prob[i][result[i]]
    if result[i] == target[i]:
      classprob[2*result[i]].append(p)
    else:
      classprob[2*result[i] + 1].append(p)

  xlabels = [[str(i+1) + "-Good", str(i+1) + "-Bad"] for i in range(nclasses)]
  xlabels = reduce(list.__add__, xlabels, [])

  # Plotting the result
  fig = plt.figure()
  fig.suptitle('Probability distribution' , fontsize=20)
  plot = fig.add_subplot(111)
  pylab.boxplot(classprob)
  pylab.xticks(range(1, 2 * nclasses + 1), xlabels)
  plot.set_xlabel('Predicted' , fontsize = 16)
  plot.set_ylabel('Probabilities' , fontsize = 16)
  plot.tick_params(axis='both', which='major', labelsize=14)
  plot.tick_params(axis='both', which='minor', labelsize=8)
  
  # Save options
  if save_as =='':
    plt.show()
  else :
    fig.savefig(save_as)

def chart(SW, a, b, label, folder, FILE):
    pylab.ioff()
    fig_width_pt = 350 					     # Get this from LaTeX using \showthe\columnwidth
    inches_per_pt = 1.0/72.27                # Convert pt to inch
    golden_mean = ((5**0.5)-1.0)/2.0         # Aesthetic ratio
    fig_width = fig_width_pt*inches_per_pt   # width in inches   
    fig_height = fig_width*golden_mean       # height in inches
    fig_size =  [fig_width,fig_height]

    params = { 'backend': 'ps',
           'axes.labelsize': 10,
           'text.fontsize': 10,
           'legend.fontsize': 10,
           'xtick.labelsize': 8,
           'ytick.labelsize': 8,
           'text.usetex': True,
           'figure.figsize': fig_size }

    pylab.rcParams.update(params)

    home = '/home/nealbob'
    img_ext = '.pdf'

    pylab.figure()
    pylab.boxplot([SW['SWA'], SW['OA'], SW['NS']], whis=5)
    pylab.axhline(y=1.0, color='0.5', linewidth=0.5, alpha=0.75, linestyle=':')
    pylab.ylim(a, b)
    pylab.ylabel(label)
    pylab.tick_params(axis='x', which = 'both', labelbottom='off')
    pylab.figtext(0.225, 0.06, 'SWA', fontsize = 10)
    pylab.figtext(0.495, 0.06, 'OA', fontsize = 10)
    pylab.figtext(0.76, 0.06, 'NS', fontsize = 10)
    pylab.savefig(home + folder + FILE + img_ext)
    pylab.show()

def makeboxplot(filteredclusts, dblibrary, figname, pool=False):
    '''takes a filtered dict of clusts worth keeping and creates a boxplot of either by lane (default) or pool'''
    indiv_cluster_count = defaultdict(int) 
    for clust, inddict in filteredclusts.items():
        for ind, reads in inddict.items():
            if ind in indiv_cluster_count.keys():
                indiv_cluster_count[ind]+=1
            else:
                indiv_cluster_count[ind]+=1 
    
    t = gdata_tools.get_table_as_dict(dblibrary)
    db_ind_countd = Util.countdict([d['sampleid'] for d in t if d['sampleid'] in indiv_cluster_count.keys()[3]]) #creates a table of individual dicts from google spreadsheet
    indiv_by_group = defaultdict(list)
    for d in t:
        if 'pool' in d:
            indkey = (d.get('flowcell',None),d.get('lane',None),d.get('index',None),d.get('sampleid',None))
            if indkey in indiv_cluster_count:
                if pool == True:
                    indiv_by_group[(d['flowcell'],d['lane'],d.get('index',None),d['pool'])].append(indiv_cluster_count[indkey]) 
                else:
                    indiv_by_group[(d['flowcell'],d['lane'],d.get('index',None))].append(indiv_cluster_count[indkey])
    
    boxes = []
    labels = []
    for group,indcounts in indiv_by_group.items():
        boxes.append(indcounts)
        labels.append(group)
    boxplt = pylab.figure(1)
    pylab.boxplot(boxes)
    pylab.xticks(arange(1,(len(labels)+1)),labels,fontsize='small') #legend with best location (0) if pools
    boxplt.savefig(figname)

def quartile_plot(
        fits,
        group_index_start, group_index_end,
        model_param_index,
        ylim=None,
        log=True,
        xlabel=None,
        ylabel=None,
        labels=None):
    model_param_values = [
        fit_params(fits, group_index, model_param_index)
        for group_index in xrange(
            group_index_start, group_index_end)
    ]
    fig = plt.figure(figsize=(len(model_param_values), 7))
    if log is True:
        plt.yscale('log')
    if ylim is not None:
        plt.ylim(ylim)
    if xlabel is not None:
        plt.xlabel(xlabel)
    if ylabel is not None:
        plt.ylabel(ylabel)
    plt.boxplot(
        model_param_values,
        labels=labels,
        showmeans=True)
    plt.grid()
    plt.show()

def chart(idx, a, b, label, FILE):
    pylab.ioff()
    fig_width_pt = 350 					     # Get this from LaTeX using \showthe\columnwidth
    inches_per_pt = 1.0/72.27                # Convert pt to inch
    golden_mean = ((5**0.5)-1.0)/2.0         # Aesthetic ratio
    fig_width = fig_width_pt*inches_per_pt   # width in inches   
    fig_height = fig_width*golden_mean       # height in inches
    fig_size =  [fig_width*0.42,fig_height]

    params = { 'backend': 'ps',
           'axes.labelsize': 10,
           'text.fontsize': 10,
           'legend.fontsize': 10,
           'xtick.labelsize': 8,
           'ytick.labelsize': 8,
           'text.usetex': True,
           'figure.figsize': fig_size }

    pylab.rcParams.update(params)

    home = '/home/nealbob'
    folder = '/Dropbox/Thesis/IMG/chapter3/'
    img_ext = '.pdf'

    pylab.figure()
    pylab.boxplot(idx, whis=100)
    pylab.ylim(a, b)
    #pylab.ylabel(label)
    pylab.tick_params(axis='x', which = 'both', labelbottom='off')
    pylab.savefig(home + folder + FILE + img_ext)
    pylab.show()

def whiskers(i1, i2, lab1="", lab2=""):
    width = 0.35
    l1 = pb.boxplot([d[:, i1] for d in data] , positions=np.arange(len(data))-1.03*width/2., widths=width)
    l2 = pb.boxplot([d[:, i2] for d in data] , positions=np.arange(len(data))+1.03*width/2., widths=width)
    pb.xticks(np.arange(len(data)),[fn.split('raw')[0].replace('_',' ') for fn in fnames], rotation=45)
    pb.xlim(-1.2*width, len(data)-1+1.2*width)

    for key, lines in l1.iteritems():
        pb.setp(lines, lw=1)
        if key == "boxes":
            pb.setp(lines, color='b', lw=1.4)
        if key == 'whiskers':
            pb.setp(lines, color='b')
        if key == 'fliers':
            pb.setp(lines, color='b')
        if key == 'medians':
            pb.setp(lines, color='k', lw=1.4)
    for key, lines in l2.iteritems():
        pb.setp(lines, lw=1.2)
        if key == "boxes":
            pb.setp(lines, color='g', lw=1.4)
        if key == 'whiskers':
            pb.setp(lines, color='g')
        if key == 'fliers':
            pb.setp(lines, color='g')
        if key == 'medians':
            pb.setp(lines, color='k', lw=1.4)

def plot():
    swarmsize_marks = [20, 50, 100, 200]
    times = {}
    for mark in swarmsize_marks:
        times[mark] = []
    for time_filename, size_filename, label, style in lines_to_plot:
        time_file = open('parser_results/' + time_filename)
        size_file = open('parser_results/' + size_filename)
        for line in time_file:
            time = float(line.split()[0])
            size = int(size_file.next().split()[0])
            for mark in swarmsize_marks:
                if size <= mark:
                    times[mark].append(time)
                    break
    xs = []
    labels = []
    for mark in swarmsize_marks:
        xs.append(times[mark])
        labels.append('<=%d' % mark)
    pylab.boxplot(xs)
    pylab.setp(pylab.gca(), 'xticklabels', labels)
    pylab.savefig(output_filename)
#    pylab.close()
    

    print 'Output saved to:', output_filename

def do_proc(resdir, timedir):
    """
    EXPS on IPC6_SEQ_ELEVATORS_12 & IPC6_TEMPO_OPENSTACKS_17
    steadyState=50
    1) popsize=48 & runmax=1 & maxseconds=0
    2) RESTART case: popsize=96 & runmax=0 & maxseconds=1799
    foreach nthreads: 1, 24, 48
    repeat 11 times
    """

    if not options.cores: return

    for field, popsize, runmax, maxseconds in [
        ("PROC", 48, 1, 0),
        #("RESTART_PROC", 96, 0, 1799)
        ]:
        for name, domain, instance in SAMPLES:
            local_logger = logging.getLogger("GECCO2011.PROC.%s" % name)
            plotdata = []
            for num in range(1, options.nruns+1):
                subdata = []
                for nthreads in [1, 24, 48]:
                    field_name = "%s_%s_%d" % (field, "DYNAMIC" if options.dynamic else "STATIC", nthreads)
                    time_filename = PATTERN_TIME_FILENAME % {"TIMEDIR": timedir, "NAME": name, "FIELD": field_name, "NUM": num}
                    res_filename = PATTERN_RES_FILENAME % {"RESDIR": resdir, "NAME": name, "FIELD": field_name, "NUM": num}
                    plan_filename = PATTERN_PLAN_FILENAME % {"RESDIR": resdir, "NAME": name, "FIELD": field_name, "NUM": num}
                    cmd = PATTERN_CMD % {"DOMAIN": domain,
                                         "INSTANCE": instance,
                                         "LOOP": 1,
                                         "DYNAMIC": 1 if options.dynamic else 0,
                                         "THREADS": nthreads,
                                         "RUNMAX": runmax,
                                         "POPSIZE": popsize,
                                         "OFFSPRINGS": popsize*7,
                                         "MAXSECONDS": maxseconds,
                                         "GENSTEADY": 50,
                                         "TIME_FILENAME": time_filename,
                                         "RES_FILENAME": res_filename,
                                         "PLAN_FILENAME": plan_filename,
                                         }
                    local_logger.debug(cmd)
                    if options.execute:
                        os.system( cmd )
                    if options.plot:
                        try:
                            f = open(time_filename).readlines()
                            t1 = float(f[1].split()[-1])
                            tp = f[4].split()[-1].split(':')
                            tp = float(int(tp[0]) * 60 + float(tp[1]))
                            subdata.append([t1, tp, t1 / tp])
                        except IOError:
                            pass

                if options.plot:
                    if len(subdata):
                        plotdata.append(subdata)

            if options.plot:
                local_logger.info(plotdata)
                pylab.boxplot( plotdata )

def graphDepthComparison(benchType):
    clf()
    
    data = filter(table,
                  timestamp=range(1336921433, 1336922429+1),
                  benchType=benchType)
    writeUnits = 160
    
    xData = project(data, 'depth')
    yData = project(data, 'latency')
    
    print len(xData)
    print len(yData)
    
    # Each sample represents 5 trials.
    yData = map(lambda x:x/5, yData)
    
    (xData, yData) = condense(xData, yData)
    
    pylab.boxplot(yData)
    fmt = ticker.FixedFormatter(map(str, xData))
    ax = gca()
    ax.get_xaxis().set_major_formatter(fmt)
    ax.set_ylabel("Sequential 4K block write latency (s)")
    ax.set_xlabel("Depth (number of parent directories)")
    ax.get_yaxis().grid(color='gray', linestyle='dashed')
    ax.get_yaxis().set_major_locator(ticker.MaxNLocator(10))
    title('Backend: DynamoDB; Provisioning Units = %d' % writeUnits)
    pylab.ylim([0,0.1])
    
    pylab.show()

def graphPageSizeComparison(benchType, backend, writeUnits):
    clf()
    
    data = filter(table,
                  benchType=benchType,
                  backend=backend,
                  writeUnits=writeUnits)
    
    xData = project(data, 'pageSize')
    yData = project(data, 'latency')
    
    # Each sample represents 10 trials.
    yData = map(lambda x:x/10, yData)
    
    (xData, yData) = condense(xData, yData)
    
    pylab.boxplot(yData)
    fmt = ticker.FixedFormatter(map(str, xData))
    ax = gca()
    ax.get_xaxis().set_major_formatter(fmt)
    ax.set_ylabel("Sequential 4K block write latency (s)")
    ax.set_xlabel("Page size (B)")
    ax.get_yaxis().grid(color='gray', linestyle='dashed')
    ax.get_yaxis().set_major_locator(ticker.MaxNLocator(15))
    if backend == 's3':
        title('Backend: S3')
    else:
        title('Backend: DynamoDB; Provisioning Units = %d' % writeUnits)
    
    pylab.show()

def plot_res_paper(df):
    """

    :param df:  contain field classifier_name, accuarcy, and fold
    :return:
    """
    ticks = []
    i = 0
    data_to_plot = []
    for g, v in df.groupby(df.classifier_name):
        data_to_plot.append(v['accuracy'].values)
        ticks.append(g)
        print v
    pylab.boxplot(data_to_plot)
    pylab.xticks(range(1, 1+ len(data_to_plot)), ticks)



    pylab.gca().invert_xaxis()
    pylab.ylabel('Classification accuracy')
    pylab.xlabel('Fold (cross validation fold for test)')
    pylab.gca().yaxis.set_ticks(np.arange(0, 1, 0.1))
    pylab.ylim((0,1))
    pylab.legend()
    pylab.show()
    return

    def genderBoxplots(self, women, men, labels, path):
        data = [women.edition_count.values, men.edition_count.values]

        plt.figure()
        plt.boxplot(data)

        # mark the mean
        means = [np.mean(x) for x in data]
        print(means)

        plt.scatter(range(1, len(data) + 1), means, color="red", marker=">", s=20)
        plt.ylabel("num editions")
        plt.xticks(range(1, len(data) + 1), labels)
        plt.savefig(
            path + "/numeditions_gender_box_withOutlier" + self.pre + "-" + self.post + ".png", bbox_inches="tight"
        )

        plt.figure()
        plt.boxplot(data, sym="")
        # mark the mean
        means = [np.mean(x) for x in data]
        print(means)

        plt.scatter(range(1, len(data) + 1), means, color="red", marker=">", s=20)
        plt.ylabel("num editions")
        plt.xticks(range(1, len(data) + 1), labels)
        plt.savefig(path + "/numeditions_gender_box" + self.pre + "-" + self.post + ".png", bbox_inches="tight")

def finalgen(names):
    names = eval(names)
    totaleff = []
    for name in names:
        resultsfolder = "results/"+name+"/"
        final = resultsfolder + "gen049.dat"
        population = []
        name = final.rstrip('.dat')
        efflist = []

        resultsfile = open(final, 'r')
        for line in resultsfile:
            population.append(eval(line))

        for indiv in population:
            # if "fullrandom" in name:
            #     print "found", name
            #     lift = indiv['fitness'][0] - 0.5
            # else:
            lift = indiv['fitness'][0]
            drag = 5.0 - indiv['fitness'][1]
            efficiency = lift/drag
            efflist.append(efficiency)
        aveeff = ave(efflist)
        stdeff = std(efflist,aveeff)
        print "efficieny average", aveeff, "+-", stdeff
        totaleff.append(efflist)
    pylab.boxplot(totaleff)
    pylab.show()
    
    bwblift, bwbdrag = LIFT, 5 - DRAG
    print "bwbefficiency", bwblift/bwbdrag

def analyze(real, samples, skip=0, thr=0.9):
  real = pickle.load(open(real, 'rb'))
  samples = pickle.load(open(samples, 'rb'))
  thr=float(thr)

  def flatten(measurements):
    shared, exclusive = [], []
    for es, ss in measurements:
      exclusive.extend(es[skip:])
      shared.extend(ss[skip:])
    return exclusive, shared

  true_values = OrderedDict()
  for vm, measurements in real.results.items():
    shared, exclusive = flatten(measurements)
    true_values[vm] = mean(shared)/mean(exclusive)
  print(true_values)

  means = OrderedDict()
  nums = []
  avgms, avgdevs = [], []
  #for vm, measurements in sorted(samples.results.items()):
  for vm, measurements in sorted(samples.results.items()):
    print("calculating", vm)
    shared, exclusive = flatten(measurements)
    def myfilter(l): return [e for e in l if e != 0]
    shared = myfilter(shared)
    exclusive = myfilter(exclusive)
    ns = []
    true = true_values[vm]
    for _ in range(1000):
      sh_samples, exc_samples = [], []
      n = 0
      while True:
        n += 1
        sh_samples.append(choice(shared))
        exc_samples.append(choice(exclusive))
        cur = mean(sh_samples)/mean(exc_samples)
        prec = 1 - abs(1-cur/true)
        if prec > thr:
          ns.append(n)
          break
        if n > 20:
          print(vm, "max precision:", prec)
          break
    if not ns:
      print("no data points for", vm)
      continue
    nums.append(ns)
    #m = mean(ns)
    #d = pstdev(ns)
    #rd = d/m*100
    #avgdevs.append(rd)
    #avgms.append(m)
    #print("{vm}: {m:.1f} {rd:.1f}%".format(vm=vm, m=m,d=d,rd=rd))
    #means[vm]=mean(nums)
  ticks = real.mapping
  p.xticks(range(len(ticks)), ticks)
  p.boxplot(nums)

def main():
    # exon, intron, unknown
    specific = [[], [], []]
    nonspecific = [[], [], []]
    foldspecific = [[], [], []]
    foldnonspecific = [[], [], []]
    for prefix in sys.argv[1:]:
        tempexonic, tempspecific, tempnonspecific, tempfoldspecific, tempfoldnonspecific, templength = getData(
            prefix + ".exonic.overlap.out.annotation.txt", ["exon"]
        )
        exonic = tempexonic[0]
        exoniclength = templength[0]
        specific[0].append(tempspecific[0])
        nonspecific[0].append(tempnonspecific[0])
        foldspecific[0].append(tempfoldspecific[0])
        foldnonspecific[0].append(tempfoldnonspecific[0])
        tempData, tempspecific, tempnonspecific, tempfoldspecific, tempfoldnonspecific, templength = getData(
            prefix + ".novel.overlap.out.annotation.txt", ["intron", "unknown"]
        )
        intronic = tempData[0]
        unknown = tempData[1]
        introniclength = templength[0]
        unknownlength = templength[1]
        specific[1].append(tempspecific[0])
        specific[2].append(tempspecific[1])
        nonspecific[1].append(tempnonspecific[0])
        nonspecific[2].append(tempnonspecific[1])
        foldspecific[1].append(tempfoldspecific[0])
        foldspecific[2].append(tempfoldspecific[1])
        foldnonspecific[1].append(tempfoldnonspecific[0])
        foldnonspecific[2].append(tempfoldnonspecific[1])
        plotData = [exonic, intronic, unknown]
        print prefix
        print "exonic: ", len(exonic)
        print "intronic: ", len(intronic)
        print "unknown: ", len(unknown)
        fig = pl.figure()
        pl.boxplot(plotData)
        pl.ylim([2, 15])
        pl.ylabel("Log Expression Level")
        pl.xticks([1, 2, 3], ["Exonic", "Intronic", "Unknown"])
        pl.title(prefix.replace("_fsorted", "").replace("_", " "))
        fig.savefig(prefix + ".expression.png", dpi=fig.dpi)

        fig = pl.figure()
        pl.boxplot([exoniclength, introniclength, unknownlength])
        pl.ylim([60, 2500])
        pl.ylabel("Transcript Length")
        pl.xticks([1, 2, 3], ["Exonic", "Intronic", "Unknown"])
        pl.title(prefix.replace("_fsorted", "").replace("_", " "))
        fig.savefig(prefix + ".length.png", dpi=fig.dpi)
        # pl.show()
    abbr = []
    for i in sys.argv[1:]:
        tokens = i.split("_")
        abbr.append(tokens[0][0].upper() + tokens[1][0:2].title())
    plotSpec(specific, nonspecific, abbr, ["exonic", "intronic", "unknown"], "abs")
    plotSpec(foldspecific, foldnonspecific, abbr, ["exonic", "intronic", "unknown"], "fold")