Fernando Perez wrote: > > Please! That example with the top labels looks great, and it's a very > useful way of displaying the numerical key parts of the dataset. > > Cheers, > > f >
OK, here is a bloxplot example based on the one previously shown. I just replaced my environmental data with some random data to make things easier to run, and accordingly I had to make up some story around the data (testing bootstrap resampling). Fee free to rework the code as you see fit, but hopefully this is a helpful example. http://www.nabble.com/file/p24764036/boxplotExampleForums.png -------------------------- boxplotdemo.py -------------------------- import numpy as np import matplotlib.pyplot as plt from matplotlib.patches import Polygon #Generate some data from five different probability distributions, each with #different characteristics. We want to play with how an IID bootstrap resample #of the data preserves the distributional properties of the original sample, and #a boxplot is one visual tool to make this assessment numDists = 5 randomDists = ['Normal(1,1)',' Lognormal(1,1)', 'Exp(1)', 'Gumbel(6,4)', 'Triangular(2,9,11)'] N = 500 norm = np.random.normal(1,1, N) logn = np.random.lognormal(1,1, N) expo = np.random.exponential(1, N) gumb = np.random.gumbel(6, 4, N) tria = np.random.triangular(2, 9, 11, N) #Generate some random indices that we'll use to resample the original data #arrays. For code brevity, just use the same random indices for each array bootstrapIndices = np.random.random_integers(0, N-1, N) normBoot = norm[bootstrapIndices] expoBoot = expo[bootstrapIndices] gumbBoot = gumb[bootstrapIndices] lognBoot = logn[bootstrapIndices] triaBoot = tria[bootstrapIndices] data = [norm, normBoot, logn, lognBoot, expo, expoBoot, gumb, gumbBoot, tria, triaBoot] fig = plt.figure(figsize=(10,6)) fig.canvas.set_window_title('A Boxplot Example') ax1 = fig.add_subplot(111) plt.subplots_adjust(left=0.075, right=0.95, top=0.9, bottom=0.25) bp = plt.boxplot(data, notch=0, sym='+', vert=1, whis=1.5) plt.setp(bp['boxes'], color='black') plt.setp(bp['whiskers'], color='black') plt.setp(bp['fliers'], color='red', marker='+') #Add a horizontal grid to the plot, but make it very light in color so we can #use it for reading data values but not be distracting ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5) #Hide these grid behind plot objects ax1.set_axisbelow(True) ax1.set_title('Comparison of IID Bootstrap Resampling Across Five Distributions') ax1.set_xlabel('Distribution') ax1.set_ylabel('Value') #Now fill the boxes with desired colors boxColors = ['darkkhaki','royalblue'] numBoxes = numDists*2 medians = range(numBoxes) for i in range(numBoxes): box = bp['boxes'][i] boxX = [] boxY = [] for j in range(5): boxX.append(box.get_xdata()[j]) boxY.append(box.get_ydata()[j]) boxCoords = zip(boxX,boxY) #Alternate between Dark Khaki and Royal Blue k = i % 2 boxPolygon = Polygon(boxCoords, facecolor=boxColors[k]) ax1.add_patch(boxPolygon) #Now draw the median lines back over what we just filled in med = bp['medians'][i] medianX = [] medianY = [] for j in range(2): medianX.append(med.get_xdata()[j]) medianY.append(med.get_ydata()[j]) plt.plot(medianX, medianY, 'k') medians[i] = medianY[0] #Finally, overplot the sample averages, with horixzontal alignment in the #center of each box plt.plot([np.average(med.get_xdata().data)], [np.average(data[i])], color='w', marker='*', markeredgecolor='k') #Set the axes ranges and axes labels ax1.set_xlim(0.5, numBoxes+0.5) top = 40 bottom = -5 ax1.set_ylim(bottom, top) xtickNames = plt.setp(ax1, xticklabels=np.repeat(randomDists, 2)) plt.setp(xtickNames, rotation=45, fontsize=8) #Due to the Y-axis scale being different across samples, it can be hard to #compare differences in medians across the samples. Add upper X-axis tick labels #with the sample medians to aid in comparison (just use two decimal places of #precision) pos = np.arange(numBoxes)+1 upperLabels = [str(np.round(s, 2)) for s in medians] weights = ['bold', 'semibold'] for tick,label in zip(range(numBoxes),ax1.get_xticklabels()): k = tick % 2 ax1.text(pos[tick], top-(top*0.05), upperLabels[tick], horizontalalignment='center', size='x-small', weight=weights[k], color=boxColors[k]) #Finally, add a basic legend plt.figtext(0.80, 0.08, str(N) + ' Random Numbers' , backgroundcolor=boxColors[0], color='black', weight='roman', size='x-small') plt.figtext(0.80, 0.045, 'IID Bootstrap Resample', backgroundcolor=boxColors[1], color='white', weight='roman', size='x-small') plt.figtext(0.80, 0.015, '*', color='white', backgroundcolor='silver', weight='roman', size='medium') plt.figtext(0.815, 0.013, ' Average Value', color='black', weight='roman', size='x-small') plt.show() ----- Josh Hemann Statistical Advisor http://www.vni.com/ Visual Numerics jhem...@vni.com | P 720.407.4214 | F 720.407.4199 -- View this message in context: http://www.nabble.com/Radar---Spider-Chars-tp17876254p24764036.html Sent from the matplotlib - users mailing list archive at Nabble.com. ------------------------------------------------------------------------------ Let Crystal Reports handle the reporting - Free Crystal Reports 2008 30-Day trial. Simplify your report design, integration and deployment - and focus on what you do best, core application coding. Discover what's new with Crystal Reports now. http://p.sf.net/sfu/bobj-july _______________________________________________ Matplotlib-users mailing list Matplotlib-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/matplotlib-users
