matplotlib：组箱形图
有没有办法在matplotlib中将boxlot分组？
假设我们有三个“A”，“B”和“C”组，每个我们都想为“苹果”和“桔子”创build一个盒子。 如果分组不可能直接进行，我们可以创build所有六个组合并将它们并排排列。 什么是最简单的方式来可视化的分组？ 我试图避免将刻度标签设置为“A +苹果”之类的东西，因为我的场景涉及比“A”更长的名称。
如何使用颜色来区分“苹果”和“橙子”和间隔来分隔“A”，“B”和“C”？
像这样的东西：
from pylab import plot, show, savefig, xlim, figure, \ hold, ylim, legend, boxplot, setp, axes # function for setting the colors of the box plots pairs def setBoxColors(bp): setp(bp['boxes'][0], color='blue') setp(bp['caps'][0], color='blue') setp(bp['caps'][1], color='blue') setp(bp['whiskers'][0], color='blue') setp(bp['whiskers'][1], color='blue') setp(bp['fliers'][0], color='blue') setp(bp['fliers'][1], color='blue') setp(bp['medians'][0], color='blue') setp(bp['boxes'][1], color='red') setp(bp['caps'][2], color='red') setp(bp['caps'][3], color='red') setp(bp['whiskers'][2], color='red') setp(bp['whiskers'][3], color='red') setp(bp['fliers'][2], color='red') setp(bp['fliers'][3], color='red') setp(bp['medians'][1], color='red') # Some fake data to plot A= [[1, 2, 5,], [7, 2]] B = [[5, 7, 2, 2, 5], [7, 2, 5]] C = [[3,2,5,7], [6, 7, 3]] fig = figure() ax = axes() hold(True) # first boxplot pair bp = boxplot(A, positions = [1, 2], widths = 0.6) setBoxColors(bp) # second boxplot pair bp = boxplot(B, positions = [4, 5], widths = 0.6) setBoxColors(bp) # thrid boxplot pair bp = boxplot(C, positions = [7, 8], widths = 0.6) setBoxColors(bp) # set axes limits and labels xlim(0,9) ylim(0,9) ax.set_xticklabels(['A', 'B', 'C']) ax.set_xticks([1.5, 4.5, 7.5]) # draw temporary red and blue lines and use them to create a legend hB, = plot([1,1],'b-') hR, = plot([1,1],'r-') legend((hB, hR),('Apples', 'Oranges')) hB.set_visible(False) hR.set_visible(False) savefig('boxcompare.png') show() 
一个简单的方法是使用pandas 。 我从绘图文档中调整了一个例子：
In [1]: import pandas as pd In [2]: df = pd.DataFrame(np.random.rand(12,2), columns=['Apples', 'Oranges'] ) In [3]: df['Categories'] = pd.Series(list('AAAABBBBCCCC')) In [4]: pd.options.display.mpl_style = 'default' In [5]: df.boxplot(by='Categories') Out[5]: array([<matplotlib.axes.AxesSubplot object at 0x51a5190>, <matplotlib.axes.AxesSubplot object at 0x53fddd0>], dtype=object)
这是我的版本。 它存储基于类别的数据。
import matplotlib.pyplot as plt import numpy as np data_a = [[1,2,5], [5,7,2,2,5], [7,2,5]] data_b = [[6,4,2], [1,2,5,3,2], [2,3,5,1]] mu = [3.93, 7.761, 14.319] alpha = [0.9996197532958419, 0.9702573729698682, 0.9375845650647818] ticks = ['A', 'B', 'C'] def set_box_color(bp, color): plt.setp(bp['boxes'], color=color) plt.setp(bp['whiskers'], color=color) plt.setp(bp['caps'], color=color) plt.setp(bp['medians'], color=color) plt.figure() bpl = plt.boxplot(data_a, positions=np.array(xrange(len(data_a)))*2.0-0.4, sym='', widths=0.6) bpr = plt.boxplot(data_b, positions=np.array(xrange(len(data_b)))*2.0+0.4, sym='', widths=0.6) set_box_color(bpl, '#D7191C') # colors are from http://colorbrewer2.org/ set_box_color(bpr, '#2C7BB6') # draw temporary red and blue lines and use them to create a legend plt.plot([], c='#D7191C', label='Apples') plt.plot([], c='#2C7BB6', label='Oranges') plt.legend() plt.xticks(xrange(0, len(ticks) * 2, 2), ticks) plt.xlim(-2, len(ticks)*2) plt.ylim(0, 8) plt.tight_layout() plt.savefig('boxcompare.png')
我缺乏声誉，所以我不能在这里发表一个图片。 您可以运行它并查看结果。 基本上和Molly非常相似。
为了增加对话，我find了一种更优雅的方式，通过迭代对象本身的字典来改变盒子的颜色
import numpy as np import matplotlib.pyplot as plt def color_box(bp, color): # Define the elements to color. You can also add medians, fliers and means elements = ['boxes','caps','whiskers'] # Iterate over each of the elements changing the color for elem in elements: [plt.setp(bp[elem][idx], color=color) for idx in xrange(len(bp[elem]))] return a = np.random.uniform(0,10,[100,5]) bp = plt.boxplot(a) color_box(bp, 'red')
干杯!
一些假数据
df = pd.DataFrame({'Group':['A','A','A','B','C','B','B','C','A','C'],\ 'Apple':np.random.rand(10),'Orange':np.random.rand(10)}) df = df[['Group','Apple','Orange']] Group Apple Orange 0 A 0.465636 0.537723 1 A 0.560537 0.727238 2 A 0.268154 0.648927 3 B 0.722644 0.115550 4 C 0.586346 0.042896 5 B 0.562881 0.369686 6 B 0.395236 0.672477 7 C 0.577949 0.358801 8 A 0.764069 0.642724 9 C 0.731076 0.302369
我想你应该使用Seaborn库来创build这些types的自定义图块。在你的情况下，我首先已经融化了你的数据框，将其转换成适当的格式，然后创build你select的boxplot。
Import pandas as pd import matplotlib.pyplot as plt Import seaborn as sns dd=pd.melt(df,id_vars=['Group'],value_vars=['Apple','Orange'],var_name='fruits') sns.boxplot(x='Group',y='value',data=dd,hue='fruits')
所以使用Seaborn编码非常简单。 
下面是我写的一个函数，它把Molly的代码和我在互联网上发现的一些其他代码做成稍微有点分组的箱形图：
import numpy as np import matplotlib.pyplot as plt def custom_legend(colors, labels, linestyles=None): """ Creates a list of matplotlib Patch objects that can be passed to the legend(...) function to create a custom legend. :param colors: A list of colors, one for each entry in the legend. You can also include a linestyle, for example: 'k--' :param labels: A list of labels, one for each entry in the legend. """ if linestyles is not None: assert len(linestyles) == len(colors), "Length of linestyles must match length of colors." h = list() for k,(c,l) in enumerate(zip(colors, labels)): clr = c ls = 'solid' if linestyles is not None: ls = linestyles[k] patch = patches.Patch(color=clr, label=l, linestyle=ls) h.append(patch) return h def grouped_boxplot(data, group_names=None, subgroup_names=None, ax=None, subgroup_colors=None, box_width=0.6, box_spacing=1.0): """ Draws a grouped boxplot. The data should be organized in a hierarchy, where there are multiple subgroups for each main group. :param data: A dictionary of length equal to the number of the groups. The key should be the group name, the value should be a list of arrays. The length of the list should be equal to the number of subgroups. :param group_names: (Optional) The group names, should be the same as data.keys(), but can be ordered. :param subgroup_names: (Optional) Names of the subgroups. :param subgroup_colors: A list specifying the plot color for each subgroup. :param ax: (Optional) The axis to plot on. """ if group_names is None: group_names = data.keys() if ax is None: ax = plt.gca() plt.sca(ax) nsubgroups = np.array([len(v) for v in data.values()]) assert len(np.unique(nsubgroups)) == 1, "Number of subgroups for each property differ!" nsubgroups = nsubgroups[0] if subgroup_colors is None: subgroup_colors = list() for k in range(nsubgroups): subgroup_colors.append(np.random.rand(3)) else: assert len(subgroup_colors) == nsubgroups, "subgroup_colors length must match number of subgroups (%d)" % nsubgroups def _decorate_box(_bp, _d): plt.setp(_bp['boxes'], lw=0, color='k') plt.setp(_bp['whiskers'], lw=3.0, color='k') # fill in each box with a color assert len(_bp['boxes']) == nsubgroups for _k,_box in enumerate(_bp['boxes']): _boxX = list() _boxY = list() for _j in range(5): _boxX.append(_box.get_xdata()[_j]) _boxY.append(_box.get_ydata()[_j]) _boxCoords = zip(_boxX, _boxY) _boxPolygon = plt.Polygon(_boxCoords, facecolor=subgroup_colors[_k]) ax.add_patch(_boxPolygon) # draw a black line for the median for _k,_med in enumerate(_bp['medians']): _medianX = list() _medianY = list() for _j in range(2): _medianX.append(_med.get_xdata()[_j]) _medianY.append(_med.get_ydata()[_j]) plt.plot(_medianX, _medianY, 'k', linewidth=3.0) # draw a black asterisk for the mean plt.plot([np.mean(_med.get_xdata())], [np.mean(_d[_k])], color='w', marker='*', markeredgecolor='k', markersize=12) cpos = 1 label_pos = list() for k in group_names: d = data[k] nsubgroups = len(d) pos = np.arange(nsubgroups) + cpos label_pos.append(pos.mean()) bp = plt.boxplot(d, positions=pos, widths=box_width) _decorate_box(bp, d) cpos += nsubgroups + box_spacing plt.xlim(0, cpos-1) plt.xticks(label_pos, group_names) if subgroup_names is not None: leg = custom_legend(subgroup_colors, subgroup_names) plt.legend(handles=leg)
你可以使用这样的function：
data = { 'A':[np.random.randn(100), np.random.randn(100) + 5], 'B':[np.random.randn(100)+1, np.random.randn(100) + 9], 'C':[np.random.randn(100)-3, np.random.randn(100) -5] } grouped_boxplot(data, group_names=['A', 'B', 'C'], subgroup_names=['Apples', 'Oranges'], subgroup_colors=['#D02D2E', '#D67700']) plt.show()
