pandas - 多索引绘图

Question

我有一些数据，我使用以下代码操作了数据框：

import pandas as pd
import numpy as np

data = pd.DataFrame([[0,0,0,3,6,5,6,1],[1,1,1,3,4,5,2,0],[2,1,0,3,6,5,6,1],[3,0,0,2,9,4,2,1],[4,0,1,3,4,8,1,1],[5,1,1,3,3,5,9,1],[6,1,0,3,3,5,6,1],[7,0,1,3,4,8,9,1]], columns=["id", "sex", "split", "group0Low", "group0High", "group1Low", "group1High", "trim"])
data

#remove all where trim == 0
trimmed = data[(data.trim == 1)]
trimmed

#create df with columns to be split
columns = ['group0Low', 'group0High', 'group1Low', 'group1High']
to_split = trimmed[columns]
to_split

level_group = np.where(to_split.columns.str.contains('0'), 0, 1)
# output: array([0, 0, 1, 1])
level_low_high = np.where(to_split.columns.str.contains('Low'), 'low', 'high')
# output: array(['low', 'high', 'low', 'high'], dtype='<U4')

multi_level_columns = pd.MultiIndex.from_arrays([level_group, level_low_high], names=['group', 'val'])
to_split.columns = multi_level_columns
to_split.stack(level='group')

sex = trimmed['sex']
split = trimmed['split']
horizontalStack = pd.concat([sex, split, to_split], axis=1)
horizontalStack

finalData = horizontalStack.groupby(['split', 'sex', 'group'])
finalData.mean()

我的问题是，我如何使用 ggplot 或 seaborn 绘制平均数据，这样对于每个“拆分”级别，我都会得到一个如下所示的图表：

在代码的底部，您可以看到我尝试拆分组因子以便可以分隔条，但这导致了错误 (KeyError: 'group')，我认为这与我使用多索引的方式

Answer 1

我会使用 seaborn 的因子图。

假设你有这样的数据：

import numpy as np
import pandas

import seaborn
seaborn.set(style='ticks') 
np.random.seed(0)

groups = ('Group 1', 'Group 2')
sexes = ('Male', 'Female')
means = ('Low', 'High')
index = pandas.MultiIndex.from_product(
    [groups, sexes, means], 
   names=['Group', 'Sex', 'Mean']
)

values = np.random.randint(low=20, high=100, size=len(index))
data = pandas.DataFrame(data={'val': values}, index=index).reset_index()
print(data)

     Group     Sex  Mean  val
0  Group 1    Male   Low   64
1  Group 1    Male  High   67
2  Group 1  Female   Low   84
3  Group 1  Female  High   87
4  Group 2    Male   Low   87
5  Group 2    Male  High   29
6  Group 2  Female   Low   41
7  Group 2  Female  High   56

然后，您可以使用一个命令 + 加上一条额外的线来创建因子图，以删除一些冗余（对于您的数据）x-labels：

fg = seaborn.factorplot(x='Group', y='val', hue='Mean', 
                        col='Sex', data=data, kind='bar')
fg.set_xlabels('')

这给了我：

Answer 2

在related question 中，我找到了@Stein 的替代解决方案，它将多索引级别编码为不同的标签。以下是您的示例的外观：

import pandas as pd
import matplotlib.pyplot as plt
from itertools import groupby
import numpy as np 
%matplotlib inline

groups = ('Group 1', 'Group 2')
sexes = ('Male', 'Female')
means = ('Low', 'High')
index = pd.MultiIndex.from_product(
    [groups, sexes, means], 
   names=['Group', 'Sex', 'Mean']
)

values = np.random.randint(low=20, high=100, size=len(index))
data = pd.DataFrame(data={'val': values}, index=index)
# unstack last level to plot two separate columns
data = data.unstack(level=-1)

def add_line(ax, xpos, ypos):
    line = plt.Line2D([xpos, xpos], [ypos + .1, ypos],
                      transform=ax.transAxes, color='gray')
    line.set_clip_on(False)
    ax.add_line(line)

def label_len(my_index,level):
    labels = my_index.get_level_values(level)
    return [(k, sum(1 for i in g)) for k,g in groupby(labels)]

def label_group_bar_table(ax, df):
    ypos = -.1
    scale = 1./df.index.size
    for level in range(df.index.nlevels)[::-1]:
        pos = 0
        for label, rpos in label_len(df.index,level):
            lxpos = (pos + .5 * rpos)*scale
            ax.text(lxpos, ypos, label, ha='center', transform=ax.transAxes)
            add_line(ax, pos*scale, ypos)
            pos += rpos
        add_line(ax, pos*scale , ypos)
        ypos -= .1

ax = data['val'].plot(kind='bar')
#Below 2 lines remove default labels
ax.set_xticklabels('')
ax.set_xlabel('')
label_group_bar_table(ax, data)

这给出了：