在配对图中显示相关值

Question

我有以下数据：

prop_tenure  prop_12m  prop_6m  
0.00         0.00      0.00   
0.00         0.00      0.00   
0.06         0.06      0.10   
0.38         0.38      0.25   
0.61         0.61      0.66   
0.01         0.01      0.02   
0.10         0.10      0.12   
0.04         0.04      0.04   
0.22         0.22      0.22 

我正在做一个配对图，如下所示：

sns.pairplot(data)
plt.show()

但是我想显示变量之间的相关系数，如果可能的话，显示每个变量的偏度和峰度。 你如何在seaborn中做到这一点？

Answer 1

据我所知，没有开箱即用的功能可以执行此操作，您必须创建自己的：

from scipy.stats import pearsonr
import matplotlib.pyplot as plt 

def corrfunc(x, y, ax=None, **kws):
    """Plot the correlation coefficient in the top left hand corner of a plot."""
    r, _ = pearsonr(x, y)
    ax = ax or plt.gca()
    ax.annotate(f'ρ = {r:.2f}', xy=(.1, .9), xycoords=ax.transAxes)

使用您的输入的示例：

import seaborn as sns; sns.set(style='white')
import pandas as pd

data = {'prop_tenure': [0.0, 0.0, 0.06, 0.38, 0.61, 0.01, 0.10, 0.04, 0.22], 
        'prop_12m':    [0.0, 0.0, 0.06, 0.38, 0.61, 0.01, 0.10, 0.04, 0.22], 
        'prop_6m':     [0.0, 0.0, 0.10, 0.25, 0.66, 0.02, 0.12, 0.04, 0.22]}

df = pd.DataFrame(data)

g = sns.pairplot(df)
g.map_lower(corrfunc)
plt.show()

Answer 2

顺便提一下，对于最新版本的seaborn（

>0.11.0

），上面的答案不再有效。但您需要添加一个

hue=None

才能使其再次工作。

def corrfunc(x, y, hue=None, ax=None, **kws):
    """Plot the correlation coefficient in the top left hand corner of a plot."""
    r, _ = pearsonr(x, y)
    ax = ax or plt.gca()
    ax.annotate(f'ρ = {r:.2f}', xy=(.1, .9), xycoords=ax.transAxes)

参考此问题https://github.com/mwaskom/seaborn/issues/2307#issuecomment-702980853

Answer 3

如果您正在寻找包含每个色调级别的相关值，我修改了上面的代码。觉得有用就点个赞吧

 def corrfunc(x, y, hue=None, ax=None, **kws):
    '''Plot the correlation coefficient in the bottom left hand corner of a plot.'''
    if hue is not None:
        hue_order = pd.unique(g.hue_vals)
        color_dict = dict(zip(hue_order, sns.color_palette('tab10', hue_order.shape[0]) ))
        groups = x.groupby(g.hue_vals)
        r_values = []
        for name, group in groups:
            mask = (~group.isnull()) & (~y[group.index].isnull())
            if mask.sum() > 0:
                r, _ = pearsonr(group[mask], y[group.index][mask])
                r_values.append((name, r))
        text = '\n'.join([f'{name}: ρ = {r:.2f}' for name, r in r_values])
        fontcolors = [color_dict[name] for name in hue_order]
        
    else:
        mask = (~x.isnull()) & (~y.isnull())
        if mask.sum() > 0:
            r, _ = pearsonr(x[mask], y[mask])
            text = f'ρ = {r:.2f}'
            fontcolors = 'grey'
            # print(fontcolors)
        else:
            text = ''
            fontcolors = 'grey'
        
    ax = ax or plt.gca()
    if hue is not None:
        for i, name in enumerate(hue_order):
            text_i = [f'{name}: ρ = {r:.2f}' for n, r in r_values if n==name][0]
            # print(text_i)
            color_i = fontcolors[i]
            ax.annotate(text_i, xy=(.02, .98-i*.05), xycoords='axes fraction', ha='left', va='top',
                        color=color_i, fontsize=10)
    else:
        ax.annotate(text, xy=(.02, .98), xycoords='axes fraction', ha='left', va='top',
                    color=fontcolors, fontsize=10)


penguins = sns.load_dataset('penguins')
g = sns.pairplot(penguins, hue='species',diag_kind='hist',kind='reg', plot_kws={'line_kws':{'color':'red'}})
g.map_lower(corrfunc, hue='species')