在 matplotlib、seaborn 中为多个绘图创建单个图例

Create a single legend for multiple plot in matplotlib, seaborn

我正在使用 "iris.csv" 数据制作箱线图。我试图通过测量(即花瓣长度、花瓣宽度、萼片长度、萼片宽度)将数据分成多个数据框,然后在 forloop 上制作箱线图,从而添加子图。

最后,我想一次为所有箱形图添加一个通用图例。但是,我做不到。我已经使用几个 Whosebug 问题尝试了几个教程和方法,但我无法修复它。

这是我的代码:

import seaborn as sns 
from matplotlib import pyplot

iris_data = "iris.csv"
names = ['sepal-length', 'sepal-width', 'petal-length', 'petal-width', 'class']
dataset = read_csv(iris_data, names=names)


# Reindex the dataset by species so it can be pivoted for each species 
reindexed_dataset = dataset.set_index(dataset.groupby('class').cumcount())
cols_to_pivot = ['sepal-length', 'sepal-width', 'petal-length', 'petal-width']

# empty dataframe 
reshaped_dataset = pd.DataFrame()
for var_name in cols_to_pivot:
    pivoted_dataset = reindexed_dataset.pivot(columns='class', values=var_name).rename_axis(None,axis=1)
    pivoted_dataset['measurement'] = var_name
    reshaped_dataset = reshaped_dataset.append(pivoted_dataset, ignore_index=True)


## Now, lets spit the dataframe into groups by-measurements.
grouped_dfs_02 = []
for group in reshaped_dataset.groupby('measurement') :
    grouped_dfs_02.append(group[1])


## make the box plot of several measured variables, compared between species 

pyplot.figure(figsize=(20, 5), dpi=80)
pyplot.suptitle('Distribution of floral traits in the species of iris')

sp_name=['Iris-setosa', 'Iris-versicolor', 'Iris-virginica']
setosa = mpatches.Patch(color='red')
versi = mpatches.Patch(color='green')
virgi = mpatches.Patch(color='blue')

my_pal = {"Iris-versicolor": "g", "Iris-setosa": "r", "Iris-virginica":"b"}
plt_index = 0


# for i, df in enumerate(grouped_dfs_02):
for group_name, df in reshaped_dataset.groupby('measurement'):

    axi = pyplot.subplot(1, len(grouped_dfs_02), plt_index + 1)
    sp_name=['Iris-setosa', 'Iris-versicolor', 'Iris-virginica']
    df_melt = df.melt('measurement', var_name='species', value_name='values')

    sns.boxplot(data=df_melt, x='species', y='values', ax = axi, orient="v", palette=my_pal)
    pyplot.title(group_name)
    plt_index += 1


# Move the legend to an empty part of the plot
pyplot.legend(title='species', labels = sp_name, 
         handles=[setosa, versi, virgi], bbox_to_anchor=(19, 4),
           fancybox=True, shadow=True, ncol=5)


pyplot.show()

剧情如下:

如何在主图中添加一个普通的图例,在主图之外,在"main suptitle"旁边?

要定位图例,重要的是设置 loc 参数作为锚点。 (默认的 loc'best',这意味着您事先不知道它会在哪里结束)。位置是从0,0(当前斧头的左下角)到1,1:当前斧头的左上角。这不包括标题等的填充,因此值可能会超出 0, 1 范围。 "current ax" 是最后激活的。

请注意,除了 plt.legend(使用轴),您还可以使用 plt.gcf().legend,它使用 "figure"。然后,坐标为完整图左下角的0,0(即"figure")和右上角的1,1。缺点是不会为图例创建额外的 space,因此您需要手动设置顶部填充(例如 plt.gcf().subplots_adjust(top=0.8))。一个缺点是您不能再使用 plt.tight_layout(),并且很难将图例与轴对齐。

import seaborn as sns
from matplotlib import pyplot as plt
from matplotlib import patches as mpatches
import pandas as pd

dataset = sns.load_dataset("iris")

# Reindex the dataset by species so it can be pivoted for each species
reindexed_dataset = dataset.set_index(dataset.groupby('species').cumcount())
cols_to_pivot = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width']

# empty dataframe
reshaped_dataset = pd.DataFrame()
for var_name in cols_to_pivot:
    pivoted_dataset = reindexed_dataset.pivot(columns='species', values=var_name).rename_axis(None, axis=1)
    pivoted_dataset['measurement'] = var_name
    reshaped_dataset = reshaped_dataset.append(pivoted_dataset, ignore_index=True)

## Now, lets spit the dataframe into groups by-measurements.
grouped_dfs_02 = []
for group in reshaped_dataset.groupby('measurement'):
    grouped_dfs_02.append(group[1])

## make the box plot of several measured variables, compared between species
plt.figure(figsize=(20, 5), dpi=80)
plt.suptitle('Distribution of floral traits in the species of iris')

sp_name = ['Iris-setosa', 'Iris-versicolor', 'Iris-virginica']
setosa = mpatches.Patch(color='red')
versi = mpatches.Patch(color='green')
virgi = mpatches.Patch(color='blue')

my_pal = {"versicolor": "g", "setosa": "r", "virginica": "b"}
plt_index = 0

# for i, df in enumerate(grouped_dfs_02):
for group_name, df in reshaped_dataset.groupby('measurement'):
    axi = plt.subplot(1, len(grouped_dfs_02), plt_index + 1)
    sp_name = ['Iris-setosa', 'Iris-versicolor', 'Iris-virginica']
    df_melt = df.melt('measurement', var_name='species', value_name='values')

    sns.boxplot(data=df_melt, x='species', y='values', ax=axi, orient="v", palette=my_pal)
    plt.title(group_name)
    plt_index += 1

# Move the legend to an empty part of the plot
plt.legend(title='species', labels=sp_name,
           handles=[setosa, versi, virgi], bbox_to_anchor=(1, 1.23),
           fancybox=True, shadow=True, ncol=5, loc='upper right')
plt.tight_layout()
plt.show()

  • 以下实现将重构代码以生成绘图并根据 how do I make a single legend for many subplots with matplotlib? 添加图例
  • 鸢尾花数据集已经是 seaborn 的一部分,它作为数据框加载。
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# load iris data
iris = sns.load_dataset("iris")

   sepal_length  sepal_width  petal_length  petal_width species
0           5.1          3.5           1.4          0.2  setosa
1           4.9          3.0           1.4          0.2  setosa
2           4.7          3.2           1.3          0.2  setosa
3           4.6          3.1           1.5          0.2  setosa
4           5.0          3.6           1.4          0.2  setosa

# create figure
fig = plt.figure(figsize=(20, 5), dpi=80)

# add subplots
for i, col in enumerate(iris.columns[:-1], 1):
    plt.subplot(1, 4, i)
    ax = sns.boxplot(x='species', y=col, data=iris, hue='species')
    ax.get_legend().remove()
    plt.title(col)

# add legend
handles, labels = ax.get_legend_handles_labels()
fig.legend(handles, labels, loc='upper right', ncol=3, bbox_to_anchor=(.75, 0.98))

# add subtitle
fig.suptitle('Distribution of floral traits in the species of iris')

plt.show()