Python数据可视化（七）：箱线图绘制

使用seaborn包绘制箱线图

# libraries & dataset
import seaborn as sns
import matplotlib.pyplot as plt
# set a grey background (use sns.set_theme() if seaborn version 0.11.0 or above) 
sns.set(style="darkgrid")

# 加载示例数据集
df = sns.load_dataset('iris')
df.head()

	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

# 绘制基础箱线图
sns.boxplot(y=df["sepal_length"])
plt.show()

image.png

# 绘制多个变量的箱线图
sns.boxplot(data=df.loc[:, ['sepal_length', 'sepal_width']])
plt.show()

image.png

# 绘制分组箱线图
sns.boxplot(x=df["species"], y=df["sepal_length"])
plt.show()

image.png

# 添加扰动点
# boxplot
ax = sns.boxplot(x='species', y='sepal_length', data=df)
# add stripplot
ax = sns.stripplot(x='species', y='sepal_length', data=df, color="orange", jitter=0.2, size=4)

# add title
plt.title("Boxplot with jitter", loc="left")

# show the graph
plt.show()

image.png

# 设置linewidth参数自定义边框线的宽度
sns.boxplot(x=df["species"], y=df["sepal_length"], linewidth=5)
plt.show()

image.png

# 设置notch=True参数添加缺口
sns.boxplot(x=df["species"], y=df["sepal_length"], notch=True)
plt.show()

image.png

# 设置width参数之定义箱型的宽度
sns.boxplot(x=df["species"], y=df["sepal_length"], width=0.3)
plt.show()

image.png

# 自定义颜色
# 设置palette参数自定义颜色画板
sns.boxplot(x=df["species"], y=df["sepal_length"], palette="Blues")
plt.show()

image.png

# 设置color参数自定义颜色
sns.boxplot(x=df["species"], y=df["sepal_length"], color='skyblue')
plt.show()

image.png

# 对每组设置不同的颜色
my_pal = {"versicolor": "g", "setosa": "b", "virginica":"m"}
sns.boxplot(x=df["species"], y=df["sepal_length"], palette=my_pal)
plt.show()

image.png

# 设置order参数自定义分组的排序
sns.boxplot(x='species', y='sepal_length', data=df, order=["versicolor", "virginica", "setosa"])
plt.show()

image.png

# 根据每组的中位数进行降序排序
# Find the order
my_order = df.groupby(by=["species"])["sepal_length"].median().iloc[::-1].index

# Give it to the boxplot
sns.boxplot(x='species', y='sepal_length', data=df, order=my_order)
plt.show()

image.png

# 添加文本注释标签
ax = sns.boxplot(x="species", y="sepal_length", data=df)

# Calculate number of obs per group & median to position labels
medians = df.groupby(['species'])['sepal_length'].median().values
nobs = df['species'].value_counts().values
nobs = [str(x) for x in nobs.tolist()]
nobs = ["n: " + i for i in nobs]

# Add it to the plot
pos = range(len(nobs))
for tick,label in zip(pos,ax.get_xticklabels()):
    ax.text(pos[tick],
            medians[tick] + 0.03,
            nobs[tick],
            horizontalalignment='center',
            size='x-small',
            color='w',
            weight='semibold')

plt.show()

image.png

# 按分组变量填充颜色
df = sns.load_dataset('tips')
df.head()

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4

sns.boxplot(x="day", y="total_bill", hue="smoker", data=df, palette="Set1", width=0.5)
plt.show()

image.png

# Grouped violinplot
sns.violinplot(x="day", y="total_bill", hue="smoker", data=df, palette="Pastel1")
plt.show()

image.png

参考来源：https://www.python-graph-gallery.com/boxplot/