使用seaborn包繪制箱線圖

# 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")

# 加載示例數(shù)據(jù)集
df = sns.load_dataset('iris')
df.head()

# 繪制基礎(chǔ)箱線圖
sns.boxplot(y=df["sepal_length"])
plt.show()

image.png

# 繪制多個(gè)變量的箱線圖
sns.boxplot(data=df.loc[:, ['sepal_length', 'sepal_width']])
plt.show()

image.png

# 繪制分組箱線圖
sns.boxplot(x=df["species"], y=df["sepal_length"])
plt.show()

image.png

# 添加擾動(dòng)點(diǎn)
# 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

# 設(shè)置linewidth參數(shù)自定義邊框線的寬度
sns.boxplot(x=df["species"], y=df["sepal_length"], linewidth=5)
plt.show()

image.png

# 設(shè)置notch=True參數(shù)添加缺口
sns.boxplot(x=df["species"], y=df["sepal_length"], notch=True)
plt.show()

image.png

# 設(shè)置width參數(shù)之定義箱型的寬度
sns.boxplot(x=df["species"], y=df["sepal_length"], width=0.3)
plt.show()

image.png

# 自定義顏色
# 設(shè)置palette參數(shù)自定義顏色畫板
sns.boxplot(x=df["species"], y=df["sepal_length"], palette="Blues")
plt.show()

image.png

# 設(shè)置color參數(shù)自定義顏色
sns.boxplot(x=df["species"], y=df["sepal_length"], color='skyblue')
plt.show()

image.png

# 對(duì)每組設(shè)置不同的顏色
my_pal = {"versicolor": "g", "setosa": "b", "virginica":"m"}
sns.boxplot(x=df["species"], y=df["sepal_length"], palette=my_pal)
plt.show()

image.png

# 設(shè)置order參數(shù)自定義分組的排序
sns.boxplot(x='species', y='sepal_length', data=df, order=["versicolor", "virginica", "setosa"])
plt.show()

image.png

# 根據(jù)每組的中位數(shù)進(jìn)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

# 添加文本注釋標(biāo)簽
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

# 按分組變量填充顏色
df = sns.load_dataset('tips')
df.head()

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

參考來(lái)源：https://www.python-graph-gallery.com/boxplot/