Seaborn 箱线图：如何在 Python 中创建和自定义箱线图

import seaborn as sns
import matplotlib.pyplot as plt
 
# 加载内置数据集
tips = sns.load_dataset("tips")
 
# 基本垂直箱线图
sns.boxplot(data=tips, y="total_bill")
plt.title("总账单分布")
plt.show()

sns.boxplot(data=tips, x="day", y="total_bill")
plt.title("一周各天的总账单")
plt.show()

# 长格式：每行是一次餐厅访问
sns.boxplot(data=tips, x="day", y="total_bill")
plt.show()

import pandas as pd
import numpy as np
 
# 创建宽格式数据
np.random.seed(42)
wide_df = pd.DataFrame({
    "Group A": np.random.normal(50, 10, 100),
    "Group B": np.random.normal(60, 15, 100),
    "Group C": np.random.normal(45, 8, 100),
})
 
sns.boxplot(data=wide_df)
plt.title("比较三组（宽格式数据）")
plt.ylabel("值")
plt.show()

iris = sns.load_dataset("iris")
 
# 仅选择测量列
measurement_cols = iris[["sepal_length", "sepal_width", "petal_length", "petal_width"]]
sns.boxplot(data=measurement_cols)
plt.title("鸢尾花特征分布")
plt.xticks(rotation=15)
plt.show()

# 使用命名调色板
sns.boxplot(data=tips, x="day", y="total_bill", palette="Set2")
plt.title("自定义调色板")
plt.show()

# 所有箱线图使用单一颜色
sns.boxplot(data=tips, x="day", y="total_bill", color="skyblue")
plt.title("统一颜色")
plt.show()

sns.boxplot(data=tips, x="total_bill", y="day", orient="h")
plt.title("水平箱线图")
plt.show()

sns.boxplot(data=tips, x="day", y="total_bill", hue="sex")
plt.title("按天和性别的总账单")
plt.legend(title="性别")
plt.show()

plt.figure(figsize=(12, 6))
sns.boxplot(data=tips, x="day", y="total_bill", hue="smoker", palette="muted")
plt.title("按天和吸烟状态的总账单")
plt.show()

plt.figure(figsize=(10, 6))
sns.boxplot(data=tips, x="day", y="total_bill", palette="pastel")
sns.stripplot(data=tips, x="day", y="total_bill", color="0.3", size=3, jitter=True, alpha=0.5)
plt.title("带有带状图叠加的箱线图")
plt.show()

plt.figure(figsize=(10, 6))
sns.boxplot(data=tips, x="day", y="total_bill", palette="pastel")
sns.swarmplot(data=tips, x="day", y="total_bill", color="0.25", size=3, alpha=0.6)
plt.title("带有散点图叠加的箱线图")
plt.show()

iris = sns.load_dataset("iris")
 
# 从宽格式转换为长格式
iris_long = iris.melt(id_vars="species", var_name="measurement", value_name="cm")
 
plt.figure(figsize=(12, 6))
sns.boxplot(data=iris_long, x="measurement", y="cm", palette="Set3")
plt.title("鸢尾花测量值比较")
plt.show()

plt.figure(figsize=(14, 6))
sns.boxplot(data=iris_long, x="measurement", y="cm", hue="species", palette="husl")
plt.title("按品种的鸢尾花测量值")
plt.legend(title="品种", bbox_to_anchor=(1.05, 1), loc="upper left")
plt.tight_layout()
plt.show()

# Matplotlib 箱线图（更冗长）
import matplotlib.pyplot as plt
 
fig, ax = plt.subplots(figsize=(8, 5))
data_by_day = [tips[tips["day"] == d]["total_bill"].values for d in ["Thur", "Fri", "Sat", "Sun"]]
bp = ax.boxplot(data_by_day, labels=["Thur", "Fri", "Sat", "Sun"], patch_artist=True)
for patch, color in zip(bp["boxes"], ["#8dd3c7", "#ffffb3", "#bebada", "#fb8072"]):
    patch.set_facecolor(color)
ax.set_title("Matplotlib 箱线图（手动样式）")
ax.set_ylabel("总账单")
plt.show()

# Seaborn 等效（简洁）
sns.boxplot(data=tips, x="day", y="total_bill", palette="Set3",
            order=["Thur", "Fri", "Sat", "Sun"])
plt.title("Seaborn 箱线图（一行）")
plt.show()

fig, axes = plt.subplots(1, 2, figsize=(14, 5))
 
sns.boxplot(data=tips, x="day", y="total_bill", palette="Set2", ax=axes[0])
axes[0].set_title("箱线图")
 
sns.violinplot(data=tips, x="day", y="total_bill", palette="Set2", ax=axes[1])
axes[1].set_title("小提琴图")
 
plt.tight_layout()
plt.show()

pip install pygwalker

import pandas as pd
import pygwalker as pyg
 
tips = pd.read_csv("https://raw.githubusercontent.com/mwaskom/seaborn-data/master/tips.csv")
walker = pyg.walk(tips)