Python数据可视化（四）：频率直方图绘制

使用seaborn包绘制直方图

# 导入所需的python包
# 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
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

# 使用distplot函数绘制基础直方图
sns.distplot(df["sepal_length"],hist=True, kde=False)
plt.show()

image.png

# 设置kde=True添加密度曲线
sns.distplot(df["sepal_length"],hist=True, kde=True)
plt.show()

image.png

# 设置bins参数更改bin的个数
sns.distplot(df["sepal_length"],hist=True, kde=True, bins=30)
plt.show()

image.png

# 设置rug=True参数添加轴须线
sns.distplot(df["sepal_length"], kde=True, rug=True)
# in the next version of the distplot function, one would have to write:
# sns.distplot(data=df, x="sepal_length", kde=True, rug=True) # note that 'kind' is 'hist' by default
plt.show()

image.png

# 自定义轴须线的颜色和宽度
sns.distplot(df["sepal_length"],
             kde=True,
             rug=True,
             rug_kws={"color": "r", "alpha": 0.3, "linewidth": 2, "height":0.2})
# in the next version of the distplot function, one would have to write:
# sns.distplot(data=df, x="sepal_length", kde=True, rug=True, rug_kws={"color": "r", "alpha":0.3, "linewidth": 2, "height":0.2 })
plt.show()

image.png

# 自定义密度曲线的颜色和宽度
sns.distplot(df["sepal_length"],
             kde=True,
             kde_kws={"color": "g", "alpha": 0.3, "linewidth": 5, "shade": True})
# in the next version of the distplot function, one would have to write:
# sns.distplot(data=df, x="sepal_length", kde=True, kde_kws={"color": "g", "alpha": 0.3, "linewidth": 5, "shade": True})
plt.show()

image.png

# 绘制多个变量的直方图
sns.distplot(df["sepal_length"], color="skyblue", label="Sepal Length", kde=True)
sns.distplot(df["sepal_width"], color="red", label="Sepal Width", kde=True)

plt.legend() 
plt.show()

image.png

# 分面展示多个直方图
# 设置画板
fig, axs = plt.subplots(2, 2, figsize=(7, 7))

# 分别绘制多个直方图
sns.distplot(df["sepal_length"], kde=True, color="skyblue", ax=axs[0, 0])
sns.distplot(df["sepal_width"], kde=True, color="olive", ax=axs[0, 1])
sns.distplot(df["petal_length"], kde=True, color="gold", ax=axs[1, 0])
sns.distplot(df["petal_width"], kde=True, color="teal", ax=axs[1, 1])

plt.show()

image.png

# 使用jointplot函数绘制边际直方图

# Custom the inside plot: options are: “scatter” | “reg” | “resid” | “kde” | “hex”
sns.jointplot(x=df["sepal_length"], y=df["sepal_width"], kind='scatter')
sns.jointplot(x=df["sepal_length"], y=df["sepal_width"], kind='hex')
sns.jointplot(x=df["sepal_length"], y=df["sepal_width"], kind='kde')

plt.show()

image.png image.png image.png

# 自定义颜色
# Then you can pass arguments to each type:
sns.jointplot(x=df["sepal_length"], y=df["sepal_width"], kind='scatter', s=200, color='m', edgecolor="skyblue", linewidth=2)

# Custom the color
sns.set(style="white", color_codes=True)
sns.jointplot(x=df["sepal_length"], y=df["sepal_width"], kind='kde', color="skyblue")

plt.show()

image.png image.png

# 自定义直方图的bins数
# Custom the histogram:
sns.jointplot(x=df["sepal_length"], y=df["sepal_width"], kind='hex', marginal_kws=dict(bins=30, color="r"))

plt.show()

image.png

# 添加箱线图

# creating a figure composed of two matplotlib.Axes objects (ax_box and ax_hist)
f, (ax_box, ax_hist) = plt.subplots(2, sharex=True, gridspec_kw={"height_ratios": (.15, .85)})

# assigning a graph to each ax
sns.boxplot(df["sepal_length"], ax=ax_box)
sns.distplot(df.sepal_length, ax=ax_hist)

# Remove x axis name for the boxplot
ax_box.set(xlabel='')
plt.show()

image.png

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