seaborn学习笔记2.0

分类变量的可视化

1、stripplot()

stripplot(x=None, y=None, hue=None, data=None, order=None, hue_order=None, jitter=True, dodge=False, orient=None, color=None, palette=None, size=5, edgecolor='gray', linewidth=0, ax=None, **kwargs)

import seaborn as sns
from matplotlib import pyplot as plt

sns.set_style('darkgrid')
tips = sns.load_dataset('tips')
sns.stripplot(x='day', y='total_bill', data=tips)
plt.show()

 

其中jitter参数可以控制抖动程度，可以是bool型也可以是具体数值，抖动可以减少数据重叠

                          不使用抖动(jitter=False)                                           使用抖动(jitter=True)

当设置hue参数时，根据hue参数进行不同颜色显示，例如，设置hue='smoker'

当有hue参数时，设置dodge参数可以分离不用类别数据，例如，设置dodge=True

2、swamplot()

swarmplot(x=None, y=None, hue=None, data=None, order=None, hue_order=None, dodge=False, orient=None, color=None, palette=None, size=5, edgecolor='gray', linewidth=0, ax=None, **kwargs)

import seaborn as sns
from matplotlib import pyplot as plt

sns.set_style('darkgrid')
tips = sns.load_dataset('tips')
sns.swarmplot(x='day', y='total_bill', data=tips, hue='sex')
plt.show()

当x为数值型变量

import seaborn as sns
from matplotlib import pyplot as plt

sns.set_style('darkgrid')
tips = sns.load_dataset('tips')
ax=sns.swarmplot(x='size', y='total_bill',data=tips.query("size != 7"))
plt.show()

其中tips.query("size != 7")表示绘制x中size != 7的数据

通过order设置x数据显示顺序，例如，设置order=[1, 3, 2, 4, 5, 6]

import seaborn as sns
from matplotlib import pyplot as plt

sns.set_style('darkgrid')
tips = sns.load_dataset('tips')
ax=sns.swarmplot(x='size', y='total_bill', order=[1, 3, 2, 4, 5, 6],data=tips.query("size != 7"))
plt.show()

可以看到size=2和size=3的顺序交换了

交换x,y轴数据对于当类别名称相对较长或有许多类别时有帮助

import seaborn as sns
from matplotlib import pyplot as plt

sns.set_style('darkgrid')
tips = sns.load_dataset('tips')
ax = sns.swarmplot(y='day', x='total_bill', data=tips)
plt.show()

也可以旋转一下坐标

import seaborn as sns
from matplotlib import pyplot as plt

sns.set_style('darkgrid')
tips = sns.load_dataset('tips')
ax = sns.swarmplot(x='size', y='total_bill', data=tips)
ax.set_xticklabels(ax.get_xticklabels(), rotation=-45)
plt.show()

 

3、boxplot()

boxplot(x=None, y=None, hue=None, data=None, order=None, hue_order=None, orient=None, color=None, palette=None, saturation=0.75, width=0.8, dodge=True, fliersize=5, linewidth=None, whis=1.5, notch=False, ax=None, **kwargs)

import seaborn as sns
from matplotlib import pyplot as plt

sns.set_style('darkgrid')
tips = sns.load_dataset('tips')
ax = sns.boxplot(x="day", y="total_bill", hue='smoker', dodge=True, data=tips)
ax.legend(shadow=False, fancybox=False, ncol=1, fontsize=10, loc='upper left')
plt.show()

其中hue参数，dodge参数的设置前面已经提到过，这里不再赘述

import seaborn as sns
from matplotlib import pyplot as plt

sns.set_style('darkgrid')
tips = sns.load_dataset('tips')
ax = sns.boxplot(x="day", y="total_bill", hue='smoker', dodge=True, data=tips)
ax.legend(shadow=False, fancybox=False, ncol=1, fontsize=10, loc='upper left')
plt.show()

4、boxenplot()

boxenplot(x=None, y=None, hue=None, data=None, order=None, hue_order=None, orient=None, color=None, palette=None, saturation=0.75, width=0.8, dodge=True, k_depth='proportion', linewidth=None, scale='exponential', outlier_prop=None, ax=None, **kwargs)
 

import seaborn as sns
from matplotlib import pyplot as plt

sns.set_style('darkgrid')
diamonds = sns.load_dataset("diamonds")
ax = sns.boxenplot(x="color", y="price", data=diamonds.sort_values("color"))
#ax.legend(shadow=True, fancybox=True, ncol=1, fontsize=10, loc='upper left')
plt.show()

 

 

 

5、violinplot()

violinplot(x=None, y=None, hue=None, data=None, order=None, hue_order=None, bw='scott', cut=2, scale='area', scale_hue=True, gridsize=100, width=0.8, inner='box', split=False, dodge=True, orient=None, linewidth=None, color=None, palette=None, saturation=0.75, ax=None, **kwargs)

import seaborn as sns
from matplotlib import pyplot as plt

sns.set_style('darkgrid')
tips = sns.load_dataset("tips")
ax = sns.violinplot(y="total_bill", x="day", inner="stick", hue="sex", split=True, data=tips)
#ax.legend(shadow=True, fancybox=True, ncol=1, fontsize=10, loc='upper right')
plt.show()

inner参数可以设置为 {"box", "quartile", "point", "stick", None}

如果是box，绘制一个小型的箱线图，如果是quartiles，绘制四分位数分布，如果是point或者stick，画每一个数据，如果是None，不做任何修饰

6、barplot()

barplot(x=None, y=None, hue=None, data=None, order=None, hue_order=None, estimator=, ci=95, n_boot=1000, units=None, orient=None, color=None, palette=None, saturation=0.75, errcolor='.26', errwidth=None, capsize=None, dodge=True, ax=None, **kwargs)

import seaborn as sns
from matplotlib import pyplot as plt

sns.set_style('darkgrid')
titanic = sns.load_dataset("titanic")
ax = sns.barplot(x="sex", y="survived", hue="class", data=titanic)
#ax.legend()
plt.show()

其中ci参数可以设置是否绘制error bar，如果为整数，则绘制估计数周围整数大小的置信区间，如果为sd，绘制标准差，如果为None，不绘制error bar。另外置信区间范围内数值是使用bootstrapping方法计算出来的

Bootstrapping算法，指的就是利用有限的样本资料经由多次重复抽样，重新建立起足以代表母体样本分布的新样本。bootstrapping方法的实现很简单，假设抽取的样本大小为n:

在原样本中有放回的抽样，抽取n次。每抽一次形成一个新的样本，重复操作，形成很多新样本，通过这些样本就可以计算出样本的一个分布。

7、countplot()

countplot(x=None, y=None, hue=None, data=None, order=None, hue_order=None, orient=None, color=None, palette=None, saturation=0.75, dodge=True, ax=None, **kwargs)

import seaborn as sns
from matplotlib import pyplot as plt

sns.set_style('darkgrid')
titanic = sns.load_dataset("titanic")
ax = sns.countplot(x="deck", palette="ch:.25", data=titanic)
#ax.legend()
plt.show()

countplot显示的是观察值，而不是统计值

8、pointplot()

pointplot(x=None, y=None, hue=None, data=None, order=None, hue_order=None, estimator=, ci=95, n_boot=1000, units=None, markers='o', linestyles='-', dodge=False, join=True, scale=1, orient=None, color=None, palette=None, errwidth=None, capsize=None, ax=None, **kwargs)

import seaborn as sns
from matplotlib import pyplot as plt

sns.set_style('darkgrid')
titanic = sns.load_dataset("titanic")
ax = sns.pointplot(x="class", y="survived", hue="sex",
                   palette={"male": "g", "female": "m"},
                   markers=["^", "o"], linestyles=["-", "--"],
                   data=titanic)
#ax.legend()
plt.show()

通过设置palette，不同marker和不同linestyle来区分不同类别