南大《探索数据的奥秘》课件示例代码笔记15

In [34]: import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
import seaborn as sns
%matplotlib inline
df=pd.read_csv('C:\Python\Scripts\my_data\iris.csv',header=None,
names=['sepal_length','sepal_width','petal_length','petal_width','
target'])
my_data=df[['sepal_length','sepal_width']].iloc[:50]
sns.lmplot(x='sepal_length',y='sepal_width',data=my_data,ci=None)
#order 默认为 1，线性拟合
Out[34]: <seaborn.axisgrid.FacetGrid at 0x1b1dba2fa58>

In [41]: my_data['sample']=np.random.randint(1,3,len(my_data))
my_data.head()
Out[41]: sepal_length sepal_width sample
0 5.1 3.5 1
1 4.9 3.0 2
2 4.7 3.2 1
3 4.6 3.1 1
4 5.0 3.6 1
In [24]: my_data.groupby('sample')[['sepal_length','sepal_width']].mean()
Out[24]: sepal_length sepal_width
sample
1 4.988889 3.366667
2 5.015625 3.446875
In [42]: sns.lmplot(x='sepal_length',y='sepal_width',data=my_data,ci=None,hue='sample')
Out[42]: <seaborn.axisgrid.FacetGrid at 0x1b1dcc0cb70>

In [59]: sns.lmplot(x='sepal_length',y='sepal_width',data=my_data,ci=None,hue='sample',
order=6)
plt.ylim(2.5,4.5)
Out[59]: (2.5, 4.5)

In [31]: sns.lmplot(x='sepal_length',y='sepal_width',data=my_data,ci=None,hue='sample',
order=2)
Out[31]: <seaborn.axisgrid.FacetGrid at 0x1b1db96b7f0>