python作业之pandas seaborn

题目为：

Part 1
For each of the four datasets…

Compute the mean and variance of both x and y
Compute the correlation coefficient between x and y
Compute the linear regression line: y=β0+β1x+ϵy=β0+β1x+ϵ (hint: use statsmodels and look at the Statsmodels notebook)

Part 2
Using Seaborn, visualize all four datasets.

hint: use sns.FacetGrid combined with plt.scatter
代码：

import random  

import numpy as np  
import scipy as sp  
import pandas as pd  
import matplotlib.pyplot as plt  
import seaborn as sns  

import statsmodels.api as sm  
import statsmodels.formula.api as smf 

sns.set_context("talk")  
anscombe = pd.read_csv('anscombe.csv')  

#part 1  
mx = anscombe.groupby('dataset').mean().x  
my = anscombe.groupby('dataset').mean().y  
vx = anscombe.groupby('dataset').var().x  
vy = anscombe.groupby('dataset').var().y  
print('x mean : \n', mx, '\n')  
print('y mean : \n', my, '\n')  
print('x var : \n', vx, '\n')  
print('y var : \n', vy, '\n')  

cor = anscombe.groupby('dataset').corr()  
print('correlation : \n', cor, '\n')  

for a in [anscombe[anscombe.dataset == i] for i in ['I', 'II', 'III', 'IV']]:  
    s_x = sm.add_constant(np.array(a.x))  
    s_y = np.array(a.y)  
    beta_pair = sm.OLS(s_y, s_x).fit()  
    print('β1, β0 = ', beta_pair.params)  


#part 2  
temp = sns.FacetGrid(data=anscombe, col='dataset', col_wrap=4)  
temp.map(plt.scatter, 'x', 'y')  
plt.show()  

结果：