emu193课程ipython的教程课后作业

Part1：

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  
  
#分数据集输出x和y的均值  
print('The mean of x and y:')  
print(anascombe.groupby(['dataset'])[['x', 'y']].mean())  
  
#分数据集输出x和y的方差  
print('\nThe varience of x and y:')  
print(anascombe.groupby(['dataset'])[['x', 'y']].var())  
  
#分数据集输出x和y的关联系数  
print('\nThe correlation coefficient between x and y:')  
print(anascombe.groupby(['dataset'])[['x', 'y']].corr());  
  
#对每一个数据集学习一个拟合曲线出来  
datasets = ['I', 'II', 'III', 'IV']  
for dataset in datasets:  
    lin_model = smf.ols('y ~ x', anascombe[anascombe['dataset'] == dataset]).fit()  
    print('\nThe linear model for dataset', dataset)  
    print(lin_model.summary())  
  
print('\n')  

Part2：

import matplotlib.pyplot as plt  
import seaborn as sns  
  
g = sns.FacetGrid(anascombe, col='dataset', hue="y")  
g.map(plt.scatter, 'x', 'y')