Python 数据处理练习

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

anascombe = pd.read_csv('anscombe.csv')

print(anascombe.groupby('dataset')['x','y'].mean())
print(anascombe.groupby('dataset')['x','y'].var())

lin_model = smf.ols('y ~ x', anascombe).fit()
print(lin_model.summary())

g = sns.FacetGrid(anascombe, col='dataset')
g.map(plt.scatter, 'x', 'y')
plt.show()

运行结果：