代码:
#matplotlib inline
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
import statistics as sta
import scipy.stats.stats as stats
anascombe = sns.load_dataset("anscombe")
#显示平均数
print("the mean of x and y are:")
print(anascombe.groupby('dataset')['x','y'].mean())
print("\n")
#显示方差
print("the variance of x and y are:")
print(anascombe.groupby('dataset')['x', 'y'].var())
print("\n")
print("the correlation coefficient between x and y are:")
print(anascombe.groupby('dataset').corr())
print("\n")
print("the first linear regression line:")
lin_model_1 = smf.ols('y ~ x', anascombe.groupby('dataset').get_group('I')).fit()
print(lin_model_1.params)
print("\n")
print("the second linear regression line:")
lin_model_2 = smf.ols('y ~ x', anascombe.groupby('dataset').get_group('II')).fit()
print(lin_model_2.params)
print("\n")
print("the third linear regression line:")
lin_model_3 = smf.ols('y ~ x', anascombe.groupby('dataset').get_group('III')).fit()
print(lin_model_3.params)
print("\n")
print("the fourth linear regression line:")
lin_model_4 = smf.ols('y ~ x', anascombe.groupby('dataset').get_group('IV')).fit()
print(lin_model_4.params)
#part2
#数据可视化
sns.set(style='whitegrid')
g = sns.FacetGrid(anascombe, col="dataset")
g.map(plt.scatter, "x","y")
plt.show()
part 1运行结果:
part 2运行结果: