給定一個csv檔案，完成：

Part 1: For each of the four datasets:

Compute the mean and the variance of both x and y

Compute the correlation coefficient between x and y

Compute the linear regression line: y = β0 + β1x + ε

Part 2: Use seaborn to visualize all four datasets.

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

dataset_names = ['I', 'II', 'III', 'IV']
for i in dataset_names:
    n = len(anascombe[anascombe.dataset == i])
    is_train = np.random.rand(n) < 0.7
    train = anascombe[anascombe.dataset == i][is_train].reset_index(drop=True)
    test = anascombe[anascombe.dataset == i][~is_train].reset_index(drop=True)
    
    lin_model = smf.ols('y ~ x', train).fit()
    print(lin_model.summary())

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

最終輸出如下：