高级编程技术第十八次作业

Anscombe's quartet

Anscombe's quartet comprises of four datasets, and is rather famous. Why? You'll find out in this exercise.

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+ϵ (hint: use statsmodels and look at the Statsmodels notebook)

代码：

Compute the mean and variance of both x and y

print("The mean is")
print(anascombe.groupby("dataset").mean())
print("The variance is")
print(anascombe.groupby("dataset").var())

Compute the correlation coefficient between  x and  y

print("The correlation coefficient is")
print(anascombe.groupby("dataset").x.corr(anascombe.y))

Compute the linear regression line:  y=β0+β1x+ϵ (hint: use statsmodels and look at the Statsmodels notebook)

print("The linear regression line of each dataset is")
for i in ['I', 'II', 'III', 'IV']:
	dataset = anascombe[anascombe['dataset']==i]
	x = sm.add_constant(np.array(dataset.x))
	y = np.array(dataset.y)
	lin_model = sm.OLS(y, x).fit()
	print('y = ' + str(lin_model.params[0]) + "+" + str(lin_model.params[1]) + "x")

Part 2

Using Seaborn, visualize all four datasets.

hint: use sns.FacetGrid combined with plt.scatter

代码：

sns.FacetGrid(data=anascombe, col='dataset', col_wrap=2).map(plt.scatter, 'x', 'y')
plt.show()