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=β 0 +β 1 x+ϵ y=β0+β1x+ϵ (hint: use statsmodels and look at the Statsmodels notebook)
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
sns.set_context("talk")
anascombe = pd.read_csv('data/anscombe.csv')
anascombe.head()
print("x mean:", str(anascombe['x'].mean()))
print("x variance:", str(anascombe['x'].var()))
print("y mean:", str(anascombe['y'].mean()))
print('y veriance', str(anascombe['y'].var()))
print('correlation coefficient:', (np.corrcoef(np.array([anascombe['x'], anascombe['y']])))[0][1])
ac = np.random.rand(len(anascombe)) < 0.5
smf.ols('y~x', anascombe[ac].reset_index(drop=True)).fit().summary() seaborn as sns
import statsmodels.api as sm
import statsmodels.formula.api as smf
sns.set_context("talk")
anascombe = pd.read_csv('data/anscombe.csv')
anascombe.head()
print("x mean:", str(anascombe['x'].mean()))
print("x variance:", str(anascombe['x'].var()))
print("y mean:", str(anascombe['y'].mean()))
print('y veriance', str(anascombe['y'].var()))
print('correlation coefficient:', (np.corrcoef(np.array([anascombe['x'], anascombe['y']])))[0][1])
ac = np.random.rand(len(anascombe)) < 0.5
smf.ols('y~x', anascombe[ac].reset_index(drop=True)).fit().summary()
Part 2¶
Using Seaborn, visualize all four datasets.
hint: use sns.FacetGrid combined with plt.scatter
sns.FacetGrid(anascombe, col="dataset").map(plt.scatter, "x","y")