%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")
Anscombe’s quartet
Anscombe’s quartet comprises of four datasets, and is rather famous. Why? You’ll find out in this exercise.
anascombe = pd.read_csv('data/anscombe.csv')
anascombe.head()
.dataframe tbody tr th:only-of-type { vertical-align: middle; } .dataframe tbody tr th { vertical-align: top; } .dataframe thead th { text-align: right; }
|
dataset |
x |
y |
0 |
I |
10.0 |
8.04 |
1 |
I |
8.0 |
6.95 |
2 |
I |
13.0 |
7.58 |
3 |
I |
9.0 |
8.81 |
4 |
I |
11.0 |
8.33 |
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)
dataset = anascombe[anascombe.dataset == "I"]
print("dataset 'I':\n")
print(" The mean of x is %0.2f, and the variance is %0.2lf." % (dataset['x'].mean(), dataset['x'].var()))
print(" The mean of y is %0.2f, and the variance is %0.2lf.\n" % (dataset['y'].mean(), dataset['y'].var()))
a = np.array([dataset['x'], dataset['y']])
b = np.corrcoef(a)
print(" The correlation coefficient between x and y is %lf.\n" % b[0][1])
n = len(dataset)
is_train = np.random.rand(n) < 0.7
train = dataset[is_train].reset_index(drop=True)
test = dataset[~is_train].reset_index(drop=True)
lin_model = smf.ols('x ~ y', train).fit()
lin_model.summary()
dataset 'I':
The mean of x is 9.00, and the variance is 11.00.
The mean of y is 7.50, and the variance is 4.13.
The correlation coefficient between x and y is 0.816421.
OLS Regression Results
Dep. Variable: |
x |
R-squared: |
0.635 |
Model: |
OLS |
Adj. R-squared: |
0.574 |
Method: |
Least Squares |
F-statistic: |
10.43 |
Date: |
Mon, 11 Jun 2018 |
Prob (F-statistic): |
0.0179 |
Time: |
12:08:36 |
Log-Likelihood: |
-16.703 |
No. Observations: |
8 |
AIC: |
37.41 |
Df Residuals: |
6 |
BIC: |
37.57 |
Df Model: |
1 |
|
|
Covariance Type: |
nonrobust |
|
|
|
coef |
std err |
t |
P>|t| |
[0.025 |
0.975] |
Intercept |
-1.2102 |
3.335 |
-0.363 |
0.729 |
-9.371 |
6.951 |
y |
1.4174 |
0.439 |
3.230 |
0.018 |
0.344 |
2.491 |
Omnibus: |
0.024 |
Durbin-Watson: |
2.656 |
Prob(Omnibus): |
0.988 |
Jarque-Bera (JB): |
0.188 |
Skew: |
0.082 |
Prob(JB): |
0.910 |
Kurtosis: |
2.268 |
Cond. No. |
32.3 |
dataset = anascombe[anascombe.dataset == "II"]
print("dataset 'II':\n")
print(" The mean of x is %0.2f, and the variance is %0.2f.\n" % (dataset['x'].mean(), dataset['x'].var()))
print(" The mean of y is %0.2f, and the variance is %0.2f.\n" % (dataset['y'].mean(), dataset['y'].var()))
a = np.array([dataset['x'], dataset['y']])
b = np.corrcoef(a)
print(" The correlation coefficient between x and y is %lf.\n" % b[0][1])
n = len(dataset)
is_train = np.random.rand(n) < 0.7
train = dataset[is_train].reset_index(drop=True)
test = dataset[~is_train].reset_index(drop=True)
lin_model = smf.ols('x ~ y', train).fit()
lin_model.summary()
dataset 'II':
The mean of x is 9.00, and the variance is 11.00.
The mean of y is 7.50, and the variance is 4.13.
The correlation coefficient between x and y is 0.816237.
OLS Regression Results
Dep. Variable: |
x |
R-squared: |
0.678 |
Model: |
OLS |
Adj. R-squared: |
0.638 |
Method: |
Least Squares |
F-statistic: |
16.85 |
Date: |
Mon, 11 Jun 2018 |
Prob (F-statistic): |
0.00341 |
Time: |
12:08:36 |
Log-Likelihood: |
-20.461 |
No. Observations: |
10 |
AIC: |
44.92 |
Df Residuals: |
8 |
BIC: |
45.53 |
Df Model: |
1 |
|
|
Covariance Type: |
nonrobust |
|
|
|
coef |
std err |
t |
P>|t| |
[0.025 |
0.975] |
Intercept |
-1.2852 |
2.568 |
-0.501 |
0.630 |
-7.206 |
4.636 |
y |
1.3882 |
0.338 |
4.105 |
0.003 |
0.608 |
2.168 |
Omnibus: |
2.361 |
Durbin-Watson: |
2.780 |
Prob(Omnibus): |
0.307 |
Jarque-Bera (JB): |
1.184 |
Skew: |
0.829 |
Prob(JB): |
0.553 |
Kurtosis: |
2.694 |
Cond. No. |
29.9 |
dataset = anascombe[anascombe.dataset == "III"]
print("dataset 'III':\n")
print(" The mean of x is %0.2f, and the variance is %0.2f.\n" % (dataset['x'].mean(), dataset['x'].var()))
print(" The mean of y is %0.2f, and the variance is %0.2f.\n" % (dataset['y'].mean(), dataset['y'].var()))
a = np.array([dataset['x'], dataset['y']])
b = np.corrcoef(a)
print(" The correlation coefficient between x and y is %lf.\n" % b[0][1])
n = len(dataset)
is_train = np.random.rand(n) < 0.7
train = dataset[is_train].reset_index(drop=True)
test = dataset[~is_train].reset_index(drop=True)
lin_model = smf.ols('x ~ y', train).fit()
lin_model.summary()
dataset 'III':
The mean of x is 9.00, and the variance is 11.00.
The mean of y is 7.50, and the variance is 4.12.
The correlation coefficient between x and y is 0.816287.
OLS Regression Results
Dep. Variable: |
x |
R-squared: |
0.704 |
Model: |
OLS |
Adj. R-squared: |
0.655 |
Method: |
Least Squares |
F-statistic: |
14.27 |
Date: |
Mon, 11 Jun 2018 |
Prob (F-statistic): |
0.00921 |
Time: |
12:08:36 |
Log-Likelihood: |
-16.338 |
No. Observations: |
8 |
AIC: |
36.68 |
Df Residuals: |
6 |
BIC: |
36.84 |
Df Model: |
1 |
|
|
Covariance Type: |
nonrobust |
|
|
|
coef |
std err |
t |
P>|t| |
[0.025 |
0.975] |
Intercept |
-1.0892 |
2.651 |
-0.411 |
0.695 |
-7.575 |
5.396 |
y |
1.2835 |
0.340 |
3.777 |
0.009 |
0.452 |
2.115 |
Omnibus: |
1.577 |
Durbin-Watson: |
2.069 |
Prob(Omnibus): |
0.455 |
Jarque-Bera (JB): |
0.749 |
Skew: |
0.708 |
Prob(JB): |
0.688 |
Kurtosis: |
2.506 |
Cond. No. |
27.6 |
dataset = anascombe[anascombe.dataset == "IV"]
print("dataset 'IV':\n")
print(" The mean of x is %0.2f, and the variance is %0.2f.\n" % (dataset['x'].mean(), dataset['x'].var()))
print(" The mean of y is %0.2f, and the variance is %0.2f.\n" % (dataset['y'].mean(), dataset['y'].var()))
a = np.array([dataset['x'], dataset['y']])
b = np.corrcoef(a)
print(" The correlation coefficient between x and y is %lf.\n" % b[0][1])
n = len(dataset)
is_train = np.random.rand(n) < 0.7
train = dataset[is_train].reset_index(drop=True)
test = dataset[~is_train].reset_index(drop=True)
lin_model = smf.ols('x ~ y', train).fit()
lin_model.summary()
dataset 'IV':
The mean of x is 9.00, and the variance is 11.00.
The mean of y is 7.50, and the variance is 4.12.
The correlation coefficient between x and y is 0.816521.
OLS Regression Results
Dep. Variable: |
x |
R-squared: |
-inf |
Model: |
OLS |
Adj. R-squared: |
-inf |
Method: |
Least Squares |
F-statistic: |
-6.000 |
Date: |
Mon, 11 Jun 2018 |
Prob (F-statistic): |
1.00 |
Time: |
12:08:36 |
Log-Likelihood: |
253.03 |
No. Observations: |
8 |
AIC: |
-502.1 |
Df Residuals: |
6 |
BIC: |
-501.9 |
Df Model: |
1 |
|
|
Covariance Type: |
nonrobust |
|
|
|
coef |
std err |
t |
P>|t| |
[0.025 |
0.975] |
Intercept |
8.0000 |
1.13e-14 |
7.08e+14 |
0.000 |
8.000 |
8.000 |
y |
-1.11e-16 |
1.54e-15 |
-0.072 |
0.945 |
-3.88e-15 |
3.66e-15 |
Omnibus: |
154.682 |
Durbin-Watson: |
0.000 |
Prob(Omnibus): |
0.000 |
Jarque-Bera (JB): |
3.000 |
Skew: |
0.000 |
Prob(JB): |
0.223 |
Kurtosis: |
0.000 |
Cond. No. |
46.5 |
Part 2
Using Seaborn, visualize all four datasets.
hint: use sns.FacetGrid combined with plt.scatter
g = sns.FacetGrid(anascombe, col="dataset")
g.map(plt.scatter, "x","y")