notebook.community

Edit and run



In [68]:

    
import pandas as pd  
import matplotlib.pyplot as plt  
import seaborn as sns  
from scipy import stats  
import numpy as np



In [69]:

    
anscombe = sns.load_dataset("anscombe")



In [70]:

    
anscombe



In [71]:

    
anscombe.groupby("dataset").describe()



In [72]:

    
anscombe.corr()



In [73]:

    
for data_set in anscombe.dataset.unique(): 
    #anscombe[anscombe.dataset==data_set].plot(kind='scatter', x='x',y='y')
    df = anscombe[anscombe.dataset==data_set]
    slope, intercept, r_val, p_val, slope_std_error = stats.linregress(x=df.x, y=df.y)
    print('y={:.2f}x+{:.2f}'.format(slope, intercept))









    



y=0.50x+3.00
y=0.50x+3.00
y=0.50x+3.00
y=0.50x+3.00



In [74]:

    
for data_set in anscombe.dataset.unique(): 
    df = anscombe[anscombe.dataset==data_set]
    sns.lmplot(x="x", y="y", data=df);
    plt.title("Data set {}: y={:.2f}x+{:.2f} (p: {:.2f}, R^2: {:.2f})".format(data_set, slope, intercept, p_val, r_val))



In [ ]:

	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
5	I	14.0	9.96
6	I	6.0	7.24
7	I	4.0	4.26
8	I	12.0	10.84
9	I	7.0	4.82
10	I	5.0	5.68
11	II	10.0	9.14
12	II	8.0	8.14
13	II	13.0	8.74
14	II	9.0	8.77
15	II	11.0	9.26
16	II	14.0	8.10
17	II	6.0	6.13
18	II	4.0	3.10
19	II	12.0	9.13
20	II	7.0	7.26
21	II	5.0	4.74
22	III	10.0	7.46
23	III	8.0	6.77
24	III	13.0	12.74
25	III	9.0	7.11
26	III	11.0	7.81
27	III	14.0	8.84
28	III	6.0	6.08
29	III	4.0	5.39
30	III	12.0	8.15
31	III	7.0	6.42
32	III	5.0	5.73
33	IV	8.0	6.58
34	IV	8.0	5.76
35	IV	8.0	7.71
36	IV	8.0	8.84
37	IV	8.0	8.47
38	IV	8.0	7.04
39	IV	8.0	5.25
40	IV	19.0	12.50
41	IV	8.0	5.56
42	IV	8.0	7.91
43	IV	8.0	6.89

	x								y
	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max
dataset
I	11.0	9.0	3.316625	4.0	6.5	9.0	11.5	14.0	11.0	7.500909	2.031568	4.26	6.315	7.58	8.57	10.84
II	11.0	9.0	3.316625	4.0	6.5	9.0	11.5	14.0	11.0	7.500909	2.031657	3.10	6.695	8.14	8.95	9.26
III	11.0	9.0	3.316625	4.0	6.5	9.0	11.5	14.0	11.0	7.500000	2.030424	5.39	6.250	7.11	7.98	12.74
IV	11.0	9.0	3.316625	8.0	8.0	8.0	8.0	19.0	11.0	7.500909	2.030579	5.25	6.170	7.04	8.19	12.50

	x	y
x	1.000000	0.816366
y	0.816366	1.000000