Metody eksploracji danych

http://home.agh.edu.pl/~pszwed/med/regression/xy-001.arff http://home.agh.edu.pl/~pszwed/med/regression/xy-002.arff http://home.agh.edu.pl/~pszwed/med/regression/xy-003.arff http://home.agh.edu.pl/~pszwed/med/regression/xy-004.arff http://home.agh.edu.pl/~pszwed/med/regression/xy-005.arff http://home.agh.edu.pl/~pszwed/med/regression/xy-006.arff http://home.agh.edu.pl/~pszwed/med/regression/xy-007.arff http://home.agh.edu.pl/~pszwed/med/regression/xy-008.arff http://home.agh.edu.pl/~pszwed/med/regression/xy-009.arff http://home.agh.edu.pl/~pszwed/med/regression/xy-010.arff

# % matplotlib notebook
 
import matplotlib.pyplot as plt
import numpy as np
from scipy import stats
from io import StringIO
 
data = """
0.246939,9.011391
0.895519,8.950505
0.971588,9.671047
1.188316,14.735488
1.741884,10.265625
2.196002,13.501097
2.637403,13.887849
2.788188,17.180626
3.50202,19.321529
3.531476,16.089503
3.995073,14.937624
4.66407,18.389229
4.88705,22.798099
5.644447,25.351644
6.537993,26.94125
6.654565,20.387372
6.981497,21.255345
7.099548,27.745566
7.453511,22.811026
8.145089,22.388721
8.865577,28.027686
8.983554,25.146826
9.939295,34.305519
10.132365,33.500249
10.804992,35.683783
10.956247,33.300984
11.135499,30.047647
12.080814,35.787975
12.647943,40.051468
12.741248,35.344707
13.37512,33.765994
13.699004,38.776812
13.795843,37.091575
14.474034,38.114638
15.033079,45.589492
15.592465,40.631264
16.192292,48.739644
16.65253,48.830867
16.832643,50.325774
17.577283,45.206373
17.853024,53.339617
18.763727,48.279457
19.045983,55.953631
19.26704,50.470961
19.537664,51.928816
19.987968,49.376176
20.603744,52.380207
21.373748,61.677885
22.242239,57.668626
22.710625,56.161207
23.706639,65.423664
23.991602,60.008664
24.26953,61.870482
24.899023,66.002296
25.110234,70.342272
25.960459,68.472507
26.712467,72.751912
26.730612,73.491421
26.832166,73.970975
27.234095,74.192411
27.263899,67.012532
28.186481,71.667746
28.609198,70.126676
29.00642,71.713675
29.344191,78.395062
29.652469,72.427284
30.009633,80.863626
30.176943,73.542808
30.616236,80.771572
30.89822,80.967313
31.684718,77.600474
32.564911,79.397491
33.03557,80.840347
33.132668,83.721291
33.820815,88.970661
34.109682,89.530881
34.661445,93.863877
35.162583,89.337648
35.432228,87.968034
36.122985,90.976234
36.532793,91.573681
37.008879,97.673479
37.712701,92.459677
38.486883,94.410451
38.99117,104.222796
39.663589,105.80185
40.241739,101.458148
40.519365,105.707817
40.910886,103.881927
40.998451,99.379055
41.420003,105.555433
42.057595,103.837871
42.374651,107.950421
43.164247,106.545838
44.086193,107.721106
44.137013,110.703987
44.41119,107.948371
45.148115,115.274231
45.845917,112.39734
46.47258,115.871904
"""
inp =  StringIO(data)
x, y = np.loadtxt(inp, delimiter=',', usecols=(0, 1), unpack=True,skiprows=6)
 
plt.scatter(x,y,s=80, marker='+')
 
 
#plot function
fx=np.linspace(-10,60,100)
fy=2.3702*fx+6.1973
ftrue=2.37*fx+7
plt.plot(fx,fy,linewidth=2,color='r')
plt.plot(fx,ftrue,linewidth=1,linestyle='--',color='g')
 
plt.xlim(-10,60)
plt.grid(True)
plt.xlabel('X')
plt.ylabel('Y')
r = stats.pearsonr(x, y)[0] 
plt.title('Regression $f_{true} = 2.37x+7$ r=' + str(r))
plt.show()