Untitled
unknown
plain_text
4 years ago
21 kB
5
Indexable
C:\Users\Felix\PycharmProjects\pythonProject\venv\Scripts\python.exe "C:\Program Files\JetBrains\PyCharm 2021.2.1\plugins\python\helpers\pydev\pydevconsole.py" --mode=client --port=64936
import sys; print('Python %s on %s' % (sys.version, sys.platform))
sys.path.extend(['C:\\Users\\Felix\\PycharmProjects\\machine-learning2', 'C:/Users/Felix/PycharmProjects/machine-learning2'])
PyDev console: starting.
Python 3.8.10 (tags/v3.8.10:3d8993a, May 3 2021, 11:48:03) [MSC v.1928 64 bit (AMD64)] on win32
runfile('C:/Users/Felix/PycharmProjects/machine-learning2/main.py', wdir='C:/Users/Felix/PycharmProjects/machine-learning2')
C:\Users\Felix\PycharmProjects\machine-learning2
Cross validation fold 1/10: has the lambda value 1e1.0
Offset 0.0
std_hydro 6.493662708593406e+29
std_wind 2.593454102305807e+161
std_solar 3.7559734772364737e+199
std_biomass 0.0
std_nuclear 0.0
std_biofuels 0.0
Cross validation fold 2/10: has the lambda value 1e1.0
Offset 0.0
std_hydro 6.493662708593406e+29
std_wind 2.593454102305807e+161
std_solar 3.7559734772364737e+199
std_biomass 0.0
std_nuclear 0.0
std_biofuels 0.0
Cross validation fold 3/10: has the lambda value 1e1.0
Offset 0.0
std_hydro 6.493662708593406e+29
std_wind 2.593454102305807e+161
std_solar 3.7559734772364737e+199
std_biomass 0.0
std_nuclear 0.0
std_biofuels 0.0
Cross validation fold 4/10: has the lambda value 1e2.0
Offset 0.0
std_hydro 6.493662708593406e+29
std_wind 2.593454102305807e+161
std_solar 3.7559734772364737e+199
std_biomass 0.0
std_nuclear 0.0
std_biofuels 0.0
Cross validation fold 5/10: has the lambda value 1e1.0
Offset 0.0
std_hydro 6.493662708593406e+29
std_wind 2.593454102305807e+161
std_solar 3.7559734772364737e+199
std_biomass 0.0
std_nuclear 0.0
std_biofuels 0.0
Cross validation fold 6/10: has the lambda value 1e1.0
Offset 0.0
std_hydro 6.493662708593406e+29
std_wind 2.593454102305807e+161
std_solar 3.7559734772364737e+199
std_biomass 0.0
std_nuclear 0.0
std_biofuels 0.0
Cross validation fold 7/10: has the lambda value 1e1.0
Offset 0.0
std_hydro 6.493662708593406e+29
std_wind 2.593454102305807e+161
std_solar 3.7559734772364737e+199
std_biomass 0.0
std_nuclear 0.0
std_biofuels 0.0
Cross validation fold 8/10: has the lambda value 1e1.0
Offset 0.0
std_hydro 6.493662708593406e+29
std_wind 2.593454102305807e+161
std_solar 3.7559734772364737e+199
std_biomass 0.0
std_nuclear 0.0
std_biofuels 0.0
Cross validation fold 9/10: has the lambda value 1e2.0
Offset 0.0
std_hydro 6.493662708593406e+29
std_wind 2.593454102305807e+161
std_solar 3.7559734772364737e+199
std_biomass 0.0
std_nuclear 0.0
std_biofuels 0.0
Cross validation fold 10/10: has the lambda value 1e1.0
Offset 0.0
std_hydro 0.44
std_wind 0.25
std_solar -0.16
std_biomass 0.33
std_nuclear 0.32
std_biofuels -0.22
Linear regression without feature selection:
- Training error: 0.2233985382509828
- Test error: 0.23005267968225426
- R^2 train: 0.7765406682799204
- R^2 test: 0.7694048308045904
Regularized linear regression:
- Training error: 0.2235752733396504
- Test error: 0.229970193383863
- R^2 train: 0.7763638850963134
- R^2 test: 0.7694875116147427
Weights in last fold:
Offset 0.0
std_hydro 0.44
std_wind 0.25
std_solar -0.16
std_biomass 0.33
std_nuclear 0.32
std_biofuels -0.22
Replicate: 1/1
Iter Loss Rel. loss
C:\Users\Felix\PycharmProjects\pythonProject\venv\lib\site-packages\torch\nn\modules\loss.py:520: UserWarning: Using a target size (torch.Size([3291])) that is different to the input size (torch.Size([3291, 1])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.
return F.mse_loss(input, target, reduction=self.reduction)
Final loss:
994 0.98524773 9.679529e-07
Best loss: 0.9852477312088013
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0212284 4.7390648e-05
2000 0.9976872 6.6314087e-06
3000 0.99380046 2.2791007e-06
Final loss:
3507 0.9929806 9.0038907e-07
Best loss: 0.9929805994033813
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9790843 1.4732246e-05
2000 0.9710726 5.094532e-06
3000 0.968206 1.1081138e-06
Final loss:
3051 0.9681487 9.850485e-07
Best loss: 0.9681487083435059
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
709 0.9056353 9.872283e-07
Best loss: 0.9056352972984314
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9241547 2.708841e-06
Final loss:
1043 0.9240902 9.675125e-07
Best loss: 0.9240902066230774
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
847 0.95595247 9.3526495e-07
Best loss: 0.9559524655342102
Replicate: 1/1
Iter Loss Rel. loss
1000 1.002736 2.7461456e-05
2000 0.9833151 3.9400256e-06
Final loss:
2623 0.98185384 9.712987e-07
Best loss: 0.9818538427352905
Replicate: 1/1
Iter Loss Rel. loss
C:\Users\Felix\PycharmProjects\pythonProject\venv\lib\site-packages\torch\nn\modules\loss.py:520: UserWarning: Using a target size (torch.Size([3292])) that is different to the input size (torch.Size([3292, 1])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.
return F.mse_loss(input, target, reduction=self.reduction)
1000 0.9824225 3.8160662e-05
Final loss:
1827 0.97609377 9.770305e-07
Best loss: 0.9760937690734863
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0022136 1.4630143e-05
Final loss:
1741 0.99710554 9.564418e-07
Best loss: 0.9971055388450623
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9810098 3.9492843e-06
Final loss:
1865 0.97941804 9.737144e-07
Best loss: 0.9794180393218994
Replicate: 1/1
Iter Loss Rel. loss
1000 0.994765 8.148825e-06
Final loss:
1325 0.99361044 9.598061e-07
Best loss: 0.9936104416847229
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
630 1.0226604 9.325417e-07
Best loss: 1.0226603746414185
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9948235 1.3780383e-06
Final loss:
1056 0.9947576 8.987806e-07
Best loss: 0.9947575926780701
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0445946 1.5976794e-06
Final loss:
1064 1.0445077 9.130363e-07
Best loss: 1.0445077419281006
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0431893 3.3139315e-06
Final loss:
1436 1.0422955 9.149742e-07
Best loss: 1.0422954559326172
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
923 1.0638434 8.9644163e-07
Best loss: 1.0638433694839478
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9509946 6.894325e-06
2000 0.94780487 1.2577393e-06
Final loss:
2083 0.9477105 9.433987e-07
Best loss: 0.9477105140686035
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0271865 4.4100393e-06
Final loss:
1244 1.0266266 9.2893896e-07
Best loss: 1.0266265869140625
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0817457 2.5235355e-05
Final loss:
1652 1.0767621 9.96397e-07
Best loss: 1.076762080192566
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
955 1.0629141 8.9722533e-07
Best loss: 1.0629141330718994
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0561572 2.5960212e-06
Final loss:
1274 1.0556123 9.034315e-07
Best loss: 1.055612325668335
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0456482 1.0260453e-06
Final loss:
1025 1.0456184 9.120664e-07
Best loss: 1.0456184148788452
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
970 0.99069345 9.626322e-07
Best loss: 0.9906934499740601
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0086472 3.7819793e-06
2000 1.0063756 1.7768081e-06
3000 1.0047412 1.3051127e-06
Final loss:
3434 1.0041937 9.4969073e-07
Best loss: 1.004193663597107
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
796 0.92811173 8.9909895e-07
Best loss: 0.928111732006073
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9500775 1.3802036e-06
Final loss:
1054 0.95001423 9.41111e-07
Best loss: 0.9500142335891724
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
471 1.0261054 9.2941076e-07
Best loss: 1.0261054039001465
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0379533 1.6882715e-05
Final loss:
1936 1.0330124 9.231965e-07
Best loss: 1.0330123901367188
Replicate: 1/1
Iter Loss Rel. loss
1000 0.959688 3.0433002e-06
Final loss:
1490 0.9588726 9.945777e-07
Best loss: 0.9588726162910461
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0425172 4.9169207e-06
Final loss:
1708 1.0408254 9.162665e-07
Best loss: 1.040825366973877
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
189 1.0630523 8.971087e-07
Best loss: 1.0630522966384888
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0895205 1.3567209e-05
2000 1.0846852 1.5386285e-06
Final loss:
2320 1.0842094 9.895529e-07
Best loss: 1.0842094421386719
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9953064 1.9762251e-06
Final loss:
1243 0.99496275 8.985953e-07
Best loss: 0.994962751865387
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0610036 1.2359059e-06
Final loss:
1031 1.0609652 8.9887345e-07
Best loss: 1.0609651803970337
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0817248 3.3060785e-06
Final loss:
1474 1.0806589 9.928041e-07
Best loss: 1.0806589126586914
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0997015 1.842822e-06
Final loss:
1076 1.0995859 9.757151e-07
Best loss: 1.0995858907699585
Replicate: 1/1
Iter Loss Rel. loss
1000 0.96752995 3.5114704e-06
Final loss:
1495 0.96659315 9.2496913e-07
Best loss: 0.9665931463241577
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0747453 4.5476436e-06
Final loss:
1683 1.0730083 9.998828e-07
Best loss: 1.0730082988739014
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
855 1.0574577 9.0185495e-07
Best loss: 1.057457685470581
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0449998 1.9392864e-06
Final loss:
1211 1.04467 9.1289445e-07
Best loss: 1.0446699857711792
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
829 1.0358785 9.2064215e-07
Best loss: 1.0358785390853882
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
499 1.0208569 9.341892e-07
Best loss: 1.0208568572998047
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0212907 5.9528966e-06
Final loss:
1446 1.0197709 9.35184e-07
Best loss: 1.019770860671997
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0387529 3.7181482e-05
2000 1.0253586 2.5577372e-06
Final loss:
2209 1.0249497 9.304588e-07
Best loss: 1.0249496698379517
Replicate: 1/1
Iter Loss Rel. loss
1000 1.029806 8.681848e-06
Final loss:
1623 1.0275888 9.280691e-07
Best loss: 1.0275888442993164
Replicate: 1/1
Iter Loss Rel. loss
1000 0.97429967 1.6701018e-05
2000 0.969189 1.5989846e-06
Final loss:
2167 0.96897924 9.842041e-07
Best loss: 0.9689792394638062
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0676141 6.476211e-06
Final loss:
1290 1.0666219 8.941064e-07
Best loss: 1.0666218996047974
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9705255 1.7810265e-06
Final loss:
1130 0.97034 9.82824e-07
Best loss: 0.9703400135040283
Replicate: 1/1
Iter Loss Rel. loss
C:\Users\Felix\PycharmProjects\pythonProject\venv\lib\site-packages\torch\nn\modules\loss.py:520: UserWarning: Using a target size (torch.Size([3293])) that is different to the input size (torch.Size([3293, 1])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.
return F.mse_loss(input, target, reduction=self.reduction)
Final loss:
415 1.0525274 9.0607944e-07
Best loss: 1.0525274276733398
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0144153 3.877989e-06
Final loss:
1560 1.0131611 9.412851e-07
Best loss: 1.013161063194275
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0150399 1.4915033e-05
Final loss:
1794 1.0096835 9.445271e-07
Best loss: 1.0096834897994995
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9975023 1.2010388e-05
Final loss:
1925 0.9927323 9.606551e-07
Best loss: 0.9927322864532471
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9673866 1.6019407e-05
2000 0.96263164 1.6098767e-06
Final loss:
2420 0.9620764 9.293117e-07
Best loss: 0.9620764255523682
Replicate: 1/1
Iter Loss Rel. loss
1000 1.063058 4.9340515e-06
2000 1.0598615 1.7996173e-06
Final loss:
2504 1.0591164 9.0044256e-07
Best loss: 1.0591163635253906
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
969 0.9920923 9.011952e-07
Best loss: 0.9920923113822937
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0209599 1.2843801e-06
Final loss:
1058 1.0208912 9.3415775e-07
Best loss: 1.0208911895751953
Replicate: 1/1
Iter Loss Rel. loss
1000 1.009589 4.13268e-06
Final loss:
1251 1.0090244 9.4514405e-07
Best loss: 1.0090243816375732
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9344 2.226194e-05
Final loss:
1922 0.92891306 9.624893e-07
Best loss: 0.9289130568504333
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0314684 9.823559e-06
Final loss:
1551 1.0291407 9.266696e-07
Best loss: 1.0291407108306885
Replicate: 1/1
Iter Loss Rel. loss
1000 1.050801 1.4747973e-06
Final loss:
1051 1.0507354 9.076248e-07
Best loss: 1.050735354423523
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
771 1.03955 9.173907e-07
Best loss: 1.0395499467849731
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0589944 5.178119e-06
Final loss:
1444 1.0577877 9.015736e-07
Best loss: 1.0577876567840576
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0620677 1.6836368e-06
Final loss:
1278 1.0616021 8.983342e-07
Best loss: 1.0616021156311035
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
570 0.9753868 9.1663003e-07
Best loss: 0.9753867983818054
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0271652 2.4371825e-06
Final loss:
1280 1.0266869 9.288844e-07
Best loss: 1.0266869068145752
Replicate: 1/1
Iter Loss Rel. loss
1000 0.92609787 2.2976372e-05
Final loss:
1999 0.9214084 9.703284e-07
Best loss: 0.9214084148406982
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0081984 1.5607426e-05
Final loss:
1828 1.0053587 9.485902e-07
Best loss: 1.0053586959838867
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0467818 4.327486e-06
Final loss:
1413 1.045934 9.117913e-07
Best loss: 1.0459339618682861
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
976 0.98493606 8.472269e-07
Best loss: 0.9849360585212708
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
790 1.0035611 9.502893e-07
Best loss: 1.0035611391067505
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
513 1.004001 9.4987297e-07
Best loss: 1.0040010213851929
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9855558 1.6329088e-06
Final loss:
1398 0.98505986 9.681376e-07
Best loss: 0.9850598573684692
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9984879 5.0740414e-06
Final loss:
1637 0.9968594 8.9688564e-07
Best loss: 0.9968593716621399
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0048 1.0914745e-05
Final loss:
1951 1.0010853 9.5263954e-07
Best loss: 1.0010852813720703
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9955151 3.5325045e-06
Final loss:
1138 0.9952203 8.9836277e-07
Best loss: 0.9952203035354614
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9933245 9.840757e-06
2000 0.98969436 1.2045047e-06
Final loss:
2059 0.9896258 9.0344133e-07
Best loss: 0.9896258115768433
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9809536 6.8660524e-06
Final loss:
1413 0.9797938 9.733409e-07
Best loss: 0.9797937870025635
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0231436 7.689783e-06
Final loss:
1962 1.0199977 9.34976e-07
Best loss: 1.0199977159500122
Replicate: 1/1
Iter Loss Rel. loss
1000 1.012166 2.9207698e-05
2000 1.0023984 2.1406286e-06
Final loss:
2281 1.0019377 9.51829e-07
Best loss: 1.001937747001648
Replicate: 1/1
Iter Loss Rel. loss
1000 0.97911423 2.9220437e-06
Final loss:
1860 0.9756964 9.163392e-07
Best loss: 0.9756963849067688
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
966 0.8937203 9.3369727e-07
Best loss: 0.8937203288078308
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9320393 7.2903363e-06
Final loss:
1880 0.9293903 9.619949e-07
Best loss: 0.9293903112411499
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9174606 7.113378e-05
2000 0.90512586 3.6877168e-06
3000 0.90291095 1.5183167e-06
Final loss:
3394 0.9024165 9.907495e-07
Best loss: 0.9024165272712708
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
718 0.8903369 9.3724555e-07
Best loss: 0.8903368711471558
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0024183 1.0702839e-05
2000 0.99363106 3.7791476e-06
3000 0.990593 2.406821e-06
4000 0.9888974 1.1452017e-06
Final loss:
4131 0.98875123 9.0424044e-07
Best loss: 0.988751232624054
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9153418 4.890075e-05
Final loss:
1672 0.90187746 9.913417e-07
Best loss: 0.9018774628639221
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9050002 1.2184224e-05
Final loss:
1222 0.9040578 9.889509e-07
Best loss: 0.9040578007698059
Replicate: 1/1
Iter Loss Rel. loss
1000 0.95098484 3.697915e-06
Final loss:
1398 0.9502413 9.408861e-07
Best loss: 0.9502413272857666
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
874 0.86648226 9.630483e-07
Best loss: 0.8664822578430176
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9189439 5.124081e-06
Final loss:
1771 0.9168922 9.751079e-07
Best loss: 0.9168921709060669
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9529976 1.250886e-06
Final loss:
1002 0.9529957 9.381667e-07
Best loss: 0.9529957175254822
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0276155 2.1924601e-05
2000 1.0199648 1.8700107e-06
Final loss:
2213 1.019659 9.352866e-07
Best loss: 1.0196590423583984
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
514 1.0479833 9.100083e-07
Best loss: 1.0479832887649536
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0320913 1.1550253e-06
Final loss:
1023 1.0320637 9.240451e-07
Best loss: 1.0320637226104736
Replicate: 1/1
Iter Loss Rel. loss
Final loss:
540 0.98741287 9.658304e-07
Best loss: 0.9874128699302673
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9617911 4.2141155e-06
Final loss:
1710 0.96022373 9.311047e-07
Best loss: 0.9602237343788147
Replicate: 1/1
Iter Loss Rel. loss
1000 0.98111516 1.0631476e-05
Final loss:
1539 0.9783219 9.748053e-07
Best loss: 0.97832190990448
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0804278 7.7669996e-05
2000 1.0482185 4.5490037e-06
Final loss:
2718 1.0468409 9.1100134e-07
Best loss: 1.0468409061431885
Replicate: 1/1
Iter Loss Rel. loss
1000 0.9759562 3.5422256e-06
Final loss:
1369 0.9752281 9.778978e-07
Best loss: 0.9752280712127686
Replicate: 1/1
Iter Loss Rel. loss
1000 1.0555327 4.743355e-06
Final loss:
1475 1.0542041 9.0463834e-07
Best loss: 1.0542041063308716
Editor is loading...