y reir

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_CA.G.csv

@@ -0,0 +1,51 @@
+numVol;CA.G_pred;CA.G_test
+19.0;0.12508343;0.0714285714285714
+51.0;0.16728754;0.0428571428571429
+37.0;0.094143525;0.414285714285714
+85.0;0.065597326;0.0678571428571429
+62.0;0.103448376;0.0714285714285714
+107.0;0.15336469;0.107142857142857
+65.0;0.09619674;0.117857142857143
+141.0;0.07735762;0.0107142857142857
+140.0;0.063966356;0.0607142857142857
+5.0;0.08220274;0.0821428571428571
+28.0;0.09912404;0.189285714285714
+118.0;0.09224202;0.0607142857142857
+53.0;0.100117706;0.0142857142857143
+112.0;0.077050425;0.0178571428571429
+20.0;0.10331561;0.0821428571428571
+86.0;0.06343738;0.0357142857142857
+11.0;0.042440306;0.0571428571428571
+117.0;0.06860661;0.0392857142857143
+12.0;0.05306487;0.225
+132.0;0.0736416;0.192857142857143
+56.0;0.078213096;0.0392857142857143
+87.0;0.0670958;0.0607142857142857
+40.394248962402344;0.07477141;0.0464285714285714
+27.0;0.09280961;0.0571428571428571
+32.0;0.19462954;0.0464285714285714
+76.0;0.106719136;0.075
+13.0;0.07257581;0.0035714285714285
+25.0;0.11378835;0.0714285714285714
+54.0;0.09040372;0.0107142857142857
+126.0;0.15514097;0.1
+106.0;0.07023655;0.132142857142857
+82.0;0.101087876;0.0178571428571429
+73.0;0.10913714;0.485714285714286
+16.0;0.070616186;0.0678571428571429
+130.0;0.13590552;0.0714285714285714
+23.0;0.14872712;0.0785714285714286
+41.0;0.12551636;0.0214285714285714
+90.0;0.12497693;0.0035714285714285
+102.0;0.086231865;0.0678571428571429
+31.0;0.14674062;0.0821428571428571
+110.0;0.078705624;0.103571428571429
+64.0;0.077337585;0.0464285714285714
+10.0;0.094110005;0.0214285714285714
+34.0;0.1756336;0.0392857142857143
+71.0;0.098388344;0.0464285714285714
+26.0;0.08664199;0.0607142857142857
+137.0;0.08775522;0.0642857142857143
+29.0;0.08635204;0.0321428571428571
+75.0;0.1203851;0.0964285714285714
+108.0;0.1350378;0.0678571428571429

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_CA.S.csv

@@ -0,0 +1,51 @@
+numVol;CA.S_pred;CA.S_test
+19.0;0.3217833;0.241935483870968
+51.0;0.33329245;0.145161290322581
+37.0;0.3023597;0.370967741935484
+85.0;0.2991102;0.387096774193548
+62.0;0.3347687;0.306451612903226
+107.0;0.3083398;0.225806451612903
+65.0;0.31000736;0.17741935483871
+141.0;0.3388949;0.338709677419355
+140.0;0.2991102;0.354838709677419
+5.0;0.31000736;0.274193548387097
+28.0;0.2991102;0.17741935483871
+118.0;0.32095763;0.403225806451613
+53.0;0.3023597;0.467741935483871
+112.0;0.32095763;0.370967741935484
+20.0;0.2991102;0.19578702747821808
+86.0;0.2991102;0.193548387096774
+11.0;0.2991102;0.258064516129032
+117.0;0.2991102;0.1526920050382614
+12.0;0.3092536;0.193548387096774
+132.0;0.3023597;0.564516129032258
+56.0;0.3023597;0.193548387096774
+87.0;0.2991102;0.0806451612903226
+40.394248962402344;0.3388949;0.629032258064516
+27.0;0.3092536;0.129032258064516
+32.0;0.32302225;0.370967741935484
+76.0;0.3023597;0.451612903225806
+13.0;0.2991102;0.161290322580645
+25.0;0.2991102;0.387096774193548
+54.0;0.3286247;0.274193548387097
+126.0;0.3347687;0.32258064516129
+106.0;0.2991102;0.580645161290323
+82.0;0.2991102;0.387096774193548
+73.0;0.33329245;0.532258064516129
+16.0;0.2991102;0.17741935483871
+130.0;0.36067072;0.161290322580645
+23.0;0.3092536;0.5
+41.0;0.3286247;0.225806451612903
+90.0;0.30571267;0.17741935483871
+102.0;0.3347687;0.290322580645161
+31.0;0.2991102;0.0806451612903226
+110.0;0.3176571;0.17741935483871
+64.0;0.2991102;0.0967741935483871
+10.0;0.2991102;0.0645161290322581
+34.0;0.36067072;0.225806451612903
+71.0;0.31434602;0.241935483870968
+26.0;0.31000736;0.0806451612903226
+137.0;0.3400987;0.370967741935484
+29.0;0.3038474;0.354838709677419
+75.0;0.2991102;0.17776942253112793
+108.0;0.3314576;0.225806451612903

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_CA.csv

@@ -0,0 +1,51 @@
+numVol;CA_pred;CA_test
+19.0;0.35947475;0.530120481927711
+51.0;0.3786945;0.0843373493975904
+37.0;0.41655856;0.421686746987952
+85.0;0.3131146;0.481927710843374
+62.0;0.3748162;0.240963855421687
+107.0;0.333092;0.325301204819277
+65.0;0.4284063;0.72289156626506
+141.0;0.38680366;0.301204819277108
+140.0;0.36481714;0.289156626506024
+5.0;0.31258184;0.216867469879518
+28.0;0.3290296;0.204819277108434
+118.0;0.36231774;0.204819277108434
+53.0;0.36423284;0.120481927710843
+112.0;0.3583091;0.27710843373494
+20.0;0.45555767;0.108433734939759
+86.0;0.3989507;0.6784636974334717
+11.0;0.3570908;0.313253012048193
+117.0;0.3047952;0.204819277108434
+12.0;0.34676823;0.36144578313253
+132.0;0.5086006;0.819277108433735
+56.0;0.38478723;0.168674698795181
+87.0;0.3706961;0.216867469879518
+40.394248962402344;0.40965107;0.602409638554217
+27.0;0.29520458;0.228915662650602
+32.0;0.37398526;0.253012048192771
+76.0;0.4448525;0.265060240963855
+13.0;0.3436827;0.228915662650602
+25.0;0.39686137;0.180722891566265
+54.0;0.35476893;0.253012048192771
+126.0;0.32129845;0.44578313253012
+106.0;0.40482178;0.349397590361446
+82.0;0.49535435;0.228915662650602
+73.0;0.41143075;0.325301204819277
+16.0;0.26905447;0.349397590361446
+130.0;0.49325934;0.36144578313253
+23.0;0.35028246;0.228915662650602
+41.0;0.3779589;0.08854621648788452
+90.0;0.34300175;0.807228915662651
+102.0;0.36389664;0.433734939759036
+31.0;0.35403714;0.409638554216867
+110.0;0.38597474;0.253012048192771
+64.0;0.4650652;0.228915662650602
+10.0;0.48296672;0.313253012048193
+34.0;0.35651615;0.132530120481928
+71.0;0.35093942;0.132530120481928
+26.0;0.4074995;0.373493975903614
+137.0;0.37498793;0.55421686746988
+29.0;0.32387644;0.265060240963855
+75.0;0.31768584;0.493975903614458
+108.0;0.44260296;0.614457831325301

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_DHPAA.G.csv

@@ -0,0 +1,51 @@
+numVol;DHPAA.G_pred;DHPAA.G_test
+19.0;0.2619468;0.127100840336134
+51.0;0.25876188;0.0840336134453781
+37.0;0.25091794;0.195378151260504
+85.0;0.2570907;0.158613445378151
+62.0;0.25533623;0.148109243697479
+107.0;0.2616889;0.315126050420168
+65.0;0.25163823;0.112394957983193
+141.0;0.255046;0.274159663865546
+140.0;0.2525176;0.504201680672269
+5.0;0.2585512;0.0672268907563025
+28.0;0.2511933;0.18172268907563
+118.0;0.26151603;0.172268907563025
+53.0;0.25250795;0.0483193277310924
+112.0;0.25372458;0.535714285714286
+20.0;0.25643957;0.14390756302521
+86.0;0.25463784;0.121848739495798
+11.0;0.2491031;0.226890756302521
+117.0;0.25811136;0.0399159663865546
+12.0;0.25376576;0.236344537815126
+132.0;0.2532351;0.198529411764706
+56.0;0.25352576;0.0514705882352941
+87.0;0.25276625;0.197478991596639
+40.394248962402344;0.25157115;0.105042016806723
+27.0;0.25026757;0.0987394957983193
+32.0;0.25426415;0.0420168067226891
+76.0;0.26267648;0.032563025210084
+13.0;0.24990429;0.125
+25.0;0.25105923;0.186974789915966
+54.0;0.2516454;0.158613445378151
+126.0;0.25970125;0.392857142857143
+106.0;0.2556435;0.257352941176471
+82.0;0.25730824;0.26155462184874
+73.0;0.2614767;0.147058823529412
+16.0;0.2501148;0.185924369747899
+130.0;0.27638975;0.137605042016807
+23.0;0.25634116;0.0651260504201681
+41.0;0.25082487;0.107142857142857
+90.0;0.25532743;0.158613445378151
+102.0;0.25435755;0.146008403361345
+31.0;0.2781286;0.0997899159663866
+110.0;0.25773257;0.173319327731092
+64.0;0.25560132;0.141806722689076
+10.0;0.25318104;0.0336134453781513
+34.0;0.2663218;0.0871848739495798
+71.0;0.26290908;0.114495798319328
+26.0;0.24948269;0.109243697478992
+137.0;0.26321793;0.679621848739496
+29.0;0.25528955;0.149159663865546
+75.0;0.2540009;0.0934873949579832
+108.0;0.25689635;0.18172268907563

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_DHPAA.GG.csv

@@ -0,0 +1,51 @@
+numVol;DHPAA.GG_pred;DHPAA.GG_test
+19.0;0.1990213;0.007051282051282
+51.0;0.35971388;0.0198717948717949
+37.0;0.17058375;0.0506410256410256
+85.0;0.22553875;0.0634615384615385
+62.0;0.13714942;0.0935897435897436
+107.0;0.28733522;0.0692307692307692
+65.0;0.0642959;0.0461538461538462
+141.0;0.2657002;0.0916666666666667
+140.0;0.12602966;0.3
+5.0;0.18261972;0.104487179487179
+28.0;0.19869292;0.269871794871795
+118.0;0.24797624;0.0378205128205128
+53.0;0.11755003;0.0897435897435898
+112.0;0.27968436;0.423076923076923
+20.0;0.11168976;0.294871794871795
+86.0;0.14804855;0.126923076923077
+11.0;0.109712906;0.544871794871795
+117.0;0.19808277;0.0487179487179487
+12.0;0.23669937;0.173717948717949
+132.0;0.328154;0.721153846153846
+56.0;0.10062911;0.136538461538462
+87.0;0.15729614;0.0557692307692308
+40.394248962402344;0.17895034;0.0634615384615385
+27.0;0.18605086;0.0115384615384615
+32.0;0.1513577;0.0717948717948718
+76.0;0.19062316;0.125641025641026
+13.0;0.11374087;0.0314102564102564
+25.0;0.07591556;0.0333333333333333
+54.0;0.08032588;0.122435897435897
+126.0;0.3132366;0.107692307692308
+106.0;0.27684626;0.309615384615385
+82.0;0.07708468;0.219871794871795
+73.0;0.20019747;0.149358974358974
+16.0;0.19767934;0.0775641025641026
+130.0;0.33106077;0.184615384615385
+23.0;0.114388674;0.0705128205128205
+41.0;0.13958442;0.0320512820512821
+90.0;0.11067966;0.0717948717948718
+102.0;0.27398393;0.156410256410256
+31.0;0.19372943;0.0724358974358974
+110.0;0.31567773;0.161538461538462
+64.0;0.08775628;0.0743589743589744
+10.0;0.1063232;0.0724358974358974
+34.0;0.28252316;0.0993589743589744
+71.0;0.18258783;0.275
+26.0;0.11359382;0.0769230769230769
+137.0;0.32032248;0.308974358974359
+29.0;0.20381816;0.0551282051282051
+75.0;0.17019099;0.0942307692307692
+108.0;0.21512276;0.0666666666666667

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_DHPAA.GS.csv

@@ -0,0 +1,51 @@
+numVol;DHPAA.GS_pred;DHPAA.GS_test
+19.0;0.20834807;0.219387755102041
+51.0;0.19022526;0.178571428571429
+37.0;0.18377548;0.377551020408163
+85.0;0.19674528;0.395408163265306
+62.0;0.22109433;0.278061224489796
+107.0;0.25424802;0.252551020408163
+65.0;0.22964564;0.038265306122449
+141.0;0.12495522;0.076530612244898
+140.0;0.20770048;0.673469387755102
+5.0;0.17379804;0.262755102040816
+28.0;0.2887256;0.14030612244898
+118.0;0.19051632;0.104591836734694
+53.0;0.16667338;0.209183673469388
+112.0;0.24023068;0.772959183673469
+20.0;0.17867948;0.0688775510204082
+86.0;0.24643517;0.270408163265306
+11.0;0.17095488;0.0739795918367347
+117.0;0.15617982;0.26530612244898
+12.0;0.16621669;0.168367346938776
+132.0;0.18936862;0.64030612244898
+56.0;0.14196673;0.0331632653061225
+87.0;0.20426787;0.0663265306122449
+40.394248962402344;0.18009728;0.165816326530612
+27.0;0.2038638;0.0280612244897959
+32.0;0.2701551;0.0586734693877551
+76.0;0.15257633;0.102040816326531
+13.0;0.12841609;0.107142857142857
+25.0;0.20865056;0.150510204081633
+54.0;0.17780389;0.275510204081633
+126.0;0.25097498;0.3579370379447937
+106.0;0.18245715;0.155612244897959
+82.0;0.17121865;0.104591836734694
+73.0;0.21069513;0.198979591836735
+16.0;0.2295124;0.206632653061224
+130.0;0.15528336;0.229591836734694
+23.0;0.20153299;0.170918367346939
+41.0;0.19251515;0.107142857142857
+90.0;0.16738388;0.0229591836734694
+102.0;0.20346819;0.227040816326531
+31.0;0.14852653;0.13265306122449
+110.0;0.25201675;0.369897959183673
+64.0;0.19462429;0.0688775510204082
+10.0;0.20072892;0.114795918367347
+34.0;0.19964679;0.14030612244898
+71.0;0.17372681;0.364795918367347
+26.0;0.1785887;0.0663265306122449
+137.0;0.2175579;0.339285714285714
+29.0;0.1419414;0.153061224489796
+75.0;0.22002234;0.191326530612245
+108.0;0.16702437;0.183673469387755

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_DHPAA.SS.csv

@@ -0,0 +1,51 @@
+numVol;DHPAA.SS_pred;DHPAA.SS_test
+19.0;0.22611181;0.158291457286432
+51.0;0.22579657;0.1452058106660843
+37.0;0.22574621;0.0226130653266332
+85.0;0.22592473;0.3028157353401184
+62.0;0.22578014;0.351758793969849
+107.0;0.22600812;0.14070351758794
+65.0;0.22591592;0.226130653266332
+141.0;0.22564575;0.2723125219345093
+140.0;0.22564644;0.241206030150754
+5.0;0.22555882;0.16218805313110352
+28.0;0.22577502;0.42964824120603
+118.0;0.22645088;0.31030216813087463
+53.0;0.22590287;0.0678391959798995
+112.0;0.22628906;0.165829145728643
+20.0;0.22584483;0.241206030150754
+86.0;0.22572452;0.4087613523006439
+11.0;0.2254854;0.243718592964824
+117.0;0.22562332;0.376884422110553
+12.0;0.22585684;0.241206030150754
+132.0;0.22565335;0.437185929648241
+56.0;0.22613393;0.253768844221106
+87.0;0.22649324;0.3243333399295807
+40.394248962402344;0.2256187;0.16237884759902954
+27.0;0.22617209;0.120603015075377
+32.0;0.2258985;0.12767615914344788
+76.0;0.22566026;0.293969849246231
+13.0;0.22540212;0.18072277307510376
+25.0;0.22593656;0.3067292869091034
+54.0;0.22557588;0.14572864321608
+126.0;0.22583438;0.2488587200641632
+106.0;0.22550802;0.258793969849246
+82.0;0.22582716;0.510050251256281
+73.0;0.22616056;0.316582914572864
+16.0;0.22574194;0.384422110552764
+130.0;0.22597097;0.673366834170854
+23.0;0.22581324;0.221105527638191
+41.0;0.22597106;0.261306532663317
+90.0;0.22575401;0.14070351758794
+102.0;0.22580984;0.3001595735549927
+31.0;0.22612576;0.0753768844221105
+110.0;0.22568189;0.520100502512563
+64.0;0.22546242;0.26885971426963806
+10.0;0.22593038;0.0402010050251256
+34.0;0.22583514;0.226130653266332
+71.0;0.2258874;0.17390896379947662
+26.0;0.22600427;0.35427135678392
+137.0;0.22588581;0.4853130578994751
+29.0;0.22559534;0.16830211877822876
+75.0;0.22599211;0.324120603015075
+108.0;0.22587998;0.278894472361809

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_DHPAA.csv

@@ -0,0 +1,51 @@
+numVol;DHPAA_pred;DHPAA_test
+19.0;0.40845296;0.126875
+51.0;0.40834406;0.15125
+37.0;0.40917417;0.2959375
+85.0;0.40892944;0.3384375
+62.0;0.4091897;0.4165625
+107.0;0.40845457;0.549375
+65.0;0.40866458;0.1575
+141.0;0.40875432;0.495
+140.0;0.4089624;0.099375
+5.0;0.41035685;0.0634375
+28.0;0.40860224;0.30375
+118.0;0.40902284;0.616875
+53.0;0.40841928;0.27875
+112.0;0.40892696;0.336875
+20.0;0.4092309;0.226875
+86.0;0.41035604;0.2675
+11.0;0.40854618;0.3725
+117.0;0.4088937;0.6221875
+12.0;0.40914047;0.5
+132.0;0.40932107;0.838125
+56.0;0.40831414;0.1484375
+87.0;0.4089362;0.360625
+40.394248962402344;0.41041988;0.1059375
+27.0;0.40848872;0.3684375
+32.0;0.40839592;0.3921875
+76.0;0.40883934;0.5496875
+13.0;0.40867856;0.491875
+25.0;0.40910363;0.355625
+54.0;0.4085454;0.2784375
+126.0;0.41041654;0.435
+106.0;0.4090483;0.1753125
+82.0;0.4083305;0.794375
+73.0;0.4085257;0.1628125
+16.0;0.40899372;0.2675
+130.0;0.40847754;0.43
+23.0;0.40886778;0.8740625
+41.0;0.40835214;0.350625
+90.0;0.40846348;0.158125
+102.0;0.4087677;0.330625
+31.0;0.40849498;0.4090625
+110.0;0.4091909;0.30625
+64.0;0.4085601;0.46375
+10.0;0.4087593;0.1725
+34.0;0.4104898;0.3059375
+71.0;0.40905097;0.83375
+26.0;0.4090181;0.5825
+137.0;0.4084037;0.573125
+29.0;0.40878022;0.3184375
+75.0;0.40856066;0.248125
+108.0;0.40875623;0.128125

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_E.S.csv

@@ -0,0 +1,51 @@
+numVol;E.S_pred;E.S_test
+19.0;0.15678889;0.12848514318466187
+51.0;0.1492267;0.1
+37.0;0.14630799;0.1
+85.0;0.14448419;0.1
+62.0;0.14648582;0.12486165761947632
+107.0;0.16124555;0.1
+65.0;0.15678889;0.3
+141.0;0.1445922;0.061225514858961105
+140.0;0.1492267;0.1292746365070343
+5.0;0.14630799;0.2
+28.0;0.1492267;0.1
+120.0;0.1492267;0.1
+53.0;0.16124555;0.4
+112.0;0.14630799;0.19994357228279114
+20.0;0.1445922;0.1
+86.0;0.14630799;0.1
+11.0;0.15094247;0.10578096657991409
+117.0;0.14448419;0.12220365554094315
+12.0;0.14477003;0.1
+132.0;0.14648582;0.1
+56.0;0.1445922;0.1766301691532135
+87.0;0.14619997;0.12671558558940887
+38.32004928588867;0.14648582;0.09597201645374298
+27.0;0.16124555;0.1
+32.0;0.15650305;0.3
+76.0;0.16124555;0.20242704451084137
+13.0;0.15678889;0.1
+25.0;0.15678889;0.1
+54.0;0.15661106;0.3
+126.0;0.16124555;0.4
+106.0;0.14619997;0.13460958003997803
+82.0;0.15678889;0.1
+73.0;0.14477003;0.1
+16.0;0.1492267;0.1
+130.0;0.14648582;0.21001189947128296
+23.0;0.15094247;0.1
+41.0;0.15094247;0.1488361358642578
+90.0;0.14648582;0.22078964114189148
+102.0;0.1445922;0.1
+31.0;0.1492267;0.19580771028995514
+110.0;0.14477003;0.09641043841838837
+64.0;0.14630799;0.1
+10.0;0.14477003;0.11995676904916763
+34.0;0.14630799;0.3
+71.0;0.15678889;0.24756395816802979
+26.0;0.14448419;0.14359326660633087
+137.0;0.14619997;0.1
+29.0;0.15678889;0.1
+75.0;0.1445922;0.11484482139348984
+108.0;0.1445922;0.1580364853143692

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_E.csv

@@ -0,0 +1,51 @@
+numVol;E_pred;E_test
+21.0;0.092235945;0.028515160105707
+52.0;0.14515702;0.0851435371571832
+40.0;0.09672606;0.032296284164321
+88.0;0.09533456;0.104654283764256
+64.0;0.092235945;0.0667516696993224
+110.0;0.092235945;0.155917392491549
+67.0;0.09827263;0.0768663246898515
+143.0;0.09533456;0.129398271894779
+112.0;0.14515702;0.178112885731253
+5.0;0.09533456;0.0687109157090351
+30.0;0.097693965;0.065986840612533
+136.0;0.092235945;0.0730046450879974
+54.0;0.092235945;0.0400833721706261
+115.0;0.09672606;0.0398888892655983
+22.0;0.09586687;0.0697543822679745
+89.0;0.09672606;0.0526230703168419
+12.0;0.097693965;0.0949836335692954
+120.0;0.09533456;0.242731586102865
+13.0;0.09827263;0.0762935895907884
+134.0;0.09533456;0.0461560625426895
+57.0;0.09672606;0.153902137324668
+90.0;0.09672606;0.0243619804333068
+78.63773345947266;0.092235945;0.0934142922454336
+29.0;0.09672606;0.0404981466331001
+35.0;0.092235945;0.030882003394036
+79.0;0.092235945;0.115434226143362
+14.0;0.09533456;0.0756097020295104
+27.0;0.09672606;0.0417687168149786
+55.0;0.09533456;0.0681188502005413
+127.0;0.09533456;0.147361344344955
+108.0;0.09533456;0.116400339768718
+85.0;0.092235945;0.04809102788567543
+76.0;0.09533456;0.0889972989064966
+18.0;0.092235945;0.0865556585131389
+131.0;0.09533456;0.220846745999933
+25.0;0.09447874;0.0218298324132785
+44.0;0.09533456;0.0356428234811793
+93.0;0.09827263;0.179174222226163
+104.0;0.09533456;0.306563550285796
+34.0;0.09827263;0.0169402402948279
+113.0;0.097693965;0.275506018845845
+66.0;0.14515702;0.222959070492099
+11.0;0.09533456;0.1280261129140854
+37.0;0.097693965;0.0206596176219684
+74.0;0.09533456;0.0644318536563866
+28.0;0.09672606;0.0221815561501189
+139.0;0.092235945;0.0797310433804953
+32.0;0.092235945;0.164926469073301
+78.0;0.09827263;0.0733464271733605
+142.0;0.09533456;0.195219369633575

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_HE.G.csv

@@ -0,0 +1,51 @@
+numVol;HE.G_pred;HE.G_test
+19.0;0.0077462206;0.0007960199004975
+51.0;0.007921778;0.0405970149253731
+37.0;0.005891491;0.0197014925373134
+85.0;0.0059976494;0.0013930348258706
+62.0;0.0059976494;0.0037810945273631
+107.0;0.005891491;0.0037810945273631
+65.0;0.0059976494;0.0115422885572139
+141.0;0.006344036;0.0013930348258706
+140.0;0.005891491;0.0071641791044776
+5.0;0.005891491;0.0401990049751244
+28.0;0.005891491;0.0001990049751243
+120.0;0.007921778;0.0003980099502487
+53.0;0.006344036;0.0029850746268656
+112.0;0.007921778;0.0033830845771144
+20.0;0.005891491;0.0019900497512437
+86.0;0.006111335;0.0005970149253731
+11.0;0.0074109584;0.0079601990049751
+117.0;0.0059976494;0.0017910447761194
+12.0;0.005891491;0.0600995024875622
+132.0;0.0059976494;0.0035820895522388
+56.0;0.006344036;0.0001990049751243
+87.0;0.0059976494;0.001592039800995
+38.32004928588867;0.006344036;0.0003980099502487
+27.0;0.005891491;0.0007960199004975
+32.0;0.006344036;0.0007960199004975
+76.0;0.006344036;0.0003980099502487
+13.0;0.0075856242;0.0003980099502487
+25.0;0.005891491;0.0003980099502487
+54.0;0.006881165;0.0019900497512437
+126.0;0.006344036;0.0023880597014925
+106.0;0.005891491;0.0049751243781094
+82.0;0.007636083;0.0011940298507462
+73.0;0.0059976494;0.0037810945273631
+16.0;0.0077462206;0.0007960199004975
+130.0;0.0059976494;0.0003980099502487
+23.0;0.005891491;0.0009950248756218
+41.0;0.005891491;0.0001990049751243
+90.0;0.0059976494;0.0013930348258706
+102.0;0.005891491;0.0001990049751243
+31.0;0.0065046325;0.0007960199004975
+110.0;0.005891491;0.0001990049751243
+64.0;0.006344036;0.0019900497512437
+10.0;0.0077462206;0.0027860696517412
+34.0;0.006344036;0.0007960199004975
+71.0;0.010037409;0.0003980099502487
+26.0;0.0065046325;0.0029850746268656
+137.0;0.0059976494;0.0007960199004975
+29.0;0.0065046325;0.0045771144278607
+75.0;0.007921778;0.0630845771144279
+108.0;0.007921778;0.0001990049751243

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_N.G.csv

@@ -0,0 +1,51 @@
+numVol;N.G_pred;N.G_test
+19.0;0.06979666;0.0469236517623614
+51.0;0.070030406;0.140988915182464
+37.0;0.06989744;0.0196163905841325
+85.0;0.07003552;0.0399800722381367
+62.0;0.069807984;0.0321023788765724
+107.0;0.06985887;0.094345497571304
+65.0;0.06997693;0.0429380993897123
+141.0;0.06980939;0.126603562087433
+140.0;0.0698216;0.08503157645463943
+5.0;0.069854975;0.062865861252958
+28.0;0.06994359;0.0850977705816416
+120.0;0.06984958;0.067225059160543
+53.0;0.06995273;0.0208307385726741
+112.0;0.06963329;0.0759745921036244
+20.0;0.06992625;0.0477954913438784
+86.0;0.06982827;0.0266533814920912
+11.0;0.06992402;0.0361502055050442
+117.0;0.06968924;0.113308008469299
+12.0;0.069861904;0.0842882052559472
+132.0;0.06982573;0.0272761240503176
+56.0;0.069920056;0.0746668327313489
+87.0;0.06987626;0.0508780670070993
+38.32004928588867;0.06985483;0.0316664590858139
+27.0;0.06994658;0.0480134512392577
+32.0;0.0698787;0.0958400797110475
+76.0;0.07006679;0.0214534811309005
+13.0;0.06986953;0.051531946693237
+25.0;0.069911145;0.0554552248100635
+54.0;0.06996926;0.0433740191804708
+126.0;0.069831;0.0652322829742185
+106.0;0.06970388;0.0604994395316976
+82.0;0.069988355;0.0436542533316727
+73.0;0.069912314;0.0381118445634575
+16.0;0.06988615;0.0557665960891767
+130.0;0.06977025;0.0535247228795616
+23.0;0.06997477;0.0317287333416366
+41.0;0.06985175;0.0714908456843941
+90.0;0.069830336;0.0527462946817785
+102.0;0.06984481;0.0326005729231536
+31.0;0.06995481;0.0406962261800971
+110.0;0.0697227;0.0249719765848798
+64.0;0.06995842;0.0315419105741686
+10.0;0.06978267;0.0528708431934238
+34.0;0.0697979;0.061122182089924
+71.0;0.06998512;0.0461452235645784
+26.0;0.069891274;0.0929443268152946
+137.0;0.06979554;0.0823888404533566
+29.0;0.069911145;0.0960580396064267
+75.0;0.0700589;0.288921409889152
+108.0;0.06968419;0.0578527836592353

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_TFA.G.csv

@@ -0,0 +1,51 @@
+numVol;TFA.G_pred;TFA.G_test
+19.0;0.063483015;0.261120263591433
+51.0;0.06344332;0.0164744645799012
+37.0;0.06349894;0.0661724327292696
+85.0;0.063533425;0.0027457440966501
+62.0;0.063369244;0.128775398132894
+107.0;0.06353962;0.221856123009336
+65.0;0.06370372;0.0529928610653487
+141.0;0.06365033;0.0222405271828666
+140.0;0.06346715;0.0134541460735859
+5.0;0.06344471;0.0032948929159802
+28.0;0.06334223;0.020156998187303543
+118.0;0.06367961;0.123283909939594
+53.0;0.06366661;0.014940022490918636
+112.0;0.06352559;0.0881383855024712
+20.0;0.06362863;0.113124656781988
+86.0;0.06349298;0.0024711696869851
+11.0;0.063158795;0.14168039538715
+117.0;0.063342825;0.01504486333578825
+12.0;0.063602015;0.0074135090609555
+132.0;0.06350801;0.0779791323448655
+56.0;0.06355894;0.017483936622738838
+87.0;0.06336438;0.056836902800659
+40.394248962402344;0.06372342;0.0340472267984624
+27.0;0.06345602;0.0639758374519495
+32.0;0.06346504;0.152663371773751
+76.0;0.06366251;0.0820977484898407
+13.0;0.06319208;0.003099510446190834
+25.0;0.06346197;0.0886875343218012
+54.0;0.06343144;0.103239978034047
+126.0;0.06330279;0.0686436024162548
+106.0;0.06355271;0.013594849966466427
+82.0;0.06358563;0.0784827247262001
+73.0;0.06354864;0.204557935200439
+16.0;0.063403025;0.0032948929159802
+130.0;0.06340977;0.03920112922787666
+23.0;0.06340166;0.0200439319055464
+41.0;0.06344886;0.0804503020318506
+90.0;0.063507125;0.0664470071389347
+102.0;0.063388646;0.014277869302581
+31.0;0.06349107;0.130148270181219
+110.0;0.063622616;0.0345963756177924
+64.0;0.06351836;0.016416165977716446
+10.0;0.06372731;0.0096101043382756
+34.0;0.06357175;0.0395387149917628
+71.0;0.06344679;0.0738605161998902
+26.0;0.06340175;0.0186710598572213
+137.0;0.063428864;0.0884129599121362
+29.0;0.06354321;0.0645249862712795
+75.0;0.063690566;0.0236133992311917
+108.0;0.063713565;0.0186710598572213

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_TFA.S.csv

@@ -0,0 +1,51 @@
+numVol;TFA.S_pred;TFA.S_test
+19.0;0.05422252;0.0173290749940856
+51.0;0.05422252;0.0270286255027206
+37.0;0.053764272;0.018689377809321
+85.0;0.053764272;0.0120652945351313
+62.0;0.05422252;0.0256091790868228
+107.0;0.05422252;0.0219422758457535
+65.0;0.05422252;0.0440619824934942
+141.0;0.053764272;0.0194582446179323
+140.0;0.053764272;0.0854625029571801
+5.0;0.055741772;0.0458362905133665
+28.0;0.05422252;0.0082209604920747
+118.0;0.053764272;0.0830376153300213
+53.0;0.053764272;0.0003548616039744
+112.0;0.053764272;0.0518689377809321
+20.0;0.05422252;0.0145493257629524
+86.0;0.055741772;0.0272651999053702
+11.0;0.053764272;0.0192808138159451
+117.0;0.053764272;0.0055594984622663
+12.0;0.08175044;0.0329429855689614
+132.0;0.05422252;0.042287674473622
+56.0;0.053764272;0.0301632363378283
+87.0;0.05422252;0.0330612727702863
+40.394248962402344;0.055741772;0.0079843860894251
+27.0;0.053764272;0.0295718003312042
+32.0;0.05422252;0.09356517624793
+76.0;0.053764272;0.0068015140761769
+13.0;0.053764272;0.0444759876981311
+25.0;0.05422252;0.0332387035722735
+54.0;0.053764272;0.0274426307073575
+126.0;0.05620002;0.0984740951029099
+106.0;0.053764272;0.0390347764371895
+82.0;0.053764272;0.0932103146439555
+73.0;0.05422252;0.029985805535841
+16.0;0.053764272;0.003393546212464571
+130.0;0.05422252;0.052578660988881
+23.0;0.053764272;0.0041400520463685
+41.0;0.05422252;0.0065649396735273
+90.0;0.053764272;0.0180979418026969
+102.0;0.053764272;0.000591436006624
+31.0;0.05422252;0.011592145729832
+110.0;0.053764272;0.046782588123965
+64.0;0.053764272;0.006211144383996725
+10.0;0.053764272;0.0124792997397682
+34.0;0.05620002;0.0631653655074521
+71.0;0.053764272;0.0133073101490419
+26.0;0.053764272;0.0123610125384433
+137.0;0.061096683;0.0636976579134138
+29.0;0.053764272;0.0199313934232316
+75.0;0.05422252;0.0147267565649397
+108.0;0.053764272;0.0293943695292169

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_Total.CA.csv

@@ -0,0 +1,51 @@
+numVol;Total.CA_pred;Total.CA_test
+19.0;0.26935163;0.249322493224932
+51.0;0.32585254;0.111111111111111
+37.0;0.18648042;0.506775067750677
+85.0;0.21037708;0.260162601626016
+62.0;0.25419882;0.195121951219512
+107.0;0.22277682;0.227642276422764
+65.0;0.24346967;0.317073170731707
+141.0;0.29390872;0.168021680216802
+140.0;0.19562407;0.205962059620596
+5.0;0.22700727;0.192411924119241
+28.0;0.18812476;0.254742547425474
+118.0;0.21731678;0.195121951219512
+53.0;0.22909924;0.151761517615176
+112.0;0.20042203;0.173441734417344
+20.0;0.26142204;0.102981029810298
+86.0;0.22446965;0.319783197831978
+11.0;0.16731481;0.192411924119241
+117.0;0.21306998;0.0921409214092141
+12.0;0.20776425;0.319783197831978
+132.0;0.26615337;0.460704607046071
+56.0;0.22741976;0.13550135501355
+87.0;0.2235611;0.143631436314363
+40.394248962402344;0.25314713;0.311653116531165
+27.0;0.20543657;0.151761517615176
+32.0;0.32674515;0.18970189701897
+76.0;0.26662475;0.227642276422764
+13.0;0.18843767;0.116531165311653
+25.0;0.26871166;0.195121951219512
+54.0;0.2165866;0.146341463414634
+126.0;0.30984426;0.265582655826558
+106.0;0.19866858;0.311653116531165
+82.0;0.263305;0.165311653116531
+73.0;0.28384835;0.56639566395664
+16.0;0.20433843;0.195121951219512
+130.0;0.27980337;0.197831978319783
+23.0;0.23395713;0.230352303523035
+41.0;0.26997927;0.0542005420054201
+90.0;0.2634281;0.249322493224932
+102.0;0.22391118;0.233062330623306
+31.0;0.25104544;0.203252032520325
+110.0;0.2346432;0.200542005420054
+64.0;0.2344933;0.138211382113821
+10.0;0.23071104;0.132791327913279
+34.0;0.29929364;0.132791327913279
+71.0;0.21314187;0.140921409214092
+26.0;0.21808483;0.178861788617886
+137.0;0.2492913;0.2710027100271
+29.0;0.2270577;0.178861788617886
+75.0;0.2597824;0.200542005420054
+108.0;0.25259972;0.262872628726287

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_Total.DHPAA.csv

@@ -0,0 +1,51 @@
+numVol;Total.DHPAA_pred;Total.DHPAA_test
+19.0;0.3723083;0.0855740004676175
+51.0;0.3723083;0.0823006780453589
+37.0;0.42604485;0.2450315641805
+85.0;0.42604485;0.274725274725275
+62.0;0.42604485;0.361935936404021
+107.0;0.40513676;0.467617488894085
+65.0;0.40331307;0.109188683656769
+141.0;0.38363457;0.398643909282207
+140.0;0.43709487;0.30512041150339
+5.0;0.3817562;0.0514379237783493
+28.0;0.39441085;0.343932663081599
+118.0;0.38363457;0.450081833060556
+53.0;0.39340225;0.202478372691139
+112.0;0.38363457;0.536824877250409
+20.0;0.42136005;0.263034837502923
+86.0;0.41458467;0.225157820902502
+11.0;0.40778932;0.482347439794248
+117.0;0.437557;0.476502221183072
+12.0;0.42604485;0.452887537993921
+132.0;0.42136005;0.958615852232873
+56.0;0.3723083;0.123918634556932
+87.0;0.41646305;0.267009586158522
+40.394248962402344;0.40285012;0.0678045358896423
+27.0;0.41482523;0.240589198036007
+32.0;0.39340225;0.261164367547346
+76.0;0.38363457;0.425999532382511
+13.0;0.4476537;0.343932663081599
+25.0;0.4183244;0.260462941314005
+54.0;0.42623076;0.252045826513912
+126.0;0.4026701;0.379003974748656
+106.0;0.4254156;0.264671498714052
+82.0;0.37775224;0.714753331774608
+73.0;0.39373127;0.181669394435352
+16.0;0.42604485;0.249473930324994
+130.0;0.39033026;0.428337619826981
+23.0;0.38300532;0.65536591068506
+41.0;0.38767773;0.2569558101473
+90.0;0.39605477;0.119943885901333
+102.0;0.40331307;0.284545241992051
+31.0;0.42050627;0.29880757540332
+110.0;0.39321637;0.333878887070376
+64.0;0.41737112;0.338788870703764
+10.0;0.40778932;0.102174421323358
+34.0;0.38665318;0.243394902969371
+71.0;0.42604485;0.70984334814122
+26.0;0.41646305;0.45218611176058
+137.0;0.3660177;0.650689735796119
+29.0;0.38363457;0.23240589198036
+75.0;0.40778932;0.21346738368015
+108.0;0.39321637;0.128361000701426

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_Total.TFA.csv

@@ -0,0 +1,51 @@
+numVol;Total.TFA_pred;Total.TFA_test
+19.0;0.05584488;0.0607181083973922
+51.0;0.05584488;0.0253478641626934
+37.0;0.05309626;0.0272939573805585
+85.0;0.05309626;0.010606208037365
+62.0;0.05584488;0.0440790113846453
+107.0;0.05584488;0.0575557069183614
+65.0;0.05781832;0.0458304952807239
+141.0;0.05309626;0.0201420648049042
+140.0;0.05309626;0.0728811910090493
+5.0;0.05309626;0.0384839933832831
+28.0;0.054096457;0.0068599785929746
+118.0;0.05545795;0.0903473776393889
+53.0;0.05309626;0.000389218643573
+112.0;0.05309626;0.0584801011968473
+20.0;0.05584488;0.032207842755668
+86.0;0.05309626;0.0230612046317019
+11.0;0.05309626;0.0411598715578476
+117.0;0.05309626;0.0046706237228763
+12.0;0.07561501;0.0286075703026175
+132.0;0.054096457;0.0487982874379683
+56.0;0.05309626;0.0249099931886737
+87.0;0.05781832;0.0374622944439039
+40.394248962402344;0.05666285;0.0127955629074633
+27.0;0.05506646;0.0358567675391651
+32.0;0.05584488;0.104213291816678
+76.0;0.05545795;0.0203366741266907
+13.0;0.05309626;0.0366838571567578
+25.0;0.05584488;0.0432519217670526
+54.0;0.05309626;0.0410625668969544
+126.0;0.05584488;0.0933638221270799
+106.0;0.05309626;0.032207842755668
+82.0;0.05309626;0.0767733774447796
+73.0;0.05781832;0.0611073270409653
+16.0;0.05309626;0.0006811326262527
+130.0;0.054096457;0.0433492264279459
+23.0;0.05309626;0.0071518925756543
+41.0;0.05781832;0.0198501508222244
+90.0;0.05309626;0.0268560864065389
+102.0;0.05604955;0.0032110538094774
+31.0;0.054096457;0.0327916707210275
+110.0;0.05309626;0.0448087963413448
+64.0;0.05309626;0.007528466172516346
+10.0;0.05545795;0.0121630826116571
+34.0;0.05604955;0.0591612338231001
+71.0;0.05309626;0.0242288605624209
+26.0;0.05309626;0.0136713048555026
+137.0;0.05309626;0.0682592196166196
+29.0;0.05309626;0.028023742337258
+75.0;0.05604955;0.016493140021407
+108.0;0.05604955;0.0276831760241316

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_Total.VA.csv

@@ -0,0 +1,51 @@
+numVol;Total.VA_pred;Total.VA_test
+19.0;0.36253652;0.11072063863942
+51.0;0.24507274;0.111111111111111
+37.0;0.19225219;0.240140570089809
+85.0;0.22120352;0.234109939693696
+62.0;0.20412153;0.188207731354939
+107.0;0.39889938;0.302616165560328
+65.0;0.21096262;0.226560805241008
+141.0;0.30422214;0.431775782029589
+140.0;0.37495515;0.30582671699423
+5.0;0.25165212;0.100655126035837
+28.0;0.22001052;0.335112152371036
+118.0;0.34529224;0.331554514295631
+53.0;0.1846341;0.149203870016053
+112.0;0.358901;0.999739685018873
+20.0;0.22861554;0.781161872532431
+86.0;0.23577939;0.285001518504057
+11.0;0.14613147;0.347260184823637
+117.0;0.32707366;0.263829233372381
+12.0;0.3305797;0.176884029675908
+132.0;0.39021024;0.680550132326782
+56.0;0.1531436;0.146123476072715
+87.0;0.28080383;0.255238838995184
+40.394248962402344;0.19354342;0.1157967807714
+27.0;0.19054995;0.147555208468914
+32.0;0.32488996;0.170766627619419
+76.0;0.29812863;0.287084038353074
+13.0;0.1715125;0.143260011280316
+25.0;0.19373435;0.158358280185691
+54.0;0.25606298;0.221397891448653
+126.0;0.36053574;0.289730573994533
+106.0;0.38061664;0.517202481669487
+82.0;0.29542124;0.154063082997093
+73.0;0.31296465;0.218404269165691
+16.0;0.17639078;0.235498286259708
+130.0;0.40170127;0.330860341012625
+23.0;0.23475415;0.207123953316847
+41.0;0.25602436;0.183825762505966
+90.0;0.24964246;0.25207167339147
+102.0;0.29840606;0.195713479977439
+31.0;0.3099505;0.185083951581414
+110.0;0.33674052;0.246257972146297
+64.0;0.2248824;0.210464662241312
+10.0;0.23912841;0.118139615601545
+34.0;0.4115893;0.17358670658163
+71.0;0.2636411;0.241832617467135
+26.0;0.15646118;0.0874658336587271
+137.0;0.3699325;0.516551694216669
+29.0;0.2377614;0.226560805241008
+75.0;0.22427991;0.173847021562758
+108.0;0.40261355;0.224651828712742

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_VA.GG.csv

@@ -0,0 +1,51 @@
+numVol;VA.GG_pred;VA.GG_test
+19.0;0.28453064;0.082367956018064
+51.0;0.20013317;0.103818967209896
+37.0;0.2194833;0.18304535637149
+85.0;0.24461867;0.121833889652464
+62.0;0.17519431;0.164294129196937
+107.0;0.38664603;0.219271549185156
+65.0;0.19433643;0.0780973885725506
+141.0;0.2931641;0.363390928725702
+140.0;0.27534455;0.270125662674259
+5.0;0.29534823;0.0595915963086589
+28.0;0.13274787;0.26678774788926
+118.0;0.3773841;0.224082073434125
+53.0;0.15572357;0.0972413116041626
+112.0;0.27632573;0.9231657385826111
+20.0;0.26424184;0.80458472413116
+86.0;0.19324732;0.167435696053407
+11.0;0.13950175;0.237041036717063
+117.0;0.32886606;0.243716866287061
+12.0;0.29147843;0.13665815825643
+132.0;0.28586185;0.56989986255645
+56.0;0.1285431;0.148439033968192
+87.0;0.17440158;0.24160612605537
+40.394248962402344;0.14099073;0.0796681720007854
+27.0;0.18659484;0.0626349892008639
+32.0;0.3024968;0.0706361672884351
+76.0;0.22903232;0.299234243078736
+13.0;0.16122018;0.137885332809739
+25.0;0.127503;0.11314549381504
+54.0;0.18772738;0.231788729628902
+126.0;0.35864693;0.248281955625368
+106.0;0.2976021;0.360053013940703
+82.0;0.18291113;0.140192420969959
+73.0;0.2538938;0.125073630473198
+16.0;0.16381381;0.148635381896721
+130.0;0.33652288;0.299479677989397
+23.0;0.2108554;0.155360298448851
+41.0;0.19733295;0.152316905556646
+90.0;0.1912665;0.243225996465737
+102.0;0.2711708;0.174700569408993
+31.0;0.25844592;0.10558609856666
+110.0;0.3415298;0.22334576870214
+64.0;0.20699815;0.176614961712154
+10.0;0.15862578;0.076133909287257
+34.0;0.3648488;0.133762026310622
+71.0;0.23047218;0.206263498920086
+26.0;0.15625845;0.0951796583546044
+137.0;0.29900783;0.407667386609071
+29.0;0.20375678;0.0968977027292362
+75.0;0.15477471;0.0516395052032201
+108.0;0.35830015;0.149371686628706

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_VA.GS.csv

@@ -0,0 +1,51 @@
+numVol;VA.GS_pred;VA.GS_test
+19.0;0.36953816;0.222050290135397
+51.0;0.36176464;0.0967117988394584
+37.0;0.36321166;0.216247582205029
+85.0;0.36321166;0.643326885880077
+62.0;0.38546845;0.234429400386847
+107.0;0.35215852;0.329593810444874
+65.0;0.38277474;0.266537717601547
+141.0;0.35757232;0.854932301740812
+140.0;0.38831383;0.392263056092843
+5.0;0.34992003;0.102514506769826
+28.0;0.35328934;0.612379110251451
+118.0;0.36825958;0.848355899419729
+53.0;0.38277474;0.417408123791103
+112.0;0.37995788;0.194197292069632
+20.0;0.37378505;0.280851063829787
+86.0;0.351651;0.514119922630561
+11.0;0.34992003;0.36247582205029
+117.0;0.37291378;0.373694390715667
+12.0;0.39517057;0.231334622823985
+132.0;0.38680145;0.679303675048356
+56.0;0.37378505;0.19458413926499
+87.0;0.37378505;0.187620889748549
+40.394248962402344;0.38546845;0.0882011605415861
+27.0;0.37378505;0.499032882011605
+32.0;0.35328934;0.679690522243714
+76.0;0.38562965;0.0963249516441006
+13.0;0.34992003;0.0649903288201161
+25.0;0.34992003;0.397292069632495
+54.0;0.34992003;0.381044487427466
+126.0;0.3532658;0.42321083172147
+106.0;0.37412107;0.51257253384913
+82.0;0.34992003;0.270019342359768
+73.0;0.34992003;0.500580270793037
+16.0;0.36321166;0.307543520309478
+130.0;0.36004314;0.186460348162476
+23.0;0.34992003;0.294390715667311
+41.0;0.3603755;0.174854932301741
+90.0;0.34992003;0.0696324951644101
+102.0;0.35215852;0.184526112185687
+31.0;0.36176464;0.413539651837524
+110.0;0.3668724;0.402707930367505
+64.0;0.39517057;0.349709864603482
+10.0;0.38546845;0.400773694390716
+34.0;0.35061356;0.445647969052224
+71.0;0.37378505;0.204255319148936
+26.0;0.37378505;0.0588007736943907
+137.0;0.37849742;0.559767891682785
+29.0;0.34992003;0.449516441005803
+75.0;0.36176464;0.74816247582205
+108.0;0.3532658;0.741972920696325

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_VA.S.csv

@@ -0,0 +1,51 @@
+numVol;VA.S_pred;VA.S_test
+19.0;0.28014085;0.173973556019485
+51.0;0.25052896;0.11143801361322403
+37.0;0.24108545;0.331593597773139
+85.0;0.24108545;0.251913709116214
+62.0;0.28014085;0.155880306193459
+107.0;0.25631824;0.180974081158638
+65.0;0.24108545;0.532707028531663
+141.0;0.25052896;0.32050850987434387
+140.0;0.26652625;0.191718858733473
+5.0;0.24108545;0.279053583855254
+28.0;0.24521545;0.17223382045929
+118.0;0.24639902;0.224425887265136
+53.0;0.24260947;0.121433542101601
+112.0;0.24108545;0.2652180790901184
+20.0;0.25631824;0.282533054975644
+86.0;0.25052896;0.294711203897008
+11.0;0.24521545;0.130828114126653
+117.0;0.24339244;0.13535554707050323
+12.0;0.24639902;0.178844815588031
+132.0;0.24803756;0.230688935281837
+56.0;0.24870591;0.0723729993041058
+87.0;0.25052896;0.175365344467641
+40.394248962402344;0.26652625;0.14022880792617798
+27.0;0.24108545;0.203201113430759
+32.0;0.2561276;0.103340292275574
+76.0;0.25052896;0.16677527129650116
+13.0;0.24108545;0.177800974251914
+25.0;0.24803756;0.148921363952679
+54.0;0.25052896;0.16336703300476074
+126.0;0.24521545;0.156576200417537
+106.0;0.26652625;0.319067501739736
+82.0;0.25052896;0.31717565655708313
+73.0;0.26652625;0.17571329157968
+16.0;0.24108545;0.411969380654141
+130.0;0.24803756;0.132567849686848
+23.0;0.24108545;0.241127348643006
+41.0;0.25052896;0.203897007654836
+90.0;0.24339244;0.2768048942089081
+102.0;0.24108545;0.11482254697286
+31.0;0.24803756;0.160055671537926
+110.0;0.24108545;0.110299234516354
+64.0;0.24260947;0.0706332637439109
+10.0;0.24108545;0.1687543493389
+34.0;0.25631824;0.16491109132766724
+71.0;0.25052896;0.179540709812109
+26.0;0.24639902;0.176757132915797
+137.0;0.24521545;0.371955462769659
+29.0;0.24108545;0.294363256784969
+75.0;0.24803756;0.440153096729297
+108.0;0.25052896;0.2747310400009155

results/predicts/df_pred-test_xgbGCV_OneTargetOneModel_noScaling_VA.SS.csv

@@ -0,0 +1,51 @@
+numVol;VA.SS_pred;VA.SS_test
+19.0;0.2846988;0.0121278941565601
+51.0;0.26847377;0.243660418963616
+37.0;0.16735388;0.136714443219405
+85.0;0.20248967;0.320102903344359
+62.0;0.17889294;0.099595736861448
+107.0;0.22930497;0.6843072399853
+65.0;0.25774363;0.549797868430724
+141.0;0.3042203;0.277104005880191
+140.0;0.17426708;0.118706357956634
+5.0;0.34499198;0.191106210951856
+28.0;0.3090265;0.117236310180081
+118.0;0.23927005;0.152884968761485
+53.0;0.22752139;0.027930907754502
+112.0;0.30571377;0.590959206174201
+20.0;0.15512717;0.109886071297317
+86.0;0.23334122;0.468945240720323
+11.0;0.22737192;0.799705990444689
+117.0;0.19775046;0.332598309445057
+12.0;0.28226945;0.192576258728409
+132.0;0.27617124;0.608599779492834
+56.0;0.17275083;0.0922454979786843
+87.0;0.25245878;0.216832047041529
+40.394248962402344;0.356211;0.256155825064315
+27.0;0.35785192;0.127894156560088
+32.0;0.19986415;0.0826901874310915
+76.0;0.3016579;0.205071664829107
+13.0;0.22633055;0.14316320419311523
+25.0;0.23483342;0.0893054024255788
+54.0;0.30139598;0.0554943035648659
+126.0;0.28528562;0.15178243292907
+106.0;0.23201811;0.906651966188901
+82.0;0.3197206;0.167585446527012
+73.0;0.3662098;0.383682469680265
+16.0;0.2168425;0.331495773612642
+130.0;0.19035836;0.35023888276369
+23.0;0.35614145;0.148107313487688
+41.0;0.16782172;0.10327085630283
+90.0;0.27774587;0.2954796030871
+102.0;0.32961795;0.16391032708563
+31.0;0.26156527;0.392135244395443
+110.0;0.33594945;0.141859610437339
+64.0;0.26386967;0.148107313487688
+10.0;0.31098542;0.0485115766262404
+34.0;0.17737336;0.127894156560088
+71.0;0.20639971;0.216097023153252
+26.0;0.24456361;0.17103779315948486
+137.0;0.30307657;0.352076442484381
+29.0;0.28331375;0.389195148842337
+75.0;0.2799815;0.0345461227489893
+108.0;0.3159298;0.0863653068724733

scripts/RFfit.py

@@ -4,7 +4,6 @@
 """
 
 import pandas as pd
-import numpy as np
 from xgboost import XGBRFRegressor
 from sklearn.metrics import mean_squared_error
 from sklearn.model_selection import RepeatedKFold, GridSearchCV
@@ -92,7 +91,7 @@ def RFfit(X_train, X_test, X_val,  y_train, y_test,  y_val):
     return (rf_XGB)
 
 def RF_Fit_GCV(X_train, X_test, X_val, y_train, y_test, y_val, df_name, full = False, eval = False,  plot = False):
-    
+    '''
     param_grid_extensive = {
     'bootstrap': [False, True],
     'max_depth': [1, 10, 20, 30, 50, 70, 100, None],
@@ -101,7 +100,7 @@ def RF_Fit_GCV(X_train, X_test, X_val, y_train, y_test, y_val, df_name, full = F
     'min_samples_split': [2, 3, 4, 5, 8, 10, 12, 20, 30],
     'n_estimators': [10, 50, 100, 200, 300, 500, 700, 1000]
     }
-    
+    '''
     param_grid_light = {
     'max_depth': [80, 90, 100, 110],
     'max_features': [0.2, 0.5, 1],
@@ -155,9 +154,6 @@ def RF_Fit_GCV(X_train, X_test, X_val, y_train, y_test, y_val, df_name, full = F
         pickle.dump(rf_GCV, file)
     
     print(" ----------------- MODEL SAVED ----------------- ")
-
-    if (eval):
-        print("lalala")#evaluateNPlot(filename, df, df_name, y_test=y_test, X_test=X_test, full = full,  pipeline = True,  plot = plot)
-    else:
-        print(" ----------------- ENDED SCRIPT ----------------- ")
-    return (rf_GCV)
+    print(" ----------------- ENDED SCRIPT ----------------- ")
+    
+    return (rf_GCV)

scripts/XGBFfit.py

@@ -1,6 +1,9 @@
 from xgboost import XGBRegressor
 from sklearn.metrics import mean_squared_error
-import numpy as np
+from sklearn.model_selection import RepeatedKFold,  GridSearchCV
+import pandas as pd
+import pickle
+import os
 import optuna
 import time
 
@@ -74,3 +77,66 @@ def XGBfit(X_train, X_test, X_val,  y_train, y_test,  y_val):
     print(f"Tiempo predicción:    {tiempo_prediccion_xgb_xgb:.2f} segundos")
     print(f"RMSE:                 {rmse_xgb_xgb:.2f}")
     return xgb_xgb
+
+def XGBfit_GCV(X_train, X_test, X_val,  y_train, y_test,  y_val,  df_name,  full = True):
+    
+    params = {
+            'n_estimators': [100,  500,  1000],
+            'max_depth': [5, 7],#[3, 5,  7,  12],
+            'scale_pos_weight': [2, 4], #[1, 3,  5],
+            'learning_rate': [0.0001,  0.1], #[0.000001,  0.001, 0.01,  0.1],
+            'reg_lambda': [0.01,0.1],#[0.0001, 0.001,  0.1], 
+            'reg_alpha': [0.01,0.1],#[0.0001, 0.001,  0.1],
+            'colsample_bynode': [0.01,  1], #[0.001,  0.1, 1],
+            'subsample':  [0.01,  1]# [0.001,  0.1, 1],
+        }
+
+    model = XGBRegressor(
+                    tree_method = 'hist',
+                    eval_metric = 'rmse',
+                    n_jobs         = -1,
+                    random_state   = 42,
+                    enable_categorical = True
+                )
+    
+    target = y_train.name 
+    
+    print(" ----------------- SETTING UP TRAINING ----------------- ")
+    
+    cv = RepeatedKFold(n_splits=3, n_repeats=3, random_state=42)
+    
+    grid_search = GridSearchCV(estimator = model, param_grid = params, cv = cv, n_jobs = -1, verbose = 1)
+
+    print(" ----------------- STARTING GRIDSEARCH ----------------- ")
+
+    grid_search.fit(X_train, y_train)
+
+    xgb_GCV = XGBRegressor(                    
+                        tree_method        = 'hist',
+                        grow_policy        = 'depthwise',
+                        n_jobs             = -1,
+                        random_state       = 42,
+                        enable_categorical = True,
+                        **grid_search.best_params_
+                        )
+
+    xgb_GCV.fit(
+            X = pd.concat([X_train, X_val]),
+            y = pd.concat([y_train, y_val])
+    )
+    print(" ----------------- TRAINING ENDED ----------------- ")
+
+    if (full):    
+        filename = os.path.join("..", "models","xgb_Full_OneTargetPerModel"+df_name+"_"+target+".pkl")
+                
+    else: 
+        filename = os.path.join("..", "models","xgb_Met_OneTargetPerModel"+df_name+"_"+target+".pkl")
+      
+    with open(filename, 'wb') as file:
+        pickle.dump(xgb_GCV, file)
+    
+    print(" ----------------- MODEL SAVED ----------------- ")
+    print(" ----------------- ENDED SCRIPT ----------------- ")
+    
+    return (xgb_GCV)
+    

scripts/pruebas_retrain.py

@@ -14,7 +14,7 @@ from plotting import plotTestVsPredicted, plotResiduals
 # ==============================================================================
 from xgboost import XGBRegressor
 from sklearn.model_selection import train_test_split
-from XGBFfit import XGBfit
+from XGBFfit import XGBfit,  XGBfit_GCV
 from RFfit import RFfit, RF_Fit_GCV
 
 import optuna
@@ -33,7 +33,7 @@ paths = ["plasmFlav_ord.csv", "plasmAnt_ord.csv", "urineFlav_ord.csv", "urineAnt
 paths = ["../data/" + s for s in paths]
 
 for path in paths:
-    
+    print("------- READING "+ path+ " -----------")
     df, df_name = fullRead(path, sep = ",", full = False)
     
     full = True
@@ -48,6 +48,9 @@ for path in paths:
     # Filter columns where missing percentage is greater than the threshold
     columns_to_remove = missing_percentages[missing_percentages > 0.4].index
     
+    print("Columns removed by na's percentage:")
+    print(columns_to_remove)
+    
     # Drop the columns from the DataFrame
     df_filtered = df.drop(columns=columns_to_remove)
     
@@ -58,8 +61,7 @@ for path in paths:
     df_filtered.replace([0,1,0.0,1.1], np.nan,  inplace = True)
 
     # df.dropna(inplace = True)
-
-    
+    print ("----------- IMPUTING DATASET BY MICE ALGORITHM ------------------")
     iimp = IterativeImputer(
     estimator = XGBRegressor(),
     random_state = 42,
@@ -83,7 +85,7 @@ for path in paths:
     df_corr = df_filtered[numCols].corr(method="pearson")
         
     for target in df_filtered.drop(["numVol","Time", "Sweetener", "Sex"], axis = 1).columns:
-        
+        print("------------ MODELLING " + target+ " -----------")    
         df = df_filtered
         
         threshold = 0.5
@@ -92,6 +94,8 @@ for path in paths:
         # Select features highly correlated with the target
         correlated_features = target_correlation[target_correlation >= threshold].index.tolist()
         correlated_features.remove(target)
+        print("Removed features for "+target+":")
+        print(correlated_features)
         df = df.drop(correlated_features, axis=1)
 
         X = df[df["Time"] == "Initial"].set_index("numVol").drop(["Time"], axis=1) 
@@ -101,7 +105,7 @@ for path in paths:
         X_train, X_test, y_train, y_test = train_test_split(
             X,
             y,
-            train_size = 0.6,
+            train_size = 0.7,
             random_state = 42,
             shuffle = True
         )
@@ -109,7 +113,7 @@ for path in paths:
         X_train, X_val, y_train, y_val = train_test_split(
             X_train,
             y_train,
-            train_size   = 0.6,
+            train_size   = 0.7,
             random_state = 42,
             shuffle      = True
         )
@@ -118,7 +122,7 @@ for path in paths:
         print("Observaciones en validation:", X_val.shape)
         print("Observaciones en test:", X_test.shape)
         
-        RF = True
+        RF = False
         
         #X_train, scaler = scaling(X_train)
         #y_train = scaler.transform(y_train)
@@ -168,11 +172,11 @@ for path in paths:
             print(" ----------------- STARTING XGB ----------------- ")
             
             
-            modelname = "xgb_OneTargetOneModel_noScaling"
+            modelname = "xgbGCV_OneTargetOneModel_noScaling"
             
             start = time.time()
             
-            xgb_XGB = XGBfit(X_train, X_test, X_val, y_train, y_test, y_val)
+            xgb_XGB = XGBfit_GCV(X_train, X_test, X_val, y_train, y_test, y_val, df_name=df_name)
             
             end = time.time()
             
@@ -189,8 +193,9 @@ for path in paths:
             # y_pred_scaled = xgb_XGB.predict(X_test)
             # y_pred = scaler.inverse_transform(y_pred_scaled)
             # y_test = pd.DataFrame([i for i in scaler.inverse_transform(y_test)], index=y_test.index, columns= y_test.columns)
+            
             y_test.name = target+"_test"
-            y_pred = pd.Series(rf_XGB.predict(X_test), index = y_test.index, name = target+"_pred")
+            y_pred = pd.Series(xgb_XGB.predict(X_test), index = y_test.index, name = target+"_pred")
             df_predTest = pd.concat([y_pred, y_test], axis = 1)
             df_predTest.to_csv("../results/predicts/df_pred-test_"+modelname+"_"+target+".csv", sep = ";")
             #df_predTest = pd.DataFrame([i for i in y_pred], index = y_test.index, columns= y_test.columns).add_suffix("_pred").join(y_test.add_suffix('_test'))