chapter3_DataPreprocess

Applied_Predictive_Modeling Chapter3 DataPreprocess
数据预处理按照顺序包括：删除、变换、增加
数据删除
数据变换
数据增加
source('D:/2-quick/data science/10保存R的文件/R_Env/R_Env.R')
pacman::p_load(caret,AppliedPredictiveModeling,tidyverse)
data("segmentationOriginal")
segData <- subset(segmentationOriginal,Case == 'Train')
segData = mutate(segData,cellID = Cell,class = Class,case = Case) %>% .[,-(1:3)]
statusColNum <- grep('Status',names(segData))
segData = segData[,-statusColNum]
dim(segData);View(head(segData))

[1] 1009 61

predict(BoxCoxTrans(segDataAreaCh1)

[1] 1.108458 1.106383 1.104520 1.103554 1.103607 1.105523 1.099444

[8] 1.104841 1.103278 1.102555 1.108428 1.106460 1.100302 1.100188

[15] 1.106383 1.100130 1.104599 1.107503 1.105739 1.103042 1.106008

[22] 1.103633 1.107104 1.101412 1.106996 1.108260 1.107232 1.106088

[29] 1.105423 1.106827 1.106686 1.099444 1.102623 1.102041 1.105288

[36] 1.105790 1.108373 1.108504 1.104049 1.106043 1.108286 1.107536

[43] 1.102378 1.106208 1.104140 1.102691 1.101922 1.104731 1.102378

[50] 1.104731 1.100787 1.104460 1.102520 1.100245 1.105606 1.107541

[57] 1.109482 1.099829 1.103474 1.107702 1.106176 1.107212 1.100631

[64] 1.100524 1.105777 1.108534 1.103278 1.105633 1.107399 1.106859

[71] 1.107667 1.109676 1.104250 1.107339 1.104398 1.100988 1.106229

[78] 1.104357 1.100577 1.100889 1.100736 1.102156 1.105466 1.102156

[85] 1.102232 1.105726 1.103278 1.102757 1.105973 1.103250 1.104500

[92] 1.100011 1.101321 1.106959 1.102414 1.102156 1.101275 1.102080

[99] 1.106921 1.107152 1.104618 1.100188 1.109939 1.107118 1.110014

[106] 1.103042 1.105257 1.107295 1.104929 1.109161 1.101882 1.104823

[113] 1.101674 1.099890 1.105973 1.102232 1.106795 1.099829 1.103221

[120] 1.109810 1.099377 1.104206 1.102623 1.108355 1.102757 1.102691

[127] 1.106323 1.103132 1.106392 1.106343 1.105082 1.106996 1.101716

[134] 1.104460 1.104559 1.107289 1.105852 1.100130 1.102949 1.103932

[141] 1.104003 1.104140 1.100469 1.100524 1.106883 1.102378 1.099377

[148] 1.105647 1.105495 1.106353 1.106859 1.107983 1.109046 1.103191

[155] 1.101501 1.102757 1.104599 1.101922 1.103191 1.099172 1.106099

[162] 1.101086 1.106489 1.104694 1.105114 1.105288 1.099510 1.103884

[169] 1.104894 1.105226 1.104731 1.103162 1.109682 1.103633 1.106982

[176] 1.106470 1.107357 1.102194 1.106875 1.099377 1.105257 1.107712

[183] 1.102623 1.107584 1.108132 1.108437 1.099377 1.102757 1.104877

[190] 1.099890 1.099309 1.103474 1.102001 1.101501 1.101882 1.104750

[197] 1.105996 1.104228 1.105147 1.105579 1.106959 1.106099 1.099510

[204] 1.099309 1.106431 1.103011 1.105242 1.102485 1.100071 1.104377

[211] 1.101716 1.103102 1.105592 1.103859 1.099575 1.102041 1.104768

[218] 1.102623 1.102041 1.107657 1.107978 1.100988 1.106686 1.102555

[225] 1.107040 1.102520 1.102980 1.104500 1.107974 1.106703 1.102980

[232] 1.098885 1.103363 1.106967 1.105098 1.104981 1.104750 1.105752

[239] 1.106996 1.105065 1.103554 1.107179 1.102306 1.102118 1.106737

[246] 1.103391 1.099377 1.102520 1.103932 1.106890 1.106906 1.104439

[253] 1.107579 1.106165 1.105606 1.104731 1.104003 1.099241 1.103162

[260] 1.107611 1.103835 1.104805 1.108071 1.107652 1.105304 1.100736

[267] 1.109325 1.102520 1.101275 1.100011 1.104335 1.107817 1.102520

[274] 1.104095 1.103391 1.106669 1.100577 1.100988 1.102724 1.105242

[281] 1.101632 1.100577 1.099704 1.105877 1.102757 1.105777 1.106219

[288] 1.102790 1.108019 1.100988 1.103391 1.103391 1.105840 1.103736

[295] 1.100988 1.106353 1.104314 1.104877 1.104026 1.100188 1.105523

[302] 1.101841 1.105852 1.103446 1.107480 1.100889 1.107584 1.099640

[309] 1.106921 1.103581 1.102156 1.099377 1.101181 1.108208 1.099704

[316] 1.102378 1.107061 1.106770 1.105660 1.100071 1.105996 1.104206

[323] 1.102623 1.104162 1.101841 1.107428 1.106271 1.102918 1.104947

[330] 1.099575 1.106412 1.103581 1.100469 1.101588 1.101962 1.101228

[337] 1.101181 1.103501 1.107574 1.100071 1.103419 1.105015 1.099377

[344] 1.103607 1.100188 1.106392 1.103810 1.103956 1.102886 1.105620

[351] 1.103042 1.100071 1.099767 1.101716 1.103191 1.103581 1.107264

[358] 1.104206 1.105179 1.102450 1.101501 1.100071 1.102414 1.102485

[365] 1.102118 1.101501 1.104877 1.106110 1.103474 1.105777 1.099890

[372] 1.100524 1.105288 1.103250 1.104003 1.102854 1.100787 1.106250

[379] 1.105686 1.105877 1.099101 1.100245 1.104929 1.100838 1.099704

[386] 1.100838 1.109075 1.104162 1.104694 1.105423 1.099172 1.099309

[393] 1.102118 1.105257 1.103736 1.107417 1.105537 1.104929 1.102306

[400] 1.099309 1.100683 1.105048 1.102485 1.103011 1.106292 1.107047

[407] 1.105114 1.107687 1.104877 1.101134 1.099241 1.098885 1.108015

[414] 1.101367 1.101841 1.101632 1.101037 1.102156 1.104894 1.102269

[421] 1.101275 1.102450 1.105288 1.107399 1.099890 1.105098 1.103501

[428] 1.107953 1.103102 1.102156 1.108464 1.101412 1.103391 1.101922

[435] 1.099309 1.105257 1.098885 1.099309 1.102450 1.106312 1.101758

[442] 1.105509 1.103810 1.102485 1.103335 1.103011 1.105686 1.109558

[449] 1.100011 1.103335 1.103908 1.105364 1.101181 1.106669 1.100889

[456] 1.103859 1.106110 1.107172 1.108117 1.103835 1.107812 1.105226

[463] 1.101588 1.104947 1.099704 1.105985 1.101086 1.107165 1.107682

[470] 1.106634 1.107657 1.099309 1.100071 1.099241 1.100302 1.106208

[477] 1.099829 1.100577 1.104731 1.103659 1.105579 1.102378 1.102041

[484] 1.101134 1.104599 1.099704 1.099890 1.105048 1.100011 1.108603

[491] 1.100188 1.101367 1.104947 1.103474 1.099767 1.106737 1.101545

[498] 1.104805 1.106402 1.104998 1.108208 1.103419 1.099101 1.100188

[505] 1.107508 1.105114 1.103501 1.106660 1.101962 1.103278 1.106187

[512] 1.103501 1.099377 1.103607 1.101367 1.101412 1.099704 1.104929

[519] 1.102306 1.102757 1.099704 1.106737 1.104272 1.103191 1.102080

[526] 1.099172 1.100011 1.103956 1.100577 1.106479 1.103162 1.100524

[533] 1.105726 1.105082 1.100071 1.104500 1.104768 1.102757 1.099890

[540] 1.103979 1.102414 1.103501 1.099444 1.101588 1.100736 1.102269

[547] 1.099640 1.106054 1.100787 1.107932 1.100524 1.100245 1.104787

[554] 1.105273 1.099640 1.102194 1.108572 1.099510 1.102378 1.105828

[561] 1.103474 1.102194 1.101037 1.104559 1.099444 1.101412 1.104947

[568] 1.103859 1.106208 1.107399 1.106669 1.100988 1.103042 1.102269

[575] 1.101758 1.103659 1.101716 1.104656 1.108222 1.106392 1.099829

[582] 1.106695 1.107941 1.105889 1.104293 1.108098 1.102623 1.104272

[589] 1.107452 1.100736 1.099767 1.102232 1.099444 1.105889 1.109183

[596] 1.104095 1.101800 1.105802 1.103607 1.099241 1.102001 1.107345

[603] 1.104656 1.104656 1.100577 1.104072 1.103132 1.100188 1.103786

[610] 1.103501 1.106302 1.101841 1.105565 1.099640 1.108639 1.107497

[617] 1.103363 1.101367 1.101412 1.103391 1.100838 1.102001 1.105364

[624] 1.102520 1.100577 1.100787 1.102269 1.102001 1.107480 1.104805

[631] 1.103474 1.106121 1.101228 1.109348 1.099101 1.099377 1.103250

[638] 1.099101 1.105925 1.102118 1.101134 1.107277 1.104250 1.099309

[645] 1.100011 1.102450 1.106240 1.106678 1.099172 1.107761 1.104618

[652] 1.105509 1.107047 1.099309 1.105481 1.107428 1.105633 1.101086

[659] 1.100245 1.103736 1.102589 1.102232 1.103932 1.105889 1.104026

[666] 1.099172 1.102001 1.105334 1.099890 1.104140 1.099377 1.107393

[673] 1.100939 1.104841 1.102623 1.100302 1.099640 1.104377 1.101321

[680] 1.100302 1.100889 1.105739 1.105349 1.102414 1.104460 1.099172

[687] 1.103554 1.103446 1.101228 1.105509 1.100188 1.102691 1.105647

[694] 1.101037 1.099101 1.103736 1.100358 1.100988 1.100631 1.101545

[701] 1.099510 1.100302 1.106762 1.100889 1.102041 1.105423 1.103633

[708] 1.105334 1.106043 1.106020 1.106729 1.108949 1.103419 1.105179

[715] 1.104162 1.106937 1.102757 1.099640 1.102118 1.107682 1.104998

[722] 1.100011 1.104357 1.108719 1.103581 1.107205 1.108523 1.104228

[729] 1.107061 1.105394 1.101962 1.106441 1.104750 1.105889 1.105226

[736] 1.102450 1.099640 1.100683 1.103908 1.107803 1.106208 1.106065

[743] 1.107199 1.099575 1.099510 1.099309 1.098885 1.106563 1.104559

[750] 1.102194 1.103786 1.104981 1.105195 1.102485 1.100939 1.106625

[757] 1.104140 1.104140 1.106373 1.104713 1.106099 1.100889 1.103810

[764] 1.102691 1.103761 1.103250 1.099241 1.105211 1.107995 1.108280

[771] 1.102156 1.102450 1.104750 1.102589 1.102589 1.106402 1.104377

[778] 1.101228 1.100524 1.107219 1.103554 1.104460 1.098885 1.101181

[785] 1.101841 1.098885 1.103042 1.099575 1.098958 1.100577 1.102724

[792] 1.102194 1.098885 1.102485 1.099309 1.100302 1.102414 1.105973

[799] 1.102306 1.103278 1.106373 1.106088 1.103446 1.104026 1.099241

[806] 1.103307 1.101228 1.104559 1.099444 1.105334 1.105015 1.104520

[813] 1.101321 1.103335 1.101882 1.100188 1.109910 1.100071 1.103581

[820] 1.103307 1.104419 1.102450 1.101674 1.102001 1.099377 1.102623

[827] 1.103932 1.108724 1.108303 1.103835 1.100188 1.103011 1.102041

[834] 1.104912 1.105423 1.100011 1.099829 1.102118 1.103528 1.104398

[841] 1.106507 1.107423 1.102555 1.107486 1.101134 1.101367 1.105195

[848] 1.105319 1.100302 1.107363 1.107251 1.099640 1.101412 1.108067

[855] 1.100736 1.102118 1.107775 1.107732 1.101882 1.105319 1.099829

[862] 1.108590 1.106625 1.101800 1.103979 1.105452 1.099510 1.102724

[869] 1.103474 1.100838 1.101275 1.102854 1.107765 1.104894 1.099444

[876] 1.102555 1.101758 1.100683 1.105098 1.101841 1.104095 1.105523

[883] 1.100889 1.100071 1.104877 1.101181 1.103736 1.103102 1.102269

[890] 1.102724 1.105713 1.101841 1.107590 1.102555 1.104912 1.101275

[897] 1.099309 1.102520 1.099704 1.103884 1.106544 1.101086 1.104026

[904] 1.105565 1.099510 1.102485 1.099640 1.106695 1.100939 1.103042

[911] 1.103979 1.101841 1.106590 1.100071 1.099444 1.104026 1.100302

[918] 1.099951 1.100469 1.100988 1.103391 1.099767 1.105537 1.106703

[925] 1.100939 1.107541 1.100469 1.104618 1.102378 1.100577 1.101412

[932] 1.099767 1.105242 1.105349 1.100011 1.108520 1.107826 1.102001

[939] 1.100736 1.101367 1.102485 1.103979 1.102414 1.106608 1.108585

[946] 1.103607 1.104787 1.102269 1.102790 1.101922 1.108319 1.104419

[953] 1.104599 1.101275 1.106669 1.107225 1.102724 1.102980 1.103528

[960] 1.107667 1.101841 1.105452 1.104480 1.105985 1.105226 1.105098

[967] 1.109244 1.104787 1.102691 1.099309 1.102886 1.103859 1.107552

[974] 1.101882 1.105242 1.101716 1.105852 1.099101 1.106643 1.106208

[981] 1.106906 1.101275 1.104579 1.100631 1.102790 1.105131 1.102657

[988] 1.106099 1.101841 1.099575 1.104981 1.102854 1.104929 1.099890

[995] 1.109149 1.102724 1.107302 1.099704 1.105764 1.106937 1.099951

[1002] 1.106132 1.105408 1.101674 1.106383 1.109041 1.101086 1.104599

[1009] 1.106479

transformed_data = preProcess(segData,method = c('BoxCox','center'))