From d854ccd523403f52fe29fcf02d923ddae0cca4c0 Mon Sep 17 00:00:00 2001 From: Lintong Li Date: Tue, 26 Nov 2019 17:00:42 -0500 Subject: [PATCH] lots of work --- Assignment6.Rmd | 12 ++++++++---- tree1.ps | Bin 0 -> 5823 bytes tree2.ps | Bin 0 -> 4675 bytes tree3.ps | Bin 0 -> 3091 bytes 4 files changed, 8 insertions(+), 4 deletions(-) create mode 100644 tree1.ps create mode 100644 tree2.ps create mode 100644 tree3.ps diff --git a/Assignment6.Rmd b/Assignment6.Rmd index 8e65135..89106fc 100644 --- a/Assignment6.Rmd +++ b/Assignment6.Rmd @@ -25,7 +25,7 @@ library(rpart) #Upload the data sets MOOC1.csv and MOOC2.csv M1 <- read.csv("MOOC1.csv", header = TRUE) -M2 <- +M2 <- read.csv("MOOC2.csv", header = TRUE) ``` @@ -33,11 +33,11 @@ M2 <- ```{r} #Using the rpart package generate a classification tree predicting certified from the other variables in the M1 data frame. Which variables should you use? -c.tree1 <- +c.tree1 <- rpart(certified ~ grade + assignment, method="class", data=M1) #Check the results from the classifcation tree using the printcp() command - +printcp(c.tree1) #Plot your tree @@ -52,7 +52,8 @@ post(c.tree1, file = "tree1.ps", title = "MOOC") #This creates a pdf image of th #If we are worried about overfitting we can remove nodes form our tree using the prune() command, setting cp to the CP value from the table that corresponds to the number of nodes we want the tree to terminate at. Let's set it to two nodes. ```{r} -c.tree2 <- prune(c.tree1, cp = )#Set cp to the level at which you want the tree to end +printcp(c.tree1) +c.tree2 <- prune(c.tree1, cp = 0.058182 )#Set cp to the level at which you want the tree to end #Visualize this tree and compare it to the one you generated earlier @@ -77,6 +78,9 @@ table(M2$certified, M2$predict2) Choose a data file from the (University of Michigan Open Data Set)[https://github.com/bkoester/PLA/tree/master/data]. Choose an outcome variable that you would like to predict. Build two models that predict that outcome from the other variables. The first model should use raw variables, the second should feature select or feature extract variables from the data. Which model is better according to the cross validation metrics? ```{r} +M3 <- read.csv("student.course.csv", header = TRUE) +sample(nrow(M3), 10000) +c.tree3 <- rpart(ANONID ~ ANON_INSTR_ID + TERM, method="class", data=M3) ``` diff --git a/tree1.ps b/tree1.ps new file mode 100644 index 0000000000000000000000000000000000000000..e71d1b571d4a6f2dfe65bb8b2415f47d22392fdd GIT binary patch literal 5823 zcmd5=ZEu{$7XHq!IQ?L0qiScF0T!^*NVSvnMoQ`^snicqKCm!e)5`)E*u2Qs|Gm!{ z7#7xRH?34Dtz$Sd=ggevyyLSU-o9V{oK+jW^n~l2ojtG8{Z5zNuUcn1d#BrK-=w-d zr|YWh=s&vnq`N##!1?3R((-{fgaSNpEsci6gYbkbD~Z@#atyU$6(I=oG`3}=ya zy3F{5t0o8Dq|2-FoL(no)}~3#oEO!;%<^)3QGGcl8SzgLh7>6un=i`jvf8nwT4vST zynNeKMYVNSo0{mBwk@^qez{+)Ks`pGt(Vq`r0|84Ie?GZbdzu zgH3Zz@=1ehlb4xcU2Pk)-sl$S=3Cla-QHB6YrrIM;%6$mBbMD&@M1OFD0sao^7442 zG)I;iCw4b8k<{#@Mb+wid)MZk>%1stB9&QgyQcc@T=CRw*jrrk)-EMYIuizL=;)Jz z^>FS0LQ-1QU&*7T?AP^|^akcO4+{teAE1G2w=a(OPlKo>UwA^>TJgrVWzTH3WMFQs zKP-r;*=z3+fm0W(XZ*VQhAYBHMNVAO8G8n_oEx-<)d#2p7XD8XqECNeTOc7m=NUqw zu4=o@7A^G_R&55aa0nvyPK0Qeu%7;7w~~>b+OONNkQ#k_bkUSGHIY1C-J`KS@dh0B zImVEIXW>A(A(n=q>4V7{VOZ=RR^|{vX_42k#{GP0wi^y7-QgugshDRblAU+cq|m0+ zg3mlB*v<$g3vAOOVQS1ReW2Cls}~nZtFxakF0E4FefpGE&vja5`t_S%C+pZENZnGl zugMjz7psU0eavCl_}8seB37P~l;xl99%jQ)K|o2Cku-1MCMA4Wu%-vZ@@rkRCvLXL zp&*nzzVhRIVf7|KY<>Yq`rry*DnAH;OG&j3Jq9Ra&-3RpBRIUc!VAJ6T;nB_feaL0 zq>N>(9+Q!g>wA2U8!8zFc!>kobLFvezu)AYep}^eq0kOI0h@>aMX@_$e)jBe-$xD> z6De(-r1OH=j?r{4l+Mmxm1(ihwC&#an)hn#WSztfd@RxYrS-`=&wX zyzVoT;a%HOQF`Z`2Q0UsFBn; zD6#<;H}0Wkns7dRWFg&UNqgf+yN5~qK>UIF=}6RC!?;65#ZZTbQ-aC!gtsOYd92#b zkwGM62vAaZiV7!;g&X6B!tN}`t%~J69}FnUt`spQL`V9b2;*MfV|lDIEXemey*zJK z4w{Vc1MdQNqSYuC%=A+VSpf6S zwsCwY74j_X313amefHDr+_f8s*oU%8NE~zO+-E;c&Rt<*@p!zd#ddQSL9;gA+-VB{U^>Utox}bV}4H8fm3P6JDQ5yWPLT><=27A^v zkl;ahFq<(bsNSN+)}VT08#ge;Ru~Dk>Bz_EW=G6UpItoaY%CTjQAjJecc~>2!bIxj3P$G!3{Q^desks zW+RZnPD2y+8Dn-D%r?r|pf>#3()ix3JuVieJObcYZ2%GV4c;+94tdFh3AgFNFxcTn zcKiJ-VI5CriHUf?MNyk)NuP7ZBZpY+v&7`-)TGD-R5=^`#v{lJbLr@wfdZfP9P$x0 z!8#SxkR`+Mr?RA1Y8F6%g=}FP3{Z};1lffwF}Kfxl_mZ*qq7|#$>aE!A?VS8ne@2wo%Rowc*b>f5;NK4)MuIp6jyNcNh$oo-qkRd>y0Z znSP4?HY^?_J+yJe3ckODjQ^Hoi0;fS_U}pJvsQ$dazdZ$*5d1-FDp25prEbj z1N-czkt!u|46`${GvDm&%#eehF0baVl47Ojj@QOWwd5Ev#8N| z!aH14Dey*3TI5IcHp-Jaj!Kq1E;f0R=Ii6)?ucZ-Kc4SXpjzsi54Mv&+J^;c-(%d7Z&5g*H_MENT|Ir$k>{2ejfXNR+iGyM4ek z`$V5Lq*iI37}3SLGV7JDfo{su#&msCd?^8wAc>!`?k%zIZGlrPCX9^Nt1QhQGIFzJ zuCZftGf{~RC(epmKjK{*JJ)HJO;ifATsKwm=hX4oFnTLCIZK7*OH#3&Whn~BTL+&Id#DYcL@ z&k?o*Ldk;IxJZ~9v!#!;I5|5#j%uB}IzH*0g6xYIw0N!KBGGTp-;LJ6B4}+X*_31p z+X+=bnSLl?#Q4`%DiJD2NlMbs_fLyqE6<}SNl2PENRtvSB3RNBYU#Dk>OGcwIW_C9g4m`th5 zD4rI~ddQ|nsdR8~mdDv9(S7%R)Vvo%A4l!V6V5Y>^B~jt8aF#h8p zYveU;(XZ}li|fxN;GWv!yT>$8MOg-o#c7UwL!F?rtBbd2thpRkxYrTIo2o+RWILdc z)Yjq+e30!ugACe`Nq(*|{|cuaJa(82{X+p$-wCWAjYinIr5_5O^PTX<)87cdtY9uulimb=Q zjeDq>CajO2SV=cYRNq*#=V21x5r3e5S`xL^2;QQiVyMHz$|2-9!da5Er3f+MS<2y> zj4@KN$C)K1rf~EDymqYlz$+{Te6CF@@P+T<)1a=?b3qTUy;I@YVxFIQD33Q5) z+{<4katjQFTMjS&nnK+U`S2652t}aqaD}&oqjU5q9~}}z#zX)&1iB9hDICSU({G6Y zldo_>Ch%kqcWfs70EA?i_=r;qZ6!2fI4vfyrQwA5gb_>0gez1C0+EIko`R?qPNZ)o%~OfZ1DyPoP>o zN5EZBt-l5ds2&PHf@)D3{D?vu023NeZET>ylV%q-6HriXL`|$gwZS&Wz!XPeAULLj z9AlkqG1+}$c<{-EjyaRw-2n*)cmmR#3B=41o9qB#LNi2-)57H&#Q|kU&6)JEo*cvY zfW{|h)I06|tlMpONzi47am2XT9Ydc_t?Ro)>obtSj#Jabrwjf#nfol~fcELnk;VsQ z>F{kPx%4q@5(Y3KL);Rimt#VLY{LaYo#D*IXJWUw)AU{ZKL&F9ziGPCKy-bV<2w6# z$WUDyL} z85*3jQ+wLHZwJD2sNY0RjXzh%O{rEx8zSlME!Ccj!*pnNesOU!xTkpt`%pz`rYpR4 N|AQj&dV2B3`Ujnq4Nw38 literal 0 HcmV?d00001 diff --git a/tree3.ps b/tree3.ps new file mode 100644 index 0000000000000000000000000000000000000000..9c86d05525bdd37e8d72d05c677ac118a33cb287 GIT binary patch literal 3091 zcmd5;+iu%95PkPo%sv?CVqr_vC9;j8K%GlBKvD-ufqf|YK$EmWEG=p&DM?}Y-*-q! zj$}J&QJ_E!*`nvdnKL{ba`?y1-RL9NOEC(^{$Myf)2v#Hto$ql7yMQfx-v`@Gg#@Y zgujJ)5T#@kE&tjRjpkbMWAepP$^R;GOl4gT)OX+4ORYM&TnjGg3}^)LG=@n;z=wB# z;)6C{WU0gqZsC)m`MqQXEUGfEN>rU1K}&6{@=mYHM`~;iH#D_y-qBKI+|IBt67kYf z>TCvAG~)%MxwV|@D&sOs=lW>|WMZE2%;NbASz` z1r)cR<~HTA?_N;eOE5NNfO8F!{$ zYMk7N0@3wV!i6sG^<$1O0WIXkf(9mjKseS!%5IL~{k7Sz%R*@EVWtJ&8m}$EnEr@Q}^Y9giV*yTj_Co(e zh~!n5BSA`6&lpDig4VEVf)3Eceh47@#FMQBZiq+8kqWuaTeYodCQ_`bX;#Hj5V?1R zq9wI?Mz2K$=iRMexwKBfZjJW>bxoOL@-B3Zrd^Y;!O^~V9CGklIG9|+rG_*$nc5;W z!ur+vJTr(XnPW8$_lrrFmQJF?0mD|&-oy73V>a*= zywl6`IV}YLI6rNZLfiN6!8;R7b8&V3xg$pvpw|X?m4iR_!)Y)9CH5_xnf=+2U_1@N zfB=^d+n3F7syGJ9IS@BOYY4^>RxpPb+~i8A;z;BcIVOln?uY!=7kJkcx%q@3;j2H6 zND##d;tEJ`l7to@nTBE1_t}BNfjTH+Ck*`ZBr%VWQjsoyjH@ZmY$H%k`Blp?3B-!O|En+~Wn9A0Kj zRa~^E_rc-q?ap!RT^YAL8(1DFk)^n^xnyO19$_wwty|v z%eTebfT2pEhj*SK->^@><=x^657vzAB=)QWV3jd=a@sif4@o`nE-(jD?=!T)W5|); z_Lv{SsV^SSnB4z21uXbQVC~hYgRK$0DR|*8!t37tIuJYJHwDu+F}zy*Bt4s3tXIE( k2ap$bQT#%hcw=pDsKRclFNR7b433%`vAzADFD?fE1AVK(dH?_b literal 0 HcmV?d00001