From 83df68f513520de5e96e2ffad9dc00f5ba12e16a Mon Sep 17 00:00:00 2001 From: minhsphuc12 Date: Mon, 20 Jun 2016 12:24:34 +0700 Subject: [PATCH] Add files via upload --- Explanation.py | 15 +++++++ Graph.pdf | Bin 0 -> 25230 bytes Week1Assignment.py | 95 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 110 insertions(+) create mode 100644 Explanation.py create mode 100644 Graph.pdf create mode 100644 Week1Assignment.py diff --git a/Explanation.py b/Explanation.py new file mode 100644 index 00000000..6da2a6b5 --- /dev/null +++ b/Explanation.py @@ -0,0 +1,15 @@ +# -*- coding: utf-8 -*- +""" +This graph is limited to 3 levels. +With 2 chosen variables CLUSTER2, CLUSTER1, and target as SCH_YR this graph can be interpret as: +Overall in test set, there are 2544 positive, 1358 negative. +For CLUSTER1 less than 294, there are 2324 positive, 1350 negative. +For CLUSTER1 less than 103.5, there are 2 positive, 24 negative. +For CLUSTER1 more than 103.5 and less than 294, there are 2322 positive, 1326 negative. +... +in third level, I end up with 8 node, where there is some node with high probability of positive, and with big enough size (>30) such as: +leaf 3: CLUSTER1 less than 107 and larger than 103.5 +leaf 5: CLUSTER2 less than 449, CLUSTER1 less than 420.5 +leaf 7: CLUSTER2 larger than 449, CLUSTER1 less than 422 + +""" diff --git a/Graph.pdf b/Graph.pdf new file mode 100644 index 0000000000000000000000000000000000000000..540fce319a49c0a4a96930e28b605b131e791408 GIT binary patch literal 25230 zcmZs>V~{98)3$lWo;hRNwr$(CZQHhO+qP}nwzcPZ@x`|r+fm)sb!T>ER!0B0D!Pf~ zghZ(6X_z31o3Cp=AsO-L@N5k%Ai22kXr+v8Or6Z|nEpu$ka&1_v?AtKPR0)ZdMkY= zVJUqZat?OVu+trs)G#|2#MtU;yZ&JtIFXXj~T) z7b~>%KQ6HEpYE|qWX($#=k{9{c>OdgxY7zr_sYwaqSv(BuHUrTFx)>UdmgAxzn7~& zw%@!Q=kKShxSzH?XFsF9u+cm3v6K0~p0pa5@8!qqveny~==_ygfidO3leu(pc6jH% z%jZ9uSiUzszW~%uzZ>B)rUy36%iBIcfu{b5XVaY##5p+$hLQ~nfoew5J zU}->FV)%)p*(H9TcDx^5=D@x-c)OiHSaW10mxX@-3 z!xHUY6jMWF+}V84V`dE_QxD-}cU?5nj|fd%{ubLawflNhFS=oScyWVH9&S2a&*UJF znm2K}+}G7`{~VLSi_Sl56iprECAX%Q;-9$HrIVs1$-=ub6;tMzye}YJ1QEf)%nhE~ z^VF*u8t2&qPV*clEwbVJEf(473j`W(dX0?25k@bzndIslb7qq?W>qiPCD9tjvfQ2? zzJG=0U{kRd1kv7&mO_-%aQe-ZI3Wtn$5a=#GYS=Z^00b)7LN)jfrhm-kHLkMK}%BA z!eGJqnQ3M}W#UU@j#7tt5JTM0t0gB07g5JAoa}@TW{0JrBNuio>X`4qiJu#JMCSZ? zn#7u2tdpla^*gbePXoX@2Yv5HO46hTzoBt6b`;1gYj7sss{PDv0qlUnl4TRjPM&4? zki;R>1pw&?=~71B*BI(Rku(JEGI>_H=6O)b{VMHt*2Z(`oIV7pra_YZnI!7u6psX`{!qvZ}-I z*4BgSHSe~H30wk1Fa%aZ=5M}&M{|7~aY(>Rt8Fip^)sWhmh)vCb`{NS4dTz~ncLL_ zq2>14c{H3HO3io#BHP#x_!+ioGDW)*5s~0onHX^g0yIO?mpNV#z~Yyz%oDWJ2Q*mH zh|Wj%9;G7FAHNH+`+$d7?XWY@EcG|p8@Q~QKtTT?&{oyIBI=65I&5E5XkXONhFLkiaJ3T-}H9Hmyj` zFZ!1^)=m!Vy=hu8=Gz3aS_^Yc7F1dNXhZ5_kiqOHHDuo8L@8hmhn!%>Jj1sN!msj<953a>g>YBju&ey7rRv7b=<0EJT)%BH^!^*$rQt2 zM{yAUOL<@fIxNU0@L$B^{%}I6xK%r3Z5)TS=ZmiH&<~e7_{doGR%^6{1B6 z4e+dxd>m9L!#WuPn+hmZ`ThgMqlg8_tiXMyM8~l9nmJ+n04#bu5X9o0FbqQ_o^wLU zd4fKAr{1p64$IM+FfNh$Q2J(+VRTQdeHBDR#JUj{)Py-9ii&D}e@2mBc@763jViqB zyAHnXu%40#2^vcQ@F=}wzY$}su#vEx0n`Kz@gG{wY!1Fxkxw@48$;XyFWBq@TRTDx z(K03t)fM!$eaGx&iMA`X?>1u`)5^0%i`-WQO@&MI6MHqFYbtC0=|+{zNEtC%hf3Ra zH_}}P`6N7_8EB;Jg%wmFd#IpIW&`Sd#j9Wfa!f&>`#OERE}}}T9v^HZR<U49)@>2A|GMoO1P>|d>Fr+oeE>O z+gIv?6OVPEZM~jgw9`d*cRP%<;&IU;e|r@7MaGuoF1&n$`ehS-t9$=?7AP?&D)x~B zsxu}eWz`5qmx=k52}(;2t+~C}^_dFB9eSU+GQ(|g-B(U$dM^P5Q!4_xE%@Nz^7(~& zR`ZyL1w}C{(g==uWL9?A%1_Nf>aPM;J?$a)uNC@l=o0bhnlOX1?m(3p`M@u9G6B9z z2x+P#9hby(UFyQ-AT*;(6XF>XXt{dmnIj&pUY8A5P6g98O|o~c3E%!lBy3G24Ut)3N) zw2{CsYCe)Wp6xxG+#wSbg}a;~GPqMdIlCmByM<(`V>?tQZZlIbcgu?2#c7f$yYqF@ z)H4#XDYb}P79YuGx-GoUPu-c0&NKo0zssi}pUIL?4sQIIb(?kq!QLgSq(W>K-iN0k zu?1H{e=lL#UVl?<7R12WVI<=3g;&N1Dv%N4G`dq(lS2J4}tSl6wS$DkL^pKn@rs=Ghk zT8U9oC-)^@rwnL?Yo_z3NU`^hzk5i{GXL67(3cJ zI~W=};{B(B3jfzaSpSXxKPb)ie-iosL+St2_`jK(9*>cZk&W*E1=m;I?rxgH-E>@x zrprD=>Ydcs>Y2vtDXyY1;W3A7k=Jp2ES&vA>SGpR)+=>PCNOMCZAlGC5?jIDuLW$G z2pb0vAR3V5=1@&dsNmKT`NP&5ti{E8@88p6u=_i&pE<9)x9%P>r&BzpDZ4z5MnUib z9!ybeMK*0-+kbT4Svdu;hvPgpLo90)Bv}%41-zi~k6WaHGHH9eMq8otnf1$-8rywO zOTc)zKQPHYwS!P#tlF)%M|ih%Nb#N4>57tiGQZE7}$8WN?|b=~$`BKsvB`h~D});nwP2Wo!x0m+}X38K;!1{UlMG63MW zC0@#H=brD*-8&tFiwh%q_+mqNqk8Y>hdn38U<-;DMF~E|&&7isjfb@zO(k#@cyBYV zI2Jgznmi~+NeZcZKl^0!kUA#e zSp`^VUc7Nrkq;2wH0)@*8$}yXep=5D)nm6&n?qDHX16)5>%vev5pb#c6R+coY z*0OZ*5ZJ^7U)Bw*Y1Gl>h->S4xGaVX#u<&Jlm*G9@TPcjJ60S&6_^#yiNwitX8Sfg z7T%4#h*dcp+X_ni4{cxahJp>MFcm5Qn6?50e;;F$m&OYL*fa1 zW|RCWRzE49T#BYBT`5?oS5U|x{+-pYe*W2efp;aix4&KADc|W|>~@l}JI!?xT1(!r zu93K6*>%G5VufmpX9!OY|NSflsmaN(SlZlN;f7^g+zj;G9|*MG4ozg!$;cXfe&Ne0 z*~HjNTZ_N4JjT!I6NE@I>nzf2w2H9K7M|FaQRFB}Qy}8}_BUZI5wH=gfYdU}XGE@c zS$GN`oKZ4QXB-A*4#e=#cL>*nT}RtpYL+0k5Cni57&Ir{|Q+CrFhCx5{@11sadanc@8 zp2VT6_KQd3%%%~o%dao5ug~W}iMCfm!WKSV$e@c6F@)grnrkLq)e2Zm))Cx@Eg<67xx zP92Jcg&bQl=3WT9Pa5X&7+Pric0gLc8~HgQuvjEbq$Mn{Zx2S^<3M8|b!2jRN@I7R zAl*G`i!RHp_a7xZpQIQ1q{{MB_k{Msh0lqjO~#YJcE)KEf!OHp#Z&1^n^uehN{}GB zv(U{rYNbS)gUXX3uoFNM;jZFq1+n4i-=ndj8u_;$W=Uu`yWuSSC9%ba&4Og|$x$hW zV57eJ>oU*&7kq>ZfyqA#(ye@s^v??nlu#f#0XRtn_~;lz9O6#}d%Q3gc|!AnPW;th z*KnaOp^F}*qmah#?m+6qT=@ei0K9v$bxyYPXDMm-?LG3u#7<+phcD@gdq)6?wooz` z2&D|Mh42AbXkYlApT_5{!rUGSojzXO5@eusUh`+D-dV|>RUSA6x3F5KA0lNvk z7E5UrN44GW*CQVveq)QhgqR#dC(x_BR z(UJQ*R|8+&bDsas($~PQ{7iz;(SJ0)O=duZ_i7vHTJGxa8lPUPQ<=N?(Hsd^l)zSM z<#LoDEI(rX0I!S(F;|;Wuk*XacOSVwV7RA#1&<9OvW48fXC-9Yj4v`om?uL1ZAuZ3 zL)TbP40NYrYfuf%UF|L*EOV_Rwa<`%^82iM0^y$m0kFWh@Yf4hD1#Tn$R?I2 zP^d#uBYmCPn3dUgR`Y&}i2f{qpS6VJeQ|LfJxYvBk9*}-`?y!tr zO?TO-Rel|7-FW73x6PVL2~OigbA-y`9Uv5E3t`1$U4b1*k-&>PWRXsdx(bUE1AZr0 zq=#aQyyZD_z)$={%L(jSa{yjP%CtDNQuj(X5wxe~!8&bn)AgeAp_m!Hr?1M#Lt1>A zy$s(`6j7fBJ5`%DZ{bobEk^>|0yU|0br56cgplkrYUe5iMp3$fnp81V3P%zZocAMd z!%0>n3yjAv!uaYluDT;z7G5D_8r0kCcsI$*2N&~48khKGTcQ;=32I!Zg?%ART!)h~ z?b@Zv(j<>CtO*$r(L}V%Fcb97xo3+ABMPAdXO!=7!`qPiS@fMO&mHcqx4f;)v~fER zx4iW}Ew=sfTUtN4(b{qpmA%}kphXrPTW0&ZGPcD<-+f#fW6b?wX?;AgK02dDt?|6= zs2BCMzn+Nr>L~YX71iH<`m>0o*~(A~p()oX-e{Krl8RX`2v`!yo{eX)V@8L+V|E~1 z2ys`b)+p`}Pc+UjDp?>e0)WWE9f}KZJ>~amP680gp^jwi&x-MWdPmTQg>Jh5&5<2E z_}OO4K45&$%fu?fDAc&eGnsar6xs#rYS|_=s?7;eaj8N{+1gvUDxuo2G zJ-iCe8R?n`e=Bz1+D__hn6HQr1*sot(7cWRC_l+jU!D_mySA1^^|87ke<|b4>6N-w3kuu`vWOTpF+>J7zQAR5yFhlioR3|VJ zz$S({?^IC|MJ{xogfpl+h}+=IwcUx9QkhzVu01o(bt1o2IK~=Y4SnmEOaiPXBt!@j z-p>>iIu_>v)f2o`5WxqZ?iJus-eI^lb6aQq1P2a845-Y&XCdF{a3{w*3Lu0M5DZwSoAomv%>Q7O8J{lgDm|NPWyS|Mi+zPkXXT>H>hr{VJXNACy zT7%>L@+a=LNAjFi89RmTjBq zyj2tUvz?;*kC`KlH{ORFVJJm1^HIiwWeU6!jY>G`t^B*wVgfT~MokQC)%xTuvW@fh z$<8Jn!|BRPceX3ld&Z^ZO=ybId*J~8D*x-`Gp(yk6?^;1QU;@?m(H?$DH9Si=nA;( z7J;(|T3JuoVNw6G!&8PEleg;Tp=gOt0gdijWGQ-oYO`@r%F#Q?c7f zE=+fx0pW(XdBN>)eKlFKigYve&7Qr+{?kCMI=RqyIbv{Q=2tVYo4l_U!N8&z$js=f zGc}E%$Og5QD^8;>$&f$b3zSEo_xUVaDaRH}g{6YIPkY5V`g`NMq`Y7o`G+WlC}Rte z38w^J^1{K!_i$|%O3`0;Qu)JL%_wpe_c0gU%bykP7Olegloint1T|$gV#@Y|llKlB zEQ!HYetojA6v9+@GyEDx?8=tUBv3&F{tQ|oVAoFWm#-=N#Ku6zh{mLoZw!po5bCCI z8hP;GU+RtIcPR~(%goD`P0WULrvn%o&1-s9x`sQRzg}Fr`N=1%WinRwuxz@H4l`Fz zyG)eTr%W2vPvVknjYppu-}y{3t4fZN>~|| znyR(zA+wy#JjeoH-l+u71*pqTR zbknb}r6`l;i9N`B3y<^dY&Bo|R|9TA#cgE`&aRATi58Q_I^o68GwN;SQrHNKr|d>A zIaQfkLop*HwQQ(_2%DLmnV*@n)-bdYsw0v_RYg)z4-eLV43^gG)Px=FHH1;Y&kdTI z9PH^k*y^>0AGaPO?<3YK47wbY#T(%wK1~X1GGLKiU6`0Giljj>*g|c|M^H&rmke@Ff_Ylp*`f0u3aU0r;+3i_HYN zd%hjyRX)@rpMc5$`)ZQ!5ztGGvy$xjMo`c<+0>UXI4R<07gLgVxR-A4ox-T8h$K*z z)yVi~5m8yVb&iKNBt4-}3t8v6!tLoP1cmA7ktPs-)pj!aZBhi6r71xArY-gzw{kI9 z((VtnpbuasRddlgn{R`I(h)&s653o=?nh6k%fNvvBf)$;_-|vZW4%5GH#uQeK+Uba z34*b)F;ACiuQhgcQa?=_I@}Lm;dm5Pf1h9Pg70fzw%oN4g|a6rQHO$o216qY$_Xkd z?z8e3VYIl~_IH$i z%z7G(NmenjO#qP|VN^&!HzE#$D*4LE4cBtGsYC`9HXR%$Jq*Mw5u%NTEC16JZ8@NC z6wDk{nqA;=>&9+OVjr3VGzLVLZ+Dj`o+qC5bIyjuE5np2>T>{SfBsJGO-fB}P;yYH zFqV#(sk!-iDt9^Sm9p~Dhit&Bdg8F!b@clsMnQ4Q_7WV#Fh^w>H_P-1?YfXI2}z(> zWZY&kHXtV1fTWVeqrY>!qct@3KcF--Bu&zz?60?#=g)ZSCRPEWV~A zvsu!+e2I|CQeCNf3!C8jIj@B>6AA^ys4?gxgDk!rO0N0;{4A_hELx&3i+Nyzp$Ci8bVES7qU=+O1qIlde+w&;qf)Fa*~2OmN?N4D62fU zVw_S8<>-2035Ee9xTE>PI2-d}Ff-K@hg_oVE95@oLfB9Nlt}ekhmc}9 zvPBBRL&4?CKYG2wxFusLB`zOA9MbdDwA`Fked%Zw^orzon8MAEh~^47-xqeLthd)! zs@W!j(_33sohqfLny9*-(fwMB>6zM0y(0*BD5F$uWc(z$XIkqHhBl`ae*ZQ`D9u#; zt2<0?k~KxE>IYDvs8&OhxSD6hVdGAX#(9j@z}qb-w*_tPNav-p(U^)H9M;q$N|iO* zyt{Mi6TKya_it5gD!Zz`8sFs~zGuWrv6{}E0;{Ur*gP0KD$fqfo%ybWz2zT<=b`Y2 z1nfD(uDE2BigGDgJa!EjKo3i}2f)MO{2&{yWkQlfmy!)_*M0^OsobHhc?3m-y^GM2 z%lgSt44eunm7H<(28JlH0v^Y9#OT#nl|;#LK4#TTkrygQuX&owhxH%f9tyDyZZq)H zKV8{t+|Ign`bW}ec=OrCv5OPxYR}?%Ip^a#B?|S!HdPWIg&t6}DWHP=c610w!uSR; zBF`5dSx1zshP@yH{DM~8E0+~R7td^Z6!|R=jsr^U$oYSWKs`g}@b*RluvJmO@Yt5% z5c`!)jX(Q+(gG5yo?h>LhM(GFhMO!r4f~VukBKw&_~!xL*kl93Lj+(P!5ihpH8Wm! zU#^uMW4D>O>}+pjU9H7Hxpgj`YsB75zyx;q4t}7Pi9b65tp7p9K zp_Y2xDmW*UJ8DM2Wh2cAkOQ}2z0ck z%pKebOTyX_ccX2Yw{3hN(@hIaw!%5?3mTf;q^}Y>tj#cYBv?dShg+7m{cNMO73~eN zm(N3r_1{r0sav{*J+t8+UMFAGZ(F&qytqDa>wn88A3~4eV0@W;%zo%z^sTiR&JCu? zf=!npAB~KjM%-THw5(c%ktoVdS(BSC>OjuxMzolNkh{bcAUT>NvW+L+kIoz4xzh$}NPvnqgcfuyoF5tp5s(Bf z<@qSoV<{shRtqUG`J~C=^o~j~X&_9GJ(8MKPOkMq@C*#z@Q?@R<8H%N!wkB#l^Pdr z;a(yGx)~_D!LB?(T^>ArKD8UwS^4Tz$5F zrAU^aFTZ)OblVYEwMw-c%@^$ir4Jj5b$hygQ_cV%rmPJqZ9RRw$}Z=xU3J>b?QSVK zSGC(celx#WsnQ+_=9=C2fe)9Uo4;Xy$x~0>??rxrrEWKz5wbQ{sKUgfQ^Yk8?2?@%OyXolr1q7NH*564RC!j2DTHIAuVQQZ%DBg38J zEbvzOFh4EV^{3D!D?2Gsm1}CcYJYV^a8AjF`~L7K=^zSDkW3Z@`uS(yh`H4 za!yXKMr4U|)E_Bhj<8gy{RVGHw-HR!@lj_3rN~2>jvt6jBR+am@O39qz6{&xTH&!^ z9WJRkM-9d3Be$h?^fJa~1PVryhR!g&@CeI-N`cwi%2GglT)i=c;0>=Xnx>OyGW;w~ z81+Y7OEmjWKqZK*8IduhLq7!tq}wRB$3MWAeF&-nRLzE}*VTQ>6<^|n#r z$RSsffmHPyP>mcL6j9_YNg4~#i$IT}2Q)fDa*94aL-Xn%h9YW6>y&g-_iH17_gpg zHJ)rWuJ5O`x`WiL5NMv~Fy-S9GDtxxP21xp+2})`HVJr5%Y$ZXO=f@Eh2!?x4`@H< z@5YldClRRV(lJ$zKAKO3Qa}F={60>YhV#Go$;6laJOjvg#AIEWWAE&}!~y_@MQ>PP zhccP4vkJ*pu#b!aE&TWMmTxhJn&&O$Zm);C@7z8ENZ@d6jje7o&8v*@@gOS`O-&;O z3*oEP&8Y77iadKIl}@wXV5^PCSncZpi0iJSe8u;|{K-;9KbSU3W9Io?WC>||r{BwR z0aP3JsXQ-pwY)RIv{~LDsj{$<#4UkH1_u8~#}_$*ocKjnl+;Way>k*Y2N`;mq4A{x z!ej9SMF&C!Y=zP?J}+)+-h$3)%})7%_`!V*-xMW5)qazND4vretSE^OH7l!wyw>nG^iY5-kIj z#hI0brH)fS#h}UHb;ssYD>~I=b}NTCUN?*M#}S9pt^#sxl`rfkUoex5EEeb(h=93~ zhJ$0EftCdk2G>Va)9Z?pqeAreMpoM5SYeD z!GLaal|w3m3!`o+z7QqJ@HIWL@-YnqS`n5`Vm*qH;{0`i3bg5jOXV#&+d5>*;WaJD zSd;qVGy-#|MDxdx0U>vHc19S$d-S0|!6d2ZQtPWCg#dI&xRpM!%Cmj4VE54Ja*}1K zS#Iw?6+sfSXXt*tTJ*s#wfM!M#a0xBJvd(6Zya~dzkyZE{{Hj-YOq^ za=r6v*Q$6DEvle<)}YAUL0wb(J>rlhxWJl|K=g%iq+ zSH2&6B0M#@kiE-;Ez7rzgvF{rH|ir&XItZ+=rG0M3UO&D8}-#xos?(MxbW^oMaaz} zO!9{cIr=4tEiz7KlQMV}BTCHpH7tBC15{LMlGQ~u(zT14E5mxKElYG(qwtF?OZ;gp z;P2-ev^_SYR0EV{>n_4cL`Ka75(O%mh64__q{taF1`i1TTpd(x~+a6dET`-X$P& zs$6OGSF4fJl-Y|?K=VBTo8+fUktCkCdU_&~CY3{YOs|=hwIBL|mcs;LSf)*r^nazM zWj{LFH-Kb>uD~SVQR~(#IIL3DF+@fxAD5Ssq!p9&FCa))Q>{!GRBO}4@G@i;SGWvv zeJ9G}qU054l=+98urNEj$_FA#UuDqm^6lkPwN_S^cIq|M=Xg@gIiBc&hef~t+ZVWU zSX9`LEVXxix-4NK-74A1Pbc3j$XUWPU!Z=4-|5% zB`>$_W)tUPQ&~rRTH@uQOLQLmfM6G|wCyGzPk{-Bx8aIao$Hk`-{ispSj(6RTiIVa z{6@GtbeY$uM5K<3MNp}=N6<(W4V1Bp5zvZ3ovbQ#YJcFQPFAW7_FEvsm7!Z8^}%Em zlj|gd&sNwB07<8lEC?-TMXEN3bantnrqYlMMv9^$HmRvgp)3w&3eS8Ddv9~AH+=Bj z-D}@a?YMDrZw_Dmt8|`23Pym;X?IF`px={3WACujZL{%76%dCh0R>ukgv6joBsoGv zNHpF$~22OcI&cFkUuUyc=lCEL0k(dgxn%U@<(*$Dq58h0N%e#f>mI-QSN?RwZo>Iqo zy*cv*R-HJ@`dQeHr!Lx-27OOd{FsyX_Kcb&esC2kb1OBK^Zbw!r|Q&n@5hvqSQd?f zW6V{Z)%Es*_mM4TN@Y_#EEjV8O9d_lxngE2CL)LIR26;$Hmh#51&gMHh>|Qr=R#Vn zmuVe;TJJo9F{z<2Dc^+4y%>P+$b2Mq7aWkNSrY}t>YgkQk9Y;p?#&y13e;9cNE6lc zIbiUo+CWAm|9IMD1x`dlY%TSHkxb!R`kU4<5a5A7e{_)PSzp2wqST$?8!rf;llHHH zi(wL{{3cPj(^_uT0Lc8@o2peKwc5 z$dS!Uf2!Wm*yZw-(#>Mle>zMPv_B(Y7-Gbwi7O5bQflAfS9Dn zBa@gXv{im$Ah|jTxH}sSq=#89TOufrvsbc_TgPL?aVK)mq?Q{yFFh_kFWs$KWG1xK zw@ko>p10&Jz@DOm<*3?-PDCHWsO3lQl_dyExbYFL6GyFUsv*uqpNnL9t9(^v&wq;$ zIFaqWDms|h{t^xHM+HdGA!dQ+KtuNToSFmMS)c<3Z-(=qMwS|4FY)h=*WB^}hVIGfJC{IK=( ze%RNBl{CH?l)U_k2Y11+U~#zgtk^!$ZZCBW%IKusa(X%qMD4Kd`=tE?TnGM&2ljLG z&golo9{b4YD=Y#pnFhdV(uKgN6VCtl2Xk|gQQ=1_F^VzMQ=|h#j2{>97OTKHYTy;% z&Daj1K@q7A)tqCa4G6)HoXEm|3i;*1BrW@4;WVyh_{!?HrYsDANl8#_0D6Qz(0+qC z-kD-HIm(?r0OVoQUZimHJs3Nf>8{`lb}L?fHRv)b(sACq`RU8!!g9KN{dtYqW@D{w zDVTXxK{eO1kNE;4Fd%{cCY3|Nev5WQK$u>!a$A=Pu7fDtBWRGsFh9MkVverUXDKWd z!#>x(kIe#$F^3*<#QxMB)8gIR&uQ{h)2!R=uVS7drx_TwSey~4ih}-WlzFypUM(Z1 zF{|4J>e0eEMJ@Z@ONx5Ea@*u&umGs;5Cy(?{)zoqNwfLh zUux2OBq}p-Kwfr%WAdI6y}S`SiutF8Men`W6IN&c6JlAZxx*TFa5DS3!6x*fc^b2@ zNmqhjk@OxRsKsDaBIOA&tb`9D58#N@o8#W$*hehyWMIKUBX)`X{4%n=Q2PbEC=|Tl z7!e^0Z)N{YCRY#>UT7?&|K!-Lg+-9oMNGs~swxt8T{DB_cRWz zZJTTbTRIQc4^f|S-_8#y$Ey?S54~)i)v_0fV0uoj=RRcLYYrj_?o{bEgjqLhPvk@a zJ&W^YnX)KnDZnX-#~sf`VOz$%laF!VoE^7kjSu+RBEN(WU=9;*D!N3uNpuM^5=LyG3%EFtW)z!7WJH zhmu}tHDON`S5%M1R5D$I?UU`R+;n8T|71X@RAxe$WTvpAj?S-Z7z|bXcXKZLVcRT=?Eni z2dxA$F5bnxaAkv5(N+0a?DwfO+G}*s>)O?O^BOG4Q`;EsVjd?36vc;mX0Zs01zu;7 zE`PJ^vOm08ZdC=v;&s2P=ly=ZTh-0jh|WbqnhhB-ZcSLP)p1@9xs15+fIDpc2`X02 zvAKbrU9d6fz?%yezu_rL;PsI~hP`wevqX$MYiUHzf{d~2-HsJXyBUw=ks!4ue~H%u zP`BLj$d+9>mk5-bl^bG-kGv{q&N3%riLXNn5KabB+L#F+I`w@&lpJrBC9`EjT3k;# z@7%WJ$_n)vH8LYBe(ac;mpdYV2yrU@$Wv|(-mVaRX1P@OFwvaY-ZOu38H;p!e7e4I znI*VYd53?;-)8O7eZ8jihU6yaE%{72)!ZTV=KT}IR>gb8bHIM$J;N&h5%OvHJ$fVC zo&4$4mXzIlR%z-}Kyv$e=Br6OH&RW3=)vEcL za*=WD;oZ%7>?xiF{xdt2;;>-|aB#z{!L*irAx=trjuxj{cyFjS1df8AIcja~wccr%m^@;V|OG!t8 ziJqMVH`$lM@j;qnc3H<_MIj#c!?J$)5)y2)j8|uqubXfLv?y~9UK@qiSB-plu=su5 zPhpAIs(uwLw|z4Ejtqitu%Ai?6#al|i6yLeOK`TmneK+YZ=EdyOx)Dhu$Vuv7%6o13`uB?%4- zarH0bIYVI0Or%x8YMw?U+Yr47>e>(4qGk+$?ex|a^|u{bm7B}_%XHLR%CoJEf~P)a&*$*iQF6p3QD6wV{VVxX$*Vi${gOvM#h z7{!S-j67yCzB&Bn)HykZ-a*DRN@R|$v|s4JOx4^dFmrxUG9sj+;)3nzyB$!B{G%U6 zAtzHhny#%GBvU065R`I1APFq>AA*M%+&(6Le3f-b`~0(t{J3p5*_1+-Tg z_4OyrULWG)NS{pM-a~SIU>lE)2)JkX5w&Xu)Gcn2@dnT2#KU3c_g0d*=a`53t&!w6 z@U3O6X_5^M_E=1?BPeATJ~AX#)(#N)pc6<1@+9aIF#MF8p4I_sRsNfL5F9}CjyJQ( zt6OV5ZgmB1=J+<(;-oaUQq?CnnI49_0S1<4cftGZ+^%qkp&FLnYz)tLcMBsl1lnst z1b-$~k8=9q3UCQgJF>3lM?J)1FWV9q+dsHSxv{>@5>BZbV6a=vMSym#?18ZcVQ1op zk2CP~)GhH*Vn5?=ky;u{J=R;&sC(g3P<_2c=>$YFr^jITNUNR2Js@{?=GZ%x|o+I^At=(jykSC9g@e<7?V$On#CrS#L|(+(7YVkXrCaF-*T{ z7Ph=^=wHcMW4AIgwE}PWhPEt5HSH-E_UV-(*icgNu>wGU!l~RS9Rwf;d>5zC2Tzsk=pvI!6WFpAX!41Ns>}G$o+Eud{DEs$hR` z(|;G;;-L^_=fG2B-)9Zk#xBi27vnC@;GarSnA(ZX?Kp_XJWV@X6o;`gr2fvc@@{i8 zP0A9$D=0W}zt?_FDEs=2e{C<~+I{MO*(ik|T7gc~u4otbu6RY>RF8$i%OBlIZ#{oK z&unUYMQV{iYKTA~;8wl%Hi4JKf4N}N&GNd9?S!xoBlW&g{5?+XR@ z4({e>Gw1E)vgGXd-7u^GxKXEaP~`bIybuDW8F{yl_5{@y;1(_sT{~<7t5ca z6Bw9_0j14hTdOGjL&~rucQ19k_O5n}9FYo;MbBtK3JZW7KeD&Non2wbKIl{`pe2w0 zjT)sN(Kix4w&5**&=Az>4lUU52xust*Gy!HvTKC)c+}1R7snkJ9g4De4o(1VCZ~9J z!oMk7to0A8>Fyk=TJR0UKE*xDK1)2U7a+qD6vJP$_0VUJq0G3kBlV=;u|m9YQ0zX_ zz$FW`Px5!;8sk5{)UBp<9`4%VbI9MTaBryI%HE(JJy`fWK#mA~KA_#xmG>469Y)Q* zoI5ftsaCI(<9ZxzL~nU_ez)TL_PIiK;k)Q}VOf^u)y}y z#xk2!WPT|Hrsqy^4AYdCLM|oiV>9%O&#I~y4xk7=B(sYcW3_LqAERGgzi8xwGv~1n zpTNP1`Ewrt&W5y{_o-}98e{TDVCxfee3)pgY8U)W;(y@tazUE1j6d(i7@7Ps$31fA zL(5V8G>(mrjZ2!IK41}hb>o3gwZlvoX$ zt?Lv9$R+SOf2Adt^x&*?e!6Hoh}fS8FOv07TUS$-UB%>u&nCL-xVE;Q&et;mkK@I< zIfgK&Uw$P2#FJ}f_{CxE=YT*yTs~HV9#1JyfNHIvH6jde0cfo;aQKE2(=~P@rmgQl z$Ym0Jf)e(z_yJz&S?y&3BlSU^x_IOOnU6#lDCMXlY{G9M9~u}ZY>tWNvCU;Ci5puS z_+~j5pY}tYYMK(I|Fx!pbap*+@pprQX%jvpN7Ss6(#rS#LS;+^Ei;akAZD@)IspMZ zzMqXP6Zj-c=dmw%-5OWQZ4o4{C{9_@U@B0z*(a{Xs-+$Uu(&k(L~soMEu$?YvcB4l~7!%Enq`PP89BtWSIJZ{5MAN1$r8y>tUlZdM*Lw6S7E{C+x z{ko^@Av1^0#+kyMP$3B=@vIKMC7gE;Z43on#}BnH-5i7s>v%REsj}j&%ch*P1t@w< z2rBGT_n$2JV9WqoaCoi6)gy+_+ZDEX=}k;g-#l zc!VQ`CE1na7WpZBAowHrUHVn(vF%5Pcaz{UJ~&X4Uo%-_5kKJuSX^?Uy>T##Rm@Cf6+-HPZlwe#GsHu+&f3`lq!}* z!=6I+NfTj+R2yUYLt_S&(IjOjaYI8ZYm#0LT!B zWm&{g`3UNn$p6#WSwOY1t??drEd>e`2<{MqyIX0I;ts{3XrQ=jv0%kr3T<&HPM}z! zxU{sz-5rX3}&N!Ci{H@B$|C0S}Fe6M!{%5+~u$vT($ z%}G4<{#ej#wWWJ{R61RRj}Y$?5cbij{bi=)+uO+|x~Zxnx6Dl)rxBJ7w_)A& zxF`>6n@AFL9^xB1w+Rq5q2Uf$7&?#%AKks0e zXHy9mM|~||bX}?{yb`&qHLo)e7RlL6X+vE5wx$*@+fI+>QXi!$=J{hz!L{;cIovNg zBxjf+EOs?Jb8pD#N`8+?$XBlDM%D8w+Q~wm>dyN%+BD9)H1hU4g5haLU1?uO7cPtS zlai9f*KbRRHJNFU>JiR6KG4jvMy1DDH{ZM<`aBnOwc`iTb+K720%|}Xvj{V9P^A(c- zwNVbqM~qT55=lposVwR=%al^v`BAhSbf2_L1V~COa5v-VH>1vCicu*L6-C(-^_mVB zY#_PO=%Y6Y(EpY-|J9b&qeb}>4B^-Q zXg8kdYd8BFxsL=1{UN@ucQTCmZdOkA^SMBh-Ry3J`mwL_>_?%_9ez5G4W^I-=kF`$oq%k7@XN*pzjWR(#*9a4J?dfirGY+j>h(Fi$unsU zo2RA4Oq4oO;OuJaydj-u#+VoyO-zz{fl)4PV2TPwsrBQEIa4~J^(GT>eyGzKITw0K zo%F+kYG$6XGQp#9x~c8jx|6a=qe)^_JevyfdoH^36mIPW?_j4%711TZ=jnqt=N_ZS z>aOuTU@X!l@#*a~nFRxzI~n zDCd#SWX@a8BhKZnLH_swPo17)d63!C+m6exB@L~-YTTz|>d#z3u1K5i*j)-=^iLKU zY(p&yTrUaJZzRR?31#ZmDFWH%*BSet*7mzj zovhaA#O&xm1Ogg$$dzqich?5P3F{@p_Vzr`rUl{9kzi`T1+`3{oU0>x!8nF1*avmy z0}x}?lhPQ{(9wpCzie<&e$IbwdCm7q0>j(~Mvm^<+*BD;3(%yLMmco1mYTFLmEdS>W8_+5(E;+n^y1YjGNWH zjWSZ`B+LC#mc>Jd+Y^`U&!6N+w#T(%doHe_h0c1S4yGxlfNy5RW=6uEo#T`&nJg1J zvNiZ!PS5xrsXC$?E9HDHHk7nkL2zpL|DXJeFMd+;7!Sd^lxqNyS6<(ciluc^sIzvM4QD2QI0YNn~_~ zV7PGmLv-8tFhAfg1&fWfCc99lHcKP>{B%g6c|T}1@95#W422wS7E1> zWcWPHyKWyX?g0Cv@1GTrY|Pu8JcA;6mm^tHg_1*7NN92QL`K=t@-p*Azz8F$N7z9} za}sU1@{PovnxqHasbk+Z(bXu*W_uot;p0WDlsZ432s) z6qJmuZj1n(u$wS7Q(NM9a&ty-5hA=vjd*Xm-4M3NQa1hbTIXdTN=TzQW-Fvr$lqtX zoM^v}&I`IO(H9xh?kxNF-@Kugyo28Q-CSLso$hbXPqkOx-5CuB@9kMN`w$5F3e6Bd zg{lU>)WEM%AhK~}i8rwd$pRxPa)YJz((%V-N&EDa7mU%)utuxBC6A#fE5*j~G2epm zS_q4(hVr}|!hA#&y+kBAo5O7brh-LJ7~=cFrKXxt>5FEaA%Xlp_!~E8Ar>bHeX8bp zbp8}YANPZk!3ez3?7~t02+gDT>2v3_HslgWn0rhc#PL1GauTRF$LkxUc|OEPSeen$8QI|omJ>USEM<_)`L@i487Ak!LT%P zc;;U7zJ^wviYr=3&G3pocVjyJ@1K8izGX{66< zJx}Fk32u*C)gT$^7K=UXqF*{0G0;QQq#Qh)(o3wIbARTf2Mnbo{DOLo&iIEwIVNAF zLu-(Brzik6foi?PoV?;{fMXZu?;@Ru*h$=cW^wqd3yaK z_*2f8C>+OW0{vX6{3bHxU}7nU9X_&Z4!Y{8QiDyKQ7ZRv35fJ^ef{3-`ub&K!mBgwH}VSduRf$#M>mg*;Er3X;@2h6 zBwYB>9WVBHbUl2_8Rd%moy#ezUac3<_Ia6mF*YXx9hq+0Rt?= z!cExaQ|m{%k;EnW!_gx{Y;VP|IFOwCN+~oqlsqtcd85TSGsEQh2ZLWYpPH7w`GK)r z%~xo@O`)DaW0Zf&BQ1;hjxIo<>NdY00!^!_h^LiLZl@zJQgg){1q3i=Dba&gS073i z@$0H@EI%f3DlKbdR0icE%Aw-F#peiXGMbvm3hl>7+dSIqx3dwG1$B|SuP?Le?^7t~ zgT|6*{CKTjFn+EMUc(t#$@(xyiXn)>4MyP#QHax=YhkZOk+(%@<1`Ti72HYB`2w`*=#FK!t`ndM?mspc zPieF;V;`?JH|-?^{eq^ij;K&iFAog1x1gg{qYCI~huRGH_4VFFMzik^+dyy9P&0o1 zIc!}0h$e-Pg|qjU zuw0PJ{fOq31w@Rj+wc^7DJC7;c3q5HhK++(n0eP9AyowFTHXGHd>1c-D%pRtvIi?> zbi`CuGSaL*O3scQ3lb8H^}EU+iq>-_!QamNzHW!jCYq^fW=9G03@K6>p8F0HDPtNW zU1FTjZXSc76d7*}p$+Rjg^$fUf-t=1&b!L61FtaVS@T#3bFKA@MuHHG>sSl^0Pf~h zLpO2v4mCP0FBC*it17a=m&cZuJ`dKT$_8*MbrcXHGg;^bYQJEYZXY>Onxyg|BAX%GPOHG^~vc>TOM~@#g4_HOiui4|H z`s87}u4)Q>jU1`3N=+eO8b2|e8kk-c_g#K+5<~J87l46!wyFl7Kv!$>g4JNlT|Dv= zJ$pell?}6r8fiXizW7zN6{qUX{u|odlB#yf*S==yAHR4STWvlie0?Kj3QVA>(2G|> zhp>nZYgh|=Nm~#;twd8>E&TWuN6$Df`QkF#Mr(dBc=dx6mdvwWm7rg;2ieLa3KzRglQ8%b7bLOA{|} zB9%yA>U5ak?;#~hb1YDN;z0JG(+TExHIa|*epqv4b4k?Kj<94DkM1Iyw@18?i#UZ_ z5q(FQfxHho)F}X*4}8)hzB~c6-e`rQ9P~g;QGT>0sdkO#$o3%&Pe#Oh;m}||4Rw9| zh+9ygJKBKY$U{nJU!K{ON!mrR5=nCYjqEyEGUYtwwHWFCY!RBD50; z8NK$x;3(Q_-?)2kR!dA9AxU?EnP}?r(8^Zsh1eYvJz)I3!a!4d{GB8NbH`13W~eKo zqpKl1rbQD3&v`Y-?L&x2>}4bVnE2k=hLN-AbAVis8u<)DXvrtc38EPv^qd+Z_OF)mInyJt;jeXwf@PyvgxE+vrFRvvK=N19PVHfljNW4$ZK4>>;QH>i&n z=N9MWEHCuYzr42_smlN$f=#4JV$>00U7QMW1cQ0^rqDabe)^4oE2VE$8&jpK3%(jt z3Fz79f1-9#h{p~0NE6ZQ6LRZ#SuR(u)5&Vii#U?Bpb{j49H$`C$TZ67?DI(sJ5GVb z6Rm^c6GuMF49^VD=*Z`dyWSw{2QzrE?n7X$s?6o9%axp!`uyjmJ^~)pu7T|lSFFeF z$WYR2C#h!YYbWWf%PXwIh)*RKCR{}lC@xIr_$1fpfLZk0o0n699e(8m?cpsMUt8WU zKwNaY5gY5ZTS zjA|58gPB>ghxT{1}$jyc$#ly4NXc2 zFGhof9VC94_tynz6y@`^*Hae`rM%N>*b(~7Xj^oh&f9g|de*uR9`+eNY?_+Vf!1GV z_)1%_cF3Emrm(-YpTR0!5+dgkZ{h|;vrvAXgqW}Oa)XzG$nP#=>=8h=!e=PWo^1HS`p(J zGueWv74tMZ8FB3yUD9-KU00ohFbo5&dgBVp2V?mKEr~u6QL10xuxpw?wE9C2GK zWNn^wL|W+<{nIn&GueijVW+q%>2gA|5b}n71B%?JIv?|vBDoWG8 zwVnhPjY^CFRXqu|Yn)bX1rqo3>SgD2G6Gak2Zkw=z^aVk9@Wxr2pJFw_A9~#@D{H> zqA2CjE;hTq12>pcs2T>=!xh%EI*wCRg_%f$HX(Hn(i!T&B-S2Ec3h1 z>rG|s=($n+=><(aUwkP}8z<7pc!8zwlZX;YTTZ&O@br$+Gk2j%ok&d_li36Livr^6 zZlEh`o-a$swnL|5z9L_+Sk@**a0`kPzv$Bo4h=l+;%pY~u$+=Um8IZZ62pOXf8YMh zg9m4Pm)uHu40fB(aIEz^N3T+-LM|Z1`(YOi#kmm|lj9@R+b2Y<#vB`B9~SYV%S-O^ zviXgn2KCfqDm4f#SU!(m71ATCZMEiaZ^nUMcx-;^Cek}&^|{QOfEjegIa8kRDBn|E#`eNh4TAQ^+>Vs~knON>+s3oo$e0ZeUxJp^cWZR+GC=xFCv=pHR!KImM<^TfK6l zRXVt{nf(+;-^FlzuPR`3>b#?0;@y<+huz?*i zipAxAtPXT483LWd>g$B-QtP$DM#HebR@ctyti~zqU;6eoykmu^hN=5~03<`2L7%=X8W7Y;8Bx zx1AXqi8{!4|GK&Qu9EI^feK|CXR#GbZ={WNPTFgiHc3!nI0H-gF(mi{=%j2>Kn36~ zOSuOtpa(^AG}|PgvME!LItH3@0lp0rsTrjoK=!k;10MkO=hiA3Xw!Ba@Y60nXAQ(2 z^W1!HL_k}qREKx1oW7v?nW5$=uVN>8>cgLW7+Cr(7+j(_AN1de*cQANC4Uwznk+ua zo5HJ$V;Q>=%y@F=i_>$5&dq^0BQD&>RcrNig&>}<{q6|c|CXc`>U{F*;&OX!C*c!m zV^8Mj^p;wu=zGR3Y~&CKCjQYuUKxr$jl^n}lm6#<{`bB4KSXm)bM`}439*S@>03dvoqOGlxV z5T9&vCYmKxXqx9i?!c-%IP2(wz>{~MbXa|-H3*vA6k&2U@l4E?{D-Xm%qo&u`(aN^ z#uz9zU1+*WxC~bScKxsSBvpAywe>KGR-t|!x3IOnx4^$jymYURmuzzI=|4+6&2)z}sw#?0L@z1n5UR8Nt!I&*F%pRbBSuovrtrzsBxcb@>o{WjIaC&#F<6Q#1K zHL?Z-l9&*PZICY!L@xNwAsrDNMji6T$hpXKh*2|i0s})zchQ*Q=$ix*iI=O2)$Rtc zU*2{)suOob3~T!R7(RTa_19(lsZDsiq?w)gVPPII0O=OX7wh|K%BlVFg#3 zD6>PKYB1##@RzA!8_tKcP2)~t&&!w&QHdaXJ)vty^r>{ZMnD2gr#PJfaLX@A z$(at7TkIr-mE3kwXh*6-?u=1Jjk76l-pb>HHMQ7p-FhrPQizCtXeud*zMSC)}v&TK_E2y`IEUK z`NJPeI|2UZ16PlBc&^g8y&As7rc%F@(7BS0&7i7vvZ^h)zQL|27<~8du-?b&uekCE z0RKdl8xEZOLvs90jD+(nWi7$xuC~r@POfkqFmwFf z_tMN74B-9GIO*TaN)A4LK>!C2kRJd7^76s)l|p}^E0x^LUfP;VIa`Or*?)xTu=kPWMh@1ajkTG*sw6wLhf#ES>X6_{oH%kX?01P7uKRkFt@lOMO_%H&c zB?thARQ?@W$^Bmr=pXzheDH4*?l0W#ft)f*vTzaZ3ebIzv>DhEuKeHD4jZiD1%~Zi z$NOVOUZx0J9W~K5EGV*I^r%s;h;itF5CofLX}`wme%mum5yuxH~() zv~++k`hG=!Ba8kw5`gj{+o}g>7?ao z3y1gv;ODLX$%20!8l1rjzPG7tYXLU|$Fx5G4`|gL78UNlt&RKd_YshR-5vl|B>-k~ zGh0_D05_)~C(Jj@Hg0at!dx(rEKIa^HFLJHH3xG#xmvT_hn!2z)ycx$9Co{b|Nm+K zg~)RMq1?ig?RUw_n89kw$@+c`_pAAfBm3V;p01WwSTKq#9~SUG8-SmWkB1Ln1^BJO zh`ByXLu$+L$;deR0%O7x`7x$S4b~AHzyZ1PVSCE$ni-AE-RUYgA0H%9y A*Z=?k literal 0 HcmV?d00001 diff --git a/Week1Assignment.py b/Week1Assignment.py new file mode 100644 index 00000000..3e53ea20 --- /dev/null +++ b/Week1Assignment.py @@ -0,0 +1,95 @@ +# -*- coding: utf-8 -*- +""" +Spyder Editor + +This is my submission to Machine Learning Course on Coursera. +This containts heavily sample code provided in the course. +I changed the dataset, test ratio 0.2, and max_depth = 3 +I also have to use write_pdf instead of create_png to create output +Input file used: + +""" + +# -*- coding: utf-8 -*- + +from pandas import Series, DataFrame +import pandas as pd +import numpy as np +import os +import matplotlib.pylab as plt +from sklearn.cross_validation import train_test_split +from sklearn.tree import DecisionTreeClassifier +from sklearn.metrics import classification_report +import sklearn.metrics + +os.chdir("C:\Machine_learning") + +""" +Data Engineering and Analysis +""" +#Load the dataset + +AH_data = pd.read_csv("addhealth_pds.csv") +#read data +data_clean = AH_data.dropna() +#drop all NA in dataset + +#data_clean.dtypes + +# data_clean.describe() +#examine and summary data + +""" +Modeling and Prediction +""" +#Split into training and testing sets + +#predictors = data_clean[['BIO_SEX','CORE1','CORE2','HIEDBLK', +#'age','H1GI1M','H1GI1Y','H1GI2','H1GI6E','H1GI7F', +#'H1GI14','SMP07','CLUSTER1','CLUSTER2','H2GI1M']] + +predictors = data_clean[['CLUSTER2','CLUSTER1']] + + +#predictors.dtypes + +#define many data fields as predictors, + +targets = data_clean.SCH_YR +# and one for target (dependent variables) + +pred_train, pred_test, tar_train, tar_test = train_test_split(predictors, + targets, test_size=.2) +# with the order of train-test and pred-target, this train_test_spit() +# function cut predictior set and target set into two: train subset and test subset. +# test_size determine the relative size of test subset + +pred_train.shape +pred_test.shape +tar_train.shape +tar_test.shape +#check the shape (what it means??) of four subset created + +#Build model on training data +classifier=DecisionTreeClassifier() +classifier=classifier.fit(pred_train,tar_train) + #make predictions +predictions=classifier.predict(pred_test) + +sklearn.metrics.confusion_matrix(tar_test,predictions) +sklearn.metrics.accuracy_score(tar_test, predictions) + +#Displaying the decision tree +from sklearn import tree +#from StringIO import StringIO +from io import StringIO +#from StringIO import StringIO +from IPython.display import Image +out = StringIO() +tree.export_graphviz(classifier, out_file=out,max_depth=3) + + + +import pydotplus +graph=pydotplus.graph_from_dot_data(out.getvalue()) +Image(graph.write_pdf('love2.pdf')) \ No newline at end of file