From 0aa83453fc15319b80e8e490361318a56729f396 Mon Sep 17 00:00:00 2001
From: muhamad fais aizat <muhfaisaizat@gmail.com>
Date: Thu, 8 May 2025 14:39:07 +0700
Subject: [PATCH] fix:memperbaiki model svr

---
 .../__pycache__/predictTomat.cpython-310.pyc  | Bin 8826 -> 8845 bytes
 .../__pycache__/testingModel.cpython-310.pyc  | Bin 4164 -> 4117 bytes
 backend/routes/predictTomat.py                |  65 ++++++--------
 backend/routes/testingModel.py                |  85 ++++++++----------
 .../pages/Panel/TestingSVR/Normalisasi.jsx    |   6 +-
 .../pages/Panel/TestingSVR/Preprocessing.jsx  |   6 +-
 .../src/pages/Panel/TestingSVR/SplitData.jsx  |  10 +--
 7 files changed, 73 insertions(+), 99 deletions(-)

diff --git a/backend/routes/__pycache__/predictTomat.cpython-310.pyc b/backend/routes/__pycache__/predictTomat.cpython-310.pyc
index bf2d30a48648c39f27a34abb5e768bc8575f9f21..f94f08574a0dde55cd11595d7181c4fa5ee8c76a 100644
GIT binary patch
delta 3358
zcmaKuTX0)P8OL{5(vd7%S6?LAx>%BLim!2;yPKQSw4H{)G@S{Av_bVMwq#jyk2VQO
z_f(~7S}qj?PAD*O!%^roai<g7Nrx7O=~H>*0Uip2cwu-8Obfh}0j8AiTdBG90eQ}E
zzw`aS-LvPc&wtOq57zJZmOUOff#0=9qRSs0c+-2y&SrPse8uiy-eE|);8=j8a>aaG
z`)PHF@UE-Wa7ep!L`cCeJcR)FaBrPqW}dY2R*-jy?m|!Fo@}9)`?#M6?$j3gIOV}Q
zr9^nFkhJse2x(AkaiqJ{aE%z6)U0Ym+FMg-6}Dn5hN$N%g(>wLP8gt9MJ|Z?RMgQL
z98|X$kWT569n#H1Jj^3??S#wdG`b9r;Wd1Q-v}5%X)8pHZeWa)(^UVRh+|x%)e`0X
zMh~1M_`n&e|5*u%8Z9x*8NI+k)#YzW83cv$sL==cq{{zCq%c-_w-JIkjrogIcc~s}
zrNoS|?B>1|2KkT};y&3U`*^%wwHcAp1V{-b4TF>bsTah-x*fDQXi25bftFNS7}QkV
z0jdwwv{Dy9O}Et$=tFhQh{%XFEIXyA!6<=vM0Pc((Jw}&SN7MKF(A6D)|kk&PC<%_
zO>HU0JB+v(7ZXrOYxE#_?3j^|ewm06V^H?1HYvKTNj?nyQZgx1ydy&R$UK3&)~qR+
zYS30DLTc1VOJWg01*=i3L$HFoFf9jHSfffC)Uq{*F(ilJ(cDmF%$jMCd&+2`U#9tJ
z9jYlQb*ZY&I2hyyK^dzvRAiiIwi6?Mkv_Q$HI4>>T(=yMQ5oZ#)@`7V^NDr)QIeTF
z^60Hgl-zvU?O<%fVSX5i9Byih<($5l+n`M?r|V_C($tFiQZB1E?N5}&@&;>at2wb;
z=1pHQznT{(d0x*gihQ{QU7Y#SS~0tr)3?IgwPAh`88985&zmPa@#^D{(N6-Jj-~AC
zYF7UW#?DH9X|<f^8xH+;fxf7!U>>JtT2=P7a`D`T_L&m>6xL}xx1{HCsxZU!IOJ|Q
z5OzR@HoeQ)O1^l~{FleC6(Oa^O}AIlS@Q+&;vq+NZLN5&=@#XarPHf9J-^s=>N#}_
zO;%cK+Dh3{vol{3IUS~u6*;(^US2C@o1M^wLqg<Nb7sKzJ@cCHK{{;y-IwutR?5Zl
zYJ0#HGwfeU-Ft6pu6iCPqi(@gIis7e`R6r<nyaY=9-uFoM*>N&%NC}6w2yVMAROjX
zfpm=dshb7i=ut<P-EDK*AV=-YZ!>=t7^knA{|FqS*UcTl1N55tRB*6&4lad$s66jO
zcsdu^`9GO&1S>YC`^=H<XV3zDV1XUzA>b`NA^^tLvNgzn7pc6}$DJZn2!jRQl`TYg
zkazPQu)ub<(9d1GS6N`d8jvpZE3iOlaiqJ{C|ICdx~*zVx>{3c6}Dn5hA4y<XmmpN
zFtlCpZgt8o9^w6bpl&~5|J35723{2aw!G@EB8hR^tAY@xcnsX_pDLe%Ji{CqqE<*(
z+jiwpV#}`LV2N5`sI3IWFrKO5JYb1hVWh1jRG$&0B)}8{JgD4gN{sTL49XsGF`E$r
zhYPe_Y#x*(DBYl?z~MrrY8=Fti9HNrT8Vui4}rynz~TaYSPgm{)Zw<;3;GCHTu6qj
zG3k*$WpN=3ybSy(3_j+UVX(M}2wCW2>P(s6WGl84V*m^=PzY9KXJLwu!pcuCQHW>I
zO^oOgF=Apf&nWX7HsWxhjEsV*Ibk6ZGG@)n1bPk*A)_$DrU+5(c)Oi|HnC*Cdra`9
z7h%P>@JZhF9FehuV2xmboN#i1@u^b`hK|972jNJHIWVnhK2vAlzUdRpNWo<tVk<c9
z<~j`#@YJ-mje{i`Lt?v3@L9OuVL1pB8<N9(%X-TalW-0mO$l85*J6i+oyr&yJ5@U>
zM=p~ppOd4P$;&ol3@)32W0Q=4#Sh2~cq@TpjBj0c9V17Hw27^J8(uz4jB#l*CWI!O
z1y`X%ahJ85Z*NdB51IQQ-qD~no3%&m6;3g)D)uRD-wK0wWM|zD-tQGvHGs8Wj?0M#
z%-M3chJ^c?l+1F-NyzzOi<pvA7g^<)uyY6B#qD+WEQQHVe>!PslX424)#Jtt-z{ef
z9eE0$4wTQse-G2Y3Yi1a$+yFsHB(rCXvaJ$^-5ah_o;%~or01Zy6sWf`ki7q4Uf{P
z_8AyTy#Y+WE;EpYi(zlR_pXNy=k3~scI~@z)9u=Y+Y4016@nS5HDXU@WfErl`}Rt0
zZm-lVyn>r+^fKXd5Y1wQ3sz!$pD_lDG!2Wj2^MPqx&s%=PQ<~B?A%9`7+WYg?}BG`
zK-@34)M)FuamYWt<t#l*G7C44gx!?>#{5#`aP<N7<p&WDAs$8?MtlzO1qAMH`Xh*4
zh@*f*`lA>gLwphOWyA@@V~8x`2?R&v5KD+<z^zZ<2YZ!sv0OBd_kU+>io(Y!1Ertn
zD_Diw8WcDxBC87s>^ys}qQ7AV2L4FjGCvr2X#aIA+d#aAwM^fQ@h<`AZ8H-y8HfH3
zCVr0i8RBikFA#%(%pvn^bQ=}sjcB^Jg4xpu9dQP6)(pfZs?T8PMSKn6L(~w@Aub@E
zN4$XeI^r9MZz8%7-$J~I@FVJo03rxz+VjQoqW&zN-#~mDlNxN&xf0jEONe<PwuctY
z_hLgMcxU=sh!MmnAT!sx>DMt4L%d^p<3rU;7@COhBVI!M0P#b_j}Vs;>xh>TR}lYq
z)7F2CB^IKAxQh4*;CM$dTY;~ltbmV%H9g1k=IikZ`il97_z|u3;LXXziuNYdR{Z9b
z#Pnx(`QIjb9Q_pj%)cbwjlK_cnW?4&zE9T9=@QPG+FG{6vlac!&G!cP(#}^Qr|w^W
i-}I(N=st66YO>E|xZzVlqxO#(WuGv{{>yCskN*ehhH#Sr

delta 3263
zcmaJ@ZERat8NTQG`o?jb#C8(Lb{yMroH%a2lQvD;tY6Ez4=P|AFevSUm*b>%6DPes
zZRvFGye&hhfKlk3git@Q5rg%|*h+;E67UNN34!`!zsUYfViGOl$A0hwA&v69$L`in
z8i~$x-t#=~`M&qLu0Hmk#g2{kcCUuNJBhy2#^TM6*A0Dk>ef#Ux89Kf?Lm1IrTkmx
z*XG+5(O&dRgZm;HZ|5CVo#F+p$#y=#b}nerC<Zv={wib0s0EQ5h-h_2HK{a8t&0a0
z)AgzR?k&xBOLwhD8mk)b{s~h(E6oNagYF@^7_v<ahRG4NAPT9-L({0JRrE?zwn&d`
z<-I)2BUSUH$M)K7w$E<2JM2!|ZwI8S7`B7J2-nUr>$Zqeyv0h4N9``eeZ22Ht61+T
zp$~#iq}>gSsV;Yv5>s7bb`SV|#s5phDOSAK4k1nuzs)SBdL)$6Z}-X|kDt-O`$dw+
zWtZ&XiK@#Em&TwZl~RdAN<!*}I8Zep#v!JZI1VkPv|gx#RX5a5sA;7xKutH*5cHv{
zX@^%eJMx()8LkaTuk_V*rpa(ECEMz(Vn@ZGY?sk3-R=|V+K?D-wCc=`iA+=J=dE^J
zjEF4q*cMyVPA%C9*(nnd%}&aIst06L)hYBLeh{PW;=>pxEmJbhTk$Mq@MJ~t42;Tj
zohhc0iD+BQ9+Fy36HMq^tkx>@qPI9EaX@ueXEj${vxns{j`4RYORtUBwTH8cAvwfH
zs>o(q$)~a=Xe{taDA_7T!k*(ixL32|+wANHa@=)|X}S#FTJ#R+6>A^fi5+u!BX2F|
zvuwxATh@kEw)TTYv!zhlT+1!ztvzU4amwv_CMR-KmS&#FS%szJxwUgy)0(4%y#(_F
zG_3U$ff~vE8M^a<?-|dIxmGCUbCxsL9<Mw{eZC6Vaj)jq*K^j_C~heiR@XNQ{D#~5
zIKeupvas}(sYaHuxv_TfhWV)!Yl-qqo?o@{d6k&e)mHAB5bnAG*lEY<T)D8e6xg)#
zyl|#mK+bL`R^GYWF4?5B(y^TJijAexx%IqNSjKqP#%3wE(*};`L|zou^E>YH>B5R|
zIy*1B^wOqN>wJ=BoPTs?os_?rd3fP!A=V2tg<7AheBQG1Xga^}FC={;S6W@otu4`V
zPPo<DPIwzj%$3&)&WHZT*>z_=FyIThLd?g4`1dhqH87ZI^E0m=MCn$=aCI;*^ZC3k
zuL}w@bid2PJk0rdV3b{P-VGdM*PLkZD7)&M3MPAIu>|r_<&`xY&bI#IZ=B1)vWr=F
z98cHF6%i<QOAq-J_i#TCR9)19lX;3gymOWDU=>dww5}?%J)#!|*eY9VVd;6m0Gl!O
zy6=Cs7vsS5>^2d>``Xs@IOC*o-`}KJjM^1Hsy^jNe-tr_mG4AheI}d==4QRCcycP8
zIM|_CjH@2+D<!Ua#9)VJ!^5n9iX_E~Z-*C}#Q~N7Z<Rlw_<neypT{f8g<3=k))tUm
z%GyG(Hh<IFdZ3Uw1fh|$h2U)drn9A?rIgkKm7FaEXY)6mZ5C>}sdhsrXA8+tZBY7T
zhjOn_EiEhU@RnXN1Rv^!dxgbtEh9!6EhrJVl~N4Nj>6>v#h~;S;Yj#|jIJ`oV?0xZ
z>%lT(Vw{gCUmLRfF;QCf!Jk@i1#uaxO~^RehZ>;|BV;3*L|x&#8UY_g9bYvb926dt
z$6ZhIG46X!ld(m(9EQ}m_AQ-{ujm*$hKUm>Niij3e1cC_br|d5N!=d6v~Dpi2l!N#
z^=fuXrfM@B{b8!JaItA@7yD0OWrJ|mnX3(ZOQH>5Wf~@bL+qAGGFGui)x&b=ipFQ<
z@D=Tv%g$ih5tOV9%LsgXL?)z$lHt3rdY;ps)uc;I^F1_uShIIYmpv*>(NgpjTNTdL
z_VT$(or!r+`_R~1XIrk?esMswh<TN=ptOZEI-dXessSJGXbez$MDCKKbu78&Z7|r^
znAB@-IR?%Tw;z||+j@CQ7~IYGaiglg%COjp`-?`Ml;evP?bP%3B;PM5i>(EQ9}0{g
zz$2+!PlGuqTlgGas>$LZM0*#sQV(=22l~lR^pY3sBZ^)5Bv(%0BwOetDN}vhb?X&5
z0v2;A?%-7&`$qyDI+B{nhnmShl-ZAy4?T22SP<oI>u2}NBo^~d^P;Aj7d4F+aB7Ru
zWg(iTh%T(8^Fww9mo$OP%HpC9U!8W-O&OXvyscln%`|(4X)k(kXh*~mIkUwY2gkv`
zG;@Jn(6UEwy%hE`_BZEJ<oJa8jy(>4%j!EGp1ZhGu*$-Ef(U&4%I97v=LI5z+&$}d
z{^E<Utn+7I-=m*H$}#IW(E0+w7YUvv_!7aF3BE#bg5c`}rwE=W_y$4Fc`SOp{Q$#n
zP#x{4cGqw|j7Hg;PFvr5>@DZ-eNP^_Mv2!6ehk1j=m5pP0=(#&8k@?xt(!#rlHhHE
zcL;6~Bmvo@&e_-;TX)`!4IW-2wnT7-V1r<j;4Fb4C<AudtUNZoR4DQMH?0n$&l7Yy
z@5jcD`6zsu;1vQt!K(yY1Ob8|V8<w|Z7f?CsQoj7*N8N8o16I(x4!LM>Oai#&Y$|z
z!?YLcErMYJ`e~k>ZEUknL_fhzr#qg0`a2X}BKR)B_Xw&4-zV56_yNIX0*B!LeqycH
zorCdS=Z*M5_9N$m_~*^W0Xp-EGv*)AyKFi)5|jO5Bjhp-gT9&fe5Qwmb<-7QQ5L3u
z=U(FXvD-+_PVBhxQ(*I=I*lE3GgsodvbAyRugOEK?Fuc1wr1US22;cAsPj~6Jgikb
X0k7_7CNn<LnSM{#_5bQF|407==_Ew;

diff --git a/backend/routes/__pycache__/testingModel.cpython-310.pyc b/backend/routes/__pycache__/testingModel.cpython-310.pyc
index 71eefe5a236826e49636202d3bbce44cfa8e0881..396197ead4cb48c820e9abcd1e115cc49a3dbfca 100644
GIT binary patch
delta 1050
zcmZ9KO^e$`7{_NuT3MFHlKgJTZ`#-3LwYJST^5?RODP1J<Wv%Zn{l%C?#hm$1PagK
z!;(wDP*8Fx>_OgJ$SDMJ4rM<<Pp!T|dhVsrCVgaYHl!Lfn&<zU`9CxB=)`~STjN5(
zAoxsfwRX+UE9+0i-o((x_X@rb-?KQU{xH2y1V5(I038gMjPyty<wZeQGnOekWT_{H
z&?9ri=bx#gg0O`nil63=EKw5W8Kt;xqzO&rW>lJyeMlq+o;aW{^SNYB7vm`=&yt)?
zE-d8AF?ETwKo?c~+EEcKutiPOMPsJkQl%q{vLwskd|U^`vr#E2%?XsVUbsi9tN<1E
z9t&SYWnqH~n($_dtOh;Qn^OdD5Hu02AZpE2L@h*ZBqvDP3!)(F%vO+D$hydWL)JZI
z45>fUWEHAO1so{N8QwrOsX}p1Wi6^f8ES`2)*~~iM~!8Kq!CTsQ{>_ucu^CaLn_D<
z=8~i}C(?r&cw%*joR+BxeALcPCR@--I--guZPdEZ#(U~y_89qDgru9TbqRDU1UhxH
zbXsc3s?f0n-ZV3Z=2dcgQ~Kb8H(Gm4ex~8|%pQC+SzXwpja)mk#|X(fc;KV`I@+&g
z_TcZ}+6P~NhudAtO8BuTas%k{-q8CVumBH<@%rQQS+W3>g|H|A<iUgjRA2+@&;VC#
z94TV+h~FT+t=H|`HTGp#!~Zu`e;h}<J(g+*gJ^dwQhR@RFpTbqVK}%O4adRF9!+z@
zV6xx8JLswL#k?E;p1&He8prfXd}6$%>+uuw+pSzUSWHP-FiDl5AEf3mhz8+gyx)%o
zsV2hlB<RQQ%<cFb_v7#R1-cnO<zHKcz489|;7;)9U=R-X;$Qh!&NsNP@M6|o%DT&O
zzVOHPGaOo`N;x$Ymec>{hNW<-s|{MCHO3jwX_`m5$`ze9sG%BE%i2GBE^b*K(^<T2
zwJ$eRs(oO2hdPw~zp+eF|JD8q2bin3m9F5XCO?JOF-o;bKM?(g;difpv0l>u07LQ#
AApigX

delta 1080
zcmY+Czi-n(6vyvu$8l`Oank&9emdz72tq<Ipi)Kr9spG=bV5Z{#Fe(8O@r$qklran
z#e^auS#;`<bnS##kXRTHe*p^-e*myBz=8yVcTQUgpYGkg`@Hvk_B+3H-@DdkJgyUb
zPM<BVesEt|-{iy;x(S@uaBijKAgbK$fwn@JxlbL^)_kQMV{vBnrK8g(0j;gG1he~;
z5?>h@ps}PwhE%MAvXnyxCYuOP(*MU}uF6yv?NhG%@g2eqFa}nroe>o=rzgsz6DA%7
zn_);+gzz|)$l+@F35bKm^2}j{zOtzB1h;vTryy}u1nlEoa$pY$q=aR~J%vvIWu=Fb
zci<;k2^3ISxi9l{r_n=DLGT7a1wjN+wXYy5A#ss>K;ni(Mpo-bkXgv;$UY*gA2JE)
zWMAcJNDuI(AUTvM!Tki-L&`IL8d8wik$Be646=T1><xRA=luL3%45SEzW|9H%E&Vb
z8(SO_?tmj&-Y&JvVuzi|;5yYL<BQ`3FxnOIrMw8mL6zmOTnW!yC}H2qq8xfP;UTGr
zT!%m<O`x13y|L8za8PF&-bpA9h3n+rG_OJxoc82n@`8GcLLRCp;)e1r%GZwN(L+)P
z2dXGvNBLTg2(O8`k7mKa*PRakv!iRC1PWKeMxuBZqz-;HHg+Z~_5|e653dAbpo0k$
zFbP@6L7tu1liA5V^A2e=UdN)hr85f+I*P7!y6dg`%ic8p-(CaFSBhq2-)MO&t)+9g
ztS!yA*0&pK(A6_WQ-qyD(})P4HiNy`e8kJ*N$@4MPp<~g^>=hCm^W?~RpxDWJFSu7
zZ!WQxzwEDVERP~vt7{MZ;H@zyOPy};)2QhqiTNW%L<AXg7L#wA7lK{$ynRs=yClqI
zVXg$9%};Z?xU~$0npBsisP@a$E!m_l&J+$)GG$dQP*X8wjpnJY=u{Qsx0VmS#|w&0
zH5wRJ`Kqi?^{-U5sZFKvkPcTWg*)Ys`omksYK@suq_e%zed;ZsH&VN;4r^_Bw_dlc
G1Nskg9tUs$

diff --git a/backend/routes/predictTomat.py b/backend/routes/predictTomat.py
index b3e7431c..b919962d 100644
--- a/backend/routes/predictTomat.py
+++ b/backend/routes/predictTomat.py
@@ -27,7 +27,7 @@ async def read_data(db: Session = Depends(get_db)):
                 FROM predict.price_tomat AS pt 
                 JOIN predict.result_predict AS rp ON pt.id = rp.id 
                 ORDER BY rp.id ASC 
-                LIMIT 1 OFFSET 30) AS tanggal_old,
+                LIMIT 1 OFFSET 29) AS tanggal_old,
 
                 (SELECT tanggal 
                 FROM predict.price_tomat 
@@ -78,20 +78,25 @@ def predict_price(db: Session = Depends(get_db)):
         raise HTTPException(status_code=400, detail="Data tidak cukup untuk melakukan prediksi")
     
     # Preprocessing data
-    df['RataRata_Kemarin'] = pd.to_numeric(df['RataRata_Kemarin'], errors='coerce')
-    df['RataRata_Sekarang'] = pd.to_numeric(df['RataRata_Sekarang'], errors='coerce')
+    kolom_numerik = ['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'RataRata_Kemarin', 'RataRata_Sekarang']
+    df[kolom_numerik] = df[kolom_numerik].apply(pd.to_numeric, errors='coerce')
+    df[kolom_numerik] = df[kolom_numerik].replace(0, np.nan)
+    # Interpolasi nilai kosong (0 yang sudah jadi NaN)
+    df[kolom_numerik] = df[kolom_numerik].interpolate(method='linear', limit_direction='both')
+    # Drop jika masih ada NaN (misalnya di ujung data)
     df.dropna(inplace=True)
+
     df['Tanggal'] = pd.to_datetime(df['Tanggal'])
-    df['RataRata_2Hari_Lalu'] = df['RataRata_Kemarin'].shift(1)
+    # df['Harga_2Hari_Lalu'] = df['Harga_Kemarin'].shift(1)
     df.dropna(inplace=True)
     
     # Normalisasi Data
     scaler = StandardScaler()
-    df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'RataRata_Kemarin', 'RataRata_2Hari_Lalu', 'RataRata_Sekarang']] = scaler.fit_transform(
-        df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'RataRata_Kemarin', 'RataRata_2Hari_Lalu', 'RataRata_Sekarang']]
+    df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'RataRata_Kemarin',  'RataRata_Sekarang']] = scaler.fit_transform(
+        df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'RataRata_Kemarin',  'RataRata_Sekarang']]
     )
 
-    X = df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'RataRata_Kemarin', 'RataRata_2Hari_Lalu']].values
+    X = df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'RataRata_Kemarin', ]].values
     y = df['RataRata_Sekarang'].values
     ids = df['id'].values
     tanggal = df['Tanggal'].values
@@ -108,15 +113,6 @@ def predict_price(db: Session = Depends(get_db)):
     degree = int(settings.nilai_degree) if settings.nilai_degree is not None else 3
     coef0 = float(settings.nilai_coef) if settings.nilai_coef is not None else 0.0
 
-    # Inisialisasi Model SVR
-    # if kernel == "linear":
-    #     svr = SVR(kernel=kernel, C=C, epsilon=epsilon)
-    # else:
-    #     svr = SVR(kernel=kernel, C=C, gamma=gamma, epsilon=epsilon)
-    #     if kernel in ["poly", "sigmoid"]:
-    #         svr.coef0 = coef0
-    #     if kernel == "poly":
-    #         svr.degree = degree
     if kernel == "linear":
         svr = SVR(kernel="linear", C=C,  epsilon=epsilon)
 
@@ -129,19 +125,6 @@ def predict_price(db: Session = Depends(get_db)):
     elif kernel == "poly":
         svr = SVR(kernel="poly", C=C, gamma=gamma, coef0=coef0, degree=degree, epsilon=epsilon)
     
-    # **Melakukan Prediksi Rolling Window**
-    hasil_prediksi = []
-    X = df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'RataRata_Kemarin', 'RataRata_2Hari_Lalu']].values
-    y = df['RataRata_Sekarang'].values
-    
-    # # Latih model dengan semua data yang tersedia
-    # svr.fit(X, y)
-    
-    # # Prediksi harga untuk semua tanggal di masa depan
-    # for i in range(len(df)):
-    #     fitur_input = X[i]
-    #     prediksi = svr.predict([fitur_input])[0]
-    #     hasil_prediksi.append(prediksi)
 
     # Latih model dengan data latih
     svr.fit(X_train, y_train)
@@ -159,14 +142,12 @@ def predict_price(db: Session = Depends(get_db)):
     # Gabungkan hasil prediksi ke data uji
     for i in range(len(y_pred)):
         id_tomat = id_test[i]
-        tanggal_pred = tanggal_test[i]
         hasil = y_pred[i]
-        hasil_asli = y_test[i]
 
         # Invers hasil prediksi
-        dummy_row = np.zeros((1, 6))  # [0, 0, 0, 0, 0, hasil_prediksi]
-        dummy_row[0][5] = hasil
-        prediksi_asli = float(scaler.inverse_transform(dummy_row)[0][5])
+        dummy_row = np.zeros((1, 5))  # [0, 0, 0, 0, 0, hasil_prediksi]
+        dummy_row[0][4] = hasil
+        prediksi_asli = float(scaler.inverse_transform(dummy_row)[0][4])
 
         existing = db.execute(select(resultPredict).where(resultPredict.c.id == id_tomat)).fetchone()
         if existing:
@@ -214,7 +195,7 @@ def get_price_history(
         latest_date = latest_date_query[0]  # Ambil tanggal terbaru
         
         if tanggal_input == latest_date:
-            # **Melakukan Prediksi 30 Hari ke Depan**
+            # **Melakukan Prediksi 7 Hari ke Depan**
             settings = db.execute(select(settingPredict).where(settingPredict.c.status == True)).fetchone()
             if not settings:
                 raise HTTPException(status_code=400, detail="Tidak ada konfigurasi prediksi yang aktif")
@@ -237,11 +218,17 @@ def get_price_history(
                 raise HTTPException(status_code=400, detail="Data tidak cukup untuk melakukan prediksi")
 
             # Preprocessing
-            # 3. Perbaiki Format Tanggal
-            df['Tanggal'] = pd.to_datetime(df['Tanggal'], dayfirst=True, errors='coerce')
+            kolom_numerik = ['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'RataRata_Kemarin', 'RataRata_Sekarang']
+            df[kolom_numerik] = df[kolom_numerik].apply(pd.to_numeric, errors='coerce')
+            df[kolom_numerik] = df[kolom_numerik].replace(0, np.nan)
+            # Interpolasi nilai kosong (0 yang sudah jadi NaN)
+            df[kolom_numerik] = df[kolom_numerik].interpolate(method='linear', limit_direction='both')
+            # Drop jika masih ada NaN (misalnya di ujung data)
+            df.dropna(inplace=True)
 
-            # 4. Hapus Data yang Gagal Dikoreksi (jika ada)
-            df = df.dropna(subset=['Tanggal']).reset_index(drop=True)
+            df['Tanggal'] = pd.to_datetime(df['Tanggal'])
+            # df['Harga_2Hari_Lalu'] = df['Harga_Kemarin'].shift(1)
+            df.dropna(inplace=True)
 
            # 6. Normalisasi Data
             # scaler = MinMaxScaler()
diff --git a/backend/routes/testingModel.py b/backend/routes/testingModel.py
index e65c473d..974ea019 100644
--- a/backend/routes/testingModel.py
+++ b/backend/routes/testingModel.py
@@ -50,29 +50,35 @@ def predict_price(
         raise HTTPException(status_code=400, detail="Data tidak cukup untuk melakukan prediksi")
     
     # Preprocessing
-    df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin', 'Harga_Sekarang']] = df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin', 'Harga_Sekarang']].apply(pd.to_numeric, errors='coerce')
-    df.dropna(inplace=True)
-    df['Tanggal'] = pd.to_datetime(df['Tanggal'])
-    df['Harga_2Hari_Lalu'] = df['Harga_Kemarin'].shift(1)
-    # df['Harga_2Hari_Lalu'] = df['Harga_Kemarin'].shift(1).bfill()
+    # Pastikan semua kolom numerik
+    kolom_numerik = ['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin', 'Harga_Sekarang']
+    df[kolom_numerik] = df[kolom_numerik].apply(pd.to_numeric, errors='coerce')
+    df[kolom_numerik] = df[kolom_numerik].replace(0, np.nan)
+    # Interpolasi nilai kosong (0 yang sudah jadi NaN)
+    df[kolom_numerik] = df[kolom_numerik].interpolate(method='linear', limit_direction='both')
+    # Drop jika masih ada NaN (misalnya di ujung data)
     df.dropna(inplace=True)
 
+    # df['Tanggal'] = pd.to_datetime(df['Tanggal'])
+   
+    # df.dropna(inplace=True)
+
     # Simpan hasil preprocessing
     hasil_preprocessing = df.to_dict(orient='records')
 
     # Normalisasi Data
     # scaler = MinMaxScaler()
-    # df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin', 'Harga_2Hari_Lalu', 'Harga_Sekarang']] = scaler.fit_transform(df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin', 'Harga_2Hari_Lalu', 'Harga_Sekarang']])
+    # df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin',  'Harga_Sekarang']] = scaler.fit_transform(df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin', 'Harga_Sekarang']])
 
     scaler = StandardScaler()
-    df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin', 'Harga_2Hari_Lalu', 'Harga_Sekarang']] = scaler.fit_transform(df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin', 'Harga_2Hari_Lalu', 'Harga_Sekarang']])
+    df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin',  'Harga_Sekarang']] = scaler.fit_transform(df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin',  'Harga_Sekarang']])
 
 
     # Simpan hasil normalisasi
     hasil_normalisasi = df.to_dict(orient='records')
 
     # Split Data
-    X = df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin', 'Harga_2Hari_Lalu']]
+    X = df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin']]
     y = df['Harga_Sekarang']
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, shuffle=False)
 
@@ -84,23 +90,6 @@ def predict_price(
         "y_test": y_test.tolist()
     }
 
-    # Inisialisasi Model SVR dengan parameter yang dipilih
-    # svr_params = {
-    #     "kernel": kernel,
-    #     "C": C,
-    #     "gamma": gamma,
-    #     "epsilon": epsilon
-    # }
-
-    # # Jika kernel adalah Polynomial atau Sigmoid, tambahkan coef0
-    # if kernel in ["poly", "sigmoid"]:
-    #     svr_params["coef0"] = coef0
-
-    # # Jika kernel adalah Polynomial, tambahkan degree
-    # if kernel == "poly":
-    #     svr_params["degree"] = degree
-
-    # svr = SVR(**svr_params)
     if kernel == "linear":
         svr = SVR(kernel="linear", C=C,  epsilon=epsilon)
 
@@ -125,7 +114,7 @@ def predict_price(
 
    # Kembalikan skala data
     df_prediksi = df.iloc[len(X_train):].copy()
-    df_prediksi['Tanggal'] = df_prediksi['Tanggal'].dt.date
+    # df_prediksi['Tanggal'] = df_prediksi['Tanggal'].dt.date
     df_prediksi['Harga_Prediksi'] = y_pred
 
     # Daftar kolom yang telah dinormalisasi
@@ -150,33 +139,32 @@ def predict_price(
             std = np.sqrt(scaler.var_[index])
             df_prediksi[kolom] = df_prediksi[kolom] * std + mean
 
+    # Ambil nilai min dan max dari scaler
+    # data_min = scaler.data_min_
+    # data_max = scaler.data_max_
+    # feature_names = scaler.feature_names_in_.tolist()
+
+    # # Invers Harga_Prediksi berdasarkan skala 'Harga_Sekarang'
+    # index_harga_sekarang = feature_names.index('Harga_Sekarang')
+    # min_sekarang = data_min[index_harga_sekarang]
+    # max_sekarang = data_max[index_harga_sekarang]
+    # df_prediksi['Harga_Prediksi'] = df_prediksi['Harga_Prediksi'] * (max_sekarang - min_sekarang) + min_sekarang
+    # df_prediksi['Harga_Prediksi'] = df_prediksi['Harga_Prediksi'].round(0)
+
+    # # Invers kolom lain yang tersedia di df_prediksi
+    # for kolom in cols_scaled:
+    #     if kolom in df_prediksi.columns:
+    #         index = feature_names.index(kolom)
+    #         min_val = data_min[index]
+    #         max_val = data_max[index]
+    #         df_prediksi[kolom] = df_prediksi[kolom] * (max_val - min_val) + min_val
+
+
     # Export atau tampilkan hasil
     hasil_prediksi = df_prediksi[['Tanggal', 'Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak',
                                 'Harga_Kemarin', 'Harga_Sekarang', 'Harga_Prediksi']].to_dict(orient='records')
 
 
-    # # Cek jumlah data bernilai 0 awal
-    # zero_data_log = {"Sebelum Preprocessing": (df == 0).sum().to_dict()}
-
-    # # Konversi ke numerik dan hitung 0 setelah konversi
-    # df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin', 'Harga_Sekarang']] = df[['Pasar_Bandung', 'Pasar_Ngunut', 'Pasar_Ngemplak', 'Harga_Kemarin', 'Harga_Sekarang']].apply(pd.to_numeric, errors='coerce')
-    # zero_data_log["Setelah Konversi Numerik"] = (df == 0).sum().to_dict()
-
-    # # Hapus NaN dan hitung 0 setelah drop NaN
-    # df.dropna(inplace=True)
-    # zero_data_log["Setelah Drop NaN Pertama"] = (df == 0).sum().to_dict()
-
-    # # Konversi tanggal
-    # df['Tanggal'] = pd.to_datetime(df['Tanggal'], errors='coerce')
-    # zero_data_log["Setelah Konversi Tanggal"] = (df == 0).sum().to_dict()
-
-    # # Tambah fitur Harga_2Hari_Lalu
-    # df['Harga_2Hari_Lalu'] = df['Harga_Kemarin'].shift(1)
-    # zero_data_log["Setelah Tambah Harga_2Hari_Lalu"] = (df == 0).sum().to_dict()
-
-    # # Drop NaN setelah penambahan fitur dan hitung 0
-    # df.dropna(inplace=True)
-    # zero_data_log["Setelah Drop NaN Kedua"] = (df == 0).sum().to_dict()
 
 
 
@@ -188,7 +176,6 @@ def predict_price(
         "C": C,
         "Gamma": gamma,
         "Epsilon": epsilon,
-        # "Zero_Data_Log": zero_data_log,
         "Data_Asli": data_asli,
         "Hasil_Preprocessing": hasil_preprocessing,
         "Hasil_Normalisasi": hasil_normalisasi,
diff --git a/frontend/src/pages/Panel/TestingSVR/Normalisasi.jsx b/frontend/src/pages/Panel/TestingSVR/Normalisasi.jsx
index a59579e3..d7c3d80e 100644
--- a/frontend/src/pages/Panel/TestingSVR/Normalisasi.jsx
+++ b/frontend/src/pages/Panel/TestingSVR/Normalisasi.jsx
@@ -58,7 +58,7 @@ const Normalisasi = ({ result }) => {
         <div className='flex justify-between items-center mb-5'>
           <div className='grid gap-3 items-center'>
             <h1 className='text-[14px] font-semibold'>Normalisasi Data</h1>
-            <p className='pr-[30px] text-[10px]'>Tahap ini data dinormalisasi menggunakan StandardScaler agar semua nilai berada dalam rentang -0 hingga 1</p>
+            <p className='pr-[30px] text-[10px]'>Tahap ini data dinormalisasi menggunakan StandardScaler agar semua nilai berada dalam rentang negatif dan positif </p>
           </div>
           <div className="relative w-full md:w-[308px] h-[32px]">
             <SearchNormal1 className="absolute left-[16px] top-1/2 transform -translate-y-1/2" size={16} />
@@ -84,7 +84,7 @@ const Normalisasi = ({ result }) => {
                 <TableHead className="text-center font-bold text-black">Pasar Ngemplak</TableHead>
                 <TableHead className="text-center font-bold text-black">Rata-Rata Kemarin</TableHead>
                 <TableHead className="text-center font-bold text-black">Rata-Rata Sekarang</TableHead>
-                <TableHead className="text-center font-bold text-black">Harga 2Hari Lalu</TableHead>
+                {/* <TableHead className="text-center font-bold text-black">Harga 2Hari Lalu</TableHead> */}
               </TableRow>
             </TableHeader>
             <TableBody className="bg-white">
@@ -97,7 +97,7 @@ const Normalisasi = ({ result }) => {
                     <TableCell className="text-center">{item.Pasar_Ngemplak}</TableCell>
                     <TableCell className="text-center">{item.Harga_Kemarin}</TableCell>
                     <TableCell className="text-center">{item.Harga_Sekarang}</TableCell>
-                    <TableCell className="text-center">{item.Harga_2Hari_Lalu}</TableCell>
+                    {/* <TableCell className="text-center">{item.Harga_2Hari_Lalu}</TableCell> */}
                   </TableRow>
                 ))
               ) : (
diff --git a/frontend/src/pages/Panel/TestingSVR/Preprocessing.jsx b/frontend/src/pages/Panel/TestingSVR/Preprocessing.jsx
index 54dc1262..b0c461dc 100644
--- a/frontend/src/pages/Panel/TestingSVR/Preprocessing.jsx
+++ b/frontend/src/pages/Panel/TestingSVR/Preprocessing.jsx
@@ -79,7 +79,7 @@ const Preprocessing = ({ result }) => {
         <div className='flex justify-between items-center mb-5'>
           <div className='grid gap-3 items-center'>
             <h1 className='text-[14px] font-semibold'>Preprocessing</h1>
-            <p className='pr-[30px] text-[10px]'>Tahap ini dilakukan untuk mengubah kolom angka menjadi tipe numerik, menghapus nilai yang kosong, mengubah format tanggal menjadi format date time, menambahkan fitur baru Harga 2Hari Lalu sebagai tambahan informasi historis.</p>
+            <p className='pr-[30px] text-[10px]'>Tahap ini dilakukan untuk mengubah kolom angka menjadi tipe numerik, menghapus nilai yang kosong, mengisi nilai 0 dengan interpolasi linear.</p>
           </div>
           <div className='xl:flex grid gap-3'>
           <div className="relative w-full md:w-[308px] h-[32px]">
@@ -108,7 +108,7 @@ const Preprocessing = ({ result }) => {
                 <TableHead className="text-center font-bold text-black">Pasar Ngemplak</TableHead>
                 <TableHead className="text-center font-bold text-black">Rata-Rata Kemarin</TableHead>
                 <TableHead className="text-center font-bold text-black">Rata-Rata Sekarang</TableHead>
-                <TableHead className="text-center font-bold text-black">Harga 2Hari Lalu</TableHead>
+                {/* <TableHead className="text-center font-bold text-black">Harga 2Hari Lalu</TableHead> */}
               </TableRow>
             </TableHeader>
             <TableBody className="bg-white">
@@ -121,7 +121,7 @@ const Preprocessing = ({ result }) => {
                     <TableCell className="text-center">{item.Pasar_Ngemplak}</TableCell>
                     <TableCell className="text-center">{item.Harga_Kemarin}</TableCell>
                     <TableCell className="text-center">{item.Harga_Sekarang}</TableCell>
-                    <TableCell className="text-center">{item.Harga_2Hari_Lalu}</TableCell>
+                    {/* <TableCell className="text-center">{item.Harga_2Hari_Lalu}</TableCell> */}
                   </TableRow>
                 ))
               ) : (
diff --git a/frontend/src/pages/Panel/TestingSVR/SplitData.jsx b/frontend/src/pages/Panel/TestingSVR/SplitData.jsx
index 3076d030..976f8a53 100644
--- a/frontend/src/pages/Panel/TestingSVR/SplitData.jsx
+++ b/frontend/src/pages/Panel/TestingSVR/SplitData.jsx
@@ -88,7 +88,7 @@ const SplitData = ({ result }) => {
           <div className='grid gap-3 items-center'>
             <h1 className='text-[14px] font-semibold'>Memisahkan Data Latih dan Uji</h1>
             <p className='pr-[30px] text-[10px]'>Data dibagi menjadi dua bagian:</p>
-            <p className='pr-[30px] text-[10px]'>X: Fitur yang digunakan untuk memprediksi (Pasar Bandung, Pasar Ngunut, Pasar Ngemplak, Harga Rata Rata Kemarin, Harga 2Hari Lalu).</p>
+            <p className='pr-[30px] text-[10px]'>X: Fitur yang digunakan untuk memprediksi (Pasar Bandung, Pasar Ngunut, Pasar Ngemplak, Harga Rata Rata Kemarin).</p>
             <p className='pr-[30px] text-[10px]'>y: Target yang akan diprediksi (Harga Rata Rata Sekarang).</p>
           </div>
 
@@ -102,7 +102,7 @@ const SplitData = ({ result }) => {
                 <TableHead className="text-center font-bold text-black">Pasar Ngunut</TableHead>
                 <TableHead className="text-center font-bold text-black">Pasar Ngemplak</TableHead>
                 <TableHead className="text-center font-bold text-black">Rata-Rata Kemarin</TableHead>
-                <TableHead className="text-center font-bold text-black">Harga 2Hari Lalu</TableHead>
+                {/* <TableHead className="text-center font-bold text-black">Harga 2Hari Lalu</TableHead> */}
               </TableRow>
             </TableHeader>
             <TableBody className="bg-white">
@@ -113,7 +113,7 @@ const SplitData = ({ result }) => {
                     <TableCell className="text-center">{item.Pasar_Ngunut}</TableCell>
                     <TableCell className="text-center">{item.Pasar_Ngemplak}</TableCell>
                     <TableCell className="text-center">{item.Harga_Kemarin}</TableCell>
-                    <TableCell className="text-center">{item.Harga_2Hari_Lalu}</TableCell>
+                    {/* <TableCell className="text-center">{item.Harga_2Hari_Lalu}</TableCell> */}
                   </TableRow>
                 ))
               ) : (
@@ -193,7 +193,7 @@ const SplitData = ({ result }) => {
                 <TableHead className="text-center font-bold text-black">Pasar Ngunut</TableHead>
                 <TableHead className="text-center font-bold text-black">Pasar Ngemplak</TableHead>
                 <TableHead className="text-center font-bold text-black">Rata-Rata Kemarin</TableHead>
-                <TableHead className="text-center font-bold text-black">Harga 2Hari Lalu</TableHead>
+                {/* <TableHead className="text-center font-bold text-black">Harga 2Hari Lalu</TableHead> */}
               </TableRow>
             </TableHeader>
             <TableBody className="bg-white">
@@ -204,7 +204,7 @@ const SplitData = ({ result }) => {
                     <TableCell className="text-center">{item.Pasar_Ngunut}</TableCell>
                     <TableCell className="text-center">{item.Pasar_Ngemplak}</TableCell>
                     <TableCell className="text-center">{item.Harga_Kemarin}</TableCell>
-                    <TableCell className="text-center">{item.Harga_2Hari_Lalu}</TableCell>
+                    {/* <TableCell className="text-center">{item.Harga_2Hari_Lalu}</TableCell> */}
                   </TableRow>
                 ))
               ) : (