From 8fa2cdba3c614543ba5bcf802a039ee810426e34 Mon Sep 17 00:00:00 2001 From: IshaAtteri Date: Tue, 10 Mar 2026 14:14:59 -0400 Subject: [PATCH] preprocessing script --- sample_data.xlsx | Bin 0 -> 12953 bytes scripts/preprocessing.py | 37 +++++++++++++++++++++++++++++++++++++ scripts/scrape.py | 8 +++++--- 3 files changed, 42 insertions(+), 3 deletions(-) create mode 100644 sample_data.xlsx create mode 100644 scripts/preprocessing.py diff --git a/sample_data.xlsx b/sample_data.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..4d3b3f5a077d25c8a84eaa9cb148216d88580509 GIT binary patch literal 12953 zcmeHt1y@{Kwsqm|P9V6uLvWYEH9&B8cXua1aCZpq1cJM}JHg%EKJM-Ace~T~`vvcv z8sqG-N1ZiC)jrF{no}MK296GZ1V94-03v`OhyS=W2mk;M0RW%@pg}c-ZLA%QtQ~cf z-E55{Lt-BbJTh$KvMcP!uazaWcSO8mD^wNzDQ(= z`sbIaM%Bhduw`Q-oSi{V*F#DFSkk9ACw?O)!(^+2W!dYzlsynC4doXmYo*>T0ex6F z;vMW#2L)0&Ve50c1}M_uO0B82v?wsMsFGHuIpC|%$KOR!p;yZ{)jbkO9u7^RXKPiP z;(QV&5HKqPDYjxJfM*GYL9S*(za%vAg=8REZ65l;4BNfr>ZyAqj@_KGRng$2^UUo( z8560JEjL@^(qz8<749m<;p&)mprAaAZb-xESoRL))fL;w^TviY{|d`*e4j9rDdxhh zH4xe%7};zUu-1Hna*gLu4!RF>ajnXMb&mBEj~G3}$@w*X36SKXhZS4#=>{I$5B^x# z-gMzM67QjO8F4iuSCC*M@dEL~>wBENy@3Jb|07K6RTxRG-+fQ|{ad*AFx9a)vUFge z|Kt9D;rYKfCjafPm&M7*bu+>TpGiE24BXAG#vls;T?8e55-EH8O0FQ)N9B=zSZ$}k zLsrHO02B9V^?n{&Uge2893Z;=#ab4Diq1{a;8Gr(^l0YC}vl-*@NOddoz2R zA}-}d>D>C2y7WhJ4sdXtL~Qy(q#AjgUJVxptpG0=lQ+drqfbVCP5-_EWL8M&q&&E) zkt6%?+jyGKd}84N0)Hr%^zl>*#(;yq$zp})fF;q*1FnjaDVJH5ey05=VmBQ_%Z@9N zw05)?PdeH30Yzd~)O+S}@qV)G8y}52){Ef`w;m3d?$UwtLH`JX;xam70E=mSVLu=c}E2c6@lU!Qv(&I16%R1!S8Q8GoN47bzZfB#R$R$VLg=0>XBn4-qwP>E#l%t8WfD7*l(^+rrnyYQNcDnb%VK?pNy>>$q6(eaFCn}P5R@yQYkV5M zFq_g&VD-R~j0(B0ugR<6YO3GhSmx|pD$v(BD_>Bsn0V>LLbq}T6sOVG5usojqRYI zx_wKA-dSmy7~6V!?`~Mjq-Cp#TF}T~IjG|3?p60W2fWXa2gZ>`N|Plmm4VbY4p3Ew z-T!?jzjGwq7$z8e#6&yQ6>a^FTWlYp;B*bbeASXwtFr7`OM1h9zIKeBXIMUqsM3B) z#m1E`PX)3yr)UgitP$*_^Y*Y=Wfi_=J2f-Fgbxu9j>2Hxp4`t$CcWBfG-E;b3xC+R zf!UkMw-1|db{@{FD2P51sYa3o8o*Ru|Ei?2P*XUmLom=bn?bQt(k_GS{d{nHNl;7C z*uBrz>CswQJy$(4I)jJj5lCxVXfv&&#Y;juM~SC%IUlFHPwi^=IS`%P=N&hh=iK;P zURe4uM0BcIGNzYV@b|K?j(Stt<_8~-wA?GMEKz!EuU<@scaAHaF86G~AN7P3)NFa3 znMDJn>EGVF&i{^MKfd^+tM~YAelK>o0BDf+IQ~by`}b)6SM39NZ%yB`!T;{7Oi>2d z^WK`ly@oKlq&Z`tEIKj}AFCW8K@ZkZEt35m$auc|Pf%Zcu_ZukavFntOJ3QH-L?rVDMkvwW_VnY68NUdxIKGdMXUz_sQ z)_4-?$@r70HcY>>yJ>GNbItkUw4S;gZqvW!li1pTDCTzu)rm*systi%$2c{CJx+c= z)o<9Vp#o=#{I69%n7vWOh4LZb>q93MhKx@+iTUGTBTy_P5Z;b)DysrDy=_IhVd$@c zDhH8T9FEk|7KYfn&p3z;>(l9mwESxMiNS&2P=ON+(RC;;4b(ot6jgWqA6I(9<3onc5_dCh8eqOx$*y06dcV zP$qYuEbKk#*Dt#0xY^it^anv@66$@F2pyX~2iS~(0ND>Y+->5^rowN1<^IPPP4Vru zM+|` zy~re=_W_va*EQFeV-RuU?Zi_=U0xBN5m2@oLoGv->!6|R&CvXZuF)>FibvbyZ!?43 z>BKhb*dwx&f&@G2Mekc_;X&gYLaW}l_wHiNxkT1#*BmmoYD=@6CuYh#?n4?7wV8cH z#D`|A&|5ndVz&L$xFAoq!Zy@OqUd>MSW^xoLjuhS*Y1gf@P?F1<^9n)Z?*A5`{iZ? z-cxOJa8Firt(j!1)T#{MGAWqBaE8G7`Dj>FKG)Bve2@pyvmgcM%TK>GCg+Hk$ZvLM z7iOd++O@C+Ce`r?QkeG_wwFlmILzie070%)ad2J;UAF{3(sJdYbh7q$jI9K&DPIH|j}L@+3^* zYARd-F0op13KF*8E~q@~wyunpGyXHGM)Ts6x3@;k?t*zVovr1%ZQZgmu5|0fSI`fS z)h16g69i;OVff`!l*uw(lut+|nX4?V7l zB97Zr_ss;YZ3)TvVC^wm0mYv*=pe9rGeAF3vq_-enmc7Uq^U1t)Am;;T@snMP#$}+ z)Xnhl)>nZzeHR9nnKRzk-PZnoj;{`P-%68n;D||gB`a`Mvj}+9J|YrZ%Hi+ zD{dM_K?0jAXrar!Wg-OpBV@4t!ay50MV$g zo&o0x<8Gje;MJ}k#U#TMzkxl&r$M_PnH{Eju)0i1!1O~Veg=$%e5}q~UlRNHnP&pJ zDG`i(0>W4eX*cC+7^X?_qyA^=`<$bP-SN`3pPIc;O~^_fhCq9RtEAx_(5tJ75vs)L zll)go%lUwEZ!leREDrOdw{kwPj#?ZZv%Z2d7E{(2=VSw5_VHBC&uLh5_O|@?hHkEX z)+fEyDI0;5*T++qXzo0{?ye8=!8XSm9^MOQGqf!rM)$jjZG4CIU9mwN*`br$o>;4v z^~Tw`qlN3ZyXT+~lT}glyuJPu<~n7)_c&Mv08_&5aB_)qrJ4?w&|lgm zKSYG7m4fF#O4)Uh!9VFC3+&In*go0NMk7JfOIm1mh@8Tk@kxw<%c#tI05n=rw|6+! zTU=jnBKF?gE_$&TGT-3vCynx%RT5W-WD|{=2wq?N-(GH9_S@fHmyvW{2cwdVo=bgR zUuPTFU*g?An+H*8zdn?z>G<4SGWguT66k!Yy93Wm+(g4g3zHonb00Bq6)=EJ<4*}s zlawZwrh~!rvkp0o4X520#AU&%kh4VN!-z5Z((zPkf;nF+QHJg`^2``cx52bmHXbw$ zK)U%t1}CRFIK|uaIl=BLQ=9E5Z%5e9#w2ynwUib$6iT&eCUZJv3n`3(#9QAuj2+La zNxX(LZy`%3nGWSOj;NP(26@WFcMOT338JV@1`8}f+j^t4t)k-bl%ww<+g)N^H60^@ z-a^SneNV0hw#SNGolG*zmH6=jlIw#9S^Uw4= z)ScM-Zgk~;9ROW3L}Ujs2WHt{(k2%g$SgU}_LJ%|REoxMd?4;@)1jp;(RGe9ta_p7 z0ldXJ=v28w-%;MR$9T_Z119Ja=~u5=yf~_3yuU}C+>u#ec`I-o=+aUVwA0R^Zcs&^ zwd$zl58qS`PkPJIFbd9M;ZLkfo}5df)(n9%{1OzprWUm@MAcY@Wwi-O8Cm8|Q8;)M zo`psW-u~=no`s}(^8=$D*jmd_iKks^f4k`&R6mMb8K(rgJZSx^na;`@_~GoWt!}X~ z(FQJc*?+eo+pg8$E5^UDSTDPUN`trX0`2VNiI&p9#C&uhmbIJ!rjqT72|hJ5-b~v1 z$=3`#>CsIW6s{3{VSuo6)}}aoj5uA$hmuiiq+mpaflR6?upt(Q{YBYcrqPVA{FedW z_)h5-7IEFHcksH+?^sxXxy$pCSi` zPypqL|^Q~WtvgqOJInL`uyEw_DS`I;+EfroY%_|&)b6mhf@5>_EG0tp(DnGS<;0pGm3@1lC=7@0FM2-v@3WhLJ{oP`75Y|(X~cvf}Ra?<8q zIhROt+b>&freP*(lXhzPxas_WTB?s#|JkVN$$jj^G7cZS#39Y~uC-mHJb5Iy5a(=H zFQe{CA#KT{3|i`^oWs}EhP1$GRGXhS0V_Afv)ny}RjhtCh-1Sh%bt($as9}$C~CCa zC&n-0%@sOstc+U z>L-i-?zO|BwGcls#)cLwZc6A{5*F}kt%GDNCPg*1tYl}L%B_v(5Qj6D^7Ra;ek|1! z*9}4hPjPXNjM_77r_dy*E!hUC`a8F-KSpVLA+tkbw69{T9M(7Mm~pt*OI1!5L*$8V zAU$pF3CM}sO$@YoVt1P%YwoS{CtqaP5dIqVo6o@cTDs!7CC|3Tu`U3<`D#Ph5i3B0 z2XRw{g-9KsH&Hgztyeo`J?owzxPTYTyHJ<5wYK-MnQ z%N)D5npHm;Ua<49IJk0NZwn_l9EFv{Nun&SMOkPnlQJ9W<1hN~^|a<#C8UPN+ftbt zo|&5YB)>im=g)A8Z`w=q!wdK`Ye)edFb0ke|=1N8K*#b3y5Ud5L|+d zO37-^b=v}kNmyLL$Th-(lVM_YU|S%!y%?e-Vq(XoQ({Yp-3!S&jZ;B^U*0}i_x0km zBzX{hxrlX8u%QrrRO6O7QI=?=!Njt3n(Pq69NOl@*5a6BoCJMB0g(&xr)d%i*(01< zq2Z}!5~)Fx^t9OY3oYJVgOEWt7A}(*kYh(=nJBYQ>YHV64&5)tr=8sO+M>>QPZehm zkS_hAz0f|hjU*gnpHJ?(ZL0;))-4m90w=C(*spFSH14$LiCW6sr znnM^+&+&7XGLcl)5xN%lOGxq5y>}#%TUw4%I`AtIH`$_bsgrC;arQh?_VWk@`W->t zOTMErv6k&V>8bhRLC3s4iln*OjA+x;Ts?1GLKJM%ilQF{q2%l)_jS9Xk57!0;OG(; zV91bg<6$4+cTjRbrayoXs3{h7^r^x_>9(Jy%5sjfepaz;?bM-zTM;%#nBvdKk1Q)7 z#KS1ln$&`sCtC50&6tk2a$wY?F#&Vm9T#)x{s`4*=G^2O)oDnm)dIfp=DP3G;d@G? zg}0cBTFH`|1BpzRlfF(u_BwQHdF6+xVjO1maqp1?8M8va1z}lE*ZfMIrPLbGr4*43 zE9~B0Ge9ib>Eg2NDXL;=PFI_D(EH8PbaXU~vo6Yh4;={MYl7*isyHo@rZKUfF?~~U zTfeotPt8$I?J=$MR@Z)Vh|8qPCevz9?YwST+OPtHG$##y#ubUFI-E-OnTu>9UtXP$ zMv-Tt1mc(S;(;{e**;E9i5>)}TXq~&kPg}wxl}OpgjLN7YK~RbwId0}6DWw7j>70M zhi9XFHWNYNk53l$*E0r95D)Df!+mBF5e zn-w9}c{f1FNi{l-c#^}OtTc2{1!YgSdEpog0gocT&9a;bz+FgWN0&-v9 z5H5PV-gvbxHoUxWhOqij#j!t~%>lbRtj+j&Bx%@n`|fCnpNDE#Bj z1Ub$5iRL|bXP|4BW%-ZD7)YPJJV!b?o@uHJ`W}CzRB%X*@bYzUxfTdxQ(GxYDE!7O| z|BM~0w%yZ>bLuH!?0rM@2=K<_m&(fDL!??x%a0&mAk(Ep7DY5UUGW%eGO@qzRxvQ` z<})?h+oSnMjqwtAHV4a*XI-B++cion3gsV$Bx@d=Ifge3VRAMM z>39%c_ULljxL99zFSbqT*Pkq~tn(hWBIFhx<>)g@&L^j}A-#;L=A;u7ik!j+ui_79 zC`%2*EmUlOG@bVMpIqLd5^RE5#dliXQCxk?>%!R^R4d&YTwLr92?;4GvR};N`tbCG zsZB#NKUXqYc*O8=Ajs__L*}{4OhahsOH#|R?%PJE;K#iPZD$89^1^*Fb@h}O0wQ9l zE=r(q@RVxOiU}^pT76!bgOQ_3Khqp%o&(m8@`IV2uIKo8+6Aj7QYyCFyt2Dq{U&T9 zVGCGV0WW&K?C|P$f>;xpRfrmPL-SJVK=W?e+-z;4>wlm&EH0 zs+8{SMJJgGn(oJC%sZB$6nfa>G6T@!q=6O`La(UE93 zHzpTFngEJCUO{b@^0;xfx)2I#rg?x}NKA-t&K#oZbBf(QWn%jd2lPHNuY5!*A03kq&gl+C7<9z@inAkSv1O7CkPM*p~GXEJ4i;ZvwU9C=0?vQR&+Y0E?WKzcs7y++e;D<O>~62mZB0>+ZEunEz#nOVd? z8Nj6R?>}NqDQr|)-9URp;cAgEqi>)Z2_d!UaTl{VLKn$rme@D#eVY;;XOkKY!@s^m zpLef{c$F__&zl#-obOON>LF)>7PN+ypFkjO%$XqK5sDCC8!69Yf5=t!6GbbfgD0Ej z2gwYE^K~pJs#yAz^hEyI`D5!0WvoXQeaafQBW0d|sC8GhIx#N%OR`&wEdn$kL(n?2 zt_YD`KPaX{MOmV`=af2zri`d*WJqm38{9(cb?Z7!8mkV(FniH4Z`p9Y-Kx?2h3q^0kMI+Z5?V{zaT; zKW!ce`~?CAQ0umucg2!E`&5RE+~mP;Y`)~(hMb;6Dql$3Ddy`DT?+>fufzu5MnR~S ztYJ-MhYxo~&>IZnLVVaINatD<5SCQg8L75>oOt`RJnqci1Ds27DeA0_Iaa~E69!LR znG@z=`sB&5TehSP>J0RC9Y`cf@8eNQfzqH1dqfnXCFh0E>*FbV1|=P@pkjvM3hEi6 zV6II^Ne-!nKJUP&p$O%QuDDE2T1vb}K^qXO^@C!FtcI?l(qpbYazSb5h(m0(as$y( zsvZ=Jm-e#Vr{YxV@>+WEi2_^hS;aUv6!BN>HxULBsU4xW^ zx2Z1W#rEIAd+-S>N~SAB6!_!&BI-%)4T64|>=oY98;LAsb9P!lRgS~+(yJxPGoYi5 zwa}cPJS6|H#}#5P$kgzexk&C%@68-e5Ce*9duQQ@cItQs;xfYQ&cB6Dh`7 zuSRA(XWspjy~&8|{&2Qe>z?*;&&mQ~=Vk^+j7kUI8^y+U``>n26MBdK1n=D6z&lS! z@{dmI4~Focq|ZMn!@sDXKMBL0IHq@z1agoI>8tQI4CHaX1auC$7OWx^b~b)8F`7=C zQhKdXTEoK~X99Aa`7A`(g=4eJnTN~tV#E9(Zo0TI*RbmlYW5IiKDkNh&h#iR&@(1K zpBV&;(0xgew!1a0{P9fR4Rg;FTh~y@H-u2h z)HRqp%>WFK)Ip)05xN;VU}8X2+PFnpb06$(;p4GiS1d-?r+mOEf>5Y0pA>LjU;t+? zq_z9g7J-B`9tYP0@S9bS6Ylq?YL1#GY+B@X-4IOlA+2-+vR&ERnwAoUJEIn59D#1! z{s?U!AkPO363-Pe*SJS?vD->)hAOJ{sG}i_%~O(Y+oiUJr}kfPe>X-i)?mVDe?MPV z3;=-QALncP-oiQ>*((`2I{wkiGW@n@qSrUGK8|lUUzSJjH9MQGv(Pn;mMM&|cNADwwsGpTE=pf<4*Z zN0?Pau+4Ug`JRWGC}@82R3>W^5Y0SkS6Y%8xqxuO6WD9dkA}R%EMcq;A-7OT_4CqJF;6W^ zi#!~0+C_L|uO)Y`J@&`fnr5MeYo(O-4-0SZwu^Dy+yf*YJQc!Gzywg@7wX~V9Q|lp zKD@ULko069HHXir4#zd^H?h<2&)ZO|dpw~g%dY%zOA?Uw>&J8A6aj0LbCLt>V`GZf zjl=F7(yFb21G_i#@9Y?F#}hA<#Rgy4a`$jG2V0?^QZZFKQL|4_{QHG#_0gN8PR*!A=-rpJ<=MM z!vh<@5_q|g(<$46wyh)BeI#;M+giA71D4U+O5@B;UKuKz$ z;!%fcT9Mssnz}5=-wL|;Ua`_ufy;5-pu2P|M2a{H*|QUm7FoFiOt5idvRk^<<2DH@ zp=egKz*?E@q&B~jJAUfTsNwq1GwEfk&)Q&>R#(d>HjuSBf77j`!-iS1i~**cl#XKT z=Wb=uSd^P{#+u6~f=rfay87|M;q#|5Pa5C#j|?YCi2`TC@N$5!LOjgzTr>=|Kc7Zn zXWde<>^?=*I)0-Y$R)h$)lAx$_r!Af5mSWsMv6%~KIq9ulnLS##?U75@;<)%Z|~ES zgh38__db+&nh*Kky-&~9_Wzvk-Ru5&rN;@{EHlCfoq;_Pz^{JbT9t?QE7O-yyROm$ ziEA*CDKyBbAq_2yJ)ZyCFgdg6ei*gw;rb{dxr+Bm=Q?JxS3Ybf7aaopg9X-Yg6qPn zmNy1O98CQMlK@$??=LYOPsKDmG(&q|2yyT-5n#NkVy;yV%MV?ys;Qn8oL}r`MwYlH zo9s(Th@gX|H7$v@gwSj=NeAeZg*_^A1PJAM`1j{_F4FL2vyJgBwZZp^k43dy`j*A_ z-c=h3=@H=v4Z1otd3p2+>5b+VQ6X$lM}4l~Wb2TJA4jU{qU><$56xx+3XA=9O<$+^)&t09+XBJ1TO)cJd#Bk2G+ahA!!23&Vz7I&fy;$T>NeMGvTdYgE5 zdjnvv=IrFt+&#lw7XyqJvYg9)HlG~EIJ8sb9w|KVe;U41lS((;K_;FOKV2=LwddXV zl$YlWiyt6lkN6N~cx{-UhzwU#t3n=Uui6=TUbn8hZ!X;xyy+jbOjyX)Uu$0fr+|Wh z(!Gy;{$5`Huh;dj^>4)X^1%ND_)p>QzYPCai{4}6-(7T