From 8acfb436f3f1b1faa396fd76e7c9c943924c4ac9 Mon Sep 17 00:00:00 2001
From: Joshua Salako <salakojoshua1234@gmail.com>
Date: Thu, 1 May 2025 22:57:55 +0100
Subject: [PATCH] Enhance API with data loading functionality and update
 README. - Added `/load-data` endpoint to load transaction data from either a
 database or a CSV file. - Updated `SalaryAnalyticsPipeline` and `DataLoader`
 to support loading from CSV. - Implemented data validation and error handling
 for loading processes. - Revised README to include new data loading
 instructions and workflow steps. - Added checks to ensure data is loaded
 before running analysis endpoints.

---
 .gitignore                                    |   6 ++
 README.md                                     |  32 +++++--
 .../__pycache__/api.cpython-311.pyc           | Bin 13755 -> 17046 bytes
 ...consistent_amount_analyzer.cpython-311.pyc | Bin 3644 -> 3697 bytes
 .../__pycache__/data_loader.cpython-311.pyc   | Bin 7220 -> 10181 bytes
 .../__pycache__/main.cpython-311.pyc          | Bin 8617 -> 9871 bytes
 .../salary_earner_analyzer.cpython-311.pyc    | Bin 8261 -> 8276 bytes
 salary_analytics/api.py                       |  82 ++++++++++++++++--
 .../consistent_amount_analyzer.py             |  14 ++-
 salary_analytics/data_loader.py               |  59 ++++++++++++-
 salary_analytics/main.py                      |  34 ++++++--
 salary_analytics/salary_earner_analyzer.py    |   7 +-
 12 files changed, 205 insertions(+), 29 deletions(-)
 create mode 100644 .gitignore

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..18dd2cb
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,6 @@
+transaction.csv
+output/csv/final_table.csv
+output/csv/high_earner_details.csv
+output/csv/likely_salary_earner.csv
+output/plots/consistent_earners_predictions.png
+output/plots/hypothesis_overlap.png
diff --git a/README.md b/README.md
index e4bbe3a..65fbd4c 100644
--- a/README.md
+++ b/README.md
@@ -46,7 +46,6 @@ salary_analytics/
 └── api.py             # FastAPI endpoints
 ```
 
-
 ## Configuration
 
 The system can be configured through environment variables or the `config.py` file:
@@ -89,12 +88,26 @@ uvicorn salary_analytics.api:app --reload
    - `GET /`: Welcome message
    - `GET /health`: Health check
 
-2. **Analysis Endpoints**
+2. **Data Loading**
+   - `POST /load-data`: Load transaction data
+     - Parameters:
+       - `source`: Data source ('db' or 'csv')
+       - `file`: CSV file (required if source is 'csv')
+     - Example:
+       ```bash
+       # Load from database
+       curl -X POST "http://localhost:8000/load-data?source=db"
+       
+       # Load from CSV
+       curl -X POST "http://localhost:8000/load-data?source=csv" -F "file=@path/to/your/file.csv"
+       ```
+
+3. **Analysis Endpoints**
    - `POST /analyze/keyword`: Run keyword analysis
    - `POST /analyze/consistent-amount`: Run consistent amount analysis
    - `POST /analyze/transaction-type`: Run transaction type analysis
 
-3. **Report Generation**
+4. **Report Generation**
    - `POST /generate/reports`: Generate all reports
    - `GET /download/{report_type}`: Download specific reports
      - Available types:
@@ -105,12 +118,21 @@ uvicorn salary_analytics.api:app --reload
        - `inconsistent_plot`: Inconsistent earners plot
        - `hypothesis_plot`: Hypothesis overlap plot
 
-4. **Model Training**
+5. **Model Training**
    - `POST /train/models`: Train prediction models
 
-5. **Pipeline**
+6. **Pipeline**
    - `POST /run/pipeline`: Run complete pipeline
 
+### Workflow
+
+1. Start the API server
+2. Load data using the `/load-data` endpoint
+3. Run any of the analysis endpoints
+4. Generate and download reports as needed
+
+Note: All analysis endpoints require data to be loaded first. If you try to run any analysis without loading data, you'll receive a 400 error with a message to load data first.
+
 ## Docker Deployment
 
 1. Build the Docker image:
diff --git a/salary_analytics/__pycache__/api.cpython-311.pyc b/salary_analytics/__pycache__/api.cpython-311.pyc
index 8baa4c248879272f50fa658d510a0f2656f8ddb7..939b1f5484e841baf58e16cc5c546cab4e347314 100644
GIT binary patch
literal 17046
zcmeG^Yiu0HdAs-AdyvOFK8`PuE0L0TB6TE1iIONvGDVTHY>`&<a?Ciso^F@aNyj^S
z_h?yXQekW%AzT9yQWsWH8&HeXkr5h|0lP?m1h8eh?ay6d0UZ_~V6-q$qy51^4r;i6
z`hByH+dUo?+G&9R$#QmXcINwLX1|&F9y8za=T%jH3a<b8toG6~F^c+kd@wGro_LsX
zQPdk0M@>;2%{emktYgYC>zs1Vx~5#S?kV@IXUaoknKR>^Wu_RCc4d6C{wY66yEB2=
z;8c*LJ(;T6>Z$74&{T*#dowjtHGu2Qgr~yfH!>9=zqM0!<hOpRo?|#)reQWZ6$KoI
z^Jf}oo2HsbI*@6eZJBBz>0qXHcFWWjlCH|M&9+aq)0BhaBbQm@r69f4NORRIp|>3r
z^$WPQONZWOJo6oI(@+k#c1?9cZ4R!63v-c`+P9rh2De_eo!@?Yhw)_n<^5dU49(S(
z7*Z<@Z@U2#ZtWtiM&E{qUl>``)K1Pj)eLtR+^ul8Ij9p97rjAojeM}I<rvp=gPPg}
z?RT3MSQ1>b{Vlkb8&p|qJ%GF0f?_7Q)-v2J>u}>6;<lCHwy(qO1>8QfF-wAD`Pj-<
z`{;1n*5UVWh~H5GzjGb_o(=K0SHRz~4u4=n{GAo>yLi{MgNxm8l~I51hPCXfP)ql^
zUhD(>%A?m)HUhi(LFhqzT@Ute*n{2*J?LB4g997l_m}lxkQ?9!xxKu5+Qsd=;Vz@Z
zLC$-YitR6S`^S@Fe&qB?HaRz!NvD$ebS}$I=LA+vW|G1+HknOkuI1AyG4B5Yr%lYQ
zdUX`F>hW{uPLI8q;^z=c4IN9SuFMFz`7C!XDP9p(|M|I0F3F9jGra1;I7X{M{5`{q
zbGfXD&()((ojE&^=C}-hH7Q_@?^sggCvqI0i8)l}DN=Vbqq>f#Q~Aj+kVODc^epM#
zh|#;#={Y`=&XN|MI)Co;`E!ZWBj+AJ3!whv$$at@^n(}RDWoBu7I+To%VAcXmNk|X
zvb;cQEbu~M@Aj^wn98ST`IyM=X18}`lV&o*zrbfK&$GNJCT9Q;dh8~Jst0H|o6HyV
z%2~6gED*aejub~K6Y>_)*%?T2?3~sseALN5m(1sRAuF=eLT;AL3(2gQgigU2aqw0J
zcYnMu-WPMK?tD5AR1R>wm=e<3cz9pn1rY~^-gPeKQmc}gOzvtTC!}Z6Sy2sZk11%9
z&*sy~jA%g2^7%_S&V0PYBk9DHg=tU*Gk$mma^IkMYKjK2<v0(*Y0AmFcsJ)5h7!&>
z<>9?N(`4d8iAyi>L5a&&;?_!FVtUjXLNGBc8gr$v!$`5SI5|q>10a^qa&x(KHZR6i
zuRa=+stakP`leyVC4i8ZVt$oLByijk3DuuSKt1zNlu(0-#Pjn>GNSP0O(eKn3KC8+
zFQ}nJBALzR@?>R*iG;wy%LoCCf*7Hcdxv@mG4=IhqeIW07lByM9v?e(>e=JDt65wC
z;<MUlLPh#wTAz`eOULJ~32j&<M*H9vPeQb0`765mBv)Uts%Gib(y1SwDz>yQ9bfLc
zx%aiW<Z6c?yV{HG9ZM&dU%cgfZBcS{K#)lc2?6vDt!~>;x*!*a^WkF<y+P$6Hm=L2
zJYEXtO(_b)>foF!F1yTlndWF1ICr6c^b()C!ltLm3}s<#kOVx(UgTlI^Q<tR&1&=A
zU@Vhg+=PY-W0N@zMT3vCr!zco0)nm;Os54g&(4d8p1;Jiy$HD*2iY9|_&W|YAi`kH
zi-{CW6V=1<`D8i+ON5!zd4%fVrUiU$p$j8ImR*oi!zt`~0xL{toe=gw{vo)<UWk^c
z&%L1=FG=3!)#{dFV@t7iYR&Bo`F~46^d&}Xl+)*5b5cwT0FjziFZ4#p&(GP2jw;_P
za6eoImFP)|2EzMnq`z&F9-z#NqwP$drmVwq8HbTvc4oh5hr%}}*8*j)ZIQMP{suj8
zEKq+-z2&fDLO+a3;dcW}=K}pLF<sxHHTSo`@q7y$FTNGWyyg5BxV~~6E^wCWpz_32
z&<NT|34MzW8+APvQkzN6pAVT2)I!<#RHFOK6c<=@Tz6chuTn2MpP{bOv0$O&WHybm
zAYI_e3Nw}r3j#-<$MHg=34{yL0Ex%rh1RpY07A!H<A8N3C+3mk4zYz=z4YX1Hpy`U
z$V|v=)H8ukBvUEKOJB_JY%)Joi0)=D<@0kxy|Bzv$qZIBbfB-V&r;C8XFtlnc)wQQ
zGcgKoEoZBt7qDsb#W+@+CoN6SXEN6c4P$};f|#2Zh}hK@>kvB`V^mKjH#5Tvsw<tH
z&Z!<Tm%75|)xZqONA0cDD*fT&HGE0cSJH;uJk~4hfKfr_V`BKza|!+RRhk!Z&9W>j
z5C&AG(>MY8MK&)Sg|bn&#ht(n{saD&s5MW>UA@Xw|0M8gK&p$&Os~T9N=)zXJXBq?
zQoCKQ-Ko^>TxM45Ta^0Poi4e4K&c;C_M0e&?;eoq4nvTcBMNgwVvd+agLigGb%PLO
zX1~Jhmze!#QLoJODNLWl^qE<uwjY(%f7>tB^=m<9_9)CAiP>W!?3bAX3Ufd*!dI(-
zx;4t-t}aCg8+<h=)epX#y1VtA>6K|nLNNPSWU9V`Yt0R4@GCX~!EPL<k9(<4y#6uT
z`AN9@_^|VnVK=0|rh8LRY+gwGSKxkl3?hvU+m_lUnJ~)3G)g~Lq54cNmoG`9LWAvD
zpW-|xv_pf1_NVzwDmM#DEyrp)s9jBb$048^APizuCaYWmG$i2ccp7eTCq&u|ftlbA
z{P@Y2pOk94WLHda#Uxj(7_66~2c*D3$#sy3rGmE?^tw#`(*H9(8XhODutc(2=+ag(
z-=q&LHX_4Suhz?J0*+8Q4T4%>f>bV?0Eq7+EpW-LqeY+W>Q`L-lB>TMth<?(0<7d>
zHB!{{YFaqodxgJtH79Uj6I26xA|?tdi7-k~rFogcTY>pu3UA9?v5Q|2jv(ZX>$W9r
z<bg)DUa(u({B2WYmoTWZodpo`mYO$c#gRw7Rlmx`KZr4B1u<4-z(X%xocmEVr0Erp
zT`MHwth!VKh_eY$Gps#jN~NU~=grrao)*feQ%RiV>r3z)^C;{UpS_Qux%wCB>$F7>
z1`6>r^I2A(4!bXc8VXWFGl;D=7@0R<exT$-!GRJ)N75`iECac??MZE7nVBps`?(CC
z=eamLjs`RPHN%3r2s2qM?A#dICc0F23Q+UFC6JpCyQI*fNwc)sd9%qO_KPoJjtaPc
zF&PUG&DO$RaC1nl1LZuSzkp_}zze9(44>5ulOb#e)nOvmhz<>{vzT!NA`!>ckYyo#
zQ5p3K-+@A0N8-OhWJt4sdw7*;l9?6-RA#2dlni@hW<X&EBxYbW6nzltxgYA0LvbY(
zUv`-=r+!oW%X7bK`gN03cS;K~GodgO5;L(HYA@CuE=HQ(8n~7Jn}cs2l)~FVRj)x+
zy#`hF8ckLI>URtktVd}xT#8JQbLfMCyU)Kj_&&&+Ll9(USYd`GW*D^pJI)VAe@VYL
z{{FaBeMqi8q*Nc0m_vpj8ivF}G;MDj3mmJV?$!85cRKGik1(U#oF8v<!$YCjWI8F>
z2}z525cs>3vpArCW;Q^%KP6_<jm)Mr4Ond&*miqLoMwl~Y1U(yP{4C~M$LI;RA>~h
z=RU#{KyfhLH-TbfLBf-OC!9j$?I!2hxL-r8Fo6h<;z4c5gGyB-G-8<CNO%e>AloDr
zxRG!gN^NYY$zVh4sua#6EZ&=8NW(I7SYZxJ%wfWi2JeRk<<J2obil%pE_^!hVg93o
zpB$9xE@(k!o>rKrCFW_ukWT!e3~B5)XFm-8>cX!tNcCe7WM*7p#wBKaQw&MKy}Ck^
z$#*P*Y<K?J9RFvw1N8Y*Vmocfb}X}i#aUqL3-Q8slhbSr1dOKpoMl(qR>ekqrf(A%
z8?l*Alg(_{sm*YiEy!goH6*a(-<ruZ8ce3VM&Y|KrCx!1Q#{6^VW85p?|x{X9NMph
z_FH(&`A<7O<UWdh5|irAYe8l%D9i<kxj=Z#_#et+j{j!#L;6?azaE$Bk3*1|F@+hE
zn6YobW5T^NJRGGY^L($s&*g-?sMcIG&xR6tJRC|{>?I0q0Ho4G)KLFuEGoO5VzF7E
zr~1W}ZM1={XR)w2N8VyREx@^b>A1tb^;ZUGITo?QK^^W=9h~P)=Ze>E%~Z6w9GkGX
z>^4)`d;MOE%V)E=%CJ}b_CA8ewSMcd{e(Ve3`2`2=W(n)gW`oPCOguySbdVg2^ZQ}
zZD+KpW@MwqX4&Uc1Jh|ZeSygb`-^H_CVhp^TubQZGFnq=BoD_tnZ%{^%%y~uCBoKS
z6m~Sz(`lZwLyKyCrAkCKXvNobqgIn?t?T+`m{psxoa{YF=%mrKA)*&mP>Etr;Tf2%
zs@H%fmYNf?%x%XSvwi~xb%DQvTl{Z`3|lR<fvq+mGkX<guf*(KjWj=q9K0VnC`S${
zkweQ~(^lInGy4=~pTz7VTx##<-SInD?=C96V{-Sn(mlQ!>$&r^wC_n}_bE9xp~NPN
z>`tj`SYZ#Zd0i3M55&mrMFS3^FELu9ygvU|zpHtK0XJ+KY4yWWy+wuFi~%QV23*TA
zmb%CKNB2AL?E(XCkMrX_Zg?nE^#Zd`XM4&1ko|Pj+#vet9}zp-)HYPv!YyZKD`lq~
zgxTOJsD6>{9s5QU(qi4kx$@ys=K77O3g=6;C3x6`dIWa)78EcW?;>>_&Ns|+4yMq4
z4#&>mG{&(z99L+g880-O%!cHkngk~Z*%{<CEfcsUC~A3SY~~$W+uCh1SG*nHzTEv4
zcVXH{W5!x9bxzxg6gM<}VzjmkgOXK0PzY*OX>TRWK*7)97C(W=Sk?XwR&}4u^eari
z#PqK+H4m8H`wSccm^u0ZM1N^dA9q~(*PISqq7Z$F5$vhp67@V{i5~o*_U?DyYk0pw
zsy_%pW`-1INMeRIrEX|TbY#~^FZEHcf7Ijr=pZan+W9f<hKEA5m(x$+dtcHx8&UHX
z)qv&6rihp;cM=%n|CJ)L!HKD5gO_uZgnHhZZ&4U*`4$DimTyrGZ26uI>i3rNIp$5z
zBE3K@&@a$J+@>&8+<xYK8@!iQ0rGQ!m0-E>Uw~Fh?ZWA%g@ar+`Ni#u8^h%%o8o4A
zTD9P)sKD5JTD`ufHY!wB07DzpZQ)l78@-|BoEH|PewDu=SF;kfyCD*;+hD*`6ydr~
zTVE@WSR`K}JGD^8%YQG0Y9EEYo_1W_qVu}b!gcElErvskMMu*$j(DMc1U#K)!E*_n
zJHQh}U%9&eH^i#77QHH=d3A`wvp@#ndl0En%Lb3Gyd}W>EUz}Dvl|sfFI}6<fhP&<
zzb0~^=4Fy|1SjSZ{sQZ))-^o6KCPjUr8d$)*wz5a3Rx<~j6(Db(M~lJ8@!3YdkJ>^
zhuHM%z^x1Q6-&uBnTd&BOsoadM6wqY*s~U`S8GP6A&ZcB<Zf~G>&>O|e111LI`PR_
zP<CDDC#5n7Ne;CAv*0I}By6+LtjRQEWN@Ig(bI+6WUQ)Oo}o{Ic3^-rQg!4+LBNEE
ze-XC4MFH2i%Ha75wk8nubqD0dT*4(R@?%Gc@0Lg$tuz6Lb%FA#%eauyAzdF9u0ioX
z!7cs+(AE%hTQ(4Lqj#@Jb)yhu=D5Nfmzd+9w{}UfBTDPh)wW$y_lVMVY_(<Qohqee
zaJ9W#>KRko$5*%Rmf|OstxuRaYgOI`)JPlr%l@?p6^!1xECsqCtOg@LIrZu(sp+x1
zhaiF=2S=3Ph!h-IjkMnxl@2^5MNZ3+(@NyD6g>S|UE8gfl)CO^-)boQ+SQ+2fA#vU
zv>fVELR~0KzeAh#9l3i@YB~Zz4jxs4N2TD=O7(qixC$J*drhi420>;<6=qaoMpr{E
z#c=a#ef0IGAJlKZU%&l!TCVR?>ide(eo(qmjzjb%MxcJ99QQv$jt_m%aX0zij`w#+
z^+OP3=8(eRk;pfY<73QN74>PAf4tNAX>^1cZ+HH4yBi)r)rQ@gUc=D@Z4>h{1@?da
z5vkgX)B+`T+ZeLNd(P}T_|e&|dr-G6`vshnbFBBWv(;KzB&~OSvbY9uZcvbcRwZA1
zB2H>by{d3VTe<h&{EXK2cD5aZvJ>9*@69n~XSBWoIW|E*K;tmg(C5i+9QrJmoRbPo
zrb3TyKcxcD=R>BG&@^}of^)_M5JO|W?PihDhJ9B--~qHyYbyK397X@3%F2BhHy*JI
z2?MsoA1#_aVS)~D9@Lomy5m*hCF~<cMYzR>5E-1VdIL^p@!>%;z2|<UM~=jmNPO8_
z3^gEkd9uV^cFDnRCD<(myLGN|Qi?nwN1jk3Pe{QhOs=v|W(E~zP+|s&S-<a_>;D7q
z4%~VEoxv42V;z7{+DiBaCVKQ(D|N5cKRV#Nw*&P5xbx$<8y*V&l7lGtd|pHku6ZE^
zzUU}bQr5*|vXP%!^!^2K%K%+CoQLINT$Np40n&Yi)F;#~&|*1;XZ>`xVEkhq+BB}q
zX0JFe$CSG&?4uSP3-oOZyn$El4)O}c`CoEgpx$u)$hGKPa8!07Dc1pM@Ep8sF7`zi
z=f^+0{!UZbKnK-NiLR>-&2NyVo}p;?0}ob<CV$)1<V$^o;}!RUYb9W>anWYaU-lXB
z3+wzovwOii(qj8R3f8dpH_@lyN|l`@F1i=oWusWlh1QQEexPJ^Jh8TQ*|aX~b%UEt
z<Sl1q$jc`EZd+KTL67n={-!N+wQsrzvu`ccNSM7RkLRiSb=x8ej64{(x_n3JX`xJn
zRJ0wetET!<*cIsNU-Vq}*ldTd{iyMs0*7zi7aYHb;M2hV!FLlJwo!*<!H;wF>;<Cd
z#tA%$MuZu0h@`LzjR&w@pz_9s*t3KqusPjZy=y0TaVJ)@GbO&TGiD+o!(h8gpR)j_
z(GVId=q%253H<Z(Y51H1ec$y~z^m0#6RGYDpPz>hI!YbF?@*v4#NW;A2-XM+Ho=HF
zghime>V!TCJ&-DN=-r;32Y>jByg>(B=ZOFleu&`R<Jf%zcuvT@kVc36tC#pJ={joi
z<ognMr}2U-4(-5)EZ{kh9!kJ9=clLBFHS-?u0w5_9*!M?{U(xu;<8XXPGqM^4IC3;
z0ZZy^28rfZ&laj!A$L_Y-WT-!F{~RMnN)8omzkf1PgHyW0<Hky5>u$tM66C0GU7vQ
zEJ9q6R0a)493nL`31$R$4jyv?e7%J4t-8Rp;Z*lkAq_9%B6bFGcJg6m#Mxh%$7VhA
zS@?qJisoR@kG;7;vh%qN*eaTBLfkP;2dJ1=Bft+3&WD{ykY2zGWYM2Ttv2(B4MXUm
ziE?C)I2++2uD`-xVuKj{C){Eb#DFf(8@IZLi-GX1EmB|y1YI0|Uy3{@N1jt6&q=}O
zJ`03zo`3b|^3mISmkld`mm<@0WLk+#OTlRq;PY^k67IP>_TdgGd{PddRKh3WlZC3j
ze|@INcK+P=_rAXi{45|fcbA2m-eOJD8=;?uZhPgLE~Tamd`pX4cm1sGX7!pE&`BL6
z0{^P2KJc%y=9NlIDfHN_1m$;C?OJW#_Mo}velzy-IjOlvZa$|ppS$UWeZ+9>>%LoY
zxhAI6#3T~F`fJC!tgpWMyrJzuL)ZO=uDdR&p-XPqr!?$aKJgi<IkfL7S|{R!6q%GG
zlS*V#3Qn$hs3=>EPQ07?pzHl^IetWmACaOHT3C&?zy6XE-Sr^ae?QtUM+cPXz-m+L
zTi<>2dva4uX^O4++-N3g5!y<@N7zbx-yOY6zcao9N344xl#WI=rSn{X336k^KL&fA
z)%%Zyo%h^9NZ$*)j@5hb)jKiWNMpK*q_?z=R#W#5)<gcs)eWPa&W}5fA@Zla{u3VO
zr?6pqf_DB3?S==P(M-mMgzeCX>Yavf1L4CY0TmAIiy2f71l*w%a0aVk9U^YH%jzb5
z)X1MTzwC>ra)KzJaEC8(u5n5D<}4-P4w&kJvv*)YmT#(XJqr7=%!@AgP^fz5-~+j&
zs5<62;YV2FnuQ&C0ewqV53IN8^o)RJ4txS<e!e3JD9h9u{ghANNe8EVR3X#`+u@&f
z_75Na2@z5Y$dhzxl+>%bPEL+LrTW0t{}lNkK-dN##CKA4!d{A64gUOz(whp%UIfBH
zP_B|a5tYehEnfYq6DlL#+r(`dwq4+Z0^%V_ypo99fRIAu8H~^xAln+6+D~{z7v`DY
zE`7}m!zMp`&2~h18wybNijA;OvgV{|dd=aWU7+AY#8C7kEm0Gj2}Np`WDiAZk7N%;
zs!g(oBDGbj6pEB@iTo9*swMJQq^g(5Uy-Vnj8LRPOXTk}Dkj-Okzyr#C{i7gJrt?k
zl06iu1Cl+!N~i0Vyb4uY^oL*TDF#NsHI#M$>!KaNx@ZS*CWsiy-?AK4e9gBG$i7a+
z*SX~R%u}^AQ}naNn(r2awXjLz1uTeQlf>&-a;{ZVwCe#Cxlcuku1K-A;pX;YL$mga
z4{HI6uKg|L!Db*@BN1#Cbx472a-dTQbS^Q_xlrv=py>83If}JWiK;0!ZIP&kHJ6L-
zgngKG(amen1-cWuU=#&CG_WEwssZoTAGf~Tx}28jMul!%bA)L)P=)BXPRh|_=IlVY
z=*!XN+8?&wXkBwS=^-S<5JFWO8GZw(Nv3NRx)#B<BG^_0t21*5T;t1)lD}2jeR!!+
zrjID}ku^sZ4UV=DA@or*rwwZ*&^x64ClLB^g?`))eUdh_O5oe2!EppXq0lGn;Ew~i
zo>c<hBE^p&IJA5e$uN8;frNlA84>pDF+kOd*9c9ZW6QnLt|7!cq|k@f96>~Z2%(3~
zoK~GSl5d+#cPMnnnxmZ_zAdg%@KcHqsnaN3I|l!hfV_KI6E%neQK<>c=`?_QWIC$Q
e(KSa8!a;Ovl>FSeOnyoc;=`z0AW0eF9RCa2jYvTN

delta 4235
zcmcf^TWnm#_0GNfxVwAz>GeMBwY^W<Ydf)x6NnPWPvRtiA!%BvT@)=_-)m=+eKC8T
zmy(#Kfks3DMW-!|_()JiC?u`ahDucYG!8)(MU{=*mfjLk`ce7-y8N_KfvRWj?k2Y5
zeDsI0=iHg|n3;2C&SSs-BzgUS<0ZS@%3-_lmUAB;KIaI`%?lj&94B)rP9`#+BY8f>
z=Y^DzH>3=N;e?zqZ%Uc;u_0&9iz!hb8*`StHD%SurkpJ=rKG$)W!LBCoFnBxS#!>r
za_V1K$|Z}kCFjn2QXb?HWoxb>?@i5l3CDAaYkwm<7Hc^6RYx2r+pb8Lc#gY_z1nKr
z{`y=ATp~!vUTvu$uExuD*&#cxxGte`m$BDqO-j?n=K8Gqg$p**gd)oB86tahh@&eF
zmy9Tgz1r}+=1hp^wsW%g6el+-)>R9);KHqN&equBTX`JWe~P<=i(IZR#iiPiH>~rn
zI=URZgEvy=g%3&87{ytPNp^>nmMbkQ4I{VSAsxTP-?j#S_zwO=o!=N?{BV(v7~AW(
z{@5C8#1+FdFDFhJR_WMLm+Ed`L#pGBojZ|Vx5>KBRrX6NN!+39jvcz{JFM$oV~3tQ
zcIcMPd${B}_<>=72=KNc31%a``ZHq_?_w{4S{PuiK|}DKdD0qWLk7BFK>Ug+u213L
zmMGsTK(qA$c+}_MGXh-j^%=@Zm4kov4#OYXoUW5Zbs}@E?HA!%htF`FQ=Jgm*a%0O
zo$#VH!3)QrKjed5wy0n@M&Mh?MjW4kMeBfBJVu`9WD9&?+ZeR2v<ALIX%83UR0(>e
z79f2-!KOAsq^k*j8TNWlBKbIff<HtKafgL(aED0J4lhX~vFJo5n^WYlS`6ok896Lx
z)J#~OrP;zvxU6QVI$MIjNWa-)(@eSI%#1=cL$)woq!MbOiKT2w$z=<QW?{l<Caf71
zN{dvpY&$%ql+<jo0N3qto<`s^d&gXYiP>ulr<H?BL8TiI*N45FMOXbR{yo7}#0I0|
zrs#Oq_OxxmyM9sZT@rg2#NL|?U5gDpOAS4z#hXt5@12o%oRLLmY{?m`aJ*%V+>|`e
zKJ@fM3&E|6($JDLv>*-L^fWJoMixDzOP<jMUK+icaX5)@n|qs|yWzJ^xP=>$?g>eF
zQ!-At;VI`C(gYq?N4ygcM3W4}7|<_SKfHk!iz?lO$epm))kos+jO*2o`_|x;_9>a1
zx-UJoPnkME2a)3u$hvz`;=Fq+{~E!!GHf>>y4EfVkcmgharl!pF7T=ab|;$Pbh95m
z>XeKI*;vE8g_!r^E`i|7`e!^Mm{m8t;O})d)Yrk-DC)Q-D1{R6(}tgznvh1DLGdQ$
zUgk9$+FzY5r>BatqM2kx#V7D^(n@dZ+=cv_m(CW_2b3d+id0T#3YpxIa<;4qIi;Y#
ze!7k=+QUGE0j9~zJk?!h0LNt(n8RVJTg|D<A63%uxmOJAM9S9~%kL1>Zro%w4nk++
zqJMPj7|+e~*72Y)FO7=hUg5geI35I-Z{W)_T5I6j=3zYC(f)DxBoKsW0#^8Sz+oCe
z936%C1Koi!HXKK=%5=~XjCXHmL_JWfVI{f)skh7n2ZL>aNyNwuyV@eZ2)<1ofTx-^
zd|A4mC&OTExwo$AL`&D*H9gxB`@b~(V@qpb7t?YrO<P)-rhji8;@`cCYhZY62d&Lb
zEbv%!5RBmvu|YIEsk;MTa|ibHt5L6Ug-cj!`2U7KC!_FLBzkwXHb>)g`rYZbxW)x0
z1-ctm(9BdR6{%XL`g>=^M7aLoT{B8Sp&3<4*LfaA@=2!nKM>R(y~8+oE6fcniW`>1
z4GZFin;!UE^c|ml%)`xltm8>xK7@`C7p}*R<4IVIwettpHc<jXwkYNr51Q!pc*Lz2
zbhsV1I7cUsb1*E$1OsLq7F*uGx6$dYQW?Yu!|=~z1pGMBw%k0H<)HzR?eX1rd)i4-
zwFN7>YOXJ-G?Oi)^B8P$Wtv99_pp~=Lr}MZ1zrD@_E&wO(Fk`fVjbHgT<abc#|DJ?
z0pr*vP&>Br_psEu9=_=C2U(!0HJN7zsW#OB>pE9b4J)X7S5ZwXsAoG9_WDxz#b8V%
zAN;n{kEZ;%v%gv!R~h!3;L~_3ba%O2<@M@HAuPe*L^6Ov&m|-9XKNI+WFWE3%Ex$h
z*{$q1)x|Gbuzd64q8)ACI<9tW!m2$U@A4BroZV2pK~|pBn%tmP@gH;@HhmS5bPuGv
z_xQe!L(P%P9#C>e(n^Nn%Pb@5SKS3N4)^uEGRI=s!%1n`H8WdOgF7>~#uv+UKO2~o
z!`U*vcy?}0{AQ-C6f$|GnhRJONE+y4jAWh0vLao|sQbz^gox_1U~8d^)RTf-JXFxD
zj+&Fu$C3U+?B(;fO94~JIC%Bky6+PI{hRL}=H3{#PWXfymQfLN_nU6xgbxOL+xdmH
z9U=;!^qL6=FZjanZd)5{?DOfDlJE1tg=PuP;QR{@{_0>H2Dz3?S;iHFS`O{&Khbb2
z)*o%#RV#VmS|C97g4W+Ox57Q}^qQMx&gt1)E?qB>ZkuvhR?zLmYv%Io)Ra=LMG;;%
zk)Aavi<3HdgW2Rm1a*(GFN+&+>K^Su%b0_kcUZ?0!h8T@MOe5VHsU1NL&GShnWr<D
z^h;UFf|Q=BDf<bdxoi0KR4JE=g|dP-3m*-(Oqv;0EFF<E1vNWGMK(35M@m>1E-Q%h
zY_;`_W@gnP5;a2}y}eo<nx=|{>Ff-(!;iN{=UNyqD={=7Qz~hWj4Y?~Sy|30hcZ;5
ztmM#bqlv}BvdT~sW|V5ZrI%2ep;RoZlvNOPk^z=aD2uInXsMPW>={*!7h|J10}rw~
z<Uisd#-Z7qGDM%mDT`9&U1*YuKnSVuJTYJ$i9qDY-~zYhZvXJ}p)3px$KmYoIl=XW
z2xB8Xog8ocPUvLlbas&hmPnw&`-r2$A^23__~0!}AG|ms`z111;Sey|@DdrS@C*}z
z@TfnqoVJrJksWp7Bddrzkhr~0JTdB@bCJOxr7IkMZUeT%2r>>=c!rO&V+KwJPWLW!
zZGIxKNVY7IEfwCzL=Z6U!CROn#_T`oU$8_MNo<M4Dts#$yjZSq__+<3P#mdaI=M1}
VKg8GC!^vb2+}@*((b4)f{SOjxx_tlu

diff --git a/salary_analytics/__pycache__/consistent_amount_analyzer.cpython-311.pyc b/salary_analytics/__pycache__/consistent_amount_analyzer.cpython-311.pyc
index fdd512d194fb60677932804ef5987ed2577c8d47..983a4f88f042f7b3f8261505428d9032aeb750e6 100644
GIT binary patch
delta 456
zcmdlZ^HGLxIWI340}%XpA)N7!V<TTAJ0suZ40g}S?i_-=%pe&M=w!%Zp8T9$o{f1K
zBLl<g$r>E;ldrQ&GO|tn$gZJQ%T&VzQUOuRz>vaW1Jwf)31-mb++4^Z&d6vmxs%gU
zvPc#vqsd;x0;GyKfy6DA<otrlBCg4&ITh42nTxnV5;7nOf#m$W;>_Zb)Vz}Tw4B8B
z;$o0J2?+|5Ik|G{JAv#UKN=VwaEo8ymcJ{lzJl+Hw0Vcm2Q~&t**Wa<d1mp<<eS6S
z!P3JE6p~SxV|!iN;F7e#2I-5^wpXNqJm*W&&Nq0xFCd|h%uF&|Ul@SIb1u;??HP^>
zTspKba%o=S()_^6z$y8Gi^0&55o9Lc1u>nA9J&wqg?nl*aL6qFz{SXDJozJc8l%PJ
z2%br7#vpH)PX54?AR@pj`+)(KP??;<>%(X{c_Xg`qwVBVytbwmj9ecWFo};Ku`gI8
JiuiyQ005pIcjN#7

delta 440
zcmew;vqy$+IWI340}$kG<<EG*zL77Iosng72D|6vx9oz9%##b5L?#P!NKU@NE;iYT
zLs+VlA)XPW90WQUvf%6mtYD=%+<Y=XC2SA{s7itvG&wd`bBHrC>P()@Y00U{Uc>@a
zSHwB_DW`(mEtcf`g32P0TQr%9xIq#!K%$rlNF*do*5=BsF9R}v{Agf!z%71(TmG)J
z`U<`)(&imL4}`>~s883Qq`yG>qLAJdA-(HDCYOXvZt!?tKtdmxnS{B%FaU|?T%ujt
zGaMJVbZB4X(!9c@`GJ*zledTc0|$eo>>T#_JhOOa^3CDvVCmt#!7toX-oaPI2ef*!
z7WZ#PqseMKX+W}<XA+wcP_W2kvMO(a2p6mP2L@C^V)9I0A1Mov8j$WH9w70H!zMRB
fr8FniuE=Kce_mTtBSx+d44A}6kk}V25@4eM{ncy|

diff --git a/salary_analytics/__pycache__/data_loader.cpython-311.pyc b/salary_analytics/__pycache__/data_loader.cpython-311.pyc
index a22a258ca905baa617ecef88b9260178a6b27e44..c99c113d6995d2ac6f29b069b0f52f7aa3f6ccd4 100644
GIT binary patch
delta 2644
zcmZ`*Z%kX)6~FI2+hF_IJb1?c0Oy66KMsTvLYkHlLLkiwIQ*%TN}xra;XT0Af71JG
z2$mVqmJcY3R+8I|Xv<btTC+xFTH3TyCUu(jVN?3eZY>R2inb4{v=5QyD6J;(VcI><
z7($j_-}ig>-gC~q=iYnH@A=bL{xW9$t;J$OwEX1n;`}G>8&)T?cBAFx6O7D7DyJ%C
zy=;gWqoyfS)I4Qo5Q~(G1s?RFD3&`6LLbqmRHm#quDh738+Wdn*qx!L-K3jo7L9Vn
zRc5L}uDpuqq=o?UnMjcNH&b<gjQzmC*zSK@`4wv~8-Z;leK`6&T_Znb+t@Ti-nZDS
z2_48vWq~6TyoV^9AgBit<x%?1=*dw-EmyL!PX*8%T458GJ&lEmay!kW(E==`l}+6p
z>cU66Zk$0ElPlalOJi9#&B=Q5d#mdpefQGA@6<AYRs$y+KufMja|_ye!#s-!*QL3P
z8QeWsDH~;zY?k@ky3Oa#b%jf_8J--q)RO;lRR#uKUrbm?&RXkXW$R|uey7tYXobmX
zA@8!@Y9Vo;)B~iuwUUpmcHJ+LTurJ4k^G!(6l(TgBLj9W5p>Izdp>6b@<i82-l?{c
zpRtFkZ2Pq6lomJ3Ao79UYkgLdsR1iCBkmYGj_ghyK!;GGwY(5QUWAXY=$^aJT$Mv?
z+tW$wN*=><s|=b%GPk1pkxu3UJFO*V30>wU(Gufxq}={^NS5SKA|%b?cvK2WgMl}t
z*>FVZNY#TZ9GiPaTo(37DO<TM#o`HRHlB>hJ<_O;DHvzwld-qda7rnVVbQ~}@=-D;
zcD;F5hr6ho1y=5&&oTOR-(?CFGx10=8dJ~HHXojg#jz3$$7JR5wk?pHnNd`AHW`U5
zOA+deB1<W&gyTzU$yw^bHhC<1R<~_~rCFqKO!HP%5<Sv3e+KrISiYpFJ*I8pTv%0M
zJBy)65=K%DuVEa=+SLEI%^t~T#~$i0h7c*RakZek6iUn&49exOno#i}ZTOO0sKg#6
zBnM~IMGO~LFel<cdZ0=o991v`Hrcc_lCNy7t9mSef)S24SemSKRt3HG#z&}F)l-n5
z;A+sez|MnkIj}^^344NzQE<mTNhjF0()_%Fin=DF^ATV3&d9ZqtaISrG6h;!bNpbQ
zAI$QDkHp${Pi*wv?92FaVtZa}FCx}b|46WJ@HhEv!>M~i6ll!}{du83EA($U>edrQ
z1F}2U&OUP0-LA__KJb42Qr0z`a}DQR!$oAZG-<G||N3zIX2*lt?5VN*tK+%D6Zyjv
z>-wy{IY-(Yo^hM=*74gXvtlc)TlELu^Z&xX<!RmWv~79XDHe_TE_)GCxaEI>^bL-0
z0M=hCT2ZxQ!*bJdOUVh|yx`4h^;-k^&~cz)<ag@5?oUtLO>d^NPP%2NIo_Y={aM~m
z{^|J4dHRpygNZ-bKeuOHr)kac19^TR%MXx`o$f}s;UAxNz0RUPH=Om-*F)Ac#BdM!
z!>{*p4}0}P%>BQbv4J^BUae`eXn6t|GaXVDa<S&|1q^48j{+P6=mt0r@G`&&fbRjE
z1UN+@WhsSmd{zrr+z*1&00RJn6iB~q_#FN|ZP5sW08`(N6!c2;QeqhofzmL*2!I~|
zI2@k?fSALh0Am2-0235Q(bh7F1GH5z#Ajz|juiB7Cl$Pm&x48<e8Aya@a+X4zZYim
zbjtC<_>-q6@5gI@&2`eOo*tcnk5jooI79#GzbI^=G$S)_X<rdc`7uK|&ql6PSJebS
z!tO|prCGI}JTV_~anI2&l66!QWjM<CUN(S0X;q(QC}$gf^+IJ|MXC+*<rx-J!ijkW
zYXfkH66Jt0nRVcc)Xf41sn&Ux=BWgEDn*lOLYk%>9A69r4=v3ru`+S2?y}KnN*Ib!
zdI`&t8c*UGh4Q4MLprx(-6Bu7z+x?Q_7<NG|9~!4;us(ke1U?GD{+LOWRKsVV=5dU
zy^j(f7`5ww_)FPJcR_wwYhB#{#T5!y&_B%8>*ufat@Uk*j=zcCFGX)oY|e|#S-yG8
zBCaQ|1=oUGV*UP{AIk~jd0{*&jBB~BnKpeXHf6#&u`@4rX8F#qDWmwW`LnK(56@C4
z)pDBgermGbjYaALvAF)j{D$b=ohBcv9q6dfNM3QjB)}F++YUiXCQ-M`0IaDd$#wUU
z?iRhXh<4!(rWg9VkY>!#-w$r`g}adv$YXb_1F{7}z!fSY@wqul>i7)pk>)y2mjW`4
z(BVG@o(BMDwNu@$?2X3dWJKx1aXJS7+SEUh#kva>#w*&7d{NhaYKmnXMf75PqK$v^
J9a3$j{{ehJq+kF5

delta 606
zcmZ`$O=uHA6rS0-oBuRPE2h-MC3UxrAh9Y%Ye2+;DAg)UFHr~~Gf7wXC*9dqvv}~(
ziw6(k-Mv{4LJ=cgyeb~_=4}u>dFsK6f)^2I6Y-=Ud>@bR&HIMOd$ac9RQ5?GlSBfq
z-c4@2&JVIhe19;%bWtXX6}J<Ogq>_8F_I9C-AqOABGB|UM(C;F7>$gCE+7)yLL|N|
ziH_i(PIj=fCFaNYrb8X;vTUHL0s;PlvqLI9R`Ap?mG~eH&+YFixCYN>HTXQc3!id_
zK*}!~)qPwdi-N}mPY9l@VjgR|R$x0!lxef;xE^hq4xx9$X(MR2DPx_$vihp!wg@F^
zm{C3V4pZHZN?Lv^ga`TZQaF8noS~Y|$Y#`ER>Sm)c%l0J9%akPFn8Hx%yhcy?Uofp
z4rrxI6)yD%k9)L5nrzeJGPQetpQn7cDdMSb+7wm_71=v2_J&Sj0p6Almbud22%KAt
zD{iMF{^IgxK)pVfM>hN{&A_uc71xIK@}mj3e)tEr!O)IPT&c$3p;l8?MVPk+@3k2v
zBT9A+cD19qx?J2tf8`#ARlR~I!POTEXQBaF2#;BAw=1@Q9le~p8rkJYqQiRzeAJ7{
jhA5*mv6t{mUxyp>N6r$A5A30T>(`P0{XboAN+kUTUX!Z2

diff --git a/salary_analytics/__pycache__/main.cpython-311.pyc b/salary_analytics/__pycache__/main.cpython-311.pyc
index 75230c812f22a9bec5b6d7b121567b89b21fd666..4f1a3ec44893c33145e870944df2c8c6a9088771 100644
GIT binary patch
delta 2379
zcmbtVU2qds6ux&io8L{+{Ip3nX_As)o3@l+tza$k*A}E&DRykDQ(|_3V4Bq3lu}Fq
zM`mapM$`*~j534B;8ak{)Ca~VAH?wihNP3Bo%MfwaeS(S4~{c3p1Wy~B0hQN?sw0*
zzvtU~&OMWxPITHnv|7ywO8QsV-U;D~?F#N@s1D`!Mu5{uLVZ|7eT;~YqCQr%h`OV=
zPbYGqaiShjFB$+1q7l$2ngC5O%M7#3BHN8(yy_vJ>OIp-83p4QIm3P%P#N*XrxL7o
zObPVRQ2q8!a$NT+pTjxkGIJ43xx^3`w*~7+FBiicd5vo(H@z-$gR>aeVGP?F$Pe7M
z%1K7mE16+AA*rU_$&@rO6wmG@F?}W+W92H?SgxiJ1W@QX;c!^?(4G+aNZ)`@kX!l{
z)~U8Hl6hxi!P!-Gb`jptgMDO|*@wrchpfwR#Td?^eXyof_L)eZJE+TH5K=BL+2=Cz
zqOJu7bJQ%3d}7>RqdJnxfD%u|<<S9IO2xC17_-O~FiEyjs3EIN&o-!BGA&96R9#X@
zrelm|ugbq9jgDkwaX^e`;|jeLYBD)#+KxXUKbey2J^rGnan`eW#<RKLX)Ai##`$?Y
zs%yM3a$#(?cI`~<+N+Jlb=wQIoyFSDaour4z9LdEM(6DQywNZJA7+;<%W;H!W2uX&
zZs3>5q?M$SmD1UP_+Vx@on1_k@?1))_?`82REz<XIoj`8x|rsEzF)rvW-63xGqG7$
ztrvntVePE2b4J)%5PFJ2&$u1<HY~qfdwJPxealRJ%hiG6<2wrV-NpLu65odk#@ac1
zFmDY0FTU^FmRKTS%)uqy*|?k~Pxz}Ns_mbf&5jO958`~s))D&`XA_;h_)=kOwVJ$P
zuO?Z0vwjn$eV$ygCwIBMMfa*%cl(UHz2M$jbZ;Fu0p+E!3+)#=XQPkIL?4+N{p@fd
z+Fp#dml%f&#+o_1H*fUHKG-LL0m_8~L5s1Y(0dF*dx9J>57g~JB6}W>;c>JZLvR~&
zcr&^PQ!ka*p)n@M$ScU3hKQcaG4G<YWXc>gX`-k<%aWVs)uh4aAkVvaJVC-1pLGHa
z(1_N`1ZlA?*Fi`a$yP_?F#VAblTm2oWfWEeEV5Gv9WMB8uK+lOPoq63hhA_(_~8lW
zo&dbdZ9o3BB8T5%j=Q?iBy}ztV5%XJNevICl^ClsO)FFuRER8i1{NNGBiaM-r@18s
z&YQ>#4z(WK1`m~&_?^MSO)aTRBA!xOK`0OR!LCXzz#m6YUg#~=bE~f=zII>tTo2`2
zpM(0&>QW1+-M~SiGpRsW?+MG&%fm@o62l92tqULYHHCK!r^E47DjZM8Q=^Kcgm))p
zC5xNLkfT{&1BXHEeC&v>S$M|Oit;uPb{aj^K3F=S+@aCir9BqkJNnH#sMR;9)g)fk
zum}7n(2w)}K3a|5xiSyRrhXk@LFg?Cz2o*DEy6rvOuO-Syz|8N*SF_=?Nb>5s0F^G
z$am!Vj_;g-e6@IWIY6lvoKn##<#~w=Iv>Nn=}BiR15d>-?vYT53ngTuV4_e-!A)T!
zIaIj?SCKC(AH^Q>S7pCmgl^?qE&5MYO$Ib?rrujF1`srFeuyQHGmnzDJ>JD>W6HCP
zJn3>UqK?daYRTuEi`09!LiTWzW8MyMSU33@+GEhJ_jQn;!GZIxI@0Bh#LO4Lw=UiF
zFN{P>H;SOFvwS#0Q6xV+#u8qL*!e8wu~2d>X%&|Gtz+yVRs^pXHE9HopaX0#8o@Ce
zIV3#I$pM%@eM4A+p9z5^Yk#MKN-HTeQ=s`*eiA@6Z8?yThO)^_T4j~29Mj#G(o`%d
zG-@EL(HyZRut7fps<M~75(x3<dZtFl4;AbiiuMiD=K^gwWZ#UoIM6kRxvhe|=C5zF
zuwPj?kRfygSV!(u*R^>;kTu)>%PhHzPFY8R-cBi>TBt<94xe&{B!i6`k%^1US6R8h
zJh}@(D;J{b0)XnH>H-8SxYl`e7oub?7&FWxKj(vooDE&ZU1Ta$RY5bjsvC?a({c}p
zC&{f)6Xa|zoNRgq^iq!1ETY5rnfj-(WiTTSr=(W7pS%~oxN;MN;rIvRZ(9HF_l|DU
L5v698j#B>{Br#R_

delta 1281
zcmZ{kUue@;6vyxV{mU<Zez{GWCcnn~Ym?eWYibM9%4(!GDd}pa&~4C`F=l@O1NINU
z)TI-xB0l&q|KLG<+1P{3Q5Z<+i-Wy7l%X^w&@I%xkICq8Q}AUw_ZJ%4Q7_z2&b{|{
z&iCBIxw(~J9(I4HX%2$p;m_>so0b*#3e8i##_=kRxJL?Pk{V=EFz7WhDH;M&GDM_o
zNJzzykv2m?s)h||H&mp<u#c0ZW3@^6lG0`PTHF+-DO{0!!Uq(FgaLRi<=~UB8xF|F
zs0e4}B$eQf+z-EmnqgCR+Jy5I11RvP{66HBIj`x*bV@wAn5iSp5Ns+3>2*+Thn0#q
zRrRJIYx|f6;gqwLcEeKOIrO_el`x0|!}ibJNxRv^{WOjU)a)N=yJEtm<0QQRFFgJ5
zo1@RqnyW0a!3NjaV1=ctEWM_t%{_y^cJ<I0?AN-QcS~@cHYjT!x^|`x|7cUnVLU6<
zwQjiUTB!{-y3R%`Y^=)0*3_}RwZ3g?N3ADKoqK9|J-OXlOP&eky=|?cb*Doc?8G`d
zQDK=X%dDxHx{mOcz~#U*tk|J?#X5a)DTbc#RZG7TK?ASyYfIvPCF}K1DI+|7!Kzzt
zppOPujX+w!B=5JDw;f|ao%X=dV3r2pa&Um^@F+N?oaT<3mgDJt%b_4Hr?;CAZDPYI
z;(Qeot&YiubgN^&2z9_WPLE)SuoCKo3%U<phH}_AKFEc0@KkPw`{7Zz9roRc<ltr4
z2RHQ&m<h)r7xCzZW1Pgvf|o1QM}n9~E>U<Ei8JRy%l0lI7b*N3>DcGGM3<-`juXSO
z%Ct-t#R*cTNezxiPpv|<on}MmW?E%RaI1@>o1=$g08z7N7pDvJ3&pwFnpj#elY$xG
z+q6&;@Hd8C4NBXPGL4JU8OXOql?sbiS#))=ZG`Hs49U95W4B{O6CdjbMpW@9RYn_L
zw08}+qK|2%@Gf=p7=E%$OkU*r^Ko*EgW)XQg|T?|u-`5p-y#j*@+9T!25~2A?KJ3D
z<@6S5zz09X@n%8zJ^p<s*G$ryI$xYGoGZ>2cD&x2H1k<;*394+SK!A)3ZLyCiDHWX
z<<uXjl^#Dfhd3H}zf}ik=8W^_3Tbl`u68`=oujmMi|oz6to^@to}Lk5Vt=2+<NXK0
CQYVc7

diff --git a/salary_analytics/__pycache__/salary_earner_analyzer.cpython-311.pyc b/salary_analytics/__pycache__/salary_earner_analyzer.cpython-311.pyc
index 7318a9dcc29b12da7c230337da01f3fa8946db8a..d72e45e7e093680f68d707f48184809dff91aaaa 100644
GIT binary patch
delta 356
zcmX@=aK(XlIWI340}woTEu2xYk=Iz5@z7*PVOypJjFaVgmD!nUm{OQiSSIfhHdSUW
zVF#&%fEuP{j0_B`ffxd6S!$STSSEiF4vWzNiWGSQi4aZ3TP!I>`30IRMIf!WSd#M#
zDsOQYr52}_#AoKEq*fFu0mU_0iv&P=(m`r?GBVRM;!_ig@=}Y6i}*o8T*>*Rc_r~6
ziOCB@A{kRA{}Peozb;;INxa~qc+nN{q7I%LlPyJ+`0k2I%#gV#s&++Gt%K{q<`~ff
ztc(SdWu?6tOD1Om$(YSsr57==6@YB3nH(!uz|Y32|A7Hc2u!{sH<7Vna-O^dWBcTG
a`FeX-CPuCg4A{w!VDT?FWQ&A>wg3SB$6r+d

delta 371
zcmccOaMXc!IWI340}ve9#-FieBd@VA<Ce*e!nQWGOf^g?%#t7}FaYsvfUFW`r~r_v
zVOqw>z_1#KA)uBSsEQ?pdGab@Q&yH5mKx^COd?@no<P|m9Uu{+$#{z;r6|8Zlevf;
zB&Y-=ZgCf-7N?fPXXd4(R%o&o34kQhK@vO}nduqvsfk5-sYS)NxRUcr^Gf1DVnzHw
z>B(C}A{jF$^NGqScJSQLGP_{zaYf6sgXe;%+C>iayP^^^WG;%TT@h95;Ce9GT2zVg
z#^!9%1FVeslXaxM8H*=Z0Lj?RN2C`qvE_rTte%`BSHRECs{erjP6$nYEjN*|esZn6
f1Y_IeY4Y{<ZcL0^9~iKcAHm{ZaL5)318o5S-p^fa

diff --git a/salary_analytics/api.py b/salary_analytics/api.py
index fd713cb..63c3560 100644
--- a/salary_analytics/api.py
+++ b/salary_analytics/api.py
@@ -2,7 +2,7 @@
 FastAPI application for salary analytics.
 """
 
-from fastapi import FastAPI, HTTPException, BackgroundTasks
+from fastapi import FastAPI, HTTPException, BackgroundTasks, UploadFile, File
 from fastapi.responses import FileResponse
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
@@ -10,9 +10,14 @@ from typing import Optional, Dict
 import os
 import socket
 import logging
+import pandas as pd
+import tempfile
 
 from .main import SalaryAnalyticsPipeline
 from .config import OUTPUT_PATHS
+from .data_loader import DataLoader
+from .salary_predictor import SalaryPredictor
+from .salary_earner_analyzer import SalaryEarnerAnalyzer
 
 # Configure logging
 logging.basicConfig(
@@ -37,7 +42,13 @@ app.add_middleware(
 )
 
 # Global pipeline instance
-pipeline = None
+pipeline = SalaryAnalyticsPipeline()
+
+# Global variables to store loaded data and models
+data_loader = None
+df = None
+salary_predictor = None
+salary_earner_analyzer = None
 
 class AnalysisResponse(BaseModel):
     """Response model for analysis endpoints."""
@@ -45,16 +56,19 @@ class AnalysisResponse(BaseModel):
     data: Optional[Dict] = None
     file_path: Optional[str] = None
 
+def check_data_loaded():
+    """Check if data is loaded before running analytics."""
+    if pipeline.df is None:
+        raise HTTPException(
+            status_code=400,
+            detail="No data loaded. Please load data first using the /load-data endpoint."
+        )
+
 @app.on_event("startup")
 async def startup_event():
     """Initialize the pipeline on startup."""
-    global pipeline
     try:
         logger.info("Initializing pipeline...")
-        pipeline = SalaryAnalyticsPipeline()
-        if not pipeline.load_data():
-            logger.error("Failed to load data during startup")
-            raise Exception("Failed to load data during startup")
         
         # Print network information
         hostname = socket.gethostname()
@@ -86,6 +100,7 @@ async def health_check():
 async def analyze_keyword():
     """Run keyword-based salary transaction analysis."""
     try:
+        check_data_loaded()
         logger.info("Starting keyword analysis...")
         data = pipeline.run_keyword_analysis()
         logger.info(f"Keyword analysis completed. Found {len(data)} matches")
@@ -101,6 +116,7 @@ async def analyze_keyword():
 async def analyze_consistent_amount():
     """Run consistent amount transaction analysis."""
     try:
+        check_data_loaded()
         logger.info("Starting consistent amount analysis...")
         data = pipeline.run_consistent_amount_analysis()
         logger.info(f"Consistent amount analysis completed. Found {len(data)} matches")
@@ -116,6 +132,7 @@ async def analyze_consistent_amount():
 async def analyze_transaction_type():
     """Run transaction type analysis."""
     try:
+        check_data_loaded()
         logger.info("Starting transaction type analysis...")
         data = pipeline.run_transaction_type_analysis()
         logger.info(f"Transaction type analysis completed. Found {len(data)} matches")
@@ -131,6 +148,7 @@ async def analyze_transaction_type():
 async def generate_reports(background_tasks: BackgroundTasks):
     """Generate salary earner reports."""
     try:
+        check_data_loaded()
         logger.info("Starting report generation...")
         reports = pipeline.generate_salary_earner_reports()
         logger.info("Reports generated successfully")
@@ -150,6 +168,7 @@ async def generate_reports(background_tasks: BackgroundTasks):
 async def train_models():
     """Train salary prediction models."""
     try:
+        check_data_loaded()
         logger.info("Starting model training...")
         pipeline.train_salary_prediction_models()
         logger.info("Models trained successfully")
@@ -164,6 +183,7 @@ async def train_models():
 async def download_report(report_type: str):
     """Download generated reports."""
     try:
+        check_data_loaded()
         logger.info(f"Attempting to download report: {report_type}")
         file_paths = {
             "high_earners": OUTPUT_PATHS["high_earner_details"],
@@ -197,6 +217,7 @@ async def download_report(report_type: str):
 async def run_full_pipeline():
     """Run the complete salary analytics pipeline."""
     try:
+        check_data_loaded()
         logger.info("Starting full pipeline...")
         success = pipeline.run_full_pipeline()
         if not success:
@@ -209,4 +230,51 @@ async def run_full_pipeline():
         )
     except Exception as e:
         logger.error(f"Error in pipeline: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.post("/load-data")
+async def load_data(source: str = "db", file: UploadFile = None):
+    """
+    Load data from either database or CSV file.
+    
+    Args:
+        source (str): Source of data ('db' or 'csv')
+        file (UploadFile): CSV file to load (required if source is 'csv')
+    
+    Returns:
+        dict: Status of data loading
+    """
+    try:
+        if source not in ['db', 'csv']:
+            raise HTTPException(status_code=400, detail="Source must be either 'db' or 'csv'")
+        
+        if source == 'csv' and not file:
+            raise HTTPException(status_code=400, detail="File must be provided when loading from CSV")
+        
+        if source == 'csv':
+            # Save uploaded file temporarily
+            with tempfile.NamedTemporaryFile(delete=False, suffix='.csv') as temp_file:
+                content = await file.read()
+                temp_file.write(content)
+                temp_file_path = temp_file.name
+            
+            try:
+                success = pipeline.load_data(source='csv', file_path=temp_file_path)
+            finally:
+                # Clean up temporary file
+                os.unlink(temp_file_path)
+        else:
+            success = pipeline.load_data(source='db')
+        
+        if not success:
+            raise HTTPException(status_code=500, detail="Failed to load data")
+        
+        return {
+            "status": "success",
+            "message": f"Successfully loaded {len(pipeline.df)} rows of data",
+            "columns": pipeline.df.columns.tolist(),
+            "row_count": len(pipeline.df)
+        }
+    except Exception as e:
+        logger.error(f"Error loading data: {str(e)}")
         raise HTTPException(status_code=500, detail=str(e)) 
\ No newline at end of file
diff --git a/salary_analytics/consistent_amount_analyzer.py b/salary_analytics/consistent_amount_analyzer.py
index 7747ccd..3b74afc 100644
--- a/salary_analytics/consistent_amount_analyzer.py
+++ b/salary_analytics/consistent_amount_analyzer.py
@@ -40,12 +40,18 @@ class ConsistentAmountAnalyzer:
         if cv_threshold is None:
             cv_threshold = MODEL_CONFIG['cv_threshold']
 
-        self.df = self.df.groupby('accountid').apply(
+        # Create a copy of the original DataFrame
+        self.const_df = self.df.copy()
+        
+        # Calculate consistent amount flags
+        consistent_flags = self.const_df.groupby('accountid').apply(
             lambda group: self.flag_consistent_amounts(group, cv_threshold)
         ).reset_index(level=0, drop=True)
-
-        self.const_df = self.df.copy()
-        return self.df
+        
+        # Add the flags to the original DataFrame
+        self.const_df['is_consistent_amount'] = consistent_flags
+        
+        return self.const_df
 
     def get_consistent_amount_data(self):
         """Get transactions identified as having consistent amounts."""
diff --git a/salary_analytics/data_loader.py b/salary_analytics/data_loader.py
index 4032a44..8eb6d25 100644
--- a/salary_analytics/data_loader.py
+++ b/salary_analytics/data_loader.py
@@ -6,6 +6,7 @@ from sqlalchemy import create_engine, text
 import pandas as pd
 from datetime import datetime
 import logging
+import os
 from .config import DB_CONFIG, TABLE_NAME
 
 logger = logging.getLogger(__name__)
@@ -44,8 +45,49 @@ class DataLoader:
             logger.error(f"Error connecting to database: {str(e)}")
             return False
 
-    def load_data(self):
-        """Load and preprocess transaction data in chunks."""
+    def load_from_csv(self, file_path):
+        """Load data from a CSV file."""
+        try:
+            logger.info(f"Loading data from CSV file: {file_path}")
+            if not os.path.exists(file_path):
+                logger.error(f"CSV file not found: {file_path}")
+                return None
+
+            # Load data in chunks
+            chunks = []
+            for chunk in pd.read_csv(file_path, chunksize=self.chunk_size):
+                # Preprocess chunk
+                chunk['trx_start_date'] = pd.to_datetime(chunk['trx_start_date'])
+                chunk['trx_end_date'] = pd.to_datetime(chunk['trx_end_date'])
+                
+                # Rename columns if needed
+                if 'd1' in chunk.columns:
+                    chunk = chunk.rename(columns={
+                        'd1': 'trx_type',
+                        'd2': 'trx_subtype',
+                        'd3': 'initiated_by',
+                        'd4': 'customer_id'
+                    })
+                
+                chunks.append(chunk)
+            
+            # Combine all chunks
+            self.df = pd.concat(chunks, ignore_index=True)
+            logger.info(f"Successfully loaded {len(self.df)} rows from CSV")
+            
+            # Basic data validation
+            logger.info("Performing data validation...")
+            logger.info(f"Columns in dataset: {self.df.columns.tolist()}")
+            logger.info(f"Data types:\n{self.df.dtypes}")
+            logger.info(f"Missing values:\n{self.df.isnull().sum()}")
+            
+            return self.df
+        except Exception as e:
+            logger.error(f"Error loading data from CSV: {str(e)}")
+            return None
+
+    def load_from_db(self):
+        """Load and preprocess transaction data from database in chunks."""
         if not self.engine:
             logger.info("No database connection. Attempting to connect...")
             if not self.connect():
@@ -106,6 +148,19 @@ class DataLoader:
             logger.error(f"Error loading data: {str(e)}")
             return None
 
+    def load_data(self, source='db', file_path=None):
+        """Load data from either database or CSV file."""
+        if source == 'db':
+            return self.load_from_db()
+        elif source == 'csv':
+            if not file_path:
+                logger.error("File path must be provided when loading from CSV")
+                return None
+            return self.load_from_csv(file_path)
+        else:
+            logger.error(f"Invalid source: {source}. Must be 'db' or 'csv'")
+            return None
+
     def get_data(self):
         """Get the loaded DataFrame."""
         if self.df is None:
diff --git a/salary_analytics/main.py b/salary_analytics/main.py
index b50d8b7..e2781e8 100644
--- a/salary_analytics/main.py
+++ b/salary_analytics/main.py
@@ -23,11 +23,11 @@ class SalaryAnalyticsPipeline:
         self.salary_earner_analyzer = None
         self.salary_predictor = None
 
-    def load_data(self):
+    def load_data(self, source='db', file_path=None):
         """Load and preprocess the transaction data."""
         logger.info("Starting data loading process")
         self.data_loader = DataLoader()
-        self.df = self.data_loader.load_data()
+        self.df = self.data_loader.load_data(source=source, file_path=file_path)
         if self.df is not None:
             logger.info(f"Successfully loaded data with {len(self.df)} rows")
         else:
@@ -43,7 +43,11 @@ class SalaryAnalyticsPipeline:
         logger.info("Starting keyword analysis")
         self.keyword_analyzer = KeywordAnalyzer(self.df)
         self.keyword_analyzer.identify_salary_transactions()
-        return self.keyword_analyzer.get_salary_related_data()
+        keyword_data = self.keyword_analyzer.get_salary_related_data()
+        
+        # Update main DataFrame with keyword analysis results
+        self.df['is_salary_related'] = self.df.index.isin(keyword_data.index)
+        return keyword_data
 
     def run_consistent_amount_analysis(self):
         """Run consistent amount transaction analysis."""
@@ -54,7 +58,11 @@ class SalaryAnalyticsPipeline:
         logger.info("Starting consistent amount analysis")
         self.consistent_amount_analyzer = ConsistentAmountAnalyzer(self.df)
         self.consistent_amount_analyzer.identify_consistent_amount_accounts()
-        return self.consistent_amount_analyzer.get_consistent_amount_data()
+        consistent_data = self.consistent_amount_analyzer.get_consistent_amount_data()
+        
+        # Update main DataFrame with consistent amount analysis results
+        self.df['is_consistent_amount'] = self.df.index.isin(consistent_data.index)
+        return consistent_data
 
     def run_transaction_type_analysis(self):
         """Run transaction type analysis."""
@@ -65,7 +73,11 @@ class SalaryAnalyticsPipeline:
         logger.info("Starting transaction type analysis")
         self.transaction_type_analyzer = TransactionTypeAnalyzer(self.df)
         self.transaction_type_analyzer.flag_salary_type_transactions()
-        return self.transaction_type_analyzer.get_salary_type_data()
+        type_data = self.transaction_type_analyzer.get_salary_type_data()
+        
+        # Update main DataFrame with transaction type analysis results
+        self.df['is_salary_type'] = self.df.index.isin(type_data.index)
+        return type_data
 
     def generate_salary_earner_reports(self):
         """Generate salary earner reports."""
@@ -73,6 +85,14 @@ class SalaryAnalyticsPipeline:
             logger.error("Data not loaded. Call load_data() first.")
             raise ValueError("Data not loaded. Call load_data() first.")
         
+        # Ensure all analysis flags are present
+        required_columns = ['is_salary_related', 'is_consistent_amount', 'is_salary_type']
+        missing_columns = [col for col in required_columns if col not in self.df.columns]
+        
+        if missing_columns:
+            logger.error(f"Missing required columns: {missing_columns}")
+            raise ValueError(f"Missing required columns: {missing_columns}. Run all analyses first.")
+        
         logger.info("Starting salary earner report generation")
         self.salary_earner_analyzer = SalaryEarnerAnalyzer(self.df)
         return self.salary_earner_analyzer.generate_reports()
@@ -96,10 +116,10 @@ class SalaryAnalyticsPipeline:
         
         self.salary_predictor.train_and_evaluate(consistent_accounts, inconsistent_accounts)
 
-    def run_full_pipeline(self):
+    def run_full_pipeline(self, source='db', file_path=None):
         """Run the complete salary analytics pipeline."""
         logger.info("Starting full pipeline execution")
-        if not self.load_data():
+        if not self.load_data(source=source, file_path=file_path):
             logger.error("Failed to load data. Exiting pipeline.")
             return False
 
diff --git a/salary_analytics/salary_earner_analyzer.py b/salary_analytics/salary_earner_analyzer.py
index 909129e..00407ba 100644
--- a/salary_analytics/salary_earner_analyzer.py
+++ b/salary_analytics/salary_earner_analyzer.py
@@ -83,11 +83,10 @@ class SalaryEarnerAnalyzer:
 
     def analyze_salary_earners(self, final_df):
         """Analyze salary earners and identify high earners."""
-        high_earners = final_df[final_df['estimated_next_amount'] >= MODEL_CONFIG['high_earner_threshold']]
-        high_earners['least_inflow_6m'] = high_earners['least_inflow_6m']
-        count_high = len(high_earners)
-
+        high_earners = final_df[final_df['estimated_next_amount'] >= MODEL_CONFIG['high_earner_threshold']].copy()
         high_earner_details = high_earners[['accountid', 'least_inflow_6m']].reset_index(drop=True)
+        count_high = len(high_earners)
+        
         return high_earner_details, count_high
 
     def generate_reports(self):