d

.gitattributes

@@ -0,0 +1,75 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+.gif filter=lfs diff=lfs merge=lfs -text
+.pkl filter=lfs diff=lfs merge=lfs -text
+.jpg filter=lfs diff=lfs merge=lfs -text
+.mp4 filter=lfs diff=lfs merge=lfs -text
+
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Models/Clean_Job_data.csv

@@ -0,0 +1,285 @@
+Experience,Job_Pos,New Salary
+1.0,1,25000.0
+1.5,1,30000.0
+1.5,1,49804.27627052736
+1.5,1,60000.0
+1.5,1,40500.0
+1.5,1,40000.0
+1.8,1,32500.0
+1.5,1,34500.0
+1.8,1,36500.0
+1.5,1,38500.0
+1.8,1,49804.27627052736
+1.0,1,42500.0
+3.0,1,35000.0
+1.0,1,30000.0
+1.0,1,46500.0
+5.0,1,48500.0
+1.5,1,50500.0
+2.5,1,52500.0
+1.5,1,49804.27627052736
+1.0,1,56500.0
+1.0,1,58500.0
+2.5,1,60500.0
+1.8,1,49804.27627052736
+1.0,1,64500.0
+2.0,1,49804.27627052736
+1.8,1,62500.0
+1.5,1,49804.27627052736
+2.0,1,54500.0
+1.8,1,27000.0
+2.5,1,49804.27627052736
+1.5,1,32500.0
+1.8,1,40000.0
+1.5,1,49804.27627052736
+2.0,1,30000.0
+1.5,1,40500.0
+1.5,1,36500.0
+1.8,1,38500.0
+1.5,1,42500.0
+1.8,1,49804.27627052736
+1.5,1,55000.0
+1.8,1,40000.0
+1.5,1,42500.0
+1.5,1,49804.27627052736
+2.0,1,36500.0
+1.5,1,38500.0
+2.0,1,49804.27627052736
+1.8,1,49804.27627052736
+1.5,1,35000.0
+2.0,1,49804.27627052736
+1.8,1,42500.0
+1.0,1,49804.27627052736
+1.8,1,49804.27627052736
+1.5,1,45000.0
+1.5,1,49804.27627052736
+1.8,1,49804.27627052736
+1.0,1,49804.27627052736
+2.0,1,49804.27627052736
+1.8,1,70000.0
+2.0,1,49804.27627052736
+2.0,1,45000.0
+1.8,1,49804.27627052736
+1.0,1,42000.0
+1.8,1,49804.27627052736
+3.0,1,70500.0
+2.0,1,49804.27627052736
+2.0,1,49804.27627052736
+3.0,1,80000.0
+1.0,1,49804.27627052736
+2.0,1,49804.27627052736
+2.0,1,75000.0
+1.8,1,49804.27627052736
+1.0,1,70500.0
+1.8,1,49804.27627052736
+1.0,1,70500.0
+3.3,2,70000.0
+3.3,2,75000.0
+3.0,2,80000.0
+3.3,2,85000.0
+3.0,2,70000.0
+2.5,2,95000.0
+3.3,2,100000.0
+3.0,2,105000.0
+3.3,2,77853.59696090454
+2.5,2,77853.59696090454
+3.3,2,110000.0
+2.0,2,77853.59696090454
+5.0,2,70500.0
+3.3,2,70000.0
+2.0,2,77853.59696090454
+3.3,2,95000.0
+3.3,2,77853.59696090454
+3.3,2,77853.59696090454
+5.0,2,100000.0
+3.3,2,105000.0
+4.0,2,77853.59696090454
+3.3,2,88000.0
+3.0,2,70000.0
+2.0,2,77853.59696090454
+3.3,2,70500.0
+3.0,2,67000.0
+3.3,2,77853.59696090454
+4.0,2,90000.0
+2.0,2,75000.0
+3.3,2,105000.0
+3.0,2,77853.59696090454
+3.3,2,77853.59696090454
+3.0,2,95000.0
+3.3,2,77853.59696090454
+3.0,2,77853.59696090454
+3.3,2,80000.0
+10.0,2,76000.0
+2.0,2,77853.59696090454
+3.3,2,65000.0
+2.5,2,77853.59696090454
+10.0,2,70500.0
+3.3,2,85000.0
+3.0,2,110000.0
+3.3,2,95000.0
+2.5,2,100000.0
+4.0,2,77853.59696090454
+3.0,2,77853.59696090454
+3.3,2,77853.59696090454
+3.0,2,87000.0
+2.5,2,70500.0
+3.3,2,75000.0
+3.3,2,95000.0
+5.0,2,105000.0
+3.3,2,77853.59696090454
+2.5,2,77853.59696090454
+3.3,2,77853.59696090454
+2.5,2,105000.0
+3.3,2,77853.59696090454
+10.0,2,77853.59696090454
+2.0,2,77853.59696090454
+3.3,2,77853.59696090454
+2.0,2,72500.0
+3.3,2,77853.59696090454
+5.0,2,85000.0
+2.5,2,77853.59696090454
+5.0,2,80000.0
+3.3,2,90000.0
+5.5,3,105902.91765128174
+8.5,3,60000.0
+6.5,3,105902.91765128174
+4.8,3,105902.91765128174
+14.0,3,44750.0
+4.8,3,105902.91765128174
+10.0,3,105902.91765128174
+4.8,3,80000.0
+4.8,3,105902.91765128174
+5.0,3,105902.91765128174
+4.8,3,70000.0
+5.0,3,100000.0
+5.0,3,100000.0
+4.8,3,105902.91765128174
+4.8,3,90000.0
+5.0,3,105902.91765128174
+4.8,3,105902.91765128174
+4.8,3,90000.0
+2.0,3,105902.91765128174
+4.8,3,82500.0
+5.0,3,105902.91765128174
+4.8,3,105000.0
+3.0,3,105902.91765128174
+4.8,3,105902.91765128174
+4.0,3,105902.91765128174
+4.8,3,125000.0
+2.0,3,95000.0
+4.0,3,100000.0
+2.0,3,105902.91765128174
+4.0,3,110000.0
+2.0,3,105902.91765128174
+4.8,3,120000.0
+5.0,3,125000.0
+7.5,3,105902.91765128174
+5.5,3,105902.91765128174
+3.0,3,105902.91765128174
+4.8,3,125000.0
+4.8,3,105902.91765128174
+3.0,3,120000.0
+4.8,3,80000.0
+4.8,3,105902.91765128174
+2.0,3,115000.0
+4.8,3,105902.91765128174
+4.8,3,105902.91765128174
+3.0,3,105902.91765128174
+3.0,3,105902.91765128174
+4.8,3,130000.0
+4.8,3,105902.91765128174
+3.0,3,105000.0
+5.0,3,105902.91765128174
+1.0,3,105902.91765128174
+5.0,3,130.0
+8.0,3,105902.91765128174
+1.0,3,105902.91765128174
+1.5,3,125000.0
+4.8,3,105902.91765128174
+2.0,3,115000.0
+4.8,3,105902.91765128174
+4.0,3,115000.0
+4.8,3,120000.0
+3.0,3,105902.91765128174
+10.0,3,125000.0
+4.0,3,75000.0
+4.8,3,95000.0
+2.0,3,105902.91765128174
+4.8,3,125000.0
+5.0,3,105902.91765128174
+10.0,3,100000.0
+4.8,3,105000.0
+7.0,3,120000.0
+4.8,3,105902.91765128174
+4.0,3,102500.0
+5.0,3,105902.91765128174
+8.0,4,120000.0
+3.0,4,130000.0
+8.0,4,45000.0
+8.0,4,30000.0
+10.0,4,133952.23834165893
+8.0,4,154000.0
+7.5,4,133952.23834165893
+2.0,4,170000.0
+2.0,4,150000.0
+3.0,4,180000.0
+7.0,4,133952.23834165893
+10.0,4,133952.23834165893
+3.0,4,133952.23834165893
+6.2,4,133952.23834165893
+5.0,4,175000.0
+8.0,4,190000.0
+6.2,4,133952.23834165893
+2.0,4,160000.0
+8.0,4,133952.23834165893
+7.0,4,150000.0
+6.2,4,133952.23834165893
+7.0,4,105000.0
+6.2,4,133952.23834165893
+2.0,4,133952.23834165893
+6.2,4,133952.23834165893
+5.0,4,133952.23834165893
+6.2,4,130000.0
+6.2,4,133952.23834165893
+8.0,4,100000.0
+5.0,4,133952.23834165893
+6.2,4,133952.23834165893
+8.0,4,160000.0
+8.0,4,133952.23834165893
+6.2,4,133952.23834165893
+6.2,4,170000.0
+6.2,4,133952.23834165893
+8.0,4,133952.23834165893
+8.0,4,110000.0
+8.0,4,133952.23834165893
+8.0,4,133952.23834165893
+8.0,4,122500.0
+5.0,4,133952.23834165893
+3.5,4,133952.23834165893
+2.5,4,133952.23834165893
+7.5,4,120000.0
+6.2,4,160000.0
+6.2,4,137500.0
+4.0,4,133952.23834165893
+6.2,4,150000.0
+6.2,4,133952.23834165893
+8.5,4,92500.0
+5.0,4,136000.0
+8.5,4,110000.0
+7.0,4,165000.0
+6.2,4,150000.0
+6.0,4,120000.0
+5.0,4,180000.0
+6.2,4,115000.0
+6.2,4,133952.23834165893
+7.0,4,133952.23834165893
+5.0,4,80000.0
+6.2,4,100000.0
+6.0,4,133952.23834165893
+6.2,4,150000.0
+7.0,4,140000.0
+5.0,4,175000.0
+6.2,4,90000.0
+7.0,4,175000.0
+6.2,4,133952.23834165893
+5.0,4,160000.0

Models/Job_data.csv

@@ -0,0 +1,302 @@
+Job,Location,Salary,Experience,Job_Pos
+Junior Graphics Designer,Remote,"Php20,000.00  -Php30,000.00 ",At least 1 year,Junior
+Junior Product Designer,Philippines,PHP30K,1-2 years,Junior
+Junior Services Developer - Javascript (100% Remote) - Philippines,Remote,"PHP 32,000 - PHP 57,000",20 years,Junior
+Junior Software Engineers,Remote in Makati,,Minimum 1-2 years,Junior
+Junior Enterprise Growth Consultant (Work From Home),Remote,"Php50,000.00  -Php70,000.00 ",Minimum 1-2 years,Junior
+Junior Operations Associate,Remote in Manila,"PHP 28,000 - PHP 53,000",1-2 Years,Junior
+Junior Accountant (Hong Kong),Angeles,P40K,1- 2 years,Junior
+Master Data Management Junior Associate (Night Shift),Remote in Taguig,"PHP 20,000 - PHP 45,000",,Junior
+FATCA / CRS Junior Officer,Pasig,"PHP 22,000 - PHP 47,000",Minimum 1-2 years,Junior
+Junior Mobile Application Developer,Remote in Taytay,"PHP 24,000 - PHP 49,000",,Junior
+Junior Software Developer,Manila,"PHP 26,000 - PHP 51,000",1-2 years,Junior
+Junior Operations Analyst - Ballot Ingestion,Makati,,,Junior
+Junior Project Development Architect,Makati,"PHP 30,000 - PHP 55,000",at least 1 year,Junior
+Junior Front End Developer,Philippines,35K,2-4 years,Junior
+Logistics Business Planning and Control Jr. Engineer,Philippines,PHP30K,At least 1 year,Junior
+Quality Control Jr. Engineer,Philippines,"PHP 34,000 - PHP 59,000",At least 1 Year,Junior
+Junior SEO Specialist,Manila,"PHP 36,000 - PHP 61,000",5 years,Junior
+Junior Systems Engineer,Quezon City,"PHP 38,000 - PHP 63,000",1-2 years,Junior
+JUNIOR /SENIOR STRUCTURAL DESIGN ENGINEER,Makati,"PHP 40,000 - PHP 65,000",2-3 years,Junior
+Inspector (Subic),Subic,,Minimum 1-2 years,Junior
+Junior Project Development Architect,Makati,"PHP 44,000 - PHP 69,000",at least 1 year,Junior
+Junior Data Quality Analyst,Manila,"PHP 46,000 - PHP 71,000",At least 1 year,Junior
+JR. ADMINISTRATIVE ASSISTANT (COLLECTIONS),Mandaluyong,"PHP 48,000 - PHP 73,000",2-3 years,Junior
+Junior Technical Support,Malate,,,Junior
+Logistics Business Planning and Control Jr. Engineer,Philippines,"PHP 52,000 - PHP 77,000",At least 1 year,Junior
+Cash Applications Junior Associate (Nightshift),Taguig,,2 years,Junior
+Intern - HR Learning Operations,Philippines,"PHP 50,000 - PHP 75,000",,Junior
+Junior SEO Specialist,Philippines,,At least 1-2 years,Junior
+Junior Customer Care Executive,Cebu City,"PHP 42,000 - PHP 67,000",at least 2 years,Junior
+Junior Service Engineer ...,Pampanga,"PHP 27,000",,Junior
+JR. ADMINISTRATIVE ASSISTANT (COLLECTIONS),Mandaluyong,,2-3 years,Junior
+Junior Copywriter (E-commerce),Malate,"PHP 20,000 - PHP 45,000",1-2 years,Junior
+Junior Front End Developer,Philippines,PHP40K,,Junior
+Jr. UI/UX Designer,Parañaque,,1-2 years,Junior
+Cash Applications Junior Associate (Nightshift),Taguig,"Php20,000.00  -Php40,000.00 ",2 years,Junior
+Junior SEO Specialist,Philippines,"PHP 28,000 - PHP 53,000",At least 1-2 years,Junior
+Junior Layout Engineer,Alabang,"PHP 24,000 - PHP 49,000",Minimum 1-2 years,Junior
+Junior Data Scientist,Pasig,"PHP 26,000 - PHP 51,000",,Junior
+Junior Video Editor | Short-Form,Remote in Makati,"PHP 30,000 - PHP 55,000",1-2 years,Junior
+Junior Business Development,Makati,,,Junior
+"Senior/junior programmers, 3d artists",Davao City,PHP 55K,1-2 years,Junior
+Junior Security Analyst,Makati,PHP40K,,Junior
+Ocean Import Jr. Associate,Taguig,"PHP 30,000- PHP 55,000",Minimum 1-2 years,Junior
+IT Admin,Philippines,,At least 1 - 2 years,Junior
+Junior Internal Auditor,Lipa,"PHP 24,000 - PHP 49,000",2 years,Junior
+Graphic Designer,Remote in San Fernando,"PHP 26,000 - PHP 51,000",1-2 years,Junior
+Junior Specialist – Sales Administration,Makati,,2 years,Junior
+Customer Care Specialist,Philippines,,,Junior
+Junior Fourth Engineer,Philippines,"P35,000",1-2 years,Junior
+Junior Web Developer | Hybrid,Remote in Makati,,2 years,Junior
+Website Management Jr. Associate,Remote in Taguig,"PHP 30,000 - PHP 55,000",,Junior
+Software Test Engineer (Junior to Mid),Remote in Cebu City,,1 year,Junior
+Junior Sales,Philippines,,,Junior
+Virtual Executive Support,Remote in Mandaluyong,"PHP30,000 - PHP 60,000",1 -2 year,Junior
+Jr. Specialist,Makati,,1-2 years,Junior
+JR. PROGRAMMER,Remote in Pasig,"PHP, ",,Junior
+Jr. Field Agronomist- North Luzon,Cauayan,,At least 1 year,Junior
+Jr. Data Analyst,Philippines,,2 years,Junior
+Junior QA Engineer,Makati,"PHP 50,000 - PHP 90,000",,Junior
+Junior Data Analyst – Market Intelligence (Financial Market Data),Makati,,2 years,Junior
+Jr. Data Analyst,Philippines,"P45,000",2 years,Junior
+Junior QA Engineer,Makati,,,Junior
+Jr Content Writer,Pasig,"PHP42,000",At least 1 year,Junior
+Manual QA Software Tester,Remote in Taguig,,,Junior
+Scrum Master,Remote in Philippines,"PHP 58,000 - PHP 83,000",2-4 years,Junior
+Junior ABAP Developer,Pasay,,At least 2 year,Junior
+Administrative Associate- Essential Medicines and Health Technologies (EMT),Manila,,2 Years,Junior
+Junior Software Developer,Muntinlupa,"PHP 60,000 - PHP 100,000",2-4 years,Junior
+AML/KYC Junior Officer,Pasig,,1 year,Junior
+Junior Travel Analyst (US Shift),Pasig,,2 years,Junior
+Operations Processor,Taguig,"PHP 55,000 - PHP 95,000",2 years,Junior
+Jr. Software Engineer,Remote in Makati,"PHP, ",,Junior
+Junior Corporate Secretary,Pasig,"PHP 58,000 - PHP 83,000",At least 1 year,Junior
+Customer Happiness Champion,Remote in Philippines,,,Junior
+Finance and Admin Analyst (Open to Fresh Graduates),Hybrid remote in Taguig,"PHP 58,000 - PHP 83,000",0-2 years,Junior
+"Senior Specialist, Facilities",Manila,"PHP 50,000 - PHP 90,000",,Senior
+Senior Operator QA Inspector,Cavite City,"PHP 55,000 - PHP 95,000",,Senior
+"Senior Analyst, AR",Manila,"PHP 60,000 - PHP 100,000",At least 2-4 years,Senior
+Vessel IT Support – Senior Specialist,Manila,"PHP 65,000 - PHP 105,000",,Senior
+Senior Crew - Davao Del Norte (Mindanao),Davao City,"PHP 70,000",At least 2-4 years,Senior
+Senior Cashier,General Santos,"PHP 75,000 - PHP 115,000",2-3 years,Senior
+Senior Staff Technician Equipment,Cavite City,"PHP 80,000 - PHP 120,000",,Senior
+"Sr Supv, Logistics",Tanauan,"PHP 85,000 - PHP 125,000",At least 2-4 years,Senior
+Senior Director Operations Experience : 10+ years Philippines Posted 1 week ago,Philippines,"PHP 90,000 - PHP 130,000",16-18 years,Senior
+Senior Engineer,Remote,,,Senior
+Senior Crew - Negros Oriental (Visayas),Dumaguete,,2-3 years,Senior
+Field Office Personnel,Olongapo,"PHP 110,000",,Senior
+SENIOR TECHNICIAN EQUIPMENT,Cavite City,,1-3 years,Senior
+Senior Supervisor Line Maintenance,Cavite City,"PHP 58,000 - PHP 83,000",5 years,Senior
+Customer Service Advisor - WAH XP 2023,+9 locations,"PHP 50,000 - PHP 90,000",,Senior
+Technician II,Philippines,"PHP 55,000 - PHP 95,000",30 years,Senior
+Operator,Carmona,,at least 2 years,Senior
+Data Process Support,Trece Martires,"Php95,000",,Senior
+Branch Warehouse Helper - Tagum,Tagum,100K,20 years,Senior
+Physical Security Senior Manager,Mandaluyong,,,Senior
+Technical Support / Customer Service Associate - Fixed-Term,Cebu,,,Senior
+"Customer Experience Representative, Senior",Angeles,"PHP 80,000 - PHP 120,000",5 years,Senior
+Senior Staff Process Engineer,General Trias,"PHP 85,000 - PHP 125,000",,Senior
+Senior UI Designer,Philippines,"PHP 90,000 - PHP 130,000",100 years,Senior
+Sales Executive/Senior Executive - Pharma & Personal Care,Philippines,,at least 3-5 years,Senior
+Office Clerk (Cainta Branch),Pasig,"PHP 88,000 ",,Senior
+Senior IT Support,Clark Freeport Zone,P70K,3 years,Senior
+Cashier-JP Rizal,Philippines,,at least 2 years,Senior
+Senior Collection Specialist,Philippines,"PHP 58,000 - PHP 83,000",,Senior
+Senior Crew - Zamboanga Del Sur (Mindanao),Zamboanga City,67K,3 years,Senior
+Senior Collection Specialist,Philippines,,,Senior
+Senior Crew - Agusan Del Norte (Mindanao),Butuan,PHP 90K,4 years,Senior
+Senior Specialist,Manila,Php75K,At least 2 years,Senior
+Senior Logistics Specialist,Batangas City,,35 years,Senior
+Senior Recruiter,Pasig,"PHP 90,000 - PHP 120,000",,Senior
+Project Engineer (Visayas) - Panay,Hybrid remote in Iloilo City,,3 years,Senior
+Senior Crew - Cebu (Visayas),Cebu City,,,Senior
+Senior Crew - Caloocan (Metro Manila),Caloocan,"Php95,000",3 years,Senior
+Senior Product Engineer,Cavite City,,,Senior
+Senior Quality Manager,Tarlac City,,3 years,Senior
+Senior Crew - Negros Occidental (Visayas),Bacolod,80K,,Senior
+Facilities and Admin Director,Remote in Quezon City,76K,10 years,Senior
+"OPERATOR 3, PRODUCTION SUPPORT",Lapu-Lapu City,,at least 2 years,Senior
+Maintenance Supervisor,Santo Tomas,"PHP 65,000",,Senior
+"Senior/Vice President, CEO Office Strategy Projects-Manila",Philippines,,2-3 years,Senior
+Facilities and Admin Director,Remote in Quezon City,"PHP 58,000 - PHP 83,000",10 years,Senior
+"Officer, Surveillance",City of Dreams,"PHP 65,000 - PHP 105,000",,Senior
+"Senior/Vice President, CEO Office Strategy Projects-Manila",Philippines,"PHP 90,000 - PHP 130,000",3 years,Senior
+Quality Control Analyst,General Santos,"Php95,000",,Senior
+Head of Health Safety Security & Environment,Philippines,P100000,2-3 years,Senior
+Hub Supervisor-Muntinlupa,Philippines,,At least 3-5 years,Senior
+DWS - Accounts Payable Specialist - Senior Analyst,Manila,P90K,60 years,Senior
+Senior Project Professional,Taguig,,3 years,Senior
+Senior Crew - Mandaue (Visayas),Mandaue,,,Senior
+"Production/Maint, Assembly/Test",Tanauan,87K,3 years,Senior
+Senior Cashier / Accounts Monitoring Clerk,Pampanga,"PHP 58,000 - PHP 83,000",2-3 years,Senior
+TRANSMISSION LINE AND SUBSTATION PROJECT SENIOR SPECIALIST TO SENIOR OFFICER (GOPS),Philippines,"PHP 55,000 - PHP 95,000",,Senior
+Production Staff,Pasig,"PHP 75,000 - PHP 115,000",,Senior
+Senior Staff Technician Equipment Maintenance,Cavite City,"PHP 85,000 - PHP 125,000",5 Years,Senior
+Senior Crew - Iloilo (Visayas),Iloilo City,,,Senior
+Customer Service Senior Manager,Taguig,,2-3 years,Senior
+Senior Crew- Laguna (South Luzon),Calamba City,,,Senior
+Senior Crew - Bulacan (North Luzon),Baliuag,"PHP 85,000 - PHP 125,000",2-3 years,Senior
+Lubes Warehouseman (Mabini),Hybrid remote in Batangas City,,40 years,Senior
+Senior Crew - Roxas (Visayas),Roxas City,,,Senior
+Senior Operations Manager,Angeles,,At least 10 years,Senior
+Senior Systems Administrator,+1 location,"PHP 55,000 - PHP 95,000",70 years,Senior
+Senior Xero Bookkeeper - Work from Home (Philippines Based),Remote in Philippines,,2 years,Senior
+Customer care collections Senior Rep,Quezon City,,,Senior
+Senior Staff Technician Process,Cavite City,"PHP 60,000 - PHP 85,000",At least 1-3years,Senior
+Senior Project Manager,Clark Freeport Zone,,,Senior
+Regional Management Trainee,Manila,"PHP 80,000 - PHP 90,000",5 years,Senior
+Operator I,Philippines,,2-3 years,Senior
+Senior Bookkeeper,Remote in Quezon City,"PHP 75,000 - PHP 85,000",Minimum 5 years,Senior
+Senior Crew - Pampanga (North Luzon),San Fernando,"PHP 85,000 - PHP 95,000",,Senior
+Project Manager,Manila,,4 - 7 years,Project+Manager
+IT Project Manager,Remote,PHP60KPHP60K-PHP60K,7-10 years,Project+Manager
+Project Manager,Makati,,6-7 years,Project+Manager
+Project Manager,Cebu,,,Project+Manager
+Project Manager,Remote in Manila,"Php 75,000Php 82,000",14 years,Project+Manager
+PROJECT MANAGER,Pasig,,,Project+Manager
+Assistant Project Field Manager - CCPP-Philippines,Remote in Batangas City,,10 years,Project+Manager
+Care Project Manager,Philippines,"Php 70,000  -Php 100,000Php 60,000 to -Php 100,000 ",,Project+Manager
+Assistant Project Manager,Philippines,,,Project+Manager
+Project Manager,Remote,,5 years,Project+Manager
+Project Manager,Pasay,PHP70KPHP70K-PHP70K,,Project+Manager
+Consultancy Project Manager,Makati,"PHP 75,000 - PHP 125,000",5 years,Project+Manager
+Project Manager PMO,Remote in Muntinlupa,"PHP 75,000 - PHP 125,000",5 years,Project+Manager
+Senior Project Manager,Clark Freeport Zone,,,Project+Manager
+Associate Project Manager | Permanent WFH | Up to 100K,Remote in Manila,"Php 80,000  -Php 100,000Php 80,000 to -Php 100,000 ",,Project+Manager
+Consultancy Project Manager,Makati,,5 years,Project+Manager
+Project Manager,Makati,,,Project+Manager
+Associate Project Manager | Permanent WFH | Up to 100K,Remote in Manila,"Php 80,000  -Php 100,000Php 80,000 to -Php 100,000 ",,Project+Manager
+Web Project Manager,Pasong Tamo,,2 years,Project+Manager
+Project Manager,Makati,"PHP 70,000 - PHP 95,000",,Project+Manager
+Project Manager PMO,Remote in Muntinlupa,,5 years,Project+Manager
+Construction Manager (project-based),Philippines,"PHP 80,000 - PHP 130,000",,Project+Manager
+"Project Coordinator, Philippines",Philippines,,At least 3 years,Project+Manager
+Project Manager - Training & Communication,Makati,,,Project+Manager
+Project Manager (Via Verde Padre Garcia Batangas),Muntinlupa,,at least 4 years,Project+Manager
+Trainee- Project Manager,Makati,"PHP 105,000 - PHP 145,000",,Project+Manager
+Client Success Manager - /Project Management/ - WFH - 2 Headcounts,Remote in Manila,"PHP 70,000 - PHP 120,000",At least 2 years,Project+Manager
+Project Manager | Digital Advertisement,Remote in Quezon City,"PHP 75,000 - PHP 125,000",3-5 years,Project+Manager
+Project Coordinator,Cebu,,2 years,Project+Manager
+Project Coordinator,Philippines,"PHP 85,000 - PHP 135,000",At least 3-5 years,Project+Manager
+Consulting Project Associate,Remote in Manila,,2 years,Project+Manager
+Project Manager,Davao City,"PHP 95,000 - PHP 145,000",,Project+Manager
+Integrated Project Manager,Manila,"PHP 100,000 - PHP 150,000",At least 5 years,Project+Manager
+Project Manager (Philippines),Philippines,,5-10 years,Project+Manager
+Print Project Manager,Manila,,4 - 7 years,Project+Manager
+Junior Project Manager,Philippines,,At least 3 years,Project+Manager
+PROJECT MANAGER,Philippines,"PHP 105,000 - PHP 145,000",,Project+Manager
+Project Manager,Mandaluyong,,,Project+Manager
+TRANSMISSION LINE AND SUBSTATION PROJECT SENIOR SPECIALIST TO SENIOR OFFICER (GOPS),Philippines,"PHP 95,000 - PHP 145,000",At least 3 years,Project+Manager
+PROJECT MANAGER,POEA - Overseas,"PHP 65,000 - PHP 95,000",,Project+Manager
+PROJECT MANAGER | INFORMATION TECHNOLOFY | SB FINANCE | MAKATI,Makati,,,Project+Manager
+Project Assistant,Manila,"P90,000 - P140,000",2 years,Project+Manager
+HSE Manager (project-based),Philippines,,,Project+Manager
+Project Manager - United 4,Quezon City,"PHP 75,000 - PHP 125,000",70 years,Project+Manager
+Project Coordinator,Cotabato City,,,Project+Manager
+Project Manager,Hybrid remote in Mandaluyong,"PHP 100,000 - PHP 150,000",40 years,Project+Manager
+Project Engineer (Visayas) - Panay,Hybrid remote in Iloilo City,,3 years,Project+Manager
+Project Manager,Bacolod,,3 years,Project+Manager
+Atlassian Consultant & Project Manager,Makati,"P130,000",,Project+Manager
+Program Manager / Project Manager,Remote in Philippines,,,Project+Manager
+Project Manager (Solar),Mandaluyong,"PHP 80,000 - PHP 130,000",At least 3 years,Project+Manager
+Project Manager,Fort Bonifacio,,5 years,Project+Manager
+Project Coordinator,Cebu City,,At least 1 year,Project+Manager
+Project Management Officer | IT,Philippines,"130,000K",At least 5 years,Project+Manager
+Project Manager,Makati,,at least 8 years,Project+Manager
+Project Manager,Philippines,,At least 1 year,Project+Manager
+Project Manager,Manila,"Php125,000",At least 1-2 years,Project+Manager
+Implementation Project Manager,Mandaluyong,,,Project+Manager
+Project Manager,Manila,"PHP 100,000 - PHP 130,000",At least 2 years,Project+Manager
+Project Manager,Mandaluyong,,,Project+Manager
+Project Manager,Philippines,"PHP 95,000 - PHP 135,000",3-5 years,Project+Manager
+Project Manager,Remote in Philippines,"PHP 100,000 - PHP 140,000",,Project+Manager
+Project Manager,Taguig,,3 years,Project+Manager
+Project Architect Manager,Pasay,"PHP 105,000 - PHP 145,000",At least 10 years,Project+Manager
+Project Manager,Philippines,"Php75,000 ",3-5 years,Project+Manager
+Project Manager,Philippines,"PHP70,000 - PHP120,000",,Project+Manager
+Project Manager,Quezon City,,2 years,Project+Manager
+FT PROJECT MANAGER,Philippines,"PHP 105,000 - PHP 145,000",,Project+Manager
+Project Manager – PEGA,Philippines,,At least 5 years,Project+Manager
+Project Manager,Makati,"PHP 75,000 - PHP 125,000",at least 10 years,Project+Manager
+Project Coordinator,Cebu City,"PHP 80,000 - PHP 130,000",,Project+Manager
+PROJECT / OPERATIONS MANAGER,Pasig,"PHP 100,000 - PHP 140,000",7 years,Project+Manager
+PROJECT MANAGER (Customer Contact Group),Makati,,,Project+Manager
+Project Engineer,Tanauan,"PHP 85,000 - PHP 120,000",3-5 years,Project+Manager
+Sr. Project Manager,Hybrid remote in Manila,,5 years,Project+Manager
+Customer Service Representative,Cebu City,PHP120KPHP120K-PHP120K,8 years,CTO
+Customer Experience Assistant: Policy Changes,Remote in Cebu City,PHP130KPHP130K-PHP130K,3 years,CTO
+Commercial Lines Assistant,Remote in Cebu City,PHP45KPHP45K-PHP45K,8 years,CTO
+Executive Assistant,Remote in Cebu City,PHP30KPHP30K-PHP30K,8 years,CTO
+CTO – Philippines – Regional Bank,Philippines,,10 years,CTO
+Client Service Officer,Remote in Cebu City,PHP250KPHP250K-PHP250K,8 years,CTO
+Sales Admin Support,Remote in Cebu City,PHP154KPHP154K-PHP154K,8 years,CTO
+Global Campaign Manager - Employer Brand (Remote),+1 location,,5-10 years,CTO
+Senior Executive Assistant,Remote in Cebu City,PHP130KPHP130K-PHP130K,25 years,CTO
+Team Lead – Estimating Plan Prep,Cebu City,PHP170KPHP170K-PHP170K,2 years,CTO
+Visual Media Ad Specialist,Remote in Cebu City,PHP150KPHP150K-PHP150K,At least 2 years,CTO
+Web Developer,Remote in Cebu City,PHP180KPHP180K-PHP180K,At least 3 years,CTO
+Head of Information Security,Cebu City,,7 years,CTO
+Chief Transformation Officer,Philippines,,At least 10 years,CTO
+Technical Engineer,Makati,,At least 3 year,CTO
+Community Manager - Web3 Metaverse Gaming - Fully Remote - ph,Remote,,,CTO
+IT Asset Administrator,Cebu City,PHP175KPHP175K-PHP175K,At least 5 year,CTO
+HR Manager,Cebu City,PHP190KPHP190K-PHP190K,8 years,CTO
+Head - Information Security,Remote in Philippines,,,CTO
+Property Accountant,Remote in Cebu City,PHP135KPHP135K-PHP135K,30 years,CTO
+Marketing Coordinator,Remote in Cebu City,PHP160KPHP160K-PHP160K,At least 2 years,CTO
+Business Analyst,Philippines,,8 years,CTO
+Senior Back-End Engineer,Remote in Central Luzon,PHP 150KPHP,7 years,CTO
+Air Service Junior Associate,Taguig,,,CTO
+Communications/PR Manager - Blockchain - Crypto - Remote,Remote in Manila,"PHP 80,000 - PHP 130,000",7 years,CTO
+AC Manila - Cybersecurity DFIR Analyst,Pasig,,,CTO
+Product Manager Philippines,Remote,,At least 2 years,CTO
+Enterprise Account Manager,Taguig,,,CTO
+Solutions Architect,Philippines,"PHP, ",5 years,CTO
+AC Manila - Cybersecurity DFIR Senior Analyst,Pasig,PHP130KPHP130K-PHP130K,,CTO
+AC Manila - Cybersecurity DFIR Senior Analyst,Pasig,,,CTO
+Senior iOS Developer,Philippines,PHP100KPHP100K-PHP100K,8 years,CTO
+AC Manila - Organizational Development Senior Manager,Pasig,,5 years,CTO
+Software Architect (Remote),Remote in Cebu,,,CTO
+Senior Property Accountant,Remote in Cebu City,PHP160KPHP160K-PHP160K,8 years,CTO
+IOS Developer,Philippines,,8 years,CTO
+Air Operations Junior Associate,Taguig,,,CTO
+Content Creator/Copywriter - Blockchain - Crypto - Remote,Remote in Manila,PHP170KPHP170K-PHP170K,,CTO
+Senior Software Development Manager,Taguig,,,CTO
+IOS Developer (Senior),Philippines,,8 years,CTO
+Head of Application Support,Manila,"PHP 85,000 - PHP 135,000",8 years,CTO
+Senior Android Developer,Philippines,,8 years,CTO
+Android Developer (Mid & Senior),Philippines,,8 years,CTO
+Senior Android App Developer,Philippines,"Php 95,000 - PHP 150,000",8 years,CTO
+SAP Sales and Distribution Consultation,Remote in National Capital Region,,5 years,CTO
+Senior Designer Marketing (Blockchain),Remote in Manila,,3-4 years,CTO
+Outbound Sales Lead Generator (BPO Company-Alabang),Alabang,,At least 2-3 years,CTO
+Customer Success Manager,Remote,"PHP 95,000 - PHP 145,000",Minimum 5 - 10 years,CTO
+Data Analyst and Systems Support (Permanent WFH),Remote,"Php160,000.00 ",,CTO
+Software Quality Assurance Engineer,Remote in Mandaluyong,"Php120,000.00  -Php155,000.00 ",,CTO
+Sales Executive,Remote in Mandaluyong,"Php360,000.00 ",At least 3-6 years,CTO
+L2 Service Desk Engineer - WORK FROM HOME,Remote,,3-5 years,CTO
+Chief Technology Officer (CTO) - Remote,Remote in Manila,"Php200,000.00  -Php450,000.00 ",at least 10 years,CTO
+"Software Developer Trainees l 15,000 to 18,000",Angeles,Php150K,,CTO
+Production/Manufacturing Assistant,Santa Rosa City,,,CTO
+Program Manager,Remote in Makati,"Php85,000.00  -Php100,000.00 ",At least 7-10 years,CTO
+Business Analyst,Remote in Mandaluyong,"Php136,000.00",5 year,CTO
+IT Manager,Remote in Makati,"Php110,000.00 ",At least 7-10 years,CTO
+Software Developer,Angeles,"Php150,000.00  -Php180,000.00 ",7 years,CTO
+Web CTO,Remote in Manila,"Php100,000.00  -Php200,000.00 ",,CTO
+Audit Assistant,Baguio,"Php120,000.00 ",6 year,CTO
+IT Operations Manager,Makati,"Php180,000.00",5 years,CTO
+Senior PHP Developer,Remote in Pampanga,"PHP 100,000.00  130,000.00
+",,CTO
+Data Analyst and Systems Support,Remote in Manila,,,CTO
+Lead DevOps | Work From Home,Remote,"PHP, ",7 years,CTO
+IT Project Manager,Remote in Makati,"Php80,000.00  -Php80,000.00 ",At least 5 years,CTO
+IT Operations & Support Head (IT Manager),Taguig,"Php100,000.00 ",,CTO
+iOS Swift Developer,Remote,,6 year,CTO
+Sr. Data Engineer,+1 location,"Php150,000.00 ",,CTO
+Secretary,Alabang,"Php140,000.00 ",7 year,CTO
+Chief Technology Officer | Flexible Shift - Permanent Work From Home,Remote in Makati,"Php150,000.00  -Php200,000.00 ",5 years,CTO
+Senior Web Developer,Remote in Manila,"Php80,000.00  -Php100,000.00 ",,CTO
+HEAD OF THE SOFTWARE DEVELOPMENT TEAM,Taguig,"Php150,000.00  -Php200,000.00 ",7 years,CTO
+Chief Technology Officer,Taguig,,,CTO
+Chief Technology Officer (CTO),Makati,P160K,5 years,CTO

Models/indeed.csv

@@ -0,0 +1,285 @@
+Experience,Job_Pos,New Salary
+1.0,1,25000.0
+1.5,1,30000.0
+1.5,1,49804.27627052734
+1.5,1,60000.0
+1.5,1,40500.0
+1.5,1,40000.0
+1.8,1,32500.0
+1.5,1,34500.0
+1.8,1,36500.0
+1.5,1,38500.0
+1.8,1,49804.27627052734
+1.0,1,42500.0
+3.0,1,35000.0
+1.0,1,30000.0
+1.0,1,46500.0
+5.0,1,48500.0
+1.5,1,50500.0
+2.5,1,52500.0
+1.5,1,49804.27627052734
+1.0,1,56500.0
+1.0,1,58500.0
+2.5,1,60500.0
+1.8,1,49804.27627052734
+1.0,1,64500.0
+2.0,1,49804.27627052734
+1.8,1,62500.0
+1.5,1,49804.27627052734
+2.0,1,54500.0
+1.8,1,27000.0
+2.5,1,49804.27627052734
+1.5,1,32500.0
+1.8,1,40000.0
+1.5,1,49804.27627052734
+2.0,1,30000.0
+1.5,1,40500.0
+1.5,1,36500.0
+1.8,1,38500.0
+1.5,1,42500.0
+1.8,1,49804.27627052734
+1.5,1,55000.0
+1.8,1,40000.0
+1.5,1,42500.0
+1.5,1,49804.27627052734
+2.0,1,36500.0
+1.5,1,38500.0
+2.0,1,49804.27627052734
+1.8,1,49804.27627052734
+1.5,1,35000.0
+2.0,1,49804.27627052734
+1.8,1,42500.0
+1.0,1,49804.27627052734
+1.8,1,49804.27627052734
+1.5,1,45000.0
+1.5,1,49804.27627052734
+1.8,1,49804.27627052734
+1.0,1,49804.27627052734
+2.0,1,49804.27627052734
+1.8,1,70000.0
+2.0,1,49804.27627052734
+2.0,1,45000.0
+1.8,1,49804.27627052734
+1.0,1,42000.0
+1.8,1,49804.27627052734
+3.0,1,70500.0
+2.0,1,49804.27627052734
+2.0,1,49804.27627052734
+3.0,1,80000.0
+1.0,1,49804.27627052734
+2.0,1,49804.27627052734
+2.0,1,75000.0
+1.8,1,49804.27627052734
+1.0,1,70500.0
+1.8,1,49804.27627052734
+1.0,1,70500.0
+3.3,2,70000.0
+3.3,2,75000.0
+3.0,2,80000.0
+3.3,2,85000.0
+3.0,2,70000.0
+2.5,2,95000.0
+3.3,2,100000.0
+3.0,2,105000.0
+3.3,2,77853.59696090454
+2.5,2,77853.59696090454
+3.3,2,110000.0
+2.0,2,77853.59696090454
+5.0,2,70500.0
+3.3,2,70000.0
+2.0,2,77853.59696090454
+3.3,2,95000.0
+3.3,2,77853.59696090454
+3.3,2,77853.59696090454
+5.0,2,100000.0
+3.3,2,105000.0
+4.0,2,77853.59696090454
+3.3,2,88000.0
+3.0,2,70000.0
+2.0,2,77853.59696090454
+3.3,2,70500.0
+3.0,2,67000.0
+3.3,2,77853.59696090454
+4.0,2,90000.0
+2.0,2,75000.0
+3.3,2,105000.0
+3.0,2,77853.59696090454
+3.3,2,77853.59696090454
+3.0,2,95000.0
+3.3,2,77853.59696090454
+3.0,2,77853.59696090454
+3.3,2,80000.0
+10.0,2,76000.0
+2.0,2,77853.59696090454
+3.3,2,65000.0
+2.5,2,77853.59696090454
+10.0,2,70500.0
+3.3,2,85000.0
+3.0,2,110000.0
+3.3,2,95000.0
+2.5,2,100000.0
+4.0,2,77853.59696090454
+3.0,2,77853.59696090454
+3.3,2,77853.59696090454
+3.0,2,87000.0
+2.5,2,70500.0
+3.3,2,75000.0
+3.3,2,95000.0
+5.0,2,105000.0
+3.3,2,77853.59696090454
+2.5,2,77853.59696090454
+3.3,2,77853.59696090454
+2.5,2,105000.0
+3.3,2,77853.59696090454
+10.0,2,77853.59696090454
+2.0,2,77853.59696090454
+3.3,2,77853.59696090454
+2.0,2,72500.0
+3.3,2,77853.59696090454
+5.0,2,85000.0
+2.5,2,77853.59696090454
+5.0,2,80000.0
+3.3,2,90000.0
+5.5,3,105902.91765128174
+8.5,3,60000.0
+6.5,3,105902.91765128174
+4.8,3,105902.91765128174
+14.0,3,44750.0
+4.8,3,105902.91765128174
+10.0,3,105902.91765128174
+4.8,3,80000.0
+4.8,3,105902.91765128174
+5.0,3,105902.91765128174
+4.8,3,70000.0
+5.0,3,100000.0
+5.0,3,100000.0
+4.8,3,105902.91765128174
+4.8,3,90000.0
+5.0,3,105902.91765128174
+4.8,3,105902.91765128174
+4.8,3,90000.0
+2.0,3,105902.91765128174
+4.8,3,82500.0
+5.0,3,105902.91765128174
+4.8,3,105000.0
+3.0,3,105902.91765128174
+4.8,3,105902.91765128174
+4.0,3,105902.91765128174
+4.8,3,125000.0
+2.0,3,95000.0
+4.0,3,100000.0
+2.0,3,105902.91765128174
+4.0,3,110000.0
+2.0,3,105902.91765128174
+4.8,3,120000.0
+5.0,3,125000.0
+7.5,3,105902.91765128174
+5.5,3,105902.91765128174
+3.0,3,105902.91765128174
+4.8,3,125000.0
+4.8,3,105902.91765128174
+3.0,3,120000.0
+4.8,3,80000.0
+4.8,3,105902.91765128174
+2.0,3,115000.0
+4.8,3,105902.91765128174
+4.8,3,105902.91765128174
+3.0,3,105902.91765128174
+3.0,3,105902.91765128174
+4.8,3,130000.0
+4.8,3,105902.91765128174
+3.0,3,105000.0
+5.0,3,105902.91765128174
+1.0,3,105902.91765128174
+5.0,3,130.0
+8.0,3,105902.91765128174
+1.0,3,105902.91765128174
+1.5,3,125000.0
+4.8,3,105902.91765128174
+2.0,3,115000.0
+4.8,3,105902.91765128174
+4.0,3,115000.0
+4.8,3,120000.0
+3.0,3,105902.91765128174
+10.0,3,125000.0
+4.0,3,75000.0
+4.8,3,95000.0
+2.0,3,105902.91765128174
+4.8,3,125000.0
+5.0,3,105902.91765128174
+10.0,3,100000.0
+4.8,3,105000.0
+7.0,3,120000.0
+4.8,3,105902.91765128174
+4.0,3,102500.0
+5.0,3,105902.91765128174
+8.0,4,120000.0
+3.0,4,130000.0
+8.0,4,45000.0
+8.0,4,30000.0
+10.0,4,133952.23834165896
+8.0,4,154000.0
+7.5,4,133952.23834165896
+2.0,4,170000.0
+2.0,4,150000.0
+3.0,4,180000.0
+7.0,4,133952.23834165896
+10.0,4,133952.23834165896
+3.0,4,133952.23834165896
+6.2,4,133952.23834165896
+5.0,4,175000.0
+8.0,4,190000.0
+6.2,4,133952.23834165896
+2.0,4,160000.0
+8.0,4,133952.23834165896
+7.0,4,150000.0
+6.2,4,133952.23834165896
+7.0,4,105000.0
+6.2,4,133952.23834165896
+2.0,4,133952.23834165896
+6.2,4,133952.23834165896
+5.0,4,133952.23834165896
+6.2,4,130000.0
+6.2,4,133952.23834165896
+8.0,4,100000.0
+5.0,4,133952.23834165896
+6.2,4,133952.23834165896
+8.0,4,160000.0
+8.0,4,133952.23834165896
+6.2,4,133952.23834165896
+6.2,4,170000.0
+6.2,4,133952.23834165896
+8.0,4,133952.23834165896
+8.0,4,110000.0
+8.0,4,133952.23834165896
+8.0,4,133952.23834165896
+8.0,4,122500.0
+5.0,4,133952.23834165896
+3.5,4,133952.23834165896
+2.5,4,133952.23834165896
+7.5,4,120000.0
+6.2,4,160000.0
+6.2,4,137500.0
+4.0,4,133952.23834165896
+6.2,4,150000.0
+6.2,4,133952.23834165896
+8.5,4,92500.0
+5.0,4,136000.0
+8.5,4,110000.0
+7.0,4,165000.0
+6.2,4,150000.0
+6.0,4,120000.0
+5.0,4,180000.0
+6.2,4,115000.0
+6.2,4,133952.23834165896
+7.0,4,133952.23834165896
+5.0,4,80000.0
+6.2,4,100000.0
+6.0,4,133952.23834165896
+6.2,4,150000.0
+7.0,4,140000.0
+5.0,4,175000.0
+6.2,4,90000.0
+7.0,4,175000.0
+6.2,4,133952.23834165896
+5.0,4,160000.0

Models/km_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4de62a5b4d1edec0c8d722cda4c8b1c6b1f47c16ded3e96ab5fb5716d2ad427
+size 595004

Models/km_model_generator.ipynb

@@ -0,0 +1,220 @@
+{
+  "cells": [
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "uB6uMMVrfH_p"
+      },
+      "source": [
+        "# ***Activity 2***\n",
+        "\n",
+        "\n",
+        "> *Catanus, Jeziah Lois*\n",
+        "\n",
+        "> *Fagarita, Dave*\n",
+        "\n",
+        "> *Magno, Jannica Mae*\n",
+        "\n",
+        "> *Servandil, Jimuel*\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "id": "PD1hB3g9AppT"
+      },
+      "outputs": [],
+      "source": [
+        "import pandas as pd\n",
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {
+        "id": "dX9CEupAAn9v"
+      },
+      "outputs": [],
+      "source": [
+        " # Load the dataset\n",
+        "df = pd.read_csv('indeed.csv')"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bkxJeIfNfVUi"
+      },
+      "source": [
+        "# **K-Means**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "DbrYBVfBS-4H",
+        "outputId": "42bf8aaf-c357-4d4c-d34f-10a23d42e811"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "The average silhouette_score is : 0.6621242593156673\n"
+          ]
+        }
+      ],
+      "source": [
+        "from sklearn.metrics import silhouette_score\n",
+        "import numpy as np\n",
+        "import pickle\n",
+        "\n",
+        "# Define the k-means clustering algorithm\n",
+        "def k_means(data, k, max_iter):\n",
+        "    # Randomly initialize k centroids\n",
+        "    centroids = data.sample(n=k, random_state=42)\n",
+        "    centroids.index = range(k)\n",
+        "\n",
+        "    # Initialize a dictionary to store the cluster assignments\n",
+        "    clusters = {}\n",
+        "\n",
+        "    # Run the k-means algorithm for the specified number of iterations\n",
+        "    for i in range(max_iter):\n",
+        "        # Assign each data point to the nearest centroid\n",
+        "        for j in range(len(data)):\n",
+        "            distances = []\n",
+        "            for c in centroids.index:\n",
+        "              # Calculate the distances using Euclidean distance metric\n",
+        "                distances.append(np.sqrt(((data.iloc[j] - centroids.loc[c])**2).sum()))\n",
+        "            cluster = np.argmin(distances)\n",
+        "            if cluster not in clusters:\n",
+        "                clusters[cluster] = []\n",
+        "            clusters[cluster].append(j)\n",
+        "\n",
+        "        # Recalculate the centroids\n",
+        "        for c in clusters:\n",
+        "            centroids.loc[c] = data.iloc[clusters[c]].mean()\n",
+        "\n",
+        "    # Create a list of cluster assignments for each data point\n",
+        "    labels = np.zeros(len(data))\n",
+        "    for c in clusters:\n",
+        "        for i in clusters[c]:\n",
+        "            labels[i] = c\n",
+        "    \n",
+        "    # Calculate the silhouette score for evaluation\n",
+        "    silhouette_avg = silhouette_score(data, labels)\n",
+        "    print(\"The average silhouette_score is :\", silhouette_avg)\n",
+        "    \n",
+        "    # Return the cluster assignments and centroids\n",
+        "    return clusters, centroids, silhouette_avg\n",
+        "\n",
+        "# Run k-means clustering on the iris dataset with k=3\n",
+        "clusters, centroids, silhouette_avg = k_means(df.drop('Job_Pos', axis=1), k=4, max_iter=100)\n"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "L6Ish1xRfiDa"
+      },
+      "source": [
+        "# **Visualization**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "image/png": "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",
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "fig, ax = plt.subplots()\n",
+        "colors = ['r', 'g', 'b', 'y']\n",
+        "labels = ['Junior', 'Senior', 'Project Manager', 'CTO']\n",
+        "for i, c in enumerate(clusters):\n",
+        "    ax.scatter(df.loc[clusters[c], 'Experience'], df.loc[clusters[c], 'New Salary'], color=colors[i], label=labels[i])\n",
+        "ax.scatter(centroids['Experience'], centroids['New Salary'], marker='x', color='k', s=100, linewidth=2, label='Centroids')\n",
+        "ax.set_xlabel('Experience')\n",
+        "ax.set_ylabel('New Salary')\n",
+        "ax.set_title('Clustered Job Positions')\n",
+        "ax.legend()\n",
+        "\n",
+        "# save the figure object to a pickle file\n",
+        "with open('km_model.pkl', 'wb') as f:\n",
+        "    pickle.dump(fig, f)\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "image/png": "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",
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "# load the figure from the pickle file\n",
+        "with open('km_model.pkl', 'rb') as f:\n",
+        "    fig = pickle.load(f)\n",
+        "\n",
+        "# save the figure as an image file\n",
+        "fig.savefig('../static/images/cluster.png', format='png')"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "interpreter": {
+      "hash": "e9abd7bf17300ee9df567d8d9580282ee75f9a695f2d1fb59e9523387a62f2ed"
+    },
+    "kernelspec": {
+      "display_name": "Python 3.11.2 64-bit",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.11.2"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Models/knn_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60c2ba5b1b1610f028c58bd569d89f9256848a71bcd893dffb726dd71f54bd5a
+size 7153

Models/knn_model_gen.ipynb

@@ -0,0 +1,207 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "UQK1MhvbUiO1"
+      },
+      "source": [
+        "#KNN on the Iris Dataset"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 10,
+      "metadata": {
+        "id": "CtfYG2yrQ0i-"
+      },
+      "outputs": [],
+      "source": [
+        "from sklearn import neighbors\n",
+        "from sklearn.datasets import load_iris\n",
+        "from sklearn.metrics import confusion_matrix\n",
+        "from sklearn.metrics import f1_score\n",
+        "from sklearn.metrics import accuracy_score\n",
+        "import pandas as pd"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 11,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "BznYCXGPQ4dA",
+        "outputId": "4b30e9e8-2774-4870-9ff3-4f680d12b7c2"
+      },
+      "outputs": [],
+      "source": [
+        " # Load the dataset\n",
+        "data = pd.read_csv('indeed.csv')\n",
+        "\n",
+        "X = data.iloc[:, [0, 2]].values\n",
+        "y = data.iloc[:, 1].values"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 12,
+      "metadata": {
+        "id": "vICs_orGRMDG"
+      },
+      "outputs": [],
+      "source": [
+        "# Split data into training and testing sets\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 13,
+      "metadata": {
+        "id": "ah1zLnrYRONr"
+      },
+      "outputs": [],
+      "source": [
+        "# Number of nearest neighbors\n",
+        "num_neighbors = 12\n",
+        "# Step size of the visualization grid\n",
+        "step_size = 0.01\n",
+        "# Create a K Nearest Neighbors classifier model\n",
+        "clfKNN = neighbors.KNeighborsClassifier()\n",
+        "\n",
+        "clfKNN.fit(X_train, y_train)\n",
+        "\n",
+        "y_test_pred = clfKNN.predict(X_test)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 14,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "wBfBd6dtSzIn",
+        "outputId": "89876b62-9471-4474-8d15-e60732565836"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "f1_score: 0.8139534883720931\n"
+          ]
+        }
+      ],
+      "source": [
+        "f1_score = f1_score(y_test, y_test_pred, average='micro')\n",
+        "print(f'f1_score: {f1_score}')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 15,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "E4qA4gpUNH9X",
+        "outputId": "fbc9e502-a49e-422a-8863-86548187bfc2"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Accuracy: 81.3953488372093\n"
+          ]
+        }
+      ],
+      "source": [
+        "# Evaluate the model on the test data\n",
+        "accuracy = 100 * accuracy_score(y_test, y_test_pred)\n",
+        "print(f'Accuracy: {accuracy}')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 16,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "p0dObkPrSlEZ",
+        "outputId": "06d843c3-94ff-486c-d4c6-7a411edb0e40"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "[[17  2  0  0]\n",
+            " [ 0 14  5  0]\n",
+            " [ 0  4 18  1]\n",
+            " [ 1  1  2 21]]\n"
+          ]
+        }
+      ],
+      "source": [
+        "cmKNN = confusion_matrix(y_test, y_test_pred)\n",
+        "print(cmKNN)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 19,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "[1]\n"
+          ]
+        }
+      ],
+      "source": [
+        "import pickle\n",
+        "\n",
+        "pickle.dump(clfKNN, open('knn_model.pkl', 'wb'))\n",
+        "\n",
+        "knn_model_dump = pickle.load(open('knn_model.pkl', 'rb'))\n",
+        "\n",
+        "print(clfKNN.predict([[1.2, 100]]))"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "interpreter": {
+      "hash": "e9abd7bf17300ee9df567d8d9580282ee75f9a695f2d1fb59e9523387a62f2ed"
+    },
+    "kernelspec": {
+      "display_name": "Python 3.11.2 64-bit",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.11.2"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Models/linreg_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b6f9f0ed279298f30aa701e71eaa11b7ff670d088a53932f65de52d4c1aa9f
+size 445

Models/nbB_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca7539157a3ea721c45ffafa0d62c152149c43ab06391b3e023dd13f17f1c71
+size 886

Models/nbG_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba783ac46b66fc1206d940e9188f68915556d70478679f31344b1d8cdd633295
+size 866

Models/nbM_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90052f7a17c503036130ac744eacb5112ab890757499f2d178fa4a9f97943232
+size 923

README.md

@@ -0,0 +1,11 @@
+---
+title: Salary Prediction
+emoji: 🐢
+colorFrom: pink
+colorTo: green
+sdk: docker
+pinned: false
+license: unknown
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

algos.html

@@ -0,0 +1,78 @@
+<!DOCTYPE html>
+<html>
+
+<head>
+    <meta charset="utf-8 " />
+    <title>Classifiers</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='main.css')}}">
+    <link href="https://fonts.googleapis.com " rel="preconnect " />
+    <link href="https://fonts.gstatic.com " rel="preconnect " crossorigin="anonymous " />
+    <script src="https://ajax.googleapis.com/ajax/libs/webfont/1.6.26/webfont.js " type="text/javascript "></script>
+    <script type="text/javascript ">
+        WebFont.load({
+            google: {
+                families: ["Orbitron:regular,500,600,700,800,900 ", "Noto Sans Tamil:100,200,300,regular,500,600,700,800,900 ", "Inter:100,200,300,regular,500,600,700,800,900 "]
+            }
+        });
+    </script>
+    <script type="text/javascript ">
+        ! function(o, c) {
+            var n = c.documentElement,
+                t = " w-mod- ";
+            n.className += t + "js ", ("ontouchstart " in o || o.DocumentTouch && c instanceof DocumentTouch) && (n.className += t + "touch ")
+        }(window, document);
+    </script>
+</head>
+
+<body>
+    <div class="tab-container">
+        <!-- Left column (tab menu) -->
+        <div class="tab-menu">
+            <button class="tablinks active" onclick="openTab(event, 'knn')">KNN</button>
+            <button class="tablinks" onclick="openTab(event, 'linear')">Linear Regression</button>
+            <button class="tablinks" onclick="openTab(event, 'kmeans')">KMeans</button>
+            <button class="tablinks" onclick="openTab(event, 'naive-bayes')">Naive Bayes</button>
+        </div>
+
+        <!-- Right column (tab content) -->
+        <div class="tab-content">
+            <div id="linear" class="tabcontent">
+                <iframe src="{{ url_for('linear') }}" style="width:100%; height:500px;" scrolling="no"></iframe>
+            </div>
+
+            <div id="knn" class="tabcontent">
+                <iframe src="{{ url_for('knn') }}" style="width:100%; height:500px;" scrolling="no"></iframe>
+            </div>
+
+            <div id="kmeans" class="tabcontent">
+                <iframe src="{{ url_for('kmeans') }}" style="width:100%; height:500px;" scrolling="no"></iframe>
+            </div>
+
+            <div id="naive-bayes" class="tabcontent">
+                <iframe src="{{ url_for('naive') }}" style="width:100%; height:500px;" scrolling="no"></iframe>
+            </div>
+        </div>
+
+        <script>
+            document.getElementById("knn").style.display = "block";
+
+            function openTab(evt, tabName) {
+                var i, tabcontent, tablinks;
+
+                tabcontent = document.getElementsByClassName("tabcontent");
+                for (i = 0; i < tabcontent.length; i++) {
+                    tabcontent[i].style.display = "none";
+                }
+
+                tablinks = document.getElementsByClassName("tablinks");
+                for (i = 0; i < tablinks.length; i++) {
+                    tablinks[i].className = tablinks[i].className.replace(" active", "");
+                }
+
+                document.getElementById(tabName).style.display = "block";
+                evt.currentTarget.className += " active";
+            }
+        </script>
+</body>
+
+</html>

app.ipynb

@@ -0,0 +1,396 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from flask import Flask, render_template, request, url_for\n",
+    "import pickle\n",
+    "import numpy as np\n",
+    "\n",
+    "linreg = pickle.load(open('Models/lr.pkl', 'rb'))\n",
+    "knn_model = pickle.load(open('Models/knn_model.pkl', 'rb'))\n",
+    "gaussian_nb = pickle.load(open('Models/nbG_model.pkl', 'rb'))\n",
+    "multinomial_nb = pickle.load(open('Models/nbM_model.pkl', 'rb'))\n",
+    "bernoulli_nb = pickle.load(open('Models/nbB_model.pkl', 'rb'))\n",
+    "\n",
+    "job_map = {\n",
+    "    1: 'Junior',\n",
+    "    2: 'Senior',\n",
+    "    3: 'Project Manager',\n",
+    "    4: 'CTO',\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "while True:\n",
+    "    salary = float(input(\"Enter salary: \"))\n",
+    "    print(\"Salary entered: \", salary)\n",
+    "\n",
+    "    experience = float(input(\"Enter experience: \"))\n",
+    "    print(\"Experience entered: \", experience)\n",
+    "\n",
+    "    with open('Models/tts.pkl', 'rb') as f:\n",
+    "        data = pickle.load(f)\n",
+    "\n",
+    "    X=data['X']\n",
+    "    y=data['y']\n",
+    "\n",
+    "    X = np.vstack((X, np.array([salary, experience])))\n",
+    "    y= np.hstack((y, experience))  # use a new label for the user's input\n",
+    "\n",
+    "    # Split the data into training and testing sets\n",
+    "    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+    "\n",
+    "    # Fit the Naive Bayes models on the training data\n",
+    "    gaussian_nb.fit(X_train, y_train)\n",
+    "    multinomial_nb.fit(X_train, y_train)\n",
+    "    bernoulli_nb.fit(X_train, y_train)\n",
+    "\n",
+    "    # Evaluate the accuracy of the models on the testing set\n",
+    "    gaussian_accuracy = gaussian_nb.score(X_test, y_test)\n",
+    "    multinomial_accuracy = multinomial_nb.score(X_test, y_test)\n",
+    "    bernoulli_accuracy = bernoulli_nb.score(X_test, y_test)\n",
+    "\n",
+    "    # Use each Naive Bayes model to make a prediction based on the user's input values\n",
+    "    gaussian_prediction = gaussian_nb.predict([[salary, experience]])[0]\n",
+    "    multinomial_prediction = multinomial_nb.predict([[salary, experience]])[0]\n",
+    "    bernoulli_prediction = bernoulli_nb.predict([[salary, experience]])[0]\n",
+    "\n",
+    "    # Map the predicted job titles to their corresponding string values\n",
+    "    gaussian_prediction = job_map.get(gaussian_prediction)\n",
+    "    multinomial_prediction = job_map.get(multinomial_prediction)\n",
+    "    bernoulli_prediction = job_map.get(bernoulli_prediction)\n",
+    "\n",
+    "    # # Print the accuracy and predicted job title for each Naive Bayes model\n",
+    "    # print(\"Gaussian Accuracy: {:.2f}%, Prediction: {}\".format(gaussian_accuracy * 100, gaussian_prediction))\n",
+    "    # print(\"Multinomial Accuracy: {:.2f}%, Prediction: {}\".format(multinomial_accuracy * 100, multinomial_prediction))\n",
+    "    # print(\"Bernoulli Accuracy: {:.2f}%, Prediction: {}\".format(bernoulli_accuracy * 100, bernoulli_prediction))\n",
+    "    # print(\"\\n\")\n",
+    "\n",
+    "    # # Evaluate the accuracy of the models on the new input\n",
+    "    # gaussian_accuracy_new = gaussian_nb.score([[salary, experience]], [5])\n",
+    "    # multinomial_accuracy_new = multinomial_nb.score([[salary, experience]], [5])\n",
+    "    # bernoulli_accuracy_new = bernoulli_nb.score([[salary, experience]], [5])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "    #     X=data['X']\n",
+    "    #     y=data['y']\n",
+    "\n",
+    "    #     # Combine the user's input values with the existing data\n",
+    "    #     X_new = np.vstack((X, np.array([salary, experience])))\n",
+    "    #     y_new = np.hstack((y, 5))  # use a new label for the user's input\n",
+    "\n",
+    "    #     n_splits=10\n",
+    "\n",
+    "    #     # Use k-fold cross-validation to generate a new test set for each iteration\n",
+    "    #     kf = KFold(n_splits=n_splits, shuffle=False, random_state=None)\n",
+    "\n",
+    "    #     gaussian_accuracy = 0\n",
+    "    #     multinomial_accuracy = 0\n",
+    "    #     bernoulli_accuracy = 0\n",
+    "\n",
+    "    #     for train_index, test_index in kf.split(X_new):\n",
+    "    #         X_train, X_test = X_new[train_index], X_new[test_index]\n",
+    "    #         y_train, y_test = y_new[train_index], y_new[test_index]\n",
+    "\n",
+    "    #         # Fit the Naive Bayes models on the training data\n",
+    "    #         gaussian_nb.fit(X_train, y_train)\n",
+    "    #         multinomial_nb.fit(X_train, y_train)\n",
+    "    #         bernoulli_nb.fit(X_train, y_train)\n",
+    "\n",
+    "    #         # Use each Naive Bayes model to make a prediction based on the user's input values\n",
+    "    #         gaussian_prediction = gaussian_nb.predict([[salary, experience]])[0]\n",
+    "    #         multinomial_prediction = multinomial_nb.predict([[salary, experience]])[0]\n",
+    "    #         bernoulli_prediction = bernoulli_nb.predict([[salary, experience]])[0]\n",
+    "\n",
+    "    #         # Update the accuracy scores for each Naive Bayes model\n",
+    "    #         gaussian_accuracy += gaussian_nb.score(X_test, y_test)\n",
+    "    #         multinomial_accuracy += multinomial_nb.score(X_test, y_test)\n",
+    "    #         bernoulli_accuracy += bernoulli_nb.score(X_test, y_test)\n",
+    "\n",
+    "    #     # Calculate the mean accuracy for each Naive Bayes model over all folds\n",
+    "    #     gaussian_accuracy = round(gaussian_accuracy / n_splits * 100, 3)\n",
+    "    #     multinomial_accuracy = round(multinomial_accuracy / n_splits * 100, 3)\n",
+    "    #     bernoulli_accuracy = round(bernoulli_accuracy / n_splits * 100, 3)\n",
+    "\n",
+    "    #     # Map the predicted job titles to their corresponding string values\n",
+    "    #     gaussian_prediction = job_map.get(gaussian_prediction)\n",
+    "    #     multinomial_prediction = job_map.get(multinomial_prediction)\n",
+    "    #     bernoulli_prediction = job_map.get(bernoulli_prediction)\n",
+    "\n",
+    "    #     # Render the results template with the predicted job classification and accuracy scores\n",
+    "    #     return render_template('naive.html',\n",
+    "    #         gaussian_prediction=gaussian_prediction,\n",
+    "    #         multinomial_prediction=multinomial_prediction,\n",
+    "    #         bernoulli_prediction=bernoulli_prediction,\n",
+    "    #         gaussian_accuracy=str(gaussian_accuracy) + \"%\",\n",
+    "    #         multinomial_accuracy=str(multinomial_accuracy) + \"%\",\n",
+    "    #         bernoulli_accuracy=str(bernoulli_accuracy) + \"%\",\n",
+    "    #         salary=salary,\n",
+    "    #         experience=experience,\n",
+    "    #         reset=True)\n",
+    "    # else:\n",
+    "    #     # Render the job classification form\n",
+    "    #     return render_template('naive.html')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "    # if request.method == 'POST':\n",
+    "    #     # Get the user's input values\n",
+    "    #     salary = float(request.form['salary'])\n",
+    "    #     experience = float(request.form['experience'])\n",
+    "\n",
+    "    #     with open('Models/tts.pkl', 'rb') as f:\n",
+    "    #         data = pickle.load(f)\n",
+    "\n",
+    "    #     X=data['X']\n",
+    "    #     y=data['y']\n",
+    "\n",
+    "\n",
+    "    #     X = np.vstack((X, np.array([salary, experience])))\n",
+    "    #     y= np.hstack((y, 5))  # use a new label for the user's input\n",
+    "\n",
+    "\n",
+    "    #     # Split the data into training and testing sets\n",
+    "    #     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=0)\n",
+    "\n",
+    "    #     # Fit the Naive Bayes models on the training data\n",
+    "    #     gaussian_nb.fit(X_train, y_train)\n",
+    "    #     multinomial_nb.fit(X_train, y_train)\n",
+    "    #     bernoulli_nb.fit(X_train, y_train)\n",
+    "\n",
+    "    #     # Use each Naive Bayes model to make a prediction based on the user's input values\n",
+    "    #     gaussian_prediction = gaussian_nb.predict([[salary, experience]])[0]\n",
+    "    #     multinomial_prediction = multinomial_nb.predict([[salary, experience]])[0]\n",
+    "    #     bernoulli_prediction = bernoulli_nb.predict([[salary, experience]])[0]\n",
+    "\n",
+    "    #     # Evaluate the accuracy of the models on the testing set\n",
+    "    #     gaussian_accuracy = round(gaussian_nb.score(X_test, y_test) * 100, 3) \n",
+    "    #     multinomial_accuracy = round(multinomial_nb.score(X_test, y_test) * 100, 3)\n",
+    "    #     bernoulli_accuracy = round(bernoulli_nb.score(X_test, y_test) * 100, 3)\n",
+    "\n",
+    "    #     # Map the predicted job titles to their corresponding string values\n",
+    "    #     gaussian_prediction = job_map.get(gaussian_prediction)\n",
+    "    #     multinomial_prediction = job_map.get(multinomial_prediction)\n",
+    "    #     bernoulli_prediction = job_map.get(bernoulli_prediction)\n",
+    "\n",
+    "    #     # Render the results template with the predicted job classification and accuracy scores\n",
+    "    #     return render_template('naive.html',\n",
+    "    #         gaussian_prediction=gaussian_prediction,\n",
+    "    #         multinomial_prediction=multinomial_prediction,\n",
+    "    #         bernoulli_prediction=bernoulli_prediction,\n",
+    "    #         gaussian_accuracy=str(gaussian_accuracy) + \"%\",\n",
+    "    #         multinomial_accuracy=str(multinomial_accuracy) + \"%\",\n",
+    "    #         bernoulli_accuracy=str(bernoulli_accuracy) + \"%\",\n",
+    "    #         salary=salary,\n",
+    "    #         experience=experience,\n",
+    "    #         reset=True)\n",
+    "    # else:\n",
+    "    #     # Render the job classification form\n",
+    "    #     return render_template('naive.html')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Salary entered:  5000.0\n",
+      "Experience entered:  5.0\n",
+      "Gaussian Accuracy: 82.81%, Prediction: None\n",
+      "Multinomial Accuracy: 26.67%, Prediction: None\n",
+      "Bernoulli Accuracy: 21.05%, Prediction: Junior\n",
+      "\n",
+      "\n",
+      "Salary entered:  4.0\n",
+      "Experience entered:  5.0\n",
+      "Gaussian Accuracy: 82.46%, Prediction: CTO\n",
+      "Multinomial Accuracy: 25.96%, Prediction: Junior\n",
+      "Bernoulli Accuracy: 20.70%, Prediction: Junior\n",
+      "\n",
+      "\n"
+     ]
+    },
+    {
+     "ename": "ValueError",
+     "evalue": "could not convert string to float: ''",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[3], line 3\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39msklearn\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mmodel_selection\u001b[39;00m \u001b[39mimport\u001b[39;00m KFold\n\u001b[0;32m      2\u001b[0m \u001b[39mwhile\u001b[39;00m \u001b[39mTrue\u001b[39;00m:\n\u001b[1;32m----> 3\u001b[0m     salary \u001b[39m=\u001b[39m \u001b[39mfloat\u001b[39m(\u001b[39minput\u001b[39m(\u001b[39m\"\u001b[39m\u001b[39mEnter salary: \u001b[39m\u001b[39m\"\u001b[39m))\n\u001b[0;32m      4\u001b[0m     \u001b[39mprint\u001b[39m(\u001b[39m\"\u001b[39m\u001b[39mSalary entered: \u001b[39m\u001b[39m\"\u001b[39m, salary)\n\u001b[0;32m      6\u001b[0m     experience \u001b[39m=\u001b[39m \u001b[39mfloat\u001b[39m(\u001b[39minput\u001b[39m(\u001b[39m\"\u001b[39m\u001b[39mEnter experience: \u001b[39m\u001b[39m\"\u001b[39m))\n",
+      "\u001b[1;31mValueError\u001b[0m: could not convert string to float: ''"
+     ]
+    }
+   ],
+   "source": [
+    "# from sklearn.model_selection import KFold\n",
+    "# while True:\n",
+    "#     salary = float(input(\"Enter salary: \"))\n",
+    "#     print(\"Salary entered: \", salary)\n",
+    "\n",
+    "#     experience = float(input(\"Enter experience: \"))\n",
+    "#     print(\"Experience entered: \", experience)\n",
+    "\n",
+    "#     with open('Models/tts.pkl', 'rb') as f:\n",
+    "#         data = pickle.load(f)\n",
+    "\n",
+    "#     X=data['X']\n",
+    "#     y=data['y']\n",
+    "\n",
+    "#     # Combine the user's input values with the existing data\n",
+    "#     X_new = np.vstack((X, np.array([salary, experience])))\n",
+    "#     y_new = np.hstack((y, 5))  # use a new label for the user's input\n",
+    "\n",
+    "#     n_splits=5\n",
+    "\n",
+    "#     # Use k-fold cross-validation to generate a new test set for each iteration\n",
+    "#     kf = KFold(n_splits=n_splits, shuffle=True, random_state=None)\n",
+    "\n",
+    "#     gaussian_accuracy = 0\n",
+    "#     multinomial_accuracy = 0\n",
+    "#     bernoulli_accuracy = 0\n",
+    "\n",
+    "#     for train_index, test_index in kf.split(X_new):\n",
+    "#         X_train, X_test = X_new[train_index], X_new[test_index]\n",
+    "#         y_train, y_test = y_new[train_index], y_new[test_index]\n",
+    "\n",
+    "#         # Fit the Naive Bayes models on the training data\n",
+    "#         gaussian_nb.fit(X_train, y_train)\n",
+    "#         multinomial_nb.fit(X_train, y_train)\n",
+    "#         bernoulli_nb.fit(X_train, y_train)\n",
+    "\n",
+    "#         # Use each Naive Bayes model to make a prediction based on the user's input values\n",
+    "#         gaussian_prediction = gaussian_nb.predict([[salary, experience]])[0]\n",
+    "#         multinomial_prediction = multinomial_nb.predict([[salary, experience]])[0]\n",
+    "#         bernoulli_prediction = bernoulli_nb.predict([[salary, experience]])[0]\n",
+    "\n",
+    "#         # Update the accuracy scores for each Naive Bayes model\n",
+    "#         gaussian_accuracy += gaussian_nb.score(X_test, y_test)\n",
+    "#         multinomial_accuracy += multinomial_nb.score(X_test, y_test)\n",
+    "#         bernoulli_accuracy += bernoulli_nb.score(X_test, y_test)\n",
+    "\n",
+    "#     # Calculate the mean accuracy for each Naive Bayes model over all folds\n",
+    "#     gaussian_accuracy /= n_splits\n",
+    "#     multinomial_accuracy /= n_splits\n",
+    "#     bernoulli_accuracy /= n_splits\n",
+    "\n",
+    "#     # Map the predicted job titles to their corresponding string values\n",
+    "#     gaussian_prediction = job_map.get(gaussian_prediction)\n",
+    "#     multinomial_prediction = job_map.get(multinomial_prediction)\n",
+    "#     bernoulli_prediction = job_map.get(bernoulli_prediction)\n",
+    "\n",
+    "#     # Print the accuracy and predicted job title for each Naive Bayes model\n",
+    "#     print(\"Gaussian Accuracy: {:.2f}%, Prediction: {}\".format(gaussian_accuracy * 100, gaussian_prediction))\n",
+    "#     print(\"Multinomial Accuracy: {:.2f}%, Prediction: {}\".format(multinomial_accuracy * 100, multinomial_prediction))\n",
+    "#     print(\"Bernoulli Accuracy: {:.2f}%, Prediction: {}\".format(bernoulli_accuracy * 100, bernoulli_prediction))\n",
+    "#     print(\"\\n\")\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# @app.route('/predictnaive', methods=['GET', 'POST'])\n",
+    "# def predictnaive():\n",
+    "#     if request.method == 'POST':\n",
+    "#         # Get the user's input values\n",
+    "#         salary = float(request.form['salary'])\n",
+    "#         experience = float(request.form['experience'])\n",
+    "\n",
+    "#         # Load the data used to train and test the models\n",
+    "#         with open('Models/tts.pkl', 'rb') as f:\n",
+    "#             data = pickle.load(f)\n",
+    "        \n",
+    "#         # X_user = np.array([[salary, experience]])\n",
+    "#         # y_user = np.array([5])\n",
+    "#         # X_test_combined = np.concatenate((X_test, X_user))\n",
+    "#         # y_test_combined = np.concatenate((y_test, y_user))\n",
+    "\n",
+    "#         X = np.vstack((data['X'], np.array([salary, experience])))\n",
+    "#         y = np.hstack((data['y'], 5))  # use a new label for the user's input\n",
+    "        \n",
+    "#         from sklearn.model_selection import train_test_split\n",
+    "#         X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=0)\n",
+    "\n",
+    "#         # Re-fit models on combined data\n",
+    "#         gaussian_nb.fit(X_train, y_train) \n",
+    "#         multinomial_nb.fit(X_train, y_train)\n",
+    "#         bernoulli_nb.fit(X_train, y_train)\n",
+    "\n",
+    "#         # Use each Naive Bayes model to make a prediction based on the user's input values\n",
+    "#         gaussian_prediction = gaussian_nb.predict([[salary, experience]])[0]\n",
+    "#         multinomial_prediction = multinomial_nb.predict([[salary, experience]])[0]\n",
+    "#         bernoulli_prediction = bernoulli_nb.predict([[salary, experience]])[0]\n",
+    "\n",
+    "\n",
+    "#         # Calculate the accuracy of each Naive Bayes model\n",
+    "#         gaussian_accuracy = round(gaussian_nb.score(X_test, y_test), 3) * 100\n",
+    "#         multinomial_accuracy = round(multinomial_nb.score(X_test, y_test), 3) * 100\n",
+    "#         bernoulli_accuracy = round(bernoulli_nb.score(X_test, y_test), 3) * 100\n",
+    "\n",
+    "\n",
+    "#         gaussian_prediction = job_map.get(gaussian_prediction)\n",
+    "#         multinomial_prediction = job_map.get(multinomial_prediction)\n",
+    "#         bernoulli_prediction = job_map.get(bernoulli_prediction)\n",
+    "\n",
+    "#         # Render the results template with the predicted job classification and accuracy scores\n",
+    "#         return render_template('naive.html', gaussian_prediction=gaussian_prediction, multinomial_prediction=multinomial_prediction, bernoulli_prediction=bernoulli_prediction, gaussian_accuracy=gaussian_accuracy, multinomial_accuracy=multinomial_accuracy, bernoulli_accuracy=bernoulli_accuracy, salary=salary, experience=experience, reset=True)\n",
+    "#     else:\n",
+    "#         # Render the job classification form\n",
+    "#         return render_template('naive.html')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.2"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

app.py

@@ -0,0 +1,153 @@
+from flask import Flask, render_template, request, url_for
+import pickle
+import numpy as np
+
+app = Flask(__name__, static_folder='static')
+
+linreg = pickle.load(open('Models/linreg_model.pkl', 'rb'))
+knn_model = pickle.load(open('Models/knn_model.pkl', 'rb'))
+gaussian_nb = pickle.load(open('Models/nbG_model.pkl', 'rb'))
+multinomial_nb = pickle.load(open('Models/nbM_model.pkl', 'rb'))
+bernoulli_nb = pickle.load(open('Models/nbB_model.pkl', 'rb'))
+
+job_map = {
+    1: 'Junior',
+    2: 'Senior',
+    3: 'Project Manager',
+    4: 'CTO',
+}
+
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+
+@app.route('/about')
+def about():
+    return render_template('about.html')
+
+
+@app.route('/algos')
+def algos():
+    return render_template('algos.html')
+
+
+@app.route('/linear', methods=['GET', 'POST'])
+def linear():
+    return render_template('linear.html')
+
+
+@app.route('/knn', methods=['GET', 'POST'])
+def knn():
+    return render_template('knn.html')
+
+
+@app.route('/kmeans', methods=['GET', 'POST'])
+def kmeans():
+    return render_template('kmeans.html')
+
+
+@app.route('/naive', methods=['GET', 'POST'])
+def naive():
+    return render_template('naive.html')
+
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    position_level = request.form.get('comp_select')
+    experience_str = request.form.get('experience')
+    try:
+        experience = float(experience_str)
+    except ValueError:
+        return render_template('linear.html', prediction_text=f"Error: Invalid input value for experience: '{experience_str}'. Please enter a valid numerical value.")
+
+    if position_level in ['1', '2', '3', '4']:
+        int_position_level = int(position_level)
+        float_experience = float(experience)
+        int_features = [int_position_level, float_experience]
+        final_features = [np.array(int_features)]
+        prediction = linreg.predict(final_features)
+
+        
+        int_position_level = job_map.get(int(position_level))
+        predicted_salary_f = round(float(prediction.item()), 3)
+        predicted_salary = "{:,.3f}".format(predicted_salary_f)
+
+        return render_template('linear.html', position_level=f'Position: {int_position_level}',experience=f'Experience: {experience}', prediction_text=f'Predicted Salary Rate: ₱{predicted_salary}')
+
+    else:
+        return render_template('linear.html', prediction_text='Error: Invalid input values. Please select a valid position level and enter a numerical value for experience.')
+
+
+@app.route('/predictknn', methods=['POST'])
+def predictknn():
+    experience_str = request.form.get('experience')
+    salary_str = request.form.get('salary')
+    try:
+        experience = float(experience_str)
+        salary = float(salary_str)
+    except ValueError:
+        return render_template('knn.html', prediction_text=f"Error: Invalid input value. Please enter a valid numerical value for both experience and salary.")
+
+    features = [[experience, salary]]
+    prediction = knn_model.predict(features)
+    predicted_job_num = int(prediction[0])
+    predicted_job = job_map[predicted_job_num]
+
+    return render_template('knn.html', prediction_text=f'Predicted job: {predicted_job}', experience=f'Experience: {experience}', salary=f'Salary: {salary}')
+
+@app.route('/predictnaive', methods=['GET', 'POST'])
+def predictnaive():
+    # Get the user's input values
+    salary = float(request.form['salary'])
+    experience = float(request.form['experience'])
+
+    try:
+        if float(experience) < 0 or float(salary) < 0:
+            raise ValueError()
+        int_features = [salary, experience]
+
+        features = np.array(int_features).reshape(1, -1)
+        gaussian_prediction = gaussian_nb.predict(features)
+        multinomial_prediction = multinomial_nb.predict(features)
+        bernoulli_prediction = bernoulli_nb.predict(features)
+
+        # # Map the predicted job titles to their corresponding string values
+        gaussian_prediction = job_map.get(int(gaussian_prediction))
+        multinomial_prediction = job_map.get(int(multinomial_prediction))
+        bernoulli_prediction = job_map.get(int(bernoulli_prediction))
+
+
+          # Render the results template with the predicted job classification and accuracy scores
+        return render_template('naive.html',
+        gaussian_prediction=gaussian_prediction,
+        multinomial_prediction=multinomial_prediction,
+        bernoulli_prediction=bernoulli_prediction,
+        salary=salary,
+        experience=experience,
+        reset=True)
+    
+    except:
+        return render_template('naive.html')
+
+
+@app.route('/predictkm', methods=['GET'])
+def predictkm():
+
+    # render the HTML template
+    return render_template('kmeans.html')
+
+    # # convert the figure to a base64 string for embedding in the HTML template
+    # import io
+    # import base64
+    # buf = io.BytesIO()
+    # fig.savefig(buf, format='png')
+    # figdata = base64.b64encode(buf.getbuffer()).decode('utf-8')
+
+    # # render the HTML template and pass the figure data to it
+    # return render_template('kmeans.html', figdata=figdata)
+
+
+if __name__ == '__main__':
+    app.run(debug=True, port=8000)

requirements.txt

@@ -0,0 +1,7 @@
+flask==2.2.3
+numpy==1.24.2
+pickle-mixin==1.0.2
+scikit-learn==1.2.2
+gunicorn
+matplotlib
+pandas

static/css/main.css

@@ -0,0 +1,3098 @@
+@import url('https://fonts.googleapis.com/css2?family=Poppins:wght@300;400;500;600;700&display=swap');
+html {
+    -ms-text-size-adjust: 100%;
+    -webkit-text-size-adjust: 100%;
+    font-family: sans-serif;
+}
+
+body {
+    margin: 0;
+}
+
+article,
+aside,
+details,
+figcaption,
+figure,
+footer,
+header,
+hgroup,
+main,
+menu,
+nav,
+section,
+summary {
+    display: block;
+}
+
+audio,
+canvas,
+progress,
+video {
+    vertical-align: baseline;
+    display: inline-block;
+}
+
+audio:not([controls]) {
+    height: 0;
+    display: none;
+}
+
+[hidden],
+template {
+    display: none;
+}
+
+a {
+    background-color: rgba(0, 0, 0, 0);
+}
+
+a:active,
+a:hover {
+    outline: 0;
+}
+
+abbr[title] {
+    border-bottom: 1px dotted;
+}
+
+b,
+strong {
+    font-weight: bold;
+}
+
+dfn {
+    font-style: italic;
+}
+
+h1 {
+    margin: .67em 0;
+    font-size: 2em;
+}
+
+mark {
+    color: #000;
+    background: #ff0;
+}
+
+small {
+    font-size: 80%;
+}
+
+sub,
+sup {
+    vertical-align: baseline;
+    font-size: 75%;
+    line-height: 0;
+    position: relative;
+}
+
+sup {
+    top: -.5em;
+}
+
+sub {
+    bottom: -.25em;
+}
+
+img {
+    border: 0;
+}
+
+svg:not(:root) {
+    overflow: hidden;
+}
+
+figure {
+    margin: 1em 40px;
+}
+
+hr {
+    box-sizing: content-box;
+    height: 0;
+}
+
+pre {
+    overflow: auto;
+}
+
+code,
+kbd,
+pre,
+samp {
+    font-family: monospace;
+    font-size: 1em;
+}
+
+button,
+input,
+optgroup,
+select,
+textarea {
+    color: inherit;
+    font: inherit;
+    margin: 0;
+}
+
+button {
+    overflow: visible;
+}
+
+button,
+select {
+    text-transform: none;
+}
+
+button[disabled],
+html input[disabled] {
+    cursor: default;
+}
+
+button::-moz-focus-inner,
+input::-moz-focus-inner {
+    border: 0;
+    padding: 0;
+}
+
+input {
+    line-height: normal;
+}
+
+input[type="checkbox"],
+input[type="radio"] {
+    box-sizing: border-box;
+    padding: 0;
+}
+
+input[type="number"]::-webkit-inner-spin-button,
+input[type="number"]::-webkit-outer-spin-button {
+    height: auto;
+}
+
+input[type="search"]::-webkit-search-cancel-button,
+input[type="search"]::-webkit-search-decoration {
+    -webkit-appearance: none;
+}
+
+fieldset {
+    border: 1px solid silver;
+    margin: 0 2px;
+    padding: .35em .625em .75em;
+}
+
+legend {
+    border: 0;
+    padding: 0;
+}
+
+textarea {
+    overflow: auto;
+}
+
+optgroup {
+    font-weight: bold;
+}
+
+table {
+    border-collapse: collapse;
+    border-spacing: 0;
+}
+
+td,
+th {
+    padding: 0;
+}
+
+@font-face {
+    font-family: webflow-icons;
+    src: url("data:application/x-font-ttf;charset=utf-8;base64,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") format("truetype");
+    font-weight: normal;
+    font-style: normal;
+}
+
+[class^="w-icon-"],
+[class*=" w-icon-"] {
+    font-variant: normal;
+    text-transform: none;
+    -webkit-font-smoothing: antialiased;
+    -moz-osx-font-smoothing: grayscale;
+    font-style: normal;
+    font-weight: normal;
+    line-height: 1;
+    font-family: webflow-icons !important;
+}
+
+.w-icon-slider-right:before {
+    content: "";
+}
+
+.w-icon-slider-left:before {
+    content: "";
+}
+
+.w-icon-nav-menu:before {
+    content: "";
+}
+
+.w-icon-arrow-down:before,
+.w-icon-dropdown-toggle:before {
+    content: "";
+}
+
+.w-icon-file-upload-remove:before {
+    content: "";
+}
+
+.w-icon-file-upload-icon:before {
+    content: "";
+}
+
+* {
+    box-sizing: border-box;
+}
+
+html {
+    height: 100%;
+}
+
+body {
+    min-height: 100%;
+    color: #333;
+    background-color: #fff;
+    margin: 0;
+    font-family: Arial, sans-serif;
+    font-size: 14px;
+    line-height: 20px;
+}
+
+img {
+    max-width: 100%;
+    vertical-align: middle;
+    display: inline-block;
+}
+
+html.w-mod-touch * {
+    background-attachment: scroll !important;
+}
+
+.w-block {
+    display: block;
+}
+
+.w-inline-block {
+    max-width: 100%;
+    display: inline-block;
+}
+
+.w-clearfix:before,
+.w-clearfix:after {
+    content: " ";
+    grid-area: 1 / 1 / 2 / 2;
+    display: table;
+}
+
+.w-clearfix:after {
+    clear: both;
+}
+
+.w-hidden {
+    display: none;
+}
+
+.w-button {
+    color: #fff;
+    line-height: inherit;
+    cursor: pointer;
+    background-color: #3898ec;
+    border: 0;
+    border-radius: 0;
+    padding: 9px 15px;
+    text-decoration: none;
+    display: inline-block;
+}
+
+html[data-w-dynpage] [data-w-cloak] {
+    color: rgba(0, 0, 0, 0) !important;
+}
+
+h1,
+h2,
+h3,
+h4,
+h5,
+h6 {
+    margin-bottom: 10px;
+    font-weight: bold;
+}
+
+h1 {
+    margin-top: 20px;
+    font-size: 38px;
+    line-height: 44px;
+}
+
+h2 {
+    margin-top: 20px;
+    font-size: 32px;
+    line-height: 36px;
+}
+
+h3 {
+    margin-top: 20px;
+    font-size: 24px;
+    line-height: 30px;
+}
+
+h4 {
+    margin-top: 10px;
+    font-size: 18px;
+    line-height: 24px;
+}
+
+h5 {
+    margin-top: 10px;
+    font-size: 14px;
+    line-height: 20px;
+}
+
+h6 {
+    margin-top: 10px;
+    font-size: 12px;
+    line-height: 18px;
+}
+
+p {
+    margin-top: 0;
+    margin-bottom: 10px;
+}
+
+blockquote {
+    border-left: 5px solid #e2e2e2;
+    margin: 0 0 10px;
+    padding: 10px 20px;
+    font-size: 18px;
+    line-height: 22px;
+}
+
+figure {
+    margin: 0 0 10px;
+}
+
+figcaption {
+    text-align: center;
+    margin-top: 5px;
+}
+
+ul,
+ol {
+    margin-top: 0;
+    margin-bottom: 10px;
+    padding-left: 40px;
+}
+
+.w-list-unstyled {
+    padding-left: 0;
+    list-style: none;
+}
+
+.w-embed:before,
+.w-embed:after {
+    content: " ";
+    grid-area: 1 / 1 / 2 / 2;
+    display: table;
+}
+
+.w-embed:after {
+    clear: both;
+}
+
+.w-video {
+    width: 100%;
+    padding: 0;
+    position: relative;
+}
+
+.w-video iframe,
+.w-video object,
+.w-video embed {
+    width: 100%;
+    height: 100%;
+    border: none;
+    position: absolute;
+    top: 0;
+    left: 0;
+}
+
+fieldset {
+    border: 0;
+    margin: 0;
+    padding: 0;
+}
+
+button,
+[type="button"],
+[type="reset"] {
+    cursor: pointer;
+    border: 0;
+}
+
+.w-form {
+    margin: 0 0 15px;
+}
+
+.w-form-done {
+    text-align: center;
+    background-color: #ddd;
+    padding: 20px;
+    display: none;
+}
+
+.w-form-fail {
+    background-color: #ffdede;
+    margin-top: 10px;
+    padding: 10px;
+    display: none;
+}
+
+label {
+    margin-bottom: 5px;
+    font-weight: bold;
+    display: block;
+}
+
+.w-input,
+.w-select {
+    width: 100%;
+    height: 38px;
+    color: #333;
+    background-color: #fff;
+    border: 1px solid #ccc;
+    margin-bottom: 10px;
+    padding: 8px 12px;
+    font-size: 14px;
+    line-height: 1.42857;
+    display: block;
+}
+
+.w-input:-moz-placeholder,
+.w-select:-moz-placeholder {
+    color: #999;
+}
+
+.w-input::-moz-placeholder,
+.w-select::-moz-placeholder {
+    color: #999;
+    opacity: 1;
+}
+
+.w-input:-ms-input-placeholder,
+.w-select:-ms-input-placeholder {
+    color: #999;
+}
+
+.w-input::-webkit-input-placeholder,
+.w-select::-webkit-input-placeholder {
+    color: #999;
+}
+
+.w-input:focus,
+.w-select:focus {
+    border-color: #3898ec;
+    outline: 0;
+}
+
+.w-input[disabled],
+.w-select[disabled],
+.w-input[readonly],
+.w-select[readonly],
+fieldset[disabled] .w-input,
+fieldset[disabled] .w-select {
+    cursor: not-allowed;
+}
+
+.w-input[disabled]:not(.w-input-disabled),
+.w-select[disabled]:not(.w-input-disabled),
+.w-input[readonly],
+.w-select[readonly],
+fieldset[disabled]:not(.w-input-disabled) .w-input,
+fieldset[disabled]:not(.w-input-disabled) .w-select {
+    background-color: #eee;
+}
+
+textarea.w-input,
+textarea.w-select {
+    height: auto;
+}
+
+.w-select {
+    background-color: #f3f3f3;
+}
+
+.w-select[multiple] {
+    height: auto;
+}
+
+.w-form-label {
+    cursor: pointer;
+    margin-bottom: 0;
+    font-weight: normal;
+    display: inline-block;
+}
+
+.w-radio {
+    margin-bottom: 5px;
+    padding-left: 20px;
+    display: block;
+}
+
+.w-radio:before,
+.w-radio:after {
+    content: " ";
+    grid-area: 1 / 1 / 2 / 2;
+    display: table;
+}
+
+.w-radio:after {
+    clear: both;
+}
+
+.w-radio-input {
+    margin: 4px 0 0;
+    margin-top: 1px \9;
+    float: left;
+    margin-top: 3px;
+    margin-left: -20px;
+    line-height: normal;
+}
+
+.w-file-upload {
+    margin-bottom: 10px;
+    display: block;
+}
+
+.w-file-upload-input {
+    width: .1px;
+    height: .1px;
+    opacity: 0;
+    z-index: -100;
+    position: absolute;
+    overflow: hidden;
+}
+
+.w-file-upload-default,
+.w-file-upload-uploading,
+.w-file-upload-success {
+    color: #333;
+    display: inline-block;
+}
+
+.w-file-upload-error {
+    margin-top: 10px;
+    display: block;
+}
+
+.w-file-upload-default.w-hidden,
+.w-file-upload-uploading.w-hidden,
+.w-file-upload-error.w-hidden,
+.w-file-upload-success.w-hidden {
+    display: none;
+}
+
+.w-file-upload-uploading-btn {
+    cursor: pointer;
+    background-color: #fafafa;
+    border: 1px solid #ccc;
+    margin: 0;
+    padding: 8px 12px;
+    font-size: 14px;
+    font-weight: normal;
+    display: flex;
+}
+
+.w-file-upload-file {
+    background-color: #fafafa;
+    border: 1px solid #ccc;
+    flex-grow: 1;
+    justify-content: space-between;
+    margin: 0;
+    padding: 8px 9px 8px 11px;
+    display: flex;
+}
+
+.w-file-upload-file-name {
+    font-size: 14px;
+    font-weight: normal;
+    display: block;
+}
+
+.w-file-remove-link {
+    width: auto;
+    height: auto;
+    cursor: pointer;
+    margin-top: 3px;
+    margin-left: 10px;
+    padding: 3px;
+    display: block;
+}
+
+.w-icon-file-upload-remove {
+    margin: auto;
+    font-size: 10px;
+}
+
+.w-file-upload-error-msg {
+    color: #ea384c;
+    padding: 2px 0;
+    display: inline-block;
+}
+
+.w-file-upload-info {
+    padding: 0 12px;
+    line-height: 38px;
+    display: inline-block;
+}
+
+.w-file-upload-label {
+    cursor: pointer;
+    background-color: #fafafa;
+    border: 1px solid #ccc;
+    margin: 0;
+    padding: 8px 12px;
+    font-size: 14px;
+    font-weight: normal;
+    display: inline-block;
+}
+
+.w-icon-file-upload-icon,
+.w-icon-file-upload-uploading {
+    width: 20px;
+    margin-right: 8px;
+    display: inline-block;
+}
+
+.w-icon-file-upload-uploading {
+    height: 20px;
+}
+
+.w-container {
+    max-width: 940px;
+    margin-left: auto;
+    margin-right: auto;
+}
+
+.w-container:before,
+.w-container:after {
+    content: " ";
+    grid-area: 1 / 1 / 2 / 2;
+    display: table;
+}
+
+.w-container:after {
+    clear: both;
+}
+
+.w-container .w-row {
+    margin-left: -10px;
+    margin-right: -10px;
+}
+
+.w-row:before,
+.w-row:after {
+    content: " ";
+    grid-area: 1 / 1 / 2 / 2;
+    display: table;
+}
+
+.w-row:after {
+    clear: both;
+}
+
+.w-row .w-row {
+    margin-left: 0;
+    margin-right: 0;
+}
+
+.w-col {
+    float: left;
+    width: 100%;
+    min-height: 1px;
+    padding-left: 10px;
+    padding-right: 10px;
+    position: relative;
+}
+
+.w-col .w-col {
+    padding-left: 0;
+    padding-right: 0;
+}
+
+.w-col-1 {
+    width: 8.33333%;
+}
+
+.w-col-2 {
+    width: 16.6667%;
+}
+
+.w-col-3 {
+    width: 25%;
+}
+
+.w-col-4 {
+    width: 33.3333%;
+}
+
+.w-col-5 {
+    width: 41.6667%;
+}
+
+.w-col-6 {
+    width: 50%;
+}
+
+.w-col-7 {
+    width: 58.3333%;
+}
+
+.w-col-8 {
+    width: 66.6667%;
+}
+
+.w-col-9 {
+    width: 75%;
+}
+
+.w-col-10 {
+    width: 83.3333%;
+}
+
+.w-col-11 {
+    width: 91.6667%;
+}
+
+.w-col-12 {
+    width: 100%;
+}
+
+.w-hidden-main {
+    display: none !important;
+}
+
+@media screen and (max-width: 991px) {
+    .w-container {
+        max-width: 728px;
+    }
+    .w-hidden-main {
+        display: inherit !important;
+    }
+    .w-hidden-medium {
+        display: none !important;
+    }
+    .w-col-medium-1 {
+        width: 8.33333%;
+    }
+    .w-col-medium-2 {
+        width: 16.6667%;
+    }
+    .w-col-medium-3 {
+        width: 25%;
+    }
+    .w-col-medium-4 {
+        width: 33.3333%;
+    }
+    .w-col-medium-5 {
+        width: 41.6667%;
+    }
+    .w-col-medium-6 {
+        width: 50%;
+    }
+    .w-col-medium-7 {
+        width: 58.3333%;
+    }
+    .w-col-medium-8 {
+        width: 66.6667%;
+    }
+    .w-col-medium-9 {
+        width: 75%;
+    }
+    .w-col-medium-10 {
+        width: 83.3333%;
+    }
+    .w-col-medium-11 {
+        width: 91.6667%;
+    }
+    .w-col-medium-12 {
+        width: 100%;
+    }
+    .w-col-stack {
+        width: 100%;
+        left: auto;
+        right: auto;
+    }
+}
+
+@media screen and (max-width: 767px) {
+    .w-hidden-main,
+    .w-hidden-medium {
+        display: inherit !important;
+    }
+    .w-hidden-small {
+        display: none !important;
+    }
+    .w-row,
+    .w-container .w-row {
+        margin-left: 0;
+        margin-right: 0;
+    }
+    .w-col {
+        width: 100%;
+        left: auto;
+        right: auto;
+    }
+    .w-col-small-1 {
+        width: 8.33333%;
+    }
+    .w-col-small-2 {
+        width: 16.6667%;
+    }
+    .w-col-small-3 {
+        width: 25%;
+    }
+    .w-col-small-4 {
+        width: 33.3333%;
+    }
+    .w-col-small-5 {
+        width: 41.6667%;
+    }
+    .w-col-small-6 {
+        width: 50%;
+    }
+    .w-col-small-7 {
+        width: 58.3333%;
+    }
+    .w-col-small-8 {
+        width: 66.6667%;
+    }
+    .w-col-small-9 {
+        width: 75%;
+    }
+    .w-col-small-10 {
+        width: 83.3333%;
+    }
+    .w-col-small-11 {
+        width: 91.6667%;
+    }
+    .w-col-small-12 {
+        width: 100%;
+    }
+}
+
+@media screen and (max-width: 479px) {
+    .w-container {
+        max-width: none;
+    }
+    .w-hidden-main,
+    .w-hidden-medium,
+    .w-hidden-small {
+        display: inherit !important;
+    }
+    .w-hidden-tiny {
+        display: none !important;
+    }
+    .w-col {
+        width: 100%;
+    }
+    .w-col-tiny-1 {
+        width: 8.33333%;
+    }
+    .w-col-tiny-2 {
+        width: 16.6667%;
+    }
+    .w-col-tiny-3 {
+        width: 25%;
+    }
+    .w-col-tiny-4 {
+        width: 33.3333%;
+    }
+    .w-col-tiny-5 {
+        width: 41.6667%;
+    }
+    .w-col-tiny-6 {
+        width: 50%;
+    }
+    .w-col-tiny-7 {
+        width: 58.3333%;
+    }
+    .w-col-tiny-8 {
+        width: 66.6667%;
+    }
+    .w-col-tiny-9 {
+        width: 75%;
+    }
+    .w-col-tiny-10 {
+        width: 83.3333%;
+    }
+    .w-col-tiny-11 {
+        width: 91.6667%;
+    }
+    .w-col-tiny-12 {
+        width: 100%;
+    }
+}
+
+.w-widget {
+    position: relative;
+}
+
+.w-widget-map {
+    width: 100%;
+    height: 400px;
+}
+
+.w-widget-map label {
+    width: auto;
+    display: inline;
+}
+
+.w-widget-map img {
+    max-width: inherit;
+}
+
+.w-widget-map .gm-style-iw {
+    text-align: center;
+}
+
+.w-widget-map .gm-style-iw>button {
+    display: none !important;
+}
+
+.w-widget-twitter {
+    overflow: hidden;
+}
+
+.w-widget-twitter-count-shim {
+    vertical-align: top;
+    width: 28px;
+    height: 20px;
+    text-align: center;
+    background: #fff;
+    border: 1px solid #758696;
+    border-radius: 3px;
+    display: inline-block;
+    position: relative;
+}
+
+.w-widget-twitter-count-shim * {
+    pointer-events: none;
+    -webkit-user-select: none;
+    -ms-user-select: none;
+    user-select: none;
+}
+
+.w-widget-twitter-count-shim .w-widget-twitter-count-inner {
+    text-align: center;
+    color: #999;
+    font-family: serif;
+    font-size: 15px;
+    line-height: 12px;
+    position: relative;
+}
+
+.w-widget-twitter-count-shim .w-widget-twitter-count-clear {
+    display: block;
+    position: relative;
+}
+
+.w-widget-twitter-count-shim.w--large {
+    width: 36px;
+    height: 28px;
+}
+
+.w-widget-twitter-count-shim.w--large .w-widget-twitter-count-inner {
+    font-size: 18px;
+    line-height: 18px;
+}
+
+.w-widget-twitter-count-shim:not(.w--vertical) {
+    margin-left: 5px;
+    margin-right: 8px;
+}
+
+.w-widget-twitter-count-shim:not(.w--vertical).w--large {
+    margin-left: 6px;
+}
+
+.w-widget-twitter-count-shim:not(.w--vertical):before,
+.w-widget-twitter-count-shim:not(.w--vertical):after {
+    content: " ";
+    height: 0;
+    width: 0;
+    pointer-events: none;
+    border: solid rgba(0, 0, 0, 0);
+    position: absolute;
+    top: 50%;
+    left: 0;
+}
+
+.w-widget-twitter-count-shim:not(.w--vertical):before {
+    border-width: 4px;
+    border-color: rgba(117, 134, 150, 0) #5d6c7b rgba(117, 134, 150, 0) rgba(117, 134, 150, 0);
+    margin-top: -4px;
+    margin-left: -9px;
+}
+
+.w-widget-twitter-count-shim:not(.w--vertical).w--large:before {
+    border-width: 5px;
+    margin-top: -5px;
+    margin-left: -10px;
+}
+
+.w-widget-twitter-count-shim:not(.w--vertical):after {
+    border-width: 4px;
+    border-color: rgba(255, 255, 255, 0) #fff rgba(255, 255, 255, 0) rgba(255, 255, 255, 0);
+    margin-top: -4px;
+    margin-left: -8px;
+}
+
+.w-widget-twitter-count-shim:not(.w--vertical).w--large:after {
+    border-width: 5px;
+    margin-top: -5px;
+    margin-left: -9px;
+}
+
+.w-widget-twitter-count-shim.w--vertical {
+    width: 61px;
+    height: 33px;
+    margin-bottom: 8px;
+}
+
+.w-widget-twitter-count-shim.w--vertical:before,
+.w-widget-twitter-count-shim.w--vertical:after {
+    content: " ";
+    height: 0;
+    width: 0;
+    pointer-events: none;
+    border: solid rgba(0, 0, 0, 0);
+    position: absolute;
+    top: 100%;
+    left: 50%;
+}
+
+.w-widget-twitter-count-shim.w--vertical:before {
+    border-width: 5px;
+    border-color: #5d6c7b rgba(117, 134, 150, 0) rgba(117, 134, 150, 0);
+    margin-left: -5px;
+}
+
+.w-widget-twitter-count-shim.w--vertical:after {
+    border-width: 4px;
+    border-color: #fff rgba(255, 255, 255, 0) rgba(255, 255, 255, 0);
+    margin-left: -4px;
+}
+
+.w-widget-twitter-count-shim.w--vertical .w-widget-twitter-count-inner {
+    font-size: 18px;
+    line-height: 22px;
+}
+
+.w-widget-twitter-count-shim.w--vertical.w--large {
+    width: 76px;
+}
+
+.w-background-video {
+    height: 500px;
+    color: #fff;
+    position: relative;
+    overflow: hidden;
+}
+
+.w-background-video>video {
+    width: 100%;
+    height: 100%;
+    object-fit: cover;
+    z-index: -100;
+    background-position: 50%;
+    background-size: cover;
+    margin: auto;
+    position: absolute;
+    top: -100%;
+    bottom: -100%;
+    left: -100%;
+    right: -100%;
+}
+
+.w-background-video>video::-webkit-media-controls-start-playback-button {
+    -webkit-appearance: none;
+    display: none !important;
+}
+
+.w-background-video--control {
+    background-color: rgba(0, 0, 0, 0);
+    padding: 0;
+    position: absolute;
+    bottom: 1em;
+    right: 1em;
+}
+
+.w-background-video--control>[hidden] {
+    display: none !important;
+}
+
+.w-slider {
+    height: 300px;
+    text-align: center;
+    clear: both;
+    -webkit-tap-highlight-color: rgba(0, 0, 0, 0);
+    background: #ddd;
+    position: relative;
+}
+
+.w-slider-mask {
+    z-index: 1;
+    height: 100%;
+    white-space: nowrap;
+    display: block;
+    position: relative;
+    left: 0;
+    right: 0;
+    overflow: hidden;
+}
+
+.w-slide {
+    vertical-align: top;
+    width: 100%;
+    height: 100%;
+    white-space: normal;
+    text-align: left;
+    display: inline-block;
+    position: relative;
+}
+
+.w-slider-nav {
+    z-index: 2;
+    height: 40px;
+    text-align: center;
+    -webkit-tap-highlight-color: rgba(0, 0, 0, 0);
+    margin: auto;
+    padding-top: 10px;
+    position: absolute;
+    top: auto;
+    bottom: 0;
+    left: 0;
+    right: 0;
+}
+
+.w-slider-nav.w-round>div {
+    border-radius: 100%;
+}
+
+.w-slider-nav.w-num>div {
+    width: auto;
+    height: auto;
+    font-size: inherit;
+    line-height: inherit;
+    padding: .2em .5em;
+}
+
+.w-slider-nav.w-shadow>div {
+    box-shadow: 0 0 3px rgba(51, 51, 51, .4);
+}
+
+.w-slider-nav-invert {
+    color: #fff;
+}
+
+.w-slider-nav-invert>div {
+    background-color: rgba(34, 34, 34, .4);
+}
+
+.w-slider-nav-invert>div.w-active {
+    background-color: #222;
+}
+
+.w-slider-dot {
+    width: 1em;
+    height: 1em;
+    cursor: pointer;
+    background-color: rgba(255, 255, 255, .4);
+    margin: 0 3px .5em;
+    transition: background-color .1s, color .1s;
+    display: inline-block;
+    position: relative;
+}
+
+.w-slider-dot.w-active {
+    background-color: #fff;
+}
+
+.w-slider-dot:focus {
+    outline: none;
+    box-shadow: 0 0 0 2px #fff;
+}
+
+.w-slider-dot:focus.w-active {
+    box-shadow: none;
+}
+
+.w-slider-arrow-left,
+.w-slider-arrow-right {
+    width: 80px;
+    cursor: pointer;
+    color: #fff;
+    -webkit-tap-highlight-color: rgba(0, 0, 0, 0);
+    -webkit-user-select: none;
+    -ms-user-select: none;
+    user-select: none;
+    margin: auto;
+    font-size: 40px;
+    position: absolute;
+    top: 0;
+    bottom: 0;
+    left: 0;
+    right: 0;
+    overflow: hidden;
+}
+
+.w-slider-arrow-left [class^="w-icon-"],
+.w-slider-arrow-right [class^="w-icon-"],
+.w-slider-arrow-left [class*=" w-icon-"],
+.w-slider-arrow-right [class*=" w-icon-"] {
+    position: absolute;
+}
+
+.w-slider-arrow-left:focus,
+.w-slider-arrow-right:focus {
+    outline: 0;
+}
+
+.w-slider-arrow-left {
+    z-index: 3;
+    right: auto;
+}
+
+.w-slider-arrow-right {
+    z-index: 4;
+    left: auto;
+}
+
+.w-icon-slider-left,
+.w-icon-slider-right {
+    width: 1em;
+    height: 1em;
+    margin: auto;
+    top: 0;
+    bottom: 0;
+    left: 0;
+    right: 0;
+}
+
+.w-slider-aria-label {
+    clip: rect(0 0 0 0);
+    height: 1px;
+    width: 1px;
+    border: 0;
+    margin: -1px;
+    padding: 0;
+    position: absolute;
+    overflow: hidden;
+}
+
+.w-slider-force-show {
+    display: block !important;
+}
+
+.w-dropdown {
+    text-align: left;
+    z-index: 900;
+    margin-left: auto;
+    margin-right: auto;
+    display: inline-block;
+    position: relative;
+}
+
+.w-dropdown-btn,
+.w-dropdown-toggle,
+.w-dropdown-link {
+    vertical-align: top;
+    color: #222;
+    text-align: left;
+    white-space: nowrap;
+    margin-left: auto;
+    margin-right: auto;
+    padding: 20px;
+    text-decoration: none;
+    position: relative;
+}
+
+.w-dropdown-toggle {
+    -webkit-user-select: none;
+    -ms-user-select: none;
+    user-select: none;
+    cursor: pointer;
+    padding-right: 40px;
+    display: inline-block;
+}
+
+.w-dropdown-toggle:focus {
+    outline: 0;
+}
+
+.w-icon-dropdown-toggle {
+    width: 1em;
+    height: 1em;
+    margin: auto 20px auto auto;
+    position: absolute;
+    top: 0;
+    bottom: 0;
+    right: 0;
+}
+
+.w-dropdown-list {
+    min-width: 100%;
+    background: #ddd;
+    display: none;
+    position: absolute;
+}
+
+.w-dropdown-list.w--open {
+    display: block;
+}
+
+.w-dropdown-link {
+    color: #222;
+    padding: 10px 20px;
+    display: block;
+}
+
+.w-dropdown-link.w--current {
+    color: #0082f3;
+}
+
+.w-dropdown-link:focus {
+    outline: 0;
+}
+
+@media screen and (max-width: 767px) {
+    .w-nav-brand {
+        padding-left: 10px;
+    }
+}
+
+.w-lightbox-backdrop {
+    cursor: auto;
+    letter-spacing: normal;
+    text-indent: 0;
+    text-shadow: none;
+    text-transform: none;
+    visibility: visible;
+    white-space: normal;
+    word-break: normal;
+    word-spacing: normal;
+    word-wrap: normal;
+    color: #fff;
+    text-align: center;
+    z-index: 2000;
+    opacity: 0;
+    -webkit-tap-highlight-color: transparent;
+    background: rgba(0, 0, 0, .9);
+    outline: 0;
+    font-family: Helvetica Neue, Helvetica, Ubuntu, Segoe UI, Verdana, sans-serif;
+    font-size: 17px;
+    font-style: normal;
+    font-weight: 300;
+    line-height: 1.2;
+    list-style: disc;
+    position: fixed;
+    top: 0;
+    bottom: 0;
+    left: 0;
+    right: 0;
+}
+
+.w-lightbox-backdrop,
+.w-lightbox-container {
+    height: 100%;
+    -webkit-overflow-scrolling: touch;
+    overflow: auto;
+}
+
+.w-lightbox-content {
+    height: 100vh;
+    position: relative;
+    overflow: hidden;
+}
+
+.w-lightbox-view {
+    width: 100vw;
+    height: 100vh;
+    opacity: 0;
+    position: absolute;
+}
+
+.w-lightbox-view:before {
+    content: "";
+    height: 100vh;
+}
+
+.w-lightbox-group,
+.w-lightbox-group .w-lightbox-view,
+.w-lightbox-group .w-lightbox-view:before {
+    height: 86vh;
+}
+
+.w-lightbox-frame,
+.w-lightbox-view:before {
+    vertical-align: middle;
+    display: inline-block;
+}
+
+.w-lightbox-figure {
+    margin: 0;
+    position: relative;
+}
+
+.w-lightbox-group .w-lightbox-figure {
+    cursor: pointer;
+}
+
+.w-lightbox-img {
+    width: auto;
+    height: auto;
+    max-width: none;
+}
+
+.w-lightbox-image {
+    float: none;
+    max-width: 100vw;
+    max-height: 100vh;
+    display: block;
+}
+
+.w-lightbox-group .w-lightbox-image {
+    max-height: 86vh;
+}
+
+.w-lightbox-caption {
+    text-align: left;
+    text-overflow: ellipsis;
+    white-space: nowrap;
+    background: rgba(0, 0, 0, .4);
+    padding: .5em 1em;
+    position: absolute;
+    bottom: 0;
+    left: 0;
+    right: 0;
+    overflow: hidden;
+}
+
+.w-lightbox-embed {
+    width: 100%;
+    height: 100%;
+    position: absolute;
+    top: 0;
+    bottom: 0;
+    left: 0;
+    right: 0;
+}
+
+.w-lightbox-control {
+    width: 4em;
+    cursor: pointer;
+    background-position: center;
+    background-repeat: no-repeat;
+    background-size: 24px;
+    transition: all .3s;
+    position: absolute;
+    top: 0;
+}
+
+.w-lightbox-left {
+    background-image: url("data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9Ii0yMCAwIDI0IDQwIiB3aWR0aD0iMjQiIGhlaWdodD0iNDAiPjxnIHRyYW5zZm9ybT0icm90YXRlKDQ1KSI+PHBhdGggZD0ibTAgMGg1djIzaDIzdjVoLTI4eiIgb3BhY2l0eT0iLjQiLz48cGF0aCBkPSJtMSAxaDN2MjNoMjN2M2gtMjZ6IiBmaWxsPSIjZmZmIi8+PC9nPjwvc3ZnPg==");
+    display: none;
+    bottom: 0;
+    left: 0;
+}
+
+.w-lightbox-right {
+    background-image: url("data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9Ii00IDAgMjQgNDAiIHdpZHRoPSIyNCIgaGVpZ2h0PSI0MCI+PGcgdHJhbnNmb3JtPSJyb3RhdGUoNDUpIj48cGF0aCBkPSJtMC0waDI4djI4aC01di0yM2gtMjN6IiBvcGFjaXR5PSIuNCIvPjxwYXRoIGQ9Im0xIDFoMjZ2MjZoLTN2LTIzaC0yM3oiIGZpbGw9IiNmZmYiLz48L2c+PC9zdmc+");
+    display: none;
+    bottom: 0;
+    right: 0;
+}
+
+.w-lightbox-close {
+    height: 2.6em;
+    background-image: url("data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9Ii00IDAgMTggMTciIHdpZHRoPSIxOCIgaGVpZ2h0PSIxNyI+PGcgdHJhbnNmb3JtPSJyb3RhdGUoNDUpIj48cGF0aCBkPSJtMCAwaDd2LTdoNXY3aDd2NWgtN3Y3aC01di03aC03eiIgb3BhY2l0eT0iLjQiLz48cGF0aCBkPSJtMSAxaDd2LTdoM3Y3aDd2M2gtN3Y3aC0zdi03aC03eiIgZmlsbD0iI2ZmZiIvPjwvZz48L3N2Zz4=");
+    background-size: 18px;
+    right: 0;
+}
+
+.w-lightbox-strip {
+    white-space: nowrap;
+    padding: 0 1vh;
+    line-height: 0;
+    position: absolute;
+    bottom: 0;
+    left: 0;
+    right: 0;
+    overflow-x: auto;
+    overflow-y: hidden;
+}
+
+.w-lightbox-item {
+    width: 10vh;
+    box-sizing: content-box;
+    cursor: pointer;
+    padding: 2vh 1vh;
+    display: inline-block;
+}
+
+.w-lightbox-active {
+    opacity: .3;
+}
+
+.w-lightbox-thumbnail {
+    height: 10vh;
+    background: #222;
+    position: relative;
+    overflow: hidden;
+}
+
+.w-lightbox-thumbnail-image {
+    position: absolute;
+    top: 0;
+    left: 0;
+}
+
+.w-lightbox-thumbnail .w-lightbox-tall {
+    width: 100%;
+    top: 50%;
+    transform: translate(0, -50%);
+}
+
+.w-lightbox-thumbnail .w-lightbox-wide {
+    height: 100%;
+    left: 50%;
+    transform: translate(-50%);
+}
+
+.w-lightbox-spinner {
+    box-sizing: border-box;
+    width: 40px;
+    height: 40px;
+    border: 5px solid rgba(0, 0, 0, .4);
+    border-radius: 50%;
+    margin-top: -20px;
+    margin-left: -20px;
+    animation: .8s linear infinite spin;
+    position: absolute;
+    top: 50%;
+    left: 50%;
+}
+
+.w-lightbox-spinner:after {
+    content: "";
+    border: 3px solid rgba(0, 0, 0, 0);
+    border-bottom-color: #fff;
+    border-radius: 50%;
+    position: absolute;
+    top: -4px;
+    bottom: -4px;
+    left: -4px;
+    right: -4px;
+}
+
+.w-lightbox-hide {
+    display: none;
+}
+
+.w-lightbox-noscroll {
+    overflow: hidden;
+}
+
+@media (min-width: 768px) {
+    .w-lightbox-content {
+        height: 96vh;
+        margin-top: 2vh;
+    }
+    .w-lightbox-view,
+    .w-lightbox-view:before {
+        height: 96vh;
+    }
+    .w-lightbox-group,
+    .w-lightbox-group .w-lightbox-view,
+    .w-lightbox-group .w-lightbox-view:before {
+        height: 84vh;
+    }
+    .w-lightbox-image {
+        max-width: 96vw;
+        max-height: 96vh;
+    }
+    .w-lightbox-group .w-lightbox-image {
+        max-width: 82.3vw;
+        max-height: 84vh;
+    }
+    .w-lightbox-left,
+    .w-lightbox-right {
+        opacity: .5;
+        display: block;
+    }
+    .w-lightbox-close {
+        opacity: .8;
+    }
+    .w-lightbox-control:hover {
+        opacity: 1;
+    }
+}
+
+.w-lightbox-inactive,
+.w-lightbox-inactive:hover {
+    opacity: 0;
+}
+
+.w-richtext:before,
+.w-richtext:after {
+    content: " ";
+    grid-area: 1 / 1 / 2 / 2;
+    display: table;
+}
+
+.w-richtext:after {
+    clear: both;
+}
+
+.w-richtext[contenteditable="true"]:before,
+.w-richtext[contenteditable="true"]:after {
+    white-space: initial;
+}
+
+.w-richtext ol,
+.w-richtext ul {
+    overflow: hidden;
+}
+
+.w-richtext .w-richtext-figure-selected.w-richtext-figure-type-video div:after,
+.w-richtext .w-richtext-figure-selected[data-rt-type="video"] div:after,
+.w-richtext .w-richtext-figure-selected.w-richtext-figure-type-image div,
+.w-richtext .w-richtext-figure-selected[data-rt-type="image"] div {
+    outline: 2px solid #2895f7;
+}
+
+.w-richtext figure.w-richtext-figure-type-video>div:after,
+.w-richtext figure[data-rt-type="video"]>div:after {
+    content: "";
+    display: none;
+    position: absolute;
+    top: 0;
+    bottom: 0;
+    left: 0;
+    right: 0;
+}
+
+.w-richtext figure {
+    max-width: 60%;
+    position: relative;
+}
+
+.w-richtext figure>div:before {
+    cursor: default !important;
+}
+
+.w-richtext figure img {
+    width: 100%;
+}
+
+.w-richtext figure figcaption.w-richtext-figcaption-placeholder {
+    opacity: .6;
+}
+
+.w-richtext figure div {
+    color: rgba(0, 0, 0, 0);
+    font-size: 0;
+}
+
+.w-richtext figure.w-richtext-figure-type-image,
+.w-richtext figure[data-rt-type="image"] {
+    display: table;
+}
+
+.w-richtext figure.w-richtext-figure-type-image>div,
+.w-richtext figure[data-rt-type="image"]>div {
+    display: inline-block;
+}
+
+.w-richtext figure.w-richtext-figure-type-image>figcaption,
+.w-richtext figure[data-rt-type="image"]>figcaption {
+    caption-side: bottom;
+    display: table-caption;
+}
+
+.w-richtext figure.w-richtext-figure-type-video,
+.w-richtext figure[data-rt-type="video"] {
+    width: 60%;
+    height: 0;
+}
+
+.w-richtext figure.w-richtext-figure-type-video iframe,
+.w-richtext figure[data-rt-type="video"] iframe {
+    width: 100%;
+    height: 100%;
+    position: absolute;
+    top: 0;
+    left: 0;
+}
+
+.w-richtext figure.w-richtext-figure-type-video>div,
+.w-richtext figure[data-rt-type="video"]>div {
+    width: 100%;
+}
+
+.w-richtext figure.w-richtext-align-center {
+    clear: both;
+    margin-left: auto;
+    margin-right: auto;
+}
+
+.w-richtext figure.w-richtext-align-center.w-richtext-figure-type-image>div,
+.w-richtext figure.w-richtext-align-center[data-rt-type="image"]>div {
+    max-width: 100%;
+}
+
+.w-richtext figure.w-richtext-align-normal {
+    clear: both;
+}
+
+.w-richtext figure.w-richtext-align-fullwidth {
+    width: 100%;
+    max-width: 100%;
+    text-align: center;
+    clear: both;
+    margin-left: auto;
+    margin-right: auto;
+    display: block;
+}
+
+.w-richtext figure.w-richtext-align-fullwidth>div {
+    padding-bottom: inherit;
+    display: inline-block;
+}
+
+.w-richtext figure.w-richtext-align-fullwidth>figcaption {
+    display: block;
+}
+
+.w-richtext figure.w-richtext-align-floatleft {
+    float: left;
+    clear: none;
+    margin-right: 15px;
+}
+
+.w-richtext figure.w-richtext-align-floatright {
+    float: right;
+    clear: none;
+    margin-left: 15px;
+}
+
+.w-nav {
+    z-index: 1000;
+    background: #ddd;
+    position: relative;
+}
+
+.w-nav:before,
+.w-nav:after {
+    content: " ";
+    grid-area: 1 / 1 / 2 / 2;
+    display: table;
+}
+
+.w-nav:after {
+    clear: both;
+}
+
+.w-nav-brand {
+    float: left;
+    color: #333;
+    text-decoration: none;
+    position: relative;
+}
+
+.w-nav-link {
+    vertical-align: top;
+    color: #222;
+    text-align: left;
+    margin-left: auto;
+    margin-right: auto;
+    padding: 20px;
+    text-decoration: none;
+    display: inline-block;
+    position: relative;
+}
+
+.w-nav-link.w--current {
+    color: #0082f3;
+}
+
+.w-nav-menu {
+    float: right;
+    position: relative;
+}
+
+[data-nav-menu-open] {
+    text-align: center;
+    min-width: 200px;
+    background: #c8c8c8;
+    position: absolute;
+    top: 100%;
+    left: 0;
+    right: 0;
+    overflow: visible;
+    display: block !important;
+}
+
+.w--nav-link-open {
+    display: block;
+    position: relative;
+}
+
+.w-nav-overlay {
+    width: 100%;
+    display: none;
+    position: absolute;
+    top: 100%;
+    left: 0;
+    right: 0;
+    overflow: hidden;
+}
+
+.w-nav-overlay [data-nav-menu-open] {
+    top: 0;
+}
+
+.w-nav[data-animation="over-left"] .w-nav-overlay {
+    width: auto;
+}
+
+.w-nav[data-animation="over-left"] .w-nav-overlay,
+.w-nav[data-animation="over-left"] [data-nav-menu-open] {
+    z-index: 1;
+    top: 0;
+    right: auto;
+}
+
+.w-nav[data-animation="over-right"] .w-nav-overlay {
+    width: auto;
+}
+
+.w-nav[data-animation="over-right"] .w-nav-overlay,
+.w-nav[data-animation="over-right"] [data-nav-menu-open] {
+    z-index: 1;
+    top: 0;
+    left: auto;
+}
+
+.w-nav-button {
+    float: right;
+    cursor: pointer;
+    -webkit-tap-highlight-color: rgba(0, 0, 0, 0);
+    -webkit-user-select: none;
+    -ms-user-select: none;
+    user-select: none;
+    padding: 18px;
+    font-size: 24px;
+    display: none;
+    position: relative;
+}
+
+.w-nav-button:focus {
+    outline: 0;
+}
+
+.w-nav-button.w--open {
+    color: #fff;
+    background-color: #c8c8c8;
+}
+
+.w-nav[data-collapse="all"] .w-nav-menu {
+    display: none;
+}
+
+.w-nav[data-collapse="all"] .w-nav-button,
+.w--nav-dropdown-open,
+.w--nav-dropdown-toggle-open {
+    display: block;
+}
+
+.w--nav-dropdown-list-open {
+    position: static;
+}
+
+@media screen and (max-width: 991px) {
+    .w-nav[data-collapse="medium"] .w-nav-menu {
+        display: none;
+    }
+    .w-nav[data-collapse="medium"] .w-nav-button {
+        display: block;
+    }
+}
+
+@media screen and (max-width: 767px) {
+    .w-nav[data-collapse="small"] .w-nav-menu {
+        display: none;
+    }
+    .w-nav[data-collapse="small"] .w-nav-button {
+        display: block;
+    }
+    .w-nav-brand {
+        padding-left: 10px;
+    }
+}
+
+@media screen and (max-width: 479px) {
+    .w-nav[data-collapse="tiny"] .w-nav-menu {
+        display: none;
+    }
+    .w-nav[data-collapse="tiny"] .w-nav-button {
+        display: block;
+    }
+}
+
+.w-tabs {
+    position: relative;
+}
+
+.w-tabs:before,
+.w-tabs:after {
+    content: " ";
+    grid-area: 1 / 1 / 2 / 2;
+    display: table;
+}
+
+.w-tabs:after {
+    clear: both;
+}
+
+.w-tab-menu {
+    position: relative;
+}
+
+.w-tab-link {
+    vertical-align: top;
+    text-align: left;
+    cursor: pointer;
+    color: #222;
+    background-color: #ddd;
+    padding: 9px 30px;
+    text-decoration: none;
+    display: inline-block;
+    position: relative;
+}
+
+.w-tab-link.w--current {
+    background-color: #c8c8c8;
+}
+
+.w-tab-link:focus {
+    outline: 0;
+}
+
+.w-tab-content {
+    display: block;
+    position: relative;
+    overflow: hidden;
+}
+
+.w-tab-pane {
+    display: none;
+    position: relative;
+}
+
+.w--tab-active {
+    display: block;
+}
+
+@media screen and (max-width: 479px) {
+    .w-tab-link {
+        display: block;
+    }
+}
+
+.w-ix-emptyfix:after {
+    content: "";
+}
+
+@keyframes spin {
+    0% {
+        transform: rotate(0);
+    }
+    100% {
+        transform: rotate(360deg);
+    }
+}
+
+.w-dyn-empty {
+    background-color: #ddd;
+    padding: 10px;
+}
+
+.w-dyn-hide,
+.w-dyn-bind-empty,
+.w-condition-invisible {
+    display: none !important;
+}
+
+body {
+    color: #333;
+    font-family: Arial, Helvetica Neue, Helvetica, sans-serif;
+    font-size: 14px;
+    line-height: 20px;
+}
+
+.navbar-link {
+    grid-column-gap: 0px;
+    grid-row-gap: 0px;
+    flex: 0 auto;
+    justify-content: flex-start;
+    align-items: flex-start;
+    padding: 24px 12px;
+    display: flex;
+}
+
+.text {
+    color: #000;
+    font-size: 14px;
+    font-weight: 400;
+    line-height: 150%;
+}
+
+.text-4 {
+    color: #212121;
+    font-size: 18px;
+    font-weight: 400;
+    line-height: 150%;
+}
+
+.title {
+    color: #000;
+    font-size: 24px;
+    font-weight: 700;
+    line-height: 150%;
+}
+
+.description {
+    color: #000;
+    font-size: 14px;
+    font-weight: 400;
+    line-height: 150%;
+}
+
+.text-5 {
+    color: #000;
+    text-align: center;
+    font-size: 32px;
+    font-weight: 700;
+    line-height: 120%;
+}
+
+.text-6 {
+    color: #000;
+    text-align: center;
+    font-size: 16px;
+    font-weight: 400;
+    line-height: 150%;
+}
+
+.text-7 {
+    color: #000;
+    text-align: center;
+    font-size: 20px;
+    font-weight: 700;
+    line-height: 150%;
+}
+
+.text-8 {
+    color: #000;
+    text-align: center;
+    font-size: 18px;
+    font-weight: 400;
+    line-height: 150%;
+}
+
+.navbar-logo-left-2 {
+    z-index: 2147483647;
+    width: 100%;
+    max-width: 100%;
+    grid-column-gap: 0px;
+    grid-row-gap: 0px;
+    background-color: #fff;
+    justify-content: center;
+    align-items: center;
+    padding-bottom: 10px;
+    padding-left: 24px;
+    padding-right: 24px;
+    display: flex;
+    position: -webkit-sticky;
+    position: sticky;
+    top: 0;
+    bottom: 10px;
+}
+
+.navbarcontainer-2 {
+    width: 100%;
+    max-width: 1200px;
+    grid-column-gap: 0px;
+    grid-row-gap: 0px;
+    justify-content: center;
+    align-items: center;
+    padding-top: 10px;
+    display: flex;
+}
+
+.navbar-content-2 {
+    width: 100%;
+    max-width: 1200px;
+    text-align: left;
+    justify-content: center;
+    align-items: center;
+    margin-left: auto;
+    margin-right: auto;
+    display: flex;
+    position: static;
+}
+
+.frame-237640 {
+    height: 53px;
+    grid-column-gap: 5px;
+    grid-row-gap: 5px;
+    flex: 0 auto;
+    justify-content: flex-start;
+    align-items: center;
+    margin-right: auto;
+    display: flex;
+}
+
+.frame-237642 {
+    grid-column-gap: 7px;
+    grid-row-gap: 7px;
+    flex: 0 auto;
+    justify-content: flex-start;
+    align-items: center;
+    display: flex;
+}
+
+.vectors-wrapper {
+    width: 65px;
+    height: 65px;
+    grid-column-gap: 0px;
+    grid-row-gap: 0px;
+    object-fit: cover;
+    justify-content: center;
+    align-items: center;
+    display: flex;
+}
+
+.text-11 {
+    color: #000;
+    letter-spacing: .1em;
+    font-family: Orbitron, sans-serif;
+    font-size: 24px;
+    font-weight: 500;
+    line-height: 150%;
+}
+
+.navbar-menu-2 {
+    grid-column-gap: 46px;
+    grid-row-gap: 46px;
+    text-align: left;
+    flex: none;
+    justify-content: space-between;
+    align-self: center;
+    align-items: center;
+    font-family: Inter, sans-serif;
+    font-size: 24px;
+    display: flex;
+    position: fixed;
+}
+
+.hero-heading-left-2 {
+    width: 100%;
+    height: 600px;
+    grid-column-gap: 80px;
+    grid-row-gap: 80px;
+    background-color: #f5f7fa;
+    justify-content: center;
+    align-items: flex-start;
+    padding: 40px 24px 100px;
+    display: flex;
+}
+
+.container {
+    overflow: hidden;
+}
+
+.container-3 {
+    width: 100%;
+    max-width: 1200px;
+    justify-content: flex-start;
+    align-items: center;
+    display: flex;
+    margin-top: 8%;
+    margin-left: 8%;
+    overflow-x: hidden;
+}
+
+.f2wf-columns-2 {
+    flex-wrap: nowrap;
+    align-self: auto;
+    padding-left: 10px;
+    padding-right: 10px;
+}
+
+.column-4 {
+    width: 100%;
+    grid-column-gap: 24px;
+    grid-row-gap: 24px;
+    flex-direction: column;
+    justify-content: flex-start;
+    align-items: flex-start;
+    display: flex;
+}
+
+.title-copy {
+    color: #000;
+    font-family: Inter, sans-serif;
+    font-size: 56px;
+    font-weight: 700;
+    line-height: 110%;
+}
+
+.actions-2 {
+    grid-column-gap: 16px;
+    grid-row-gap: 16px;
+    border-radius: 3px;
+    flex-direction: column;
+    justify-content: flex-start;
+    align-items: flex-start;
+    padding-top: 16px;
+    display: flex;
+}
+
+.button-4 {
+    grid-column-gap: 8px;
+    grid-row-gap: 8px;
+    background-color: #000;
+    border-radius: 3px;
+    flex: 0 auto;
+    justify-content: center;
+    align-items: center;
+    padding: 12px 24px;
+    font-family: Inter, sans-serif;
+    text-decoration: none;
+    display: flex;
+}
+
+.text-12 {
+    color: #fff;
+    letter-spacing: .03em;
+    font-size: 12px;
+    font-weight: 500;
+    line-height: 140%;
+}
+
+.column-5 {
+    width: 100%;
+    grid-column-gap: 10px;
+    grid-row-gap: 10px;
+    justify-content: flex-start;
+    align-items: flex-start;
+    display: flex;
+}
+
+.image-wrapper-4 {
+    width: 85%;
+    grid-column-gap: 0px;
+    grid-row-gap: 0px;
+    flex-direction: column;
+    justify-content: center;
+    align-items: center;
+    display: flex;
+}
+
+.image-4 {
+    width: 100%;
+    height: 80%;
+    max-height: 80%;
+    grid-column-gap: 0px;
+    grid-row-gap: 0px;
+    object-fit: cover;
+    justify-content: center;
+    align-items: center;
+    display: flex;
+}
+
+.features-list-2 {
+    width: 100%;
+    height: 506px;
+    grid-column-gap: 80px;
+    grid-row-gap: 80px;
+    background-color: #fff;
+    justify-content: center;
+    align-items: flex-start;
+    padding: 64px 24px;
+    display: flex;
+}
+
+.columns-4 {
+    width: 100%;
+    max-width: 960px;
+    grid-column-gap: 80px;
+    grid-row-gap: 80px;
+    justify-content: center;
+    align-items: flex-start;
+    display: flex;
+}
+
+.content-4 {
+    width: 100%;
+    grid-column-gap: 24px;
+    grid-row-gap: 24px;
+    flex-direction: column;
+    justify-content: flex-start;
+    align-items: flex-start;
+    padding-top: 24px;
+    padding-bottom: 24px;
+    display: flex;
+}
+
+.intro-2 {
+    width: 100%;
+    grid-column-gap: 16px;
+    grid-row-gap: 16px;
+    flex-direction: column;
+    justify-content: flex-start;
+    align-items: flex-start;
+    display: flex;
+}
+
+.models-list {
+    width: 100%;
+    grid-column-gap: 24px;
+    grid-row-gap: 24px;
+    justify-content: flex-start;
+    align-items: center;
+    display: flex;
+}
+
+.image-wrapper-5 {
+    width: 80px;
+    height: 80px;
+    grid-column-gap: 0px;
+    grid-row-gap: 0px;
+    justify-content: center;
+    align-items: center;
+    display: flex;
+}
+
+.image-5 {
+    width: 80px;
+    height: 80px;
+    grid-column-gap: 0px;
+    grid-row-gap: 0px;
+    object-fit: contain;
+    flex-direction: column;
+    justify-content: center;
+    align-items: center;
+    display: flex;
+    filter: grayscale(100%);
+}
+
+.frame-237641 {
+    width: 100%;
+    height: 79px;
+    max-width: 336px;
+    grid-column-gap: 2px;
+    grid-row-gap: 2px;
+    flex-direction: column;
+    justify-content: flex-start;
+    align-items: flex-start;
+    display: flex;
+}
+
+.description-2 {
+    color: #000;
+    font-size: 20px;
+    font-weight: 700;
+    line-height: 150%;
+}
+
+.team-circles-2 {
+    width: 100%;
+    grid-column-gap: 64px;
+    grid-row-gap: 64px;
+    background-color: #fff;
+    flex-direction: column;
+    justify-content: flex-start;
+    align-items: center;
+    padding: 64px 24px;
+    display: flex;
+}
+
+.container-4 {
+    width: 100%;
+    max-width: 1200px;
+    grid-column-gap: 64px;
+    grid-row-gap: 64px;
+    flex-direction: column;
+    justify-content: flex-start;
+    align-items: center;
+    display: flex;
+}
+
+.title-section-2 {
+    width: 100%;
+    max-width: 530px;
+    grid-column-gap: 16px;
+    grid-row-gap: 16px;
+    flex-direction: column;
+    justify-content: flex-start;
+    align-items: center;
+    display: flex;
+}
+
+.columns-5 {
+    width: 100%;
+    grid-column-gap: 48px;
+    grid-row-gap: 48px;
+    justify-content: center;
+    align-items: flex-start;
+    display: flex;
+}
+
+.card-2 {
+    width: 100%;
+    grid-column-gap: 24px;
+    grid-row-gap: 24px;
+    flex-direction: column;
+    justify-content: flex-start;
+    align-items: center;
+    display: flex;
+}
+
+.image-wrapper-6 {
+    width: 100%;
+    height: 270px;
+    max-width: 270px;
+    grid-column-gap: 0px;
+    grid-row-gap: 0px;
+    justify-content: center;
+    align-items: center;
+    display: flex;
+}
+
+.image-6 {
+    width: 130%;
+    height: 270px;
+    max-width: 270px;
+    grid-column-gap: 0px;
+    grid-row-gap: 0px;
+    object-fit: cover;
+    justify-content: center;
+    align-items: center;
+    display: flex;
+}
+
+.content-5 {
+    width: 100%;
+    grid-column-gap: 16px;
+    grid-row-gap: 16px;
+    flex-direction: column;
+    justify-content: flex-start;
+    align-items: center;
+    display: flex;
+}
+
+.info-2 {
+    width: 100%;
+    grid-column-gap: 0px;
+    grid-row-gap: 0px;
+    flex-direction: column;
+    justify-content: flex-start;
+    align-items: center;
+    display: flex;
+}
+
+.footer-2 {
+    width: 100%;
+    grid-column-gap: 40px;
+    grid-row-gap: 40px;
+    background-color: #f5f7fa;
+    flex-direction: column;
+    justify-content: flex-start;
+    align-items: center;
+    padding: 60px 24px;
+    display: flex;
+}
+
+.columns-6 {
+    width: 100%;
+    max-width: 960px;
+    justify-content: center;
+    align-items: center;
+    display: flex;
+}
+
+.column-6 {
+    width: 100%;
+    max-width: 320px;
+    grid-column-gap: 24px;
+    grid-row-gap: 24px;
+    text-align: left;
+    flex-direction: column;
+    flex: 0 auto;
+    justify-content: center;
+    align-self: center;
+    align-items: center;
+    display: flex;
+}
+
+.logo-wrapper-2 {
+    grid-column-gap: 0px;
+    grid-row-gap: 0px;
+    text-align: left;
+    flex: 0 auto;
+    justify-content: center;
+    align-self: center;
+    align-items: center;
+    padding-top: 16px;
+    display: flex;
+}
+
+.utility-page-wrap {
+    width: 100vw;
+    height: 100vh;
+    max-height: 100%;
+    max-width: 100%;
+    justify-content: center;
+    align-items: center;
+    display: flex;
+}
+
+.utility-page-content {
+    width: 260px;
+    text-align: center;
+    flex-direction: column;
+    display: flex;
+}
+
+.utility-page-form {
+    flex-direction: column;
+    align-items: stretch;
+    display: flex;
+}
+
+.section {
+    text-align: left;
+    flex-flow: row;
+    align-content: flex-end;
+    justify-content: center;
+    align-items: stretch;
+    margin-top: 0;
+    margin-left: 60px;
+    margin-right: 60px;
+    padding-top: 0;
+    padding-bottom: 20px;
+    display: flex;
+}
+
+.div-block {
+    padding-right: 0;
+}
+
+.submit-button-2 {
+    text-align: left;
+    background-color: #333;
+}
+
+.heading-3 {
+    font-size: 24px;
+}
+
+.button-5 {
+    background-color: #333;
+    border-radius: 10px;
+    align-self: center;
+}
+
+.button-6 {
+    background-color: #333;
+    border-radius: 10px;
+}
+
+@media screen and (max-width: 991px) {
+    .navbar-link {
+        justify-content: center;
+    }
+    .navbar-logo-left-2 {
+        padding-right: 0;
+    }
+    .navbar-menu-2 {
+        max-width: unset;
+    }
+    .hero-heading-left-2 {
+        height: 450px;
+    }
+    .f2wf-columns-2 {
+        flex-direction: column;
+        align-items: center;
+    }
+    .button-4 {
+        text-align: left;
+        justify-content: center;
+        align-self: center;
+        align-items: center;
+    }
+    .image-4 {
+        width: 50%;
+        height: 50%;
+        flex-wrap: nowrap;
+        display: none;
+        overflow: auto;
+    }
+    .column-6 {
+        align-items: center;
+    }
+    .tabs {
+        margin-left: 10px;
+        margin-right: 10px;
+    }
+    .tabs-menu-2 {
+        justify-content: center;
+        display: flex;
+    }
+    .tabs-content {
+        padding-left: 0;
+    }
+}
+
+@media screen and (max-width: 767px) {
+    .text-4 {
+        font-size: 16px;
+    }
+    .hero-heading-left-2 {
+        height: 380px;
+    }
+    .f2wf-columns-2 {
+        height: 600px;
+    }
+    .title-copy {
+        font-size: 45px;
+    }
+    .team-circles-2 {
+        margin-top: auto;
+        position: static;
+    }
+    .card-2 {
+        flex-wrap: nowrap;
+        align-content: space-between;
+        justify-content: flex-start;
+        align-items: flex-start;
+    }
+    .image-6 {
+        width: 50%;
+        height: 100%;
+    }
+    .tabs {
+        flex-direction: column;
+        justify-content: center;
+        align-items: flex-start;
+        margin-top: 10px;
+        margin-left: 15px;
+        margin-right: 15px;
+    }
+    .tabs-menu-2 {
+        grid-column-gap: 10px;
+        grid-row-gap: 10px;
+        text-align: center;
+        flex-direction: row;
+        grid-template-rows: auto auto;
+        grid-template-columns: 1fr 1fr;
+        grid-auto-columns: 1fr;
+        justify-content: center;
+        align-self: stretch;
+        align-items: stretch;
+        display: grid;
+    }
+    .tab-link-tab-4 {
+        width: auto;
+    }
+    .paragraph {
+        font-size: 13px;
+    }
+    .heading {
+        font-size: 30px;
+    }
+    .submit-button {
+        text-align: center;
+        object-position: 50% 50%;
+        display: inline-block;
+        position: static;
+        overflow: visible;
+    }
+}
+
+@media screen and (max-width: 479px) {
+    .text-4 {
+        text-align: center;
+        font-family: Inter, sans-serif;
+        font-size: 14px;
+        line-height: 120%;
+    }
+    .vectors-wrapper {
+        width: 40px;
+        height: 40px;
+    }
+    .text-11 {
+        font-size: 15px;
+    }
+    .title-copy {
+        font-size: 30px;
+    }
+    .tabs {
+        margin-left: 16px;
+        margin-right: 16px;
+    }
+    .tabs-menu-2 {
+        grid-column-gap: 10px;
+        grid-row-gap: 10px;
+        flex: 1;
+        grid-template-rows: auto auto;
+        grid-template-columns: 1fr 1fr;
+        grid-auto-columns: 1fr;
+        grid-auto-flow: row;
+        align-self: stretch;
+        align-items: stretch;
+        justify-items: stretch;
+        font-size: 10px;
+        line-height: 12px;
+        display: grid;
+    }
+    .text-block-2 {
+        text-align: center;
+    }
+    .text-block-3 {
+        text-align: center;
+        display: block;
+        overflow: visible;
+    }
+    .tab-link-tab-4 {
+        flex-direction: row;
+        display: block;
+    }
+    .text-block-4 {
+        text-align: center;
+    }
+    .paragraph {
+        text-align: left;
+        margin-bottom: 20px;
+        font-size: 12px;
+        line-height: 15px;
+    }
+    .heading {
+        text-align: left;
+        font-size: 28px;
+        line-height: 24px;
+    }
+    .field-label,
+    .field-label-2 {
+        font-size: 15px;
+    }
+    .text-block-5 {
+        text-align: center;
+    }
+    #w-node-bdfdfb5d-318b-f1c9-e2df-4b82621eca06-3afa01cf {
+        align-self: stretch;
+        justify-self: stretch;
+    }
+}
+
+.tab-container {
+    display: flex;
+    flex-wrap: wrap;
+    margin: 0 auto;
+    max-width: 800px;
+    margin-left: 10%;
+    margin-right: 10%;
+    margin-top: 10%;
+}
+
+
+/* Style the left column (tab menu) */
+
+.tab-menu {
+    flex: 1;
+    margin-right: 10px;
+    padding-bottom: 10px;
+}
+
+
+/* Style the tab buttons inside the tab menu */
+
+.tab-menu button {
+    display: block;
+    background-color: #ddd;
+    border: none;
+    outline: none;
+    cursor: pointer;
+    padding: 14px 16px;
+    transition: 0.3s;
+    font-size: 17px;
+    margin: 0;
+    width: 100%;
+    text-align: center;
+    border-radius: 10px;
+    margin-bottom: 10px;
+}
+
+
+/* Change background color of buttons on hover */
+
+.tab-menu button:hover {
+    background-color: #ddd;
+}
+
+
+/* Create an active/current tablink class */
+
+.tab-menu button.active {
+    background-color: #ccc;
+}
+
+
+/* Style the right column (tab content) */
+
+.tab-content {
+    flex: 2;
+    background-color: #fff;
+    margin-left: 10px;
+    border-radius: 10px;
+}
+
+
+/* Style the tab content */
+
+.tabcontent {
+    display: none;
+    margin: 0 auto;
+    max-width: 800px;
+    padding: 0px 12px;
+    border-top: none;
+}
+
+iframe {
+    border: none;
+    overflow: hidden;
+}
+
+body {
+    margin: 0;
+    padding: 0;
+    font-family: Inter;
+}
+
+.responsive-bar {
+    display: none;
+}
+
+nav {
+    width: 100%;
+    position: fixed;
+    top: 0;
+    left: 0;
+    height: 80px;
+    padding: 10px 100px;
+    box-sizing: border-box;
+    transition: .5s;
+    font-family: Poppins;
+}
+
+nav.black {
+    background: rgba(0, 0, 0, 0.8);
+    height: 80px;
+    padding: 10px 50px;
+    z-index: 10;
+}
+
+nav .logo {
+    float: left;
+    display: flex;
+    align-items: center;
+}
+
+nav .logo img {
+    height: 80px;
+    transition: .5s;
+    margin-right: 10px;
+}
+
+nav .logo .logo-text {
+    color: #000;
+    letter-spacing: .1em;
+    font-family: Orbitron, sans-serif;
+    font-size: 24px;
+    font-weight: regular;
+}
+
+nav.black .logo img {
+    height: 60px;
+    filter: invert(100%);
+    font-weight: regular;
+}
+
+nav.black .logo .logo-text {
+    color: #fff;
+}
+
+nav>ul {
+    width: 100%;
+    margin: 0 auto;
+    padding: 0;
+    float: none;
+    text-align: right;
+}
+
+nav>ul>li {
+    display: inline-block;
+    margin: 0 10px;
+    color: #000;
+}
+
+nav>ul>li>a:hover {
+    background: #000;
+    color: #fff;
+}
+
+nav>ul>li>a {
+    color: #000;
+    text-decoration: none;
+    line-height: 80px;
+    padding: 5px 20px;
+    transition: .5s;
+}
+
+nav.black>ul>li>a {
+    color: #fff;
+    line-height: 60px;
+}
+
+nav.black>ul>li>a:hover {
+    background: #fff;
+    color: #000;
+}
+
+.end-button {
+    display: absolute;
+    padding: 10px 15px;
+    border: 2px solid #000;
+    border-radius: 20px;
+    background-color: #000;
+    color: #fff;
+    text-decoration: none;
+}
+
+.end-button:hover {
+    border: 2px solid #000;
+    background-color: transparent;
+    color: #000;
+}
+
+section.sec1 {
+    display: flex;
+    align-items: flex-start;
+    justify-content: flex-start;
+    flex-direction: column;
+    color: #fff;
+    width: 100%;
+    height: 100vh;
+    background: url(https://i.pinimg.com/originals/7a/d0/c9/7ad0c9b192167fbeac6f53ff97a656df.gif);
+    background-size: cover;
+}
+
+section.content {
+    margin: 0;
+    padding: 0;
+    font-size: 1.1em;
+}
+
+@media(max-width:768px) {
+    .responsive-bar {
+        display: block;
+        width: 100%;
+        height: 60px;
+        background: #262626;
+        position: fixed;
+        top: 0;
+        left: 0;
+        padding: 5px 20px;
+        box-sizing: border-box;
+        z-index: 1;
+    }
+    .responsive-bar .logo img {
+        float: left;
+        height: 50px;
+    }
+    .responsive-bar .menu h4 {
+        float: right;
+        color: #fff;
+        margin: 0;
+        padding: 0;
+        line-height: 50px;
+        cursor: pointer;
+        text-transform: uppercase;
+    }
+    nav {
+        padding: 0;
+    }
+    nav,
+    nav.black {
+        background: #262626;
+        height: 60px;
+        padding: 0;
+    }
+    nav .logo {
+        display: none;
+    }
+    nav ul {
+        position: absolute;
+        width: 100%;
+        top: 60px;
+        left: 0;
+        background: #262626;
+        float: none;
+        display: none;
+    }
+    nav ul.active {
+        display: block;
+    }
+    nav ul li {
+        width: 100%;
+    }
+    nav ul li a {
+        display: block;
+        padding: 0;
+        width: 100%;
+        text-align: center;
+        line-height: 30px !important;
+        color: #fff;
+    }
+    nav>ul {
+        width: 100%;
+        display: none;
+    }
+    nav>ul>li {
+        display: block;
+        text-align: center;
+    }
+    .active {
+        display: block;
+    }
+}

static/css/model.css

@@ -0,0 +1,128 @@
+@import url('https://fonts.googleapis.com/css2?family=Poppins:wght@300;400;500;600;700&display=swap');
+body {
+    font-family: 'Poppins', sans-serif;
+    margin: 20 px;
+    padding: 0;
+}
+
+.container {
+    max-width: 600px;
+    margin: 50px auto;
+    background-color: #fff;
+    border-radius: 8px;
+    box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1);
+    padding: 20px;
+}
+
+h1 {
+    text-align: left;
+    color: #333;
+    font-weight: 600;
+    font-size: 24px;
+    margin-bottom: 20px;
+}
+
+form {
+    display: flex;
+    flex-wrap: wrap;
+    gap: 10px;
+}
+
+label {
+    margin-bottom: 8px;
+    color: #555;
+    font-weight: 500;
+}
+
+input[type="number"] {
+    border: 1px solid #ddd;
+    border-radius: 4px;
+    flex: 1;
+    min-width: 100px;
+}
+
+button {
+    padding: 8px 16px;
+    background-color: #4CAF50;
+    color: #fff;
+    border: none;
+    border-radius: 4px;
+    cursor: pointer;
+    font-weight: 600;
+}
+
+table {
+    width: 100%;
+    border-collapse: collapse;
+    margin-bottom: 20px;
+}
+
+th,
+td {
+    padding: 8px;
+    text-align: left;
+    border-bottom: 1px solid #ddd;
+}
+
+th {
+    font-weight: 600;
+    background-color: #f9f9f9;
+}
+
+ul {
+    list-style-type: none;
+    padding: 0;
+}
+
+li {
+    margin-bottom: 10px;
+    color: #555;
+}
+
+p {
+    margin-bottom: 5px;
+    color: #333;
+}
+
+.logo {
+    width: 50px;
+    height: 50px;
+    margin-right: 10px;
+}
+
+.header {
+    display: flex;
+    align-items: center;
+    max-width: 100%;
+}
+
+.form-container {
+    display: flex;
+    flex-direction: row;
+    align-items: center;
+    justify-content: center;
+}
+
+.form-container .form-group {
+    display: flex;
+    flex-wrap: wrap;
+    gap: 2px;
+}
+
+.form-group label {
+    margin-bottom: 5px;
+}
+
+.form-group input[type="number"] {
+    padding: 8px;
+    border: 1px solid #ddd;
+    border-radius: 4px;
+    flex: 1;
+    min-width: 50px;
+}
+
+.submit-btn {
+    width: 200px;
+    margin-top: 10px;
+    align-self: center;
+}

templates/algos.html

@@ -0,0 +1,79 @@
+{% extends 'base.html' %} {% block content %}
+<!DOCTYPE html>
+<html>
+
+<head>
+    <meta charset="utf-8 " />
+    <title>Classifiers</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='main.css')}}">
+    <link href="https://fonts.googleapis.com " rel="preconnect " />
+    <link href="https://fonts.gstatic.com " rel="preconnect " crossorigin="anonymous " />
+    <script src="https://ajax.googleapis.com/ajax/libs/webfont/1.6.26/webfont.js " type="text/javascript "></script>
+    <script type="text/javascript ">
+        WebFont.load({
+            google: {
+                families: ["Orbitron:regular,500,600,700,800,900 ", "Noto Sans Tamil:100,200,300,regular,500,600,700,800,900 ", "Inter:100,200,300,regular,500,600,700,800,900 "]
+            }
+        });
+    </script>
+    <script type="text/javascript ">
+        ! function(o, c) {
+            var n = c.documentElement,
+                t = " w-mod- ";
+            n.className += t + "js ", ("ontouchstart " in o || o.DocumentTouch && c instanceof DocumentTouch) && (n.className += t + "touch ")
+        }(window, document);
+    </script>
+</head>
+
+<body>
+    <div class="tab-container">
+        <!-- Left column (tab menu) -->
+        <div class="tab-menu">
+            <button class="tablinks active" onclick="openTab(event, 'linear')">Linear Regression</button>
+            <button class="tablinks" onclick="openTab(event, 'knn')">KNN</button>
+            <button class="tablinks" onclick="openTab(event, 'kmeans')">KMeans</button>
+            <button class="tablinks" onclick="openTab(event, 'naive-bayes')">Naive Bayes</button>
+        </div>
+
+        <!-- Right column (tab content) -->
+        <div class="tab-content">
+            <div id="linear" class="tabcontent">
+                <iframe src="{{ url_for('linear') }}" style="width:100%; height:500px;" scrolling="no"></iframe>
+            </div>
+
+            <div id="knn" class="tabcontent">
+                <iframe src="{{ url_for('knn') }}" style="width:100%; height:500px;" scrolling="no"></iframe>
+            </div>
+
+            <div id="kmeans" class="tabcontent">
+                <iframe src="{{ url_for('kmeans') }}" style="width:100%; height:500px; display: flex;" scrolling="no"></iframe>
+            </div>
+
+            <div id="naive-bayes" class="tabcontent">
+                <iframe src="{{ url_for('naive') }}" style="width:100%; height:500px;" scrolling="no"></iframe>
+            </div>
+        </div>
+
+        <script>
+            document.getElementById("linear").style.display = "block";
+
+            function openTab(evt, tabName) {
+                var i, tabcontent, tablinks;
+
+                tabcontent = document.getElementsByClassName("tabcontent");
+                for (i = 0; i < tabcontent.length; i++) {
+                    tabcontent[i].style.display = "none";
+                }
+
+                tablinks = document.getElementsByClassName("tablinks");
+                for (i = 0; i < tablinks.length; i++) {
+                    tablinks[i].className = tablinks[i].className.replace(" active", "");
+                }
+
+                document.getElementById(tabName).style.display = "block";
+                evt.currentTarget.className += " active";
+            }
+        </script>
+</body>
+
+</html>{% endblock %}

templates/base.html

@@ -0,0 +1,67 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta name="viewport" content="width=device-width,initial-scale=1, user-scalable=no">
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/main.css')}}">
+    <link href="https://fonts.googleapis.com " rel="preconnect " />
+    <link rel="icon" type="image/png" href="{{ url_for('static', filename='images/logo.svg')}}"/>
+    <link href="https://fonts.gstatic.com " rel="preconnect " crossorigin="anonymous " />
+    <link href="https://stackpath.bootstrapcdn.com/font-awesome/4.7.0/css/font-awesome.min.css" rel="stylesheet">
+    <script src="https://code.jquery.com/jquery-3.3.1.js"></script>
+    <script src="https://ajax.googleapis.com/ajax/libs/webfont/1.6.26/webfont.js " type="text/javascript "></script>
+    <script type="text/javascript ">
+        WebFont.load({
+            google: {
+                families: ["Orbitron:regular,500,600,700,800,900 ", "Noto Sans Tamil:100,200,300,regular,500,600,700,800,900 ", "Inter:100,200,300,regular,500,600,700,800,900 "]
+            }
+        });
+    </script>
+
+    <script type="text/javascript">
+        $(window).on('scroll', function() {
+                if ($(window).scrollTop()) {
+                    $('nav').addClass('black');
+                } else {
+                    $('nav').removeClass('black');
+                }
+            })
+            /*menu button onclick function*/
+        $(document).ready(function() {
+            $('.menu h4').click(function() {
+                $("nav ul").toggleClass("active")
+            })
+        })
+    </script>
+</head>
+
+<body>
+    <div class="responsive-bar">
+        <div class="logo">
+            <img src="{{ url_for('static', filename='images/logo.svg') }}" alt="logo" />
+
+
+        </div>
+        <div class="menu">
+            <h4>Menu</h4>
+        </div>
+    </div>
+    <nav>
+        <div class="logo">
+            <img src="{{ url_for('static', filename='images/logo.svg') }}" alt="logo" />
+
+            <span class="logo-text">Quatro</span>
+        </div>
+        <ul>
+            <li><a href="{{ url_for('index')}}" class="menulink">Home</a></li>
+            <li><a href="{{ url_for('algos')}}" class="end-button">Classifiers</a></li>
+                
+        </ul>
+    </nav>
+
+    <div class="container">
+        {% block content %} {% endblock %}
+    </div>
+</body>
+
+</html>

templates/draft.html

@@ -0,0 +1,240 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta name="viewport" content="width=device-width,initial-scale=1, user-scalable=no">
+    <link href="https://stackpath.bootstrapcdn.com/font-awesome/4.7.0/css/font-awesome.min.css" rel="stylesheet">
+    <script src="https://code.jquery.com/jquery-3.3.1.js"></script>
+    <script src="https://ajax.googleapis.com/ajax/libs/webfont/1.6.26/webfont.js " type="text/javascript "></script>
+    <script type="text/javascript ">
+        WebFont.load({
+            google: {
+                families: ["Orbitron:regular,500,600,700,800,900 ", "Noto Sans Tamil:100,200,300,regular,500,600,700,800,900 ", "Inter:100,200,300,regular,500,600,700,800,900 "]
+            }
+        });
+    </script>
+
+    <script type="text/javascript">
+        $(window).on('scroll', function() {
+                if ($(window).scrollTop()) {
+                    $('nav').addClass('black');
+                } else {
+                    $('nav').removeClass('black');
+                }
+            })
+            /*menu button onclick function*/
+        $(document).ready(function() {
+            $('.menu h4').click(function() {
+                $("nav ul").toggleClass("active")
+            })
+        })
+    </script>
+    <style>
+        body {
+            margin: 0;
+            padding: 0;
+            font-family: Inter;
+        }
+        
+        .responsive-bar {
+            display: none;
+        }
+        
+        nav {
+            width: 100%;
+            position: fixed;
+            top: 0;
+            left: 0;
+            height: 80px;
+            padding: 10px 100px;
+            box-sizing: border-box;
+            transition: .5s;
+        }
+        
+        nav.black {
+            background: rgba(0, 0, 0, 0.8);
+            height: 80px;
+            padding: 10px 50px;
+        }
+        
+        nav .logo {
+            float: left;
+            display: flex;
+            align-items: center;
+        }
+        
+        nav .logo img {
+            height: 80px;
+            transition: .5s;
+            margin-right: 10px;
+            filter: invert(100%);
+        }
+        
+        nav .logo .logo-text {
+            color: #fff;
+            letter-spacing: .1em;
+            font-family: Orbitron, sans-serif;
+            font-size: 24px;
+            font-weight: regular;
+        }
+        
+        nav.black .logo img {
+            height: 60px;
+            filter: invert(100%);
+            font-weight: regular;
+        }
+        
+        nav.black .logo .logo-text {
+            color: #fff;
+        }
+        
+        nav>ul {
+            width: 80%;
+            margin: 0 auto;
+            padding: 0;
+            float: none;
+            text-align: center;
+        }
+        
+        nav>ul>li {
+            display: inline-block;
+            margin: 0 10px;
+        }
+        
+        nav>ul>li>a:hover {
+            background: #f00;
+            color: #fff;
+        }
+        
+        nav>ul>li>a {
+            color: #ffffff;
+            text-decoration: none;
+            line-height: 80px;
+            padding: 5px 20px;
+            transition: .5s;
+        }
+        
+        nav.black>ul>li>a {
+            color: #fff;
+            line-height: 60px;
+        }
+        
+        section.sec1 {
+            display: flex;
+            align-items: flex-start;
+            justify-content: flex-start;
+            flex-direction: column;
+            color: #fff;
+            width: 100%;
+            height: 100vh;
+            background: url(https://i.pinimg.com/originals/7a/d0/c9/7ad0c9b192167fbeac6f53ff97a656df.gif);
+            background-size: cover;
+        }
+        
+        section.content {
+            margin: 0;
+            padding: 0;
+            font-size: 1.1em;
+        }
+        
+        @media(max-width:768px) {
+            .responsive-bar {
+                display: block;
+                width: 100%;
+                height: 60px;
+                background: #262626;
+                position: fixed;
+                top: 0;
+                left: 0;
+                padding: 5px 20px;
+                box-sizing: border-box;
+                z-index: 1;
+            }
+            .responsive-bar .logo img {
+                float: left;
+                height: 50px;
+            }
+            .responsive-bar .menu h4 {
+                float: right;
+                color: #fff;
+                margin: 0;
+                padding: 0;
+                line-height: 50px;
+                cursor: pointer;
+                text-transform: uppercase;
+            }
+            nav {
+                padding: 0;
+            }
+            nav,
+            nav.black {
+                background: #262626;
+                height: 60px;
+                padding: 0;
+            }
+            nav .logo {
+                display: none;
+            }
+            nav ul {
+                position: absolute;
+                width: 100%;
+                top: 60px;
+                left: 0;
+                background: #262626;
+                float: none;
+                display: none;
+            }
+            nav ul.active {
+                display: block;
+            }
+            nav ul li {
+                width: 100%;
+            }
+            nav ul li a {
+                display: block;
+                padding: 0;
+                width: 100%;
+                text-align: center;
+                line-height: 30px !important;
+                color: #fff;
+            }
+            nav>ul {
+                width: 100%;
+                display: none;
+            }
+            nav>ul>li {
+                display: block;
+                text-align: center;
+            }
+            .active {
+                display: block;
+            }
+        }
+    </style>
+</head>
+
+<body>
+    <div class="responsive-bar">
+        <div class="logo">
+            <img src="logo.svg" alt="logo" />
+
+        </div>
+        <div class="menu">
+            <h4>Menu</h4>
+        </div>
+    </div>
+    <nav>
+        <div class="logo">
+            <img src="logo.svg" alt="logo" />
+            <span class="logo-text">Quatro</span>
+        </div>
+        <ul>
+            <li><a href="#">Home</a></li>
+            <li> <a href="#">Classifiers</a></li>
+            <li><a href="#">About us</a></li>
+
+        </ul>
+    </nav>
+</body>
+
+</html>

templates/index.html

@@ -0,0 +1,163 @@
+{% extends 'base.html' %} {% block content %}
+<!DOCTYPE html>
+<html>
+
+<head>
+    <meta charset="utf-8" />
+    <title>Machine Learning Algorithms</title>
+    <meta content="width=device-width, initial-scale=1" name="viewport" />
+    <link rel="stylesheet" href="{{ url_for('static', filename='static/css/main.css')}}">
+    <link href="https://fonts.googleapis.com" rel="preconnect" />
+    <link href="https://fonts.gstatic.com" rel="preconnect" crossorigin="anonymous" />
+    <script src="https://ajax.googleapis.com/ajax/libs/webfont/1.6.26/webfont.js" type="text/javascript"></script>
+    <script type="text/javascript">
+        WebFont.load({
+            google: {
+                families: ["Orbitron:regular,500,600,700,800,900", "Noto Sans Tamil:100,200,300,regular,500,600,700,800,900", "Inter:100,200,300,regular,500,600,700,800,900"]
+            }
+        });
+    </script>
+    <script type="text/javascript">
+        ! function(o, c) {
+            var n = c.documentElement,
+                t = " w-mod-";
+            n.className += t + "js", ("ontouchstart" in o || o.DocumentTouch && c instanceof DocumentTouch) && (n.className += t + "touch")
+        }(window, document);
+    </script>
+
+</head>
+
+<body>
+    <div class="container-3 f2wf-columns-2">
+        <div class="column-4">
+            <div class="column-4">
+                <h1 class="title-copy">Machine Learning Algorithms</h1>
+                <p class="text-4">Welcome to our Quatro Data Analysis Web App! Explore the power of machine learning models - Linear Regression, K-Nearest Neighbors, K-Means, and Naive Bayes - as we delve into job data extracted from the popular Indeed website. Our intuitive Flask-based web app empowers you to input data and obtain accurate predictions from these models. Unleash the potential of AI-driven insights. Start exploring now!</p>
+            </div>
+            <a href="{{ url_for('algos')}}" class="button-4">
+                <div class="text-12">CLASSIFY</div>
+            </a>
+            <div class="actions-2"></div>
+        </div>
+        <div class="column-5">
+            <div class="image-wrapper-4"><img src="{{ url_for('static', filename='images/hero1.gif') }}"  width="100" height="100" class="image-4" />
+            </div>
+        </div>
+    </div>
+    </div>
+    <div class="features-list-2">
+        <div class="columns-4 f2wf-columns-2">
+            <div class="column-4">
+                <div class="content-4">
+                    <div class="intro-2">
+                        <div class="title">Machine Learning Algorithms</div>
+                        <div class="description">Machine learning is a branch of artificial intelligence that focuses on developing algorithms and models that enable computers to learn and make predictions or decisions without being explicitly programmed. It involves training machines on data to recognize patterns, extract insights, and improve performance over time.
+                        </div>
+                    </div>
+                    <div class="description">
+                        <a href="https://www.ibm.com/topics/machine-learning">Learn more →</a>
+                      </div>
+                      
+                </div>
+            </div>
+            <div class="intro-2">
+                <div class="models-list">
+                    <div class="image-wrapper-5"><img src="{{ url_for('static', filename='images/Model-Linear.png') }}" loading="lazy" width="80" height="80" alt="" class="image-5" /></div>
+                    <div class="frame-237641">
+                        <div class="description-2">K-Nearest Neighbor</div>
+                        <div class="description">Classify data points based on the majority class of their nearest neighbors.</div>
+                    </div>
+                </div>
+                <div class="models-list">
+                    <div class="image-wrapper-5"><img src="{{ url_for('static', filename='images/Model-kNN.png') }}" loading="lazy" width="80" height="80" alt="" class="image-5" /></div>
+                    <div class="frame-237641">
+                        <div class="description-2">Linear Regression</div>
+                        <div class="description">Predict numerical values based on input variables and establish linear relationships.</div>
+                    </div>
+                </div>
+                <div class="models-list">
+                    <div class="image-wrapper-5"><img src="{{ url_for('static', filename='images/Model-kMeans.png') }}" loading="lazy" width="80" height="80" alt="" class="image-5" /></div>
+                    <div class="frame-237641">
+                        <div class="description-2">K-Mean Clustering</div>
+                        <div class="description">Group similar data points into clusters to identify patterns and similarities.</div>
+                    </div>
+                </div>
+                <div class="models-list">
+                    <div class="image-wrapper-5"><img src="{{ url_for('static', filename='images/Model-Naive.png') }}" loading="lazy" width="80" height="80" alt="" class="image-5" /></div>
+                    <div class="frame-237641">
+                        <div class="description-2">Naive Bayes </div>
+                        <div class="description">Use probabilistic classification to predict the likelihood of a data point belonging to a specific class.</div>
+                    </div>
+                </div>
+            </div>
+        </div>
+    </div>
+    <div class="team-circles-2">
+        <div class="container-4">
+            <div class="title-section-2">
+                <div class="text-5">Team section</div>
+                <div class="text-6">The team behind this web app is group of computer science students with a passion for machine learning and web development. Together, we leverage our expertise in data analysis, AI algorithms, and user experience to create a seamless and intuitive experience for our users.</div>
+            </div>
+            <div class="columns-5 f2wf-columns-2">
+                <div class="card-2">
+                    <div class="image-wrapper-6"><img src="https://uploads-ssl.webflow.com/642cba496c45ae8313f6671d/642cc12016271546649d87ad_Image.png" loading="lazy" width="270" height="270" srcset="https://uploads-ssl.webflow.com/642cba496c45ae8313f6671d/642cc12016271546649d87ad_Image-p-500.png 500w, https://uploads-ssl.webflow.com/642cba496c45ae8313f6671d/642cc12016271546649d87ad_Image.png 540w"
+                            sizes="(max-width: 479px) 36vw, (max-width: 767px) 135px, (max-width: 991px) 35vw, 26vw" alt="" class="image-6" /></div>
+                    <div class="content-5">
+                        <div class="info-2">
+                            <div class="text-7">Dave F. Fagarita</div>
+                            <div class="text-8">BSCS 3A</div>
+                        </div>
+                        <div class="text-6">Developer</div>
+                    </div>
+                </div>
+                <div class="card-2">
+                    <div class="image-wrapper-6"><img src="https://uploads-ssl.webflow.com/642cba496c45ae8313f6671d/642cc12016271546649d87ad_Image.png" loading="lazy" width="270" height="270" srcset="https://uploads-ssl.webflow.com/642cba496c45ae8313f6671d/642cc12016271546649d87ad_Image-p-500.png 500w, https://uploads-ssl.webflow.com/642cba496c45ae8313f6671d/642cc12016271546649d87ad_Image.png 540w"
+                            sizes="(max-width: 479px) 36vw, (max-width: 767px) 135px, (max-width: 991px) 35vw, 26vw" alt="" class="image-6" /></div>
+                    <div class="content-5">
+                        <div class="info-2">
+                            <div class="text-7">Jimuel S. Servandil</div>
+                            <div class="text-8">BSCS 3A</div>
+                        </div>
+                        <div class="text-6">Developer</div>
+                    </div>
+                </div>
+                <div class="card-2">
+                    <div class="image-wrapper-6"><img src="https://uploads-ssl.webflow.com/642cba496c45ae8313f6671d/642cc12016271546649d87ad_Image.png" loading="lazy" width="270" height="270" srcset="https://uploads-ssl.webflow.com/642cba496c45ae8313f6671d/642cc12016271546649d87ad_Image-p-500.png 500w, https://uploads-ssl.webflow.com/642cba496c45ae8313f6671d/642cc12016271546649d87ad_Image.png 540w"
+                            sizes="(max-width: 479px) 36vw, (max-width: 767px) 135px, (max-width: 991px) 35vw, 26vw" alt="" class="image-6" /></div>
+                    <div class="content-5">
+                        <div class="info-2">
+                            <div class="text-7">Jannica Mae Magno</div>
+                            <div class="text-8">BSCS 3A</div>
+                        </div>
+                        <div class="text-6">Developer</div>
+                    </div>
+                </div>
+                <div class="card-2">
+                    <div class="image-wrapper-6"><img src="https://uploads-ssl.webflow.com/642cba496c45ae8313f6671d/642cc12016271546649d87ad_Image.png" loading="lazy" width="270" height="270" srcset="https://uploads-ssl.webflow.com/642cba496c45ae8313f6671d/642cc12016271546649d87ad_Image-p-500.png 500w, https://uploads-ssl.webflow.com/642cba496c45ae8313f6671d/642cc12016271546649d87ad_Image.png 540w"
+                            sizes="(max-width: 479px) 36vw, (max-width: 767px) 135px, (max-width: 991px) 35vw, 26vw" alt="" class="image-6" /></div>
+                    <div class="content-5">
+                        <div class="info-2">
+                            <div class="text-7">Jeziah Lois Catanus</div>
+                            <div class="text-8">BSCS 3A</div>
+                        </div>
+                        <div class="text-6">Developer</div>
+                    </div>
+                </div>
+            </div>
+        </div>
+        <div class="footer-2">
+            <div class="columns-6 f2wf-columns-2">
+                <div class="column-6">
+                    <div class="logo-wrapper-2"><img src="{{ url_for('static', filename='images/logo.svg') }}" loading="lazy" width="50" height="50" alt="" class="vectors-wrapper" />
+                        <div class="text-11">Quatro</div>
+                    </div>
+                </div>
+            </div>
+        </div>
+    </div>
+    <script src="https://d3e54v103j8qbb.cloudfront.net/js/jquery-3.5.1.min.dc5e7f18c8.js?site=642cba496c45ae8313f6671d" type="text/javascript" integrity="sha256-9/aliU8dGd2tb6OSsuzixeV4y/faTqgFtohetphbbj0=" crossorigin="anonymous"></script>
+    <script src="" type="text/javascript"></script>
+</body>
+
+</html>
+{% endblock %}

templates/kmeans.html

@@ -0,0 +1,22 @@
+<!DOCTYPE html>
+<html>
+
+<head>
+    <meta charset="utf-8">
+    <title>K-Nearest Neighbor</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/model.css')}}">
+</head>
+
+<body>
+  <div class="header">
+    <img src="{{ url_for('static', filename='images/Model-kMeans.png') }}" alt="Image" class="logo">
+    <h1>K-Means Clustering</h1>
+</div>
+
+
+<img src="{{ url_for('static', filename='images/cluster.png') }}" alt="Image" style="max-width: 100%; height: auto;">
+
+
+</body>
+
+</html>

templates/knn.html

@@ -0,0 +1,50 @@
+<!DOCTYPE html>
+<html>
+
+<head>
+    <meta charset="utf-8">
+    <title>K-Nearest Neighbor</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/model.css')}}">
+    <script>
+        function validateForm() {
+            var experienceField = document.getElementById("experience");
+            var experienceValue = experienceField.value;
+            if (experienceValue < 0) {
+                alert("Experience cannot be negative.");
+                return false;
+            }
+
+            var salaryField = document.getElementById("salary");
+            var salaryValue = salaryField.value;
+            if (salaryValue < 0) {
+                alert("Salary cannot be negative.");
+                return false;
+            }
+
+            return true;
+        }
+    </script>
+</head>
+
+<body>
+    <div class="header">
+        <img src="{{ url_for('static', filename='images/Model-kNN.png') }}" alt="Image" class="logo">
+        <h1>K-Nearest Neighbor</h1>
+    </div>
+    <form method="POST" action="{{ url_for('predictknn') }}" onsubmit="return validateForm()">
+        <label for="experience">Experience:</label>
+        <input type="number" id="experience" name="experience" placeholder="Experience" required>
+
+        <label for="salary">Salary:</label>
+        <input type="number" id="salary" name="salary" placeholder="Salary" required>
+        <button type="submit" class="btn btn-primary">Classify</button>
+    </form>
+    <br>
+
+    <p>{{salary}}</p>
+    <p>{{experience}}</p>
+    <h3>{{ prediction_text }}</h3>
+
+</body>
+
+</html>

templates/linear.html

@@ -0,0 +1,53 @@
+<!DOCTYPE html>
+<html>
+
+<head>
+    <meta charset="utf-8">
+    <title>Linear Regression</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/model.css')}}">
+    <script>
+        function validateForm() {
+            var experienceField = document.getElementById("experience");
+            var experienceValue = experienceField.value;
+            if (experienceValue < 0) {
+                alert("Experience cannot be negative.");
+                return false;
+            }
+            return true;
+        }
+    </script>
+</head>
+
+<body>
+    <div class="header">
+        <img src="{{ url_for('static', filename='images/Model-Linear.png') }}" alt="Image" class="logo">
+        <h1>Linear Regression</h1>
+    </div>
+
+    <!-- Main Input For Receiving Query to our ML -->
+    <form method="post" action="{{ url_for('predict') }}" onsubmit="return validateForm()">
+        <div class="form-container">
+            <div class="form-group">
+                <label for="exampleInputPassword1">Job Position:</label><br>
+                <select class="form-select" aria-label=".form-select-sm example" name="comp_select">
+                    <option selected>Select Position</option>
+                    <option value="1">Junior</option>
+                    <option value="2">Senior</option>
+                    <option value="3">Project Manager</option>
+                    <option value="4">CTO</option>
+                </select><br><br>
+                <label for="experience">Experience:</label>
+                <input type="number" id="experience" class="form-control" name="experience" placeholder="Experience" required="required"><br><br>
+            </div>
+        </div>
+        <button type="submit" class="btn btn-primary">Predict</button>
+    </form>
+    
+    <br>
+    <label for="exampleInputPassword1">{{ position_level }}</label><br>
+    <label for="exampleInputPassword1">{{ experience }}</label><br>
+    <label for="exampleInputPassword1">{{ prediction_text }}</label>
+
+</body>
+
+</html>

templates/naive.html

@@ -0,0 +1,70 @@
+<!DOCTYPE html>
+<html>
+
+<head>
+    <meta charset="utf-8">
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/model.css')}}">
+    <script>
+        function validateForm() {
+            var experienceField = document.getElementById("experience");
+            var experienceValue = experienceField.value;
+            if (experienceValue < 0) {
+                alert("Experience cannot be negative.");
+                return false;
+            }
+
+            var salaryField = document.getElementById("salary");
+            var salaryValue = salaryField.value;
+            if (salaryValue < 0) {
+                alert("Salary cannot be negative.");
+                return false;
+            }
+
+            return true;
+        }
+    </script>
+</head>
+
+<body>
+    <div class="header">
+        <img src="{{ url_for('static', filename='images/Model-Naive.png') }}" alt="Image" class="logo">
+        <h1>Naive Bayes</h1>
+    </div>
+    <form action="{{ url_for('predictnaive') }}" method="POST" onsubmit="return validateForm()">
+        <label for="experience">Experience:</label>
+        <input type="number" id="experience" name="experience" placeholder="Experience" required>
+
+        <label for="salary">Salary:</label>
+        <input type="number" id="salary" name="salary" placeholder="Salary" required>
+
+        <button type="submit">Classify</button>
+    </form>
+
+    <ul>
+        <li>Salary: {{ salary }}</li>
+        <li>Experience: {{ experience }}</li>
+    </ul>
+    <table>
+        <tr>
+            <th>Naive Bayes Type</th>
+            <th>Prediction</th>
+        </tr>
+        <tr>
+            <td>Multinomial Naive Bayes</td>
+            <td>{{ multinomial_accuracy }}</td>
+            <td>{{ multinomial_prediction }}</td>
+        </tr>
+        <tr>
+            <td>Gaussian Naive Bayes</td>
+            <td>{{ gaussian_accuracy }}</td>
+            <td>{{ gaussian_prediction }}</td>
+        </tr>
+        <tr>
+            <td>Bernoulli Naive Bayes</td>
+            <td>{{ bernoulli_accuracy }}</td>
+            <td>{{ bernoulli_prediction }}</td>
+        </tr>
+    </table>
+</body>
+
+</html>