diff --git a/Prediction Models/sleep_disorder_predictor/data/dataset.csv b/Prediction Models/sleep_disorder_predictor/data/dataset.csv new file mode 100644 index 00000000..b7e16bd5 --- /dev/null +++ b/Prediction Models/sleep_disorder_predictor/data/dataset.csv @@ -0,0 +1,375 @@ +Person ID,Gender,Age,Occupation,Sleep Duration,Quality of Sleep,Physical Activity Level,Stress Level,BMI Category,Blood Pressure,Heart Rate,Daily Steps,Sleep Disorder +1,Male,27,Software Engineer,6.1,6,42,6,Overweight,126/83,77,4200,None +2,Male,28,Doctor,6.2,6,60,8,Normal,125/80,75,10000,None +3,Male,28,Doctor,6.2,6,60,8,Normal,125/80,75,10000,None +4,Male,28,Sales Representative,5.9,4,30,8,Obese,140/90,85,3000,Sleep Apnea +5,Male,28,Sales Representative,5.9,4,30,8,Obese,140/90,85,3000,Sleep Apnea +6,Male,28,Software Engineer,5.9,4,30,8,Obese,140/90,85,3000,Insomnia +7,Male,29,Teacher,6.3,6,40,7,Obese,140/90,82,3500,Insomnia +8,Male,29,Doctor,7.8,7,75,6,Normal,120/80,70,8000,None +9,Male,29,Doctor,7.8,7,75,6,Normal,120/80,70,8000,None +10,Male,29,Doctor,7.8,7,75,6,Normal,120/80,70,8000,None +11,Male,29,Doctor,6.1,6,30,8,Normal,120/80,70,8000,None +12,Male,29,Doctor,7.8,7,75,6,Normal,120/80,70,8000,None +13,Male,29,Doctor,6.1,6,30,8,Normal,120/80,70,8000,None +14,Male,29,Doctor,6,6,30,8,Normal,120/80,70,8000,None +15,Male,29,Doctor,6,6,30,8,Normal,120/80,70,8000,None +16,Male,29,Doctor,6,6,30,8,Normal,120/80,70,8000,None +17,Female,29,Nurse,6.5,5,40,7,Normal Weight,132/87,80,4000,Sleep Apnea +18,Male,29,Doctor,6,6,30,8,Normal,120/80,70,8000,Sleep Apnea +19,Female,29,Nurse,6.5,5,40,7,Normal Weight,132/87,80,4000,Insomnia +20,Male,30,Doctor,7.6,7,75,6,Normal,120/80,70,8000,None +21,Male,30,Doctor,7.7,7,75,6,Normal,120/80,70,8000,None +22,Male,30,Doctor,7.7,7,75,6,Normal,120/80,70,8000,None +23,Male,30,Doctor,7.7,7,75,6,Normal,120/80,70,8000,None +24,Male,30,Doctor,7.7,7,75,6,Normal,120/80,70,8000,None +25,Male,30,Doctor,7.8,7,75,6,Normal,120/80,70,8000,None +26,Male,30,Doctor,7.9,7,75,6,Normal,120/80,70,8000,None +27,Male,30,Doctor,7.8,7,75,6,Normal,120/80,70,8000,None +28,Male,30,Doctor,7.9,7,75,6,Normal,120/80,70,8000,None +29,Male,30,Doctor,7.9,7,75,6,Normal,120/80,70,8000,None +30,Male,30,Doctor,7.9,7,75,6,Normal,120/80,70,8000,None +31,Female,30,Nurse,6.4,5,35,7,Normal Weight,130/86,78,4100,Sleep Apnea +32,Female,30,Nurse,6.4,5,35,7,Normal Weight,130/86,78,4100,Insomnia +33,Female,31,Nurse,7.9,8,75,4,Normal Weight,117/76,69,6800,None +34,Male,31,Doctor,6.1,6,30,8,Normal,125/80,72,5000,None +35,Male,31,Doctor,7.7,7,75,6,Normal,120/80,70,8000,None +36,Male,31,Doctor,6.1,6,30,8,Normal,125/80,72,5000,None +37,Male,31,Doctor,6.1,6,30,8,Normal,125/80,72,5000,None +38,Male,31,Doctor,7.6,7,75,6,Normal,120/80,70,8000,None +39,Male,31,Doctor,7.6,7,75,6,Normal,120/80,70,8000,None +40,Male,31,Doctor,7.6,7,75,6,Normal,120/80,70,8000,None +41,Male,31,Doctor,7.7,7,75,6,Normal,120/80,70,8000,None +42,Male,31,Doctor,7.7,7,75,6,Normal,120/80,70,8000,None +43,Male,31,Doctor,7.7,7,75,6,Normal,120/80,70,8000,None +44,Male,31,Doctor,7.8,7,75,6,Normal,120/80,70,8000,None +45,Male,31,Doctor,7.7,7,75,6,Normal,120/80,70,8000,None +46,Male,31,Doctor,7.8,7,75,6,Normal,120/80,70,8000,None +47,Male,31,Doctor,7.7,7,75,6,Normal,120/80,70,8000,None +48,Male,31,Doctor,7.8,7,75,6,Normal,120/80,70,8000,None +49,Male,31,Doctor,7.7,7,75,6,Normal,120/80,70,8000,None +50,Male,31,Doctor,7.7,7,75,6,Normal,120/80,70,8000,Sleep Apnea +51,Male,32,Engineer,7.5,8,45,3,Normal,120/80,70,8000,None +52,Male,32,Engineer,7.5,8,45,3,Normal,120/80,70,8000,None +53,Male,32,Doctor,6,6,30,8,Normal,125/80,72,5000,None +54,Male,32,Doctor,7.6,7,75,6,Normal,120/80,70,8000,None +55,Male,32,Doctor,6,6,30,8,Normal,125/80,72,5000,None +56,Male,32,Doctor,6,6,30,8,Normal,125/80,72,5000,None +57,Male,32,Doctor,7.7,7,75,6,Normal,120/80,70,8000,None +58,Male,32,Doctor,6,6,30,8,Normal,125/80,72,5000,None +59,Male,32,Doctor,6,6,30,8,Normal,125/80,72,5000,None +60,Male,32,Doctor,7.7,7,75,6,Normal,120/80,70,8000,None +61,Male,32,Doctor,6,6,30,8,Normal,125/80,72,5000,None +62,Male,32,Doctor,6,6,30,8,Normal,125/80,72,5000,None +63,Male,32,Doctor,6.2,6,30,8,Normal,125/80,72,5000,None +64,Male,32,Doctor,6.2,6,30,8,Normal,125/80,72,5000,None +65,Male,32,Doctor,6.2,6,30,8,Normal,125/80,72,5000,None +66,Male,32,Doctor,6.2,6,30,8,Normal,125/80,72,5000,None +67,Male,32,Accountant,7.2,8,50,6,Normal Weight,118/76,68,7000,None +68,Male,33,Doctor,6,6,30,8,Normal,125/80,72,5000,Insomnia +69,Female,33,Scientist,6.2,6,50,6,Overweight,128/85,76,5500,None +70,Female,33,Scientist,6.2,6,50,6,Overweight,128/85,76,5500,None +71,Male,33,Doctor,6.1,6,30,8,Normal,125/80,72,5000,None +72,Male,33,Doctor,6.1,6,30,8,Normal,125/80,72,5000,None +73,Male,33,Doctor,6.1,6,30,8,Normal,125/80,72,5000,None +74,Male,33,Doctor,6.1,6,30,8,Normal,125/80,72,5000,None +75,Male,33,Doctor,6,6,30,8,Normal,125/80,72,5000,None +76,Male,33,Doctor,6,6,30,8,Normal,125/80,72,5000,None +77,Male,33,Doctor,6,6,30,8,Normal,125/80,72,5000,None +78,Male,33,Doctor,6,6,30,8,Normal,125/80,72,5000,None +79,Male,33,Doctor,6,6,30,8,Normal,125/80,72,5000,None +80,Male,33,Doctor,6,6,30,8,Normal,125/80,72,5000,None +81,Female,34,Scientist,5.8,4,32,8,Overweight,131/86,81,5200,Sleep Apnea +82,Female,34,Scientist,5.8,4,32,8,Overweight,131/86,81,5200,Sleep Apnea +83,Male,35,Teacher,6.7,7,40,5,Overweight,128/84,70,5600,None +84,Male,35,Teacher,6.7,7,40,5,Overweight,128/84,70,5600,None +85,Male,35,Software Engineer,7.5,8,60,5,Normal Weight,120/80,70,8000,None +86,Female,35,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +87,Male,35,Engineer,7.2,8,60,4,Normal,125/80,65,5000,None +88,Male,35,Engineer,7.2,8,60,4,Normal,125/80,65,5000,None +89,Male,35,Engineer,7.3,8,60,4,Normal,125/80,65,5000,None +90,Male,35,Engineer,7.3,8,60,4,Normal,125/80,65,5000,None +91,Male,35,Engineer,7.3,8,60,4,Normal,125/80,65,5000,None +92,Male,35,Engineer,7.3,8,60,4,Normal,125/80,65,5000,None +93,Male,35,Software Engineer,7.5,8,60,5,Normal Weight,120/80,70,8000,None +94,Male,35,Lawyer,7.4,7,60,5,Obese,135/88,84,3300,Sleep Apnea +95,Female,36,Accountant,7.2,8,60,4,Normal,115/75,68,7000,Insomnia +96,Female,36,Accountant,7.1,8,60,4,Normal,115/75,68,7000,None +97,Female,36,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +98,Female,36,Accountant,7.1,8,60,4,Normal,115/75,68,7000,None +99,Female,36,Teacher,7.1,8,60,4,Normal,115/75,68,7000,None +100,Female,36,Teacher,7.1,8,60,4,Normal,115/75,68,7000,None +101,Female,36,Teacher,7.2,8,60,4,Normal,115/75,68,7000,None +102,Female,36,Teacher,7.2,8,60,4,Normal,115/75,68,7000,None +103,Female,36,Teacher,7.2,8,60,4,Normal,115/75,68,7000,None +104,Male,36,Teacher,6.6,5,35,7,Overweight,129/84,74,4800,Sleep Apnea +105,Female,36,Teacher,7.2,8,60,4,Normal,115/75,68,7000,Sleep Apnea +106,Male,36,Teacher,6.6,5,35,7,Overweight,129/84,74,4800,Insomnia +107,Female,37,Nurse,6.1,6,42,6,Overweight,126/83,77,4200,None +108,Male,37,Engineer,7.8,8,70,4,Normal Weight,120/80,68,7000,None +109,Male,37,Engineer,7.8,8,70,4,Normal Weight,120/80,68,7000,None +110,Male,37,Lawyer,7.4,8,60,5,Normal,130/85,68,8000,None +111,Female,37,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +112,Male,37,Lawyer,7.4,8,60,5,Normal,130/85,68,8000,None +113,Female,37,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +114,Male,37,Lawyer,7.4,8,60,5,Normal,130/85,68,8000,None +115,Female,37,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +116,Female,37,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +117,Female,37,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +118,Female,37,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +119,Female,37,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +120,Female,37,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +121,Female,37,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +122,Female,37,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +123,Female,37,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +124,Female,37,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +125,Female,37,Accountant,7.2,8,60,4,Normal,115/75,68,7000,None +126,Female,37,Nurse,7.5,8,60,4,Normal Weight,120/80,70,8000,None +127,Male,38,Lawyer,7.3,8,60,5,Normal,130/85,68,8000,None +128,Female,38,Accountant,7.1,8,60,4,Normal,115/75,68,7000,None +129,Male,38,Lawyer,7.3,8,60,5,Normal,130/85,68,8000,None +130,Male,38,Lawyer,7.3,8,60,5,Normal,130/85,68,8000,None +131,Female,38,Accountant,7.1,8,60,4,Normal,115/75,68,7000,None +132,Male,38,Lawyer,7.3,8,60,5,Normal,130/85,68,8000,None +133,Male,38,Lawyer,7.3,8,60,5,Normal,130/85,68,8000,None +134,Female,38,Accountant,7.1,8,60,4,Normal,115/75,68,7000,None +135,Male,38,Lawyer,7.3,8,60,5,Normal,130/85,68,8000,None +136,Male,38,Lawyer,7.3,8,60,5,Normal,130/85,68,8000,None +137,Female,38,Accountant,7.1,8,60,4,Normal,115/75,68,7000,None +138,Male,38,Lawyer,7.1,8,60,5,Normal,130/85,68,8000,None +139,Female,38,Accountant,7.1,8,60,4,Normal,115/75,68,7000,None +140,Male,38,Lawyer,7.1,8,60,5,Normal,130/85,68,8000,None +141,Female,38,Accountant,7.1,8,60,4,Normal,115/75,68,7000,None +142,Male,38,Lawyer,7.1,8,60,5,Normal,130/85,68,8000,None +143,Female,38,Accountant,7.1,8,60,4,Normal,115/75,68,7000,None +144,Female,38,Accountant,7.1,8,60,4,Normal,115/75,68,7000,None +145,Male,38,Lawyer,7.1,8,60,5,Normal,130/85,68,8000,Sleep Apnea +146,Female,38,Lawyer,7.4,7,60,5,Obese,135/88,84,3300,Sleep Apnea +147,Male,39,Lawyer,7.2,8,60,5,Normal,130/85,68,8000,Insomnia +148,Male,39,Engineer,6.5,5,40,7,Overweight,132/87,80,4000,Insomnia +149,Female,39,Lawyer,6.9,7,50,6,Normal Weight,128/85,75,5500,None +150,Female,39,Accountant,8,9,80,3,Normal Weight,115/78,67,7500,None +151,Female,39,Accountant,8,9,80,3,Normal Weight,115/78,67,7500,None +152,Male,39,Lawyer,7.2,8,60,5,Normal,130/85,68,8000,None +153,Male,39,Lawyer,7.2,8,60,5,Normal,130/85,68,8000,None +154,Male,39,Lawyer,7.2,8,60,5,Normal,130/85,68,8000,None +155,Male,39,Lawyer,7.2,8,60,5,Normal,130/85,68,8000,None +156,Male,39,Lawyer,7.2,8,60,5,Normal,130/85,68,8000,None +157,Male,39,Lawyer,7.2,8,60,5,Normal,130/85,68,8000,None +158,Male,39,Lawyer,7.2,8,60,5,Normal,130/85,68,8000,None +159,Male,39,Lawyer,7.2,8,60,5,Normal,130/85,68,8000,None +160,Male,39,Lawyer,7.2,8,60,5,Normal,130/85,68,8000,None +161,Male,39,Lawyer,7.2,8,60,5,Normal,130/85,68,8000,None +162,Female,40,Accountant,7.2,8,55,6,Normal Weight,119/77,73,7300,None +163,Female,40,Accountant,7.2,8,55,6,Normal Weight,119/77,73,7300,None +164,Male,40,Lawyer,7.9,8,90,5,Normal,130/85,68,8000,None +165,Male,40,Lawyer,7.9,8,90,5,Normal,130/85,68,8000,None +166,Male,41,Lawyer,7.6,8,90,5,Normal,130/85,70,8000,Insomnia +167,Male,41,Engineer,7.3,8,70,6,Normal Weight,121/79,72,6200,None +168,Male,41,Lawyer,7.1,7,55,6,Overweight,125/82,72,6000,None +169,Male,41,Lawyer,7.1,7,55,6,Overweight,125/82,72,6000,None +170,Male,41,Lawyer,7.7,8,90,5,Normal,130/85,70,8000,None +171,Male,41,Lawyer,7.7,8,90,5,Normal,130/85,70,8000,None +172,Male,41,Lawyer,7.7,8,90,5,Normal,130/85,70,8000,None +173,Male,41,Lawyer,7.7,8,90,5,Normal,130/85,70,8000,None +174,Male,41,Lawyer,7.7,8,90,5,Normal,130/85,70,8000,None +175,Male,41,Lawyer,7.6,8,90,5,Normal,130/85,70,8000,None +176,Male,41,Lawyer,7.6,8,90,5,Normal,130/85,70,8000,None +177,Male,41,Lawyer,7.6,8,90,5,Normal,130/85,70,8000,None +178,Male,42,Salesperson,6.5,6,45,7,Overweight,130/85,72,6000,Insomnia +179,Male,42,Lawyer,7.8,8,90,5,Normal,130/85,70,8000,None +180,Male,42,Lawyer,7.8,8,90,5,Normal,130/85,70,8000,None +181,Male,42,Lawyer,7.8,8,90,5,Normal,130/85,70,8000,None +182,Male,42,Lawyer,7.8,8,90,5,Normal,130/85,70,8000,None +183,Male,42,Lawyer,7.8,8,90,5,Normal,130/85,70,8000,None +184,Male,42,Lawyer,7.8,8,90,5,Normal,130/85,70,8000,None +185,Female,42,Teacher,6.8,6,45,7,Overweight,130/85,78,5000,Sleep Apnea +186,Female,42,Teacher,6.8,6,45,7,Overweight,130/85,78,5000,Sleep Apnea +187,Female,43,Teacher,6.7,7,45,4,Overweight,135/90,65,6000,Insomnia +188,Male,43,Salesperson,6.3,6,45,7,Overweight,130/85,72,6000,Insomnia +189,Female,43,Teacher,6.7,7,45,4,Overweight,135/90,65,6000,Insomnia +190,Male,43,Salesperson,6.5,6,45,7,Overweight,130/85,72,6000,Insomnia +191,Female,43,Teacher,6.7,7,45,4,Overweight,135/90,65,6000,Insomnia +192,Male,43,Salesperson,6.4,6,45,7,Overweight,130/85,72,6000,Insomnia +193,Male,43,Salesperson,6.5,6,45,7,Overweight,130/85,72,6000,Insomnia +194,Male,43,Salesperson,6.5,6,45,7,Overweight,130/85,72,6000,Insomnia +195,Male,43,Salesperson,6.5,6,45,7,Overweight,130/85,72,6000,Insomnia +196,Male,43,Salesperson,6.5,6,45,7,Overweight,130/85,72,6000,Insomnia +197,Male,43,Salesperson,6.5,6,45,7,Overweight,130/85,72,6000,Insomnia +198,Male,43,Salesperson,6.5,6,45,7,Overweight,130/85,72,6000,Insomnia +199,Male,43,Salesperson,6.5,6,45,7,Overweight,130/85,72,6000,Insomnia +200,Male,43,Salesperson,6.5,6,45,7,Overweight,130/85,72,6000,Insomnia +201,Male,43,Salesperson,6.5,6,45,7,Overweight,130/85,72,6000,Insomnia +202,Male,43,Engineer,7.8,8,90,5,Normal,130/85,70,8000,Insomnia +203,Male,43,Engineer,7.8,8,90,5,Normal,130/85,70,8000,Insomnia +204,Male,43,Engineer,6.9,6,47,7,Normal Weight,117/76,69,6800,None +205,Male,43,Engineer,7.6,8,75,4,Overweight,122/80,68,6800,None +206,Male,43,Engineer,7.7,8,90,5,Normal,130/85,70,8000,None +207,Male,43,Engineer,7.7,8,90,5,Normal,130/85,70,8000,None +208,Male,43,Engineer,7.7,8,90,5,Normal,130/85,70,8000,None +209,Male,43,Engineer,7.7,8,90,5,Normal,130/85,70,8000,None +210,Male,43,Engineer,7.8,8,90,5,Normal,130/85,70,8000,None +211,Male,43,Engineer,7.7,8,90,5,Normal,130/85,70,8000,None +212,Male,43,Engineer,7.8,8,90,5,Normal,130/85,70,8000,None +213,Male,43,Engineer,7.8,8,90,5,Normal,130/85,70,8000,None +214,Male,43,Engineer,7.8,8,90,5,Normal,130/85,70,8000,None +215,Male,43,Engineer,7.8,8,90,5,Normal,130/85,70,8000,None +216,Male,43,Engineer,7.8,8,90,5,Normal,130/85,70,8000,None +217,Male,43,Engineer,7.8,8,90,5,Normal,130/85,70,8000,None +218,Male,43,Engineer,7.8,8,90,5,Normal,130/85,70,8000,None +219,Male,43,Engineer,7.8,8,90,5,Normal,130/85,70,8000,Sleep Apnea +220,Male,43,Salesperson,6.5,6,45,7,Overweight,130/85,72,6000,Sleep Apnea +221,Female,44,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,Insomnia +222,Male,44,Salesperson,6.4,6,45,7,Overweight,130/85,72,6000,Insomnia +223,Male,44,Salesperson,6.3,6,45,7,Overweight,130/85,72,6000,Insomnia +224,Male,44,Salesperson,6.4,6,45,7,Overweight,130/85,72,6000,Insomnia +225,Female,44,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,Insomnia +226,Male,44,Salesperson,6.3,6,45,7,Overweight,130/85,72,6000,Insomnia +227,Female,44,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,Insomnia +228,Male,44,Salesperson,6.3,6,45,7,Overweight,130/85,72,6000,Insomnia +229,Female,44,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,Insomnia +230,Male,44,Salesperson,6.3,6,45,7,Overweight,130/85,72,6000,Insomnia +231,Female,44,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,Insomnia +232,Male,44,Salesperson,6.3,6,45,7,Overweight,130/85,72,6000,Insomnia +233,Female,44,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,Insomnia +234,Male,44,Salesperson,6.3,6,45,7,Overweight,130/85,72,6000,Insomnia +235,Female,44,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,Insomnia +236,Male,44,Salesperson,6.3,6,45,7,Overweight,130/85,72,6000,Insomnia +237,Male,44,Salesperson,6.4,6,45,7,Overweight,130/85,72,6000,Insomnia +238,Female,44,Teacher,6.5,7,45,4,Overweight,135/90,65,6000,Insomnia +239,Male,44,Salesperson,6.3,6,45,7,Overweight,130/85,72,6000,Insomnia +240,Male,44,Salesperson,6.4,6,45,7,Overweight,130/85,72,6000,Insomnia +241,Female,44,Teacher,6.5,7,45,4,Overweight,135/90,65,6000,Insomnia +242,Male,44,Salesperson,6.3,6,45,7,Overweight,130/85,72,6000,Insomnia +243,Male,44,Salesperson,6.4,6,45,7,Overweight,130/85,72,6000,Insomnia +244,Female,44,Teacher,6.5,7,45,4,Overweight,135/90,65,6000,Insomnia +245,Male,44,Salesperson,6.3,6,45,7,Overweight,130/85,72,6000,Insomnia +246,Female,44,Teacher,6.5,7,45,4,Overweight,135/90,65,6000,Insomnia +247,Male,44,Salesperson,6.3,6,45,7,Overweight,130/85,72,6000,Insomnia +248,Male,44,Engineer,6.8,7,45,7,Overweight,130/85,78,5000,Insomnia +249,Male,44,Salesperson,6.4,6,45,7,Overweight,130/85,72,6000,None +250,Male,44,Salesperson,6.5,6,45,7,Overweight,130/85,72,6000,None +251,Female,45,Teacher,6.8,7,30,6,Overweight,135/90,65,6000,Insomnia +252,Female,45,Teacher,6.8,7,30,6,Overweight,135/90,65,6000,Insomnia +253,Female,45,Teacher,6.5,7,45,4,Overweight,135/90,65,6000,Insomnia +254,Female,45,Teacher,6.5,7,45,4,Overweight,135/90,65,6000,Insomnia +255,Female,45,Teacher,6.5,7,45,4,Overweight,135/90,65,6000,Insomnia +256,Female,45,Teacher,6.5,7,45,4,Overweight,135/90,65,6000,Insomnia +257,Female,45,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,Insomnia +258,Female,45,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,Insomnia +259,Female,45,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,Insomnia +260,Female,45,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,Insomnia +261,Female,45,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,Insomnia +262,Female,45,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,None +263,Female,45,Teacher,6.6,7,45,4,Overweight,135/90,65,6000,None +264,Female,45,Manager,6.9,7,55,5,Overweight,125/82,75,5500,None +265,Male,48,Doctor,7.3,7,65,5,Obese,142/92,83,3500,Insomnia +266,Female,48,Nurse,5.9,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +267,Male,48,Doctor,7.3,7,65,5,Obese,142/92,83,3500,Insomnia +268,Female,49,Nurse,6.2,6,90,8,Overweight,140/95,75,10000,None +269,Female,49,Nurse,6,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +270,Female,49,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +271,Female,49,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +272,Female,49,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +273,Female,49,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +274,Female,49,Nurse,6.2,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +275,Female,49,Nurse,6.2,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +276,Female,49,Nurse,6.2,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +277,Male,49,Doctor,8.1,9,85,3,Obese,139/91,86,3700,Sleep Apnea +278,Male,49,Doctor,8.1,9,85,3,Obese,139/91,86,3700,Sleep Apnea +279,Female,50,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Insomnia +280,Female,50,Engineer,8.3,9,30,3,Normal,125/80,65,5000,None +281,Female,50,Nurse,6,6,90,8,Overweight,140/95,75,10000,None +282,Female,50,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +283,Female,50,Nurse,6,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +284,Female,50,Nurse,6,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +285,Female,50,Nurse,6,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +286,Female,50,Nurse,6,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +287,Female,50,Nurse,6,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +288,Female,50,Nurse,6,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +289,Female,50,Nurse,6,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +290,Female,50,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +291,Female,50,Nurse,6,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +292,Female,50,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +293,Female,50,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +294,Female,50,Nurse,6,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +295,Female,50,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +296,Female,50,Nurse,6,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +297,Female,50,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +298,Female,50,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +299,Female,51,Engineer,8.5,9,30,3,Normal,125/80,65,5000,None +300,Female,51,Engineer,8.5,9,30,3,Normal,125/80,65,5000,None +301,Female,51,Engineer,8.5,9,30,3,Normal,125/80,65,5000,None +302,Female,51,Engineer,8.5,9,30,3,Normal,125/80,65,5000,None +303,Female,51,Nurse,7.1,7,55,6,Normal Weight,125/82,72,6000,None +304,Female,51,Nurse,6,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +305,Female,51,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +306,Female,51,Nurse,6.1,6,90,8,Overweight,140/95,75,10000,Sleep Apnea +307,Female,52,Accountant,6.5,7,45,7,Overweight,130/85,72,6000,Insomnia +308,Female,52,Accountant,6.5,7,45,7,Overweight,130/85,72,6000,Insomnia +309,Female,52,Accountant,6.6,7,45,7,Overweight,130/85,72,6000,Insomnia +310,Female,52,Accountant,6.6,7,45,7,Overweight,130/85,72,6000,Insomnia +311,Female,52,Accountant,6.6,7,45,7,Overweight,130/85,72,6000,Insomnia +312,Female,52,Accountant,6.6,7,45,7,Overweight,130/85,72,6000,Insomnia +313,Female,52,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +314,Female,52,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +315,Female,52,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +316,Female,53,Engineer,8.3,9,30,3,Normal,125/80,65,5000,Insomnia +317,Female,53,Engineer,8.5,9,30,3,Normal,125/80,65,5000,None +318,Female,53,Engineer,8.5,9,30,3,Normal,125/80,65,5000,None +319,Female,53,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +320,Female,53,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +321,Female,53,Engineer,8.5,9,30,3,Normal,125/80,65,5000,None +322,Female,53,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +323,Female,53,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +324,Female,53,Engineer,8.5,9,30,3,Normal,125/80,65,5000,None +325,Female,53,Engineer,8.3,9,30,3,Normal,125/80,65,5000,None +326,Female,53,Engineer,8.5,9,30,3,Normal,125/80,65,5000,None +327,Female,53,Engineer,8.3,9,30,3,Normal,125/80,65,5000,None +328,Female,53,Engineer,8.5,9,30,3,Normal,125/80,65,5000,None +329,Female,53,Engineer,8.3,9,30,3,Normal,125/80,65,5000,None +330,Female,53,Engineer,8.5,9,30,3,Normal,125/80,65,5000,None +331,Female,53,Engineer,8.5,9,30,3,Normal,125/80,65,5000,None +332,Female,53,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +333,Female,54,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +334,Female,54,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +335,Female,54,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +336,Female,54,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +337,Female,54,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +338,Female,54,Engineer,8.4,9,30,3,Normal,125/80,65,5000,None +339,Female,54,Engineer,8.5,9,30,3,Normal,125/80,65,5000,None +340,Female,55,Nurse,8.1,9,75,4,Overweight,140/95,72,5000,Sleep Apnea +341,Female,55,Nurse,8.1,9,75,4,Overweight,140/95,72,5000,Sleep Apnea +342,Female,56,Doctor,8.2,9,90,3,Normal Weight,118/75,65,10000,None +343,Female,56,Doctor,8.2,9,90,3,Normal Weight,118/75,65,10000,None +344,Female,57,Nurse,8.1,9,75,3,Overweight,140/95,68,7000,None +345,Female,57,Nurse,8.2,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +346,Female,57,Nurse,8.2,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +347,Female,57,Nurse,8.2,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +348,Female,57,Nurse,8.2,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +349,Female,57,Nurse,8.2,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +350,Female,57,Nurse,8.1,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +351,Female,57,Nurse,8.1,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +352,Female,57,Nurse,8.1,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +353,Female,58,Nurse,8,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +354,Female,58,Nurse,8,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +355,Female,58,Nurse,8,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +356,Female,58,Nurse,8,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +357,Female,58,Nurse,8,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +358,Female,58,Nurse,8,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +359,Female,59,Nurse,8,9,75,3,Overweight,140/95,68,7000,None +360,Female,59,Nurse,8.1,9,75,3,Overweight,140/95,68,7000,None +361,Female,59,Nurse,8.2,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +362,Female,59,Nurse,8.2,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +363,Female,59,Nurse,8.2,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +364,Female,59,Nurse,8.2,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +365,Female,59,Nurse,8,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +366,Female,59,Nurse,8,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +367,Female,59,Nurse,8.1,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +368,Female,59,Nurse,8,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +369,Female,59,Nurse,8.1,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +370,Female,59,Nurse,8.1,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +371,Female,59,Nurse,8,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +372,Female,59,Nurse,8.1,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +373,Female,59,Nurse,8.1,9,75,3,Overweight,140/95,68,7000,Sleep Apnea +374,Female,59,Nurse,8.1,9,75,3,Overweight,140/95,68,7000,Sleep Apnea \ No newline at end of file diff --git a/Prediction Models/sleep_disorder_predictor/model.py b/Prediction Models/sleep_disorder_predictor/model.py new file mode 100644 index 00000000..561526c0 --- /dev/null +++ b/Prediction Models/sleep_disorder_predictor/model.py @@ -0,0 +1,43 @@ +import streamlit as st +import pickle +import pandas as pd # Import pandas to handle DataFrames +import numpy as np +import warnings +warnings.filterwarnings("ignore") + +# Load the model and the scaler +model_path = 'Prediction Models/sleep_disorder_predictor/saved_models/Model_Prediction.sav' +preprocessor_path = 'Prediction Models/sleep_disorder_predictor/saved_models/preprocessor.sav' + +# Load the pre-trained model and scaler using pickle +loaded_model = pickle.load(open(model_path, 'rb')) +preprocessor = pickle.load(open(preprocessor_path, 'rb')) + +# Define the prediction function +def disease_get_prediction(Age, Sleep_Duration, + Heart_Rate, Daily_Steps, + Systolic, Diastolic, Occupation, Quality_of_Sleep, Gender, + Physical_Activity_Level, Stress_Level, BMI_Category): + # Create a DataFrame with the features using correct column names + features = pd.DataFrame({ + 'Age': [int(Age)], + 'Sleep Duration': [float(Sleep_Duration)], # Changed to match expected name + 'Heart Rate': [int(Heart_Rate)], # Changed to match expected name + 'Daily Steps': [int(Daily_Steps)], # Changed to match expected name + 'Systolic': [float(Systolic)], + 'Diastolic': [float(Diastolic)], + 'Occupation': [Occupation], + 'Quality of Sleep': [int(Quality_of_Sleep)], # Changed to match expected name + 'Gender': [Gender], + 'Physical Activity Level': [int(Physical_Activity_Level)], # Changed to match expected name + 'Stress Level': [int(Stress_Level)], # Changed to match expected name + 'BMI Category': [BMI_Category] # Changed to match expected name + }) + + # Apply the preprocessor (make sure it expects a DataFrame) + preprocessed_data = preprocessor.transform(features) + + # Make prediction + prediction = loaded_model.predict(preprocessed_data) + + return prediction diff --git a/Prediction Models/sleep_disorder_predictor/notebooks/sleep-disorder.ipynb b/Prediction Models/sleep_disorder_predictor/notebooks/sleep-disorder.ipynb new file mode 100644 index 00000000..9fdd3203 --- /dev/null +++ b/Prediction Models/sleep_disorder_predictor/notebooks/sleep-disorder.ipynb @@ -0,0 +1,1817 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Importing Libraries" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:50.730222Z", + "iopub.status.busy": "2024-10-28T17:03:50.729761Z", + "iopub.status.idle": "2024-10-28T17:03:50.736092Z", + "shell.execute_reply": "2024-10-28T17:03:50.734920Z", + "shell.execute_reply.started": "2024-10-28T17:03:50.730179Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "import plotly.express as px\n", + "import warnings\n", + "warnings.filterwarnings('ignore')" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:50.761933Z", + "iopub.status.busy": "2024-10-28T17:03:50.761339Z", + "iopub.status.idle": "2024-10-28T17:03:50.769291Z", + "shell.execute_reply": "2024-10-28T17:03:50.767888Z", + "shell.execute_reply.started": "2024-10-28T17:03:50.761886Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "from sklearn.preprocessing import OneHotEncoder,LabelEncoder ,RobustScaler,StandardScaler\n", + "from sklearn.compose import ColumnTransformer\n", + "from sklearn.pipeline import Pipeline\n", + "from sklearn.model_selection import train_test_split,StratifiedShuffleSplit,StratifiedKFold,cross_val_score\n", + "from imblearn.over_sampling import SMOTE\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, classification_report, confusion_matrix\n", + "from sklearn.linear_model import LogisticRegression\n", + "import xgboost as xgb\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Reading CSV data" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:50.798928Z", + "iopub.status.busy": "2024-10-28T17:03:50.798473Z", + "iopub.status.idle": "2024-10-28T17:03:50.809300Z", + "shell.execute_reply": "2024-10-28T17:03:50.808250Z", + "shell.execute_reply.started": "2024-10-28T17:03:50.798887Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "df = pd.read_csv('Prediction Models/sleep_disorder_predictor/data/dataset.csv')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# EDA" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:50.842641Z", + "iopub.status.busy": "2024-10-28T17:03:50.842174Z", + "iopub.status.idle": "2024-10-28T17:03:50.861483Z", + "shell.execute_reply": "2024-10-28T17:03:50.860244Z", + "shell.execute_reply.started": "2024-10-28T17:03:50.842596Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Person IDGenderAgeOccupationSleep DurationQuality of SleepPhysical Activity LevelStress LevelBMI CategoryBlood PressureHeart RateDaily StepsSleep Disorder
01Male27Software Engineer6.16426Overweight126/83774200NaN
12Male28Doctor6.26608Normal125/807510000NaN
23Male28Doctor6.26608Normal125/807510000NaN
34Male28Sales Representative5.94308Obese140/90853000Sleep Apnea
45Male28Sales Representative5.94308Obese140/90853000Sleep Apnea
\n", + "
" + ], + "text/plain": [ + " Person ID Gender Age Occupation Sleep Duration \\\n", + "0 1 Male 27 Software Engineer 6.1 \n", + "1 2 Male 28 Doctor 6.2 \n", + "2 3 Male 28 Doctor 6.2 \n", + "3 4 Male 28 Sales Representative 5.9 \n", + "4 5 Male 28 Sales Representative 5.9 \n", + "\n", + " Quality of Sleep Physical Activity Level Stress Level BMI Category \\\n", + "0 6 42 6 Overweight \n", + "1 6 60 8 Normal \n", + "2 6 60 8 Normal \n", + "3 4 30 8 Obese \n", + "4 4 30 8 Obese \n", + "\n", + " Blood Pressure Heart Rate Daily Steps Sleep Disorder \n", + "0 126/83 77 4200 NaN \n", + "1 125/80 75 10000 NaN \n", + "2 125/80 75 10000 NaN \n", + "3 140/90 85 3000 Sleep Apnea \n", + "4 140/90 85 3000 Sleep Apnea " + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.head(5)" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:50.871919Z", + "iopub.status.busy": "2024-10-28T17:03:50.871378Z", + "iopub.status.idle": "2024-10-28T17:03:50.880137Z", + "shell.execute_reply": "2024-10-28T17:03:50.878890Z", + "shell.execute_reply.started": "2024-10-28T17:03:50.871865Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(374, 13)" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:50.901136Z", + "iopub.status.busy": "2024-10-28T17:03:50.900697Z", + "iopub.status.idle": "2024-10-28T17:03:50.910144Z", + "shell.execute_reply": "2024-10-28T17:03:50.908782Z", + "shell.execute_reply.started": "2024-10-28T17:03:50.901095Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Person ID int64\n", + "Gender object\n", + "Age int64\n", + "Occupation object\n", + "Sleep Duration float64\n", + "Quality of Sleep int64\n", + "Physical Activity Level int64\n", + "Stress Level int64\n", + "BMI Category object\n", + "Blood Pressure object\n", + "Heart Rate int64\n", + "Daily Steps int64\n", + "Sleep Disorder object\n", + "dtype: object" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.dtypes" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:50.931656Z", + "iopub.status.busy": "2024-10-28T17:03:50.931147Z", + "iopub.status.idle": "2024-10-28T17:03:50.969450Z", + "shell.execute_reply": "2024-10-28T17:03:50.968289Z", + "shell.execute_reply.started": "2024-10-28T17:03:50.931608Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Person IDAgeSleep DurationQuality of SleepPhysical Activity LevelStress LevelHeart RateDaily Steps
count374.000000374.000000374.000000374.000000374.000000374.000000374.000000374.000000
mean187.50000042.1844927.1320867.31283459.1711235.38502770.1657756816.844920
std108.1087428.6731330.7956571.19695620.8308041.7745264.1356761617.915679
min1.00000027.0000005.8000004.00000030.0000003.00000065.0000003000.000000
25%94.25000035.2500006.4000006.00000045.0000004.00000068.0000005600.000000
50%187.50000043.0000007.2000007.00000060.0000005.00000070.0000007000.000000
75%280.75000050.0000007.8000008.00000075.0000007.00000072.0000008000.000000
max374.00000059.0000008.5000009.00000090.0000008.00000086.00000010000.000000
\n", + "
" + ], + "text/plain": [ + " Person ID Age Sleep Duration Quality of Sleep \\\n", + "count 374.000000 374.000000 374.000000 374.000000 \n", + "mean 187.500000 42.184492 7.132086 7.312834 \n", + "std 108.108742 8.673133 0.795657 1.196956 \n", + "min 1.000000 27.000000 5.800000 4.000000 \n", + "25% 94.250000 35.250000 6.400000 6.000000 \n", + "50% 187.500000 43.000000 7.200000 7.000000 \n", + "75% 280.750000 50.000000 7.800000 8.000000 \n", + "max 374.000000 59.000000 8.500000 9.000000 \n", + "\n", + " Physical Activity Level Stress Level Heart Rate Daily Steps \n", + "count 374.000000 374.000000 374.000000 374.000000 \n", + "mean 59.171123 5.385027 70.165775 6816.844920 \n", + "std 20.830804 1.774526 4.135676 1617.915679 \n", + "min 30.000000 3.000000 65.000000 3000.000000 \n", + "25% 45.000000 4.000000 68.000000 5600.000000 \n", + "50% 60.000000 5.000000 70.000000 7000.000000 \n", + "75% 75.000000 7.000000 72.000000 8000.000000 \n", + "max 90.000000 8.000000 86.000000 10000.000000 " + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:50.971646Z", + "iopub.status.busy": "2024-10-28T17:03:50.971245Z", + "iopub.status.idle": "2024-10-28T17:03:50.977082Z", + "shell.execute_reply": "2024-10-28T17:03:50.976038Z", + "shell.execute_reply.started": "2024-10-28T17:03:50.971606Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "columns = [column for column in df.columns if column!='Person ID']" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:50.988901Z", + "iopub.status.busy": "2024-10-28T17:03:50.988033Z", + "iopub.status.idle": "2024-10-28T17:03:50.999577Z", + "shell.execute_reply": "2024-10-28T17:03:50.998370Z", + "shell.execute_reply.started": "2024-10-28T17:03:50.988856Z" + }, + "trusted": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Unique values in 'Gender': ['Male' 'Female']\n", + "Unique values in 'Age': [27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 48 49 50 51 52\n", + " 53 54 55 56 57 58 59]\n", + "Unique values in 'Occupation': ['Software Engineer' 'Doctor' 'Sales Representative' 'Teacher' 'Nurse'\n", + " 'Engineer' 'Accountant' 'Scientist' 'Lawyer' 'Salesperson' 'Manager']\n", + "Unique values in 'Sleep Duration': [6.1 6.2 5.9 6.3 7.8 6. 6.5 7.6 7.7 7.9 6.4 7.5 7.2 5.8 6.7 7.3 7.4 7.1\n", + " 6.6 6.9 8. 6.8 8.1 8.3 8.5 8.4 8.2]\n", + "Unique values in 'Quality of Sleep': [6 4 7 5 8 9]\n", + "Unique values in 'Physical Activity Level': [42 60 30 40 75 35 45 50 32 70 80 55 90 47 65 85]\n", + "Unique values in 'Stress Level': [6 8 7 4 3 5]\n", + "Unique values in 'BMI Category': ['Overweight' 'Normal' 'Obese' 'Normal Weight']\n", + "Unique values in 'Blood Pressure': ['126/83' '125/80' '140/90' '120/80' '132/87' '130/86' '117/76' '118/76'\n", + " '128/85' '131/86' '128/84' '115/75' '135/88' '129/84' '130/85' '115/78'\n", + " '119/77' '121/79' '125/82' '135/90' '122/80' '142/92' '140/95' '139/91'\n", + " '118/75']\n", + "Unique values in 'Heart Rate': [77 75 85 82 70 80 78 69 72 68 76 81 65 84 74 67 73 83 86]\n", + "Unique values in 'Daily Steps': [ 4200 10000 3000 3500 8000 4000 4100 6800 5000 7000 5500 5200\n", + " 5600 3300 4800 7500 7300 6200 6000 3700]\n", + "Unique values in 'Sleep Disorder': [nan 'Sleep Apnea' 'Insomnia']\n" + ] + } + ], + "source": [ + "for column in columns:\n", + " unique_values = df[column].unique()\n", + " print(f\"Unique values in '{column}': {unique_values}\")" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:51.014238Z", + "iopub.status.busy": "2024-10-28T17:03:51.013501Z", + "iopub.status.idle": "2024-10-28T17:03:51.020264Z", + "shell.execute_reply": "2024-10-28T17:03:51.018894Z", + "shell.execute_reply.started": "2024-10-28T17:03:51.014189Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "# Replace NaN in 'Sleep Disorder' with 'No Disorder'\n", + "df['Sleep Disorder'].fillna('No Disorder', inplace=True)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:51.055209Z", + "iopub.status.busy": "2024-10-28T17:03:51.054779Z", + "iopub.status.idle": "2024-10-28T17:03:51.063757Z", + "shell.execute_reply": "2024-10-28T17:03:51.062519Z", + "shell.execute_reply.started": "2024-10-28T17:03:51.055170Z" + }, + "trusted": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Value counts of 'Sleep Disorder':\n", + "Sleep Disorder\n", + "No Disorder 219\n", + "Sleep Apnea 78\n", + "Insomnia 77\n", + "Name: count, dtype: int64\n" + ] + } + ], + "source": [ + "# Value counts of 'Sleep Disorder'\n", + "sleep_disorder_counts = df['Sleep Disorder'].value_counts()\n", + "\n", + "print(\"Value counts of 'Sleep Disorder':\")\n", + "print(sleep_disorder_counts)" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:51.120940Z", + "iopub.status.busy": "2024-10-28T17:03:51.120476Z", + "iopub.status.idle": "2024-10-28T17:03:51.132310Z", + "shell.execute_reply": "2024-10-28T17:03:51.131078Z", + "shell.execute_reply.started": "2024-10-28T17:03:51.120895Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "BMI Category\n", + "Normal Weight 216\n", + "Overweight 148\n", + "Obese 10\n", + "Name: count, dtype: int64" + ] + }, + "execution_count": 41, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df['BMI Category']=df['BMI Category'].replace({'Normal':'Normal Weight'})\n", + "df['BMI Category'].value_counts()" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:51.231739Z", + "iopub.status.busy": "2024-10-28T17:03:51.230626Z", + "iopub.status.idle": "2024-10-28T17:03:51.322202Z", + "shell.execute_reply": "2024-10-28T17:03:51.321069Z", + "shell.execute_reply.started": "2024-10-28T17:03:51.231674Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# bmi_counts = df['BMI Category'].value_counts()\n", + "fig = px.histogram(data_frame=df, x = 'BMI Category', color = 'Sleep Disorder', title='Bar Chart of BMI Category Counts')\n", + "fig.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "- Obese suffer from Insomnia and Sleep Apnea\n", + "- Very few overweighted people have no sleep disorder\n", + "- Very few people of normal weight face sleep disorder " + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:51.324785Z", + "iopub.status.busy": "2024-10-28T17:03:51.324343Z", + "iopub.status.idle": "2024-10-28T17:03:51.411588Z", + "shell.execute_reply": "2024-10-28T17:03:51.410375Z", + "shell.execute_reply.started": "2024-10-28T17:03:51.324744Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "fig = px.histogram(data_frame=df, x = 'Quality of Sleep', color = 'Sleep Disorder', title='Bar Chart of BMI Category Counts')\n", + "fig.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:51.419009Z", + "iopub.status.busy": "2024-10-28T17:03:51.418278Z", + "iopub.status.idle": "2024-10-28T17:03:51.507486Z", + "shell.execute_reply": "2024-10-28T17:03:51.506316Z", + "shell.execute_reply.started": "2024-10-28T17:03:51.418965Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "fig = px.histogram(data_frame=df, x = 'Occupation', color = 'Sleep Disorder', title='Bar Chart of BMI Category Counts')\n", + "fig.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Occupation of Nurse,Teacher, Sales person and sales representative are prone to sleep disorder" + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:03:51.609353Z", + "iopub.status.busy": "2024-10-28T17:03:51.608854Z", + "iopub.status.idle": "2024-10-28T17:03:51.934707Z", + "shell.execute_reply": "2024-10-28T17:03:51.933435Z", + "shell.execute_reply.started": "2024-10-28T17:03:51.609305Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "color_palette = {'Male': 'lightblue', 'Female': 'lightcoral'}\n", + "plt.figure(figsize=(10, 6))\n", + "sns.violinplot(x='Gender', y='Quality of Sleep', data=df, palette=color_palette)\n", + "plt.title('Distribution of Quality of Sleep by Gender', fontsize=16)\n", + "plt.xlabel('Gender', fontsize=12)\n", + "plt.ylabel('Quality of Sleep', fontsize=12)\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T17:09:56.470837Z", + "iopub.status.busy": "2024-10-28T17:09:56.470335Z", + "iopub.status.idle": "2024-10-28T17:09:56.581962Z", + "shell.execute_reply": "2024-10-28T17:09:56.580944Z", + "shell.execute_reply.started": "2024-10-28T17:09:56.470791Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "fig = px.bar(df, \n", + " x='Stress Level', \n", + " y='Quality of Sleep', \n", + " color='Stress Level',\n", + " title='Relationship between Stress Level and Quality of Sleep'\n", + " )\n", + "fig.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**Splitting Blood Pressure into two columns: Systolic and Diastolic**" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:21.373939Z", + "iopub.status.busy": "2024-10-28T15:52:21.373595Z", + "iopub.status.idle": "2024-10-28T15:52:21.385603Z", + "shell.execute_reply": "2024-10-28T15:52:21.384459Z", + "shell.execute_reply.started": "2024-10-28T15:52:21.373904Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "df = pd.concat([df, df['Blood Pressure'].str.split('/', expand=True)], axis=1).drop('Blood Pressure', axis=1)\n", + "df = df.rename(columns={0: 'Systolic', 1: 'Diastolic'})" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:21.388144Z", + "iopub.status.busy": "2024-10-28T15:52:21.387075Z", + "iopub.status.idle": "2024-10-28T15:52:21.394225Z", + "shell.execute_reply": "2024-10-28T15:52:21.393114Z", + "shell.execute_reply.started": "2024-10-28T15:52:21.388095Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "df['Systolic'] = df['Systolic'].astype(float)\n", + "df['Diastolic'] = df['Diastolic'].astype(float)" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:21.395822Z", + "iopub.status.busy": "2024-10-28T15:52:21.395467Z", + "iopub.status.idle": "2024-10-28T15:52:21.405233Z", + "shell.execute_reply": "2024-10-28T15:52:21.404074Z", + "shell.execute_reply.started": "2024-10-28T15:52:21.395777Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "numeric_features = ['Age', 'Sleep Duration', \n", + " 'Physical Activity Level', \n", + " 'Heart Rate', 'Daily Steps', 'Systolic', 'Diastolic']" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:21.407630Z", + "iopub.status.busy": "2024-10-28T15:52:21.407216Z", + "iopub.status.idle": "2024-10-28T15:52:21.903328Z", + "shell.execute_reply": "2024-10-28T15:52:21.902237Z", + "shell.execute_reply.started": "2024-10-28T15:52:21.407593Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Calculate the correlation matrix\n", + "corr_matrix = df[numeric_features].corr()\n", + "\n", + "# Set up the matplotlib figure\n", + "plt.figure(figsize=(12, 8))\n", + "\n", + "# Draw the heatmap without the mask\n", + "sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', fmt=\".2f\", vmin=-1, vmax=1, square=True)\n", + "\n", + "# Customize plot labels and title\n", + "plt.title('Correlation Heatmap of data')\n", + "plt.xticks(rotation=45)\n", + "plt.yticks(rotation=0)\n", + "\n", + "# Show plot\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:21.905311Z", + "iopub.status.busy": "2024-10-28T15:52:21.904951Z", + "iopub.status.idle": "2024-10-28T15:52:21.911332Z", + "shell.execute_reply": "2024-10-28T15:52:21.910147Z", + "shell.execute_reply.started": "2024-10-28T15:52:21.905273Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "df.drop(columns=['Person ID'],inplace = True)" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:21.913249Z", + "iopub.status.busy": "2024-10-28T15:52:21.912887Z", + "iopub.status.idle": "2024-10-28T15:52:21.922807Z", + "shell.execute_reply": "2024-10-28T15:52:21.921554Z", + "shell.execute_reply.started": "2024-10-28T15:52:21.913212Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "label_encoder = LabelEncoder()\n", + "df['Sleep Disorder'] = label_encoder.fit_transform(df['Sleep Disorder'])" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Preprocessing" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:21.924655Z", + "iopub.status.busy": "2024-10-28T15:52:21.924255Z", + "iopub.status.idle": "2024-10-28T15:52:21.931807Z", + "shell.execute_reply": "2024-10-28T15:52:21.930821Z", + "shell.execute_reply.started": "2024-10-28T15:52:21.924601Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "numeric_features = ['Age', 'Sleep Duration', \n", + " 'Heart Rate', 'Daily Steps', 'Systolic', 'Diastolic']\n", + "\n", + "categorical_features = ['Occupation','Quality of Sleep','Gender', \n", + " 'Physical Activity Level', 'Stress Level', 'BMI Category']\n" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:21.933355Z", + "iopub.status.busy": "2024-10-28T15:52:21.932990Z", + "iopub.status.idle": "2024-10-28T15:52:21.942660Z", + "shell.execute_reply": "2024-10-28T15:52:21.941656Z", + "shell.execute_reply.started": "2024-10-28T15:52:21.933322Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "preprocessor = ColumnTransformer(\n", + " transformers=[\n", + " ('num', RobustScaler(), numeric_features),\n", + " ('cat', OneHotEncoder(drop='first',sparse_output =False, handle_unknown='ignore'), categorical_features)\n", + " ])" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:21.945129Z", + "iopub.status.busy": "2024-10-28T15:52:21.944119Z", + "iopub.status.idle": "2024-10-28T15:52:21.954541Z", + "shell.execute_reply": "2024-10-28T15:52:21.953503Z", + "shell.execute_reply.started": "2024-10-28T15:52:21.945076Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "X = df.drop(columns=['Sleep Disorder'])\n", + "y = df['Sleep Disorder']" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:21.956122Z", + "iopub.status.busy": "2024-10-28T15:52:21.955781Z", + "iopub.status.idle": "2024-10-28T15:52:21.981842Z", + "shell.execute_reply": "2024-10-28T15:52:21.980737Z", + "shell.execute_reply.started": "2024-10-28T15:52:21.956084Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "X_preprocessed = preprocessor.fit_transform(X)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Handling Imbalance Data - SMOTE" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:21.988521Z", + "iopub.status.busy": "2024-10-28T15:52:21.988043Z", + "iopub.status.idle": "2024-10-28T15:52:22.049523Z", + "shell.execute_reply": "2024-10-28T15:52:22.048460Z", + "shell.execute_reply.started": "2024-10-28T15:52:21.988483Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(657, 44)" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Initialize SMOTE\n", + "smote = SMOTE(random_state=42)\n", + "\n", + "# Perform SMOTE oversampling\n", + "X_smote, y_smote = smote.fit_resample(X_preprocessed, y)\n", + "X_smote.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:22.051600Z", + "iopub.status.busy": "2024-10-28T15:52:22.051040Z", + "iopub.status.idle": "2024-10-28T15:52:22.059365Z", + "shell.execute_reply": "2024-10-28T15:52:22.058077Z", + "shell.execute_reply.started": "2024-10-28T15:52:22.051540Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "# Splitting the data into training and testing sets (e.g., 75% training, 25% testing)\n", + "X_train, X_test, y_train, y_test = train_test_split(X_smote, y_smote, test_size=0.25, random_state=42)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Model Training" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "> Logistic Regression" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:22.061042Z", + "iopub.status.busy": "2024-10-28T15:52:22.060674Z", + "iopub.status.idle": "2024-10-28T15:52:22.406045Z", + "shell.execute_reply": "2024-10-28T15:52:22.404983Z", + "shell.execute_reply.started": "2024-10-28T15:52:22.061004Z" + }, + "trusted": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Accuracy: 0.9090909090909091\n", + "Precision: 0.910767756617559\n", + "Recall: 0.9090909090909091\n", + "F1-score: 0.9084234273263184\n", + " precision recall f1-score support\n", + "\n", + " 0 0.94 0.82 0.87 38\n", + " 1 0.88 0.95 0.92 64\n", + " 2 0.92 0.92 0.92 63\n", + "\n", + " accuracy 0.91 165\n", + " macro avg 0.91 0.90 0.90 165\n", + "weighted avg 0.91 0.91 0.91 165\n", + "\n", + "Confusion Matrix:\n", + "[[31 3 4]\n", + " [ 2 61 1]\n", + " [ 0 5 58]]\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "\n", + "# Initialize Logistic Regression classifier\n", + "model_lr = LogisticRegression()\n", + "\n", + "# Fit the model on the training data\n", + "model_lr.fit(X_train, y_train)\n", + "\n", + "# Predict on the test data\n", + "y_pred_lr = model_lr.predict(X_test)\n", + "\n", + "# Calculate evaluation metrics\n", + "accuracy_lr = accuracy_score(y_test, y_pred_lr)\n", + "precision_lr = precision_score(y_test, y_pred_lr, average='weighted')\n", + "recall_lr = recall_score(y_test, y_pred_lr, average='weighted')\n", + "f1_lr = f1_score(y_test, y_pred_lr, average='weighted')\n", + "\n", + "# Print metrics\n", + "print(f'Accuracy: {accuracy_lr}')\n", + "print(f'Precision: {precision_lr}')\n", + "print(f'Recall: {recall_lr}')\n", + "print(f'F1-score: {f1_lr}')\n", + "\n", + "# Generate classification report\n", + "print(classification_report(y_test, y_pred_lr))\n", + "\n", + "# Generate confusion matrix\n", + "cm_lr = confusion_matrix(y_test, y_pred_lr)\n", + "print('Confusion Matrix:')\n", + "print(cm_lr)\n", + "\n", + "# Plot confusion matrix using seaborn\n", + "plt.figure(figsize=(8, 6))\n", + "sns.heatmap(cm_lr, annot=True, fmt='d', cmap='Blues', cbar=False)\n", + "plt.xlabel('Predicted')\n", + "plt.ylabel('Actual')\n", + "plt.title('Confusion Matrix')\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "> XGB Classifier" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:22.407759Z", + "iopub.status.busy": "2024-10-28T15:52:22.407421Z", + "iopub.status.idle": "2024-10-28T15:52:22.815315Z", + "shell.execute_reply": "2024-10-28T15:52:22.814209Z", + "shell.execute_reply.started": "2024-10-28T15:52:22.407724Z" + }, + "trusted": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Accuracy: 0.9272727272727272\n", + "Precision: 0.9287307861220904\n", + "Recall: 0.9272727272727272\n", + "F1-score: 0.9271254483064495\n", + " precision recall f1-score support\n", + "\n", + " 0 0.92 0.87 0.89 38\n", + " 1 0.90 0.97 0.93 64\n", + " 2 0.97 0.92 0.94 63\n", + "\n", + " accuracy 0.93 165\n", + " macro avg 0.93 0.92 0.92 165\n", + "weighted avg 0.93 0.93 0.93 165\n", + "\n", + "Confusion Matrix:\n", + "[[33 3 2]\n", + " [ 2 62 0]\n", + " [ 1 4 58]]\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Initialize XGBoost classifier (assuming classification task)\n", + "model_xgb = xgb.XGBClassifier()\n", + "\n", + "# Fit the model on the training data\n", + "model_xgb.fit(X_train, y_train)\n", + "\n", + "# Predict on the test data\n", + "y_pred = model_xgb.predict(X_test)\n", + "# Calculate evaluation metrics\n", + "accuracy_xgb = accuracy_score(y_test, y_pred)\n", + "precision_xgb = precision_score(y_test, y_pred, average='weighted')\n", + "recall_xgb = recall_score(y_test, y_pred, average='weighted')\n", + "f1_xgb = f1_score(y_test, y_pred, average='weighted')\n", + "\n", + "# Print metrics\n", + "print(f'Accuracy: {accuracy_xgb}')\n", + "print(f'Precision: {precision_xgb}')\n", + "print(f'Recall: {recall_xgb}')\n", + "print(f'F1-score: {f1_xgb}')\n", + "\n", + "# Generate classification report\n", + "print(classification_report(y_test, y_pred))\n", + "\n", + "# Generate confusion matrix\n", + "cm = confusion_matrix(y_test, y_pred)\n", + "print('Confusion Matrix:')\n", + "print(cm)\n", + "\n", + "# Plot confusion matrix using seaborn\n", + "plt.figure(figsize=(8, 6))\n", + "sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', cbar=False)\n", + "plt.xlabel('Predicted')\n", + "plt.ylabel('Actual')\n", + "plt.title('Confusion Matrix')\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "> Cross Eval XGB Model" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:22.816883Z", + "iopub.status.busy": "2024-10-28T15:52:22.816547Z", + "iopub.status.idle": "2024-10-28T15:52:23.747124Z", + "shell.execute_reply": "2024-10-28T15:52:23.746245Z", + "shell.execute_reply.started": "2024-10-28T15:52:22.816848Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "xgb_model = xgb.XGBClassifier(random_state=42, use_label_encoder=False, eval_metric='mlogloss')\n", + "\n", + "# Define cross-validation strategy\n", + "cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)\n", + "\n", + "# Perform cross-validation\n", + "scores = cross_val_score(xgb_model, X_smote, y_smote, cv=cv, scoring='accuracy')" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:23.748929Z", + "iopub.status.busy": "2024-10-28T15:52:23.748405Z", + "iopub.status.idle": "2024-10-28T15:52:23.754591Z", + "shell.execute_reply": "2024-10-28T15:52:23.753587Z", + "shell.execute_reply.started": "2024-10-28T15:52:23.748890Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([0.92424242, 0.89393939, 0.93129771, 0.9389313 , 0.92366412])" + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "scores" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "> Gradient Boosting Classifier" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:23.756639Z", + "iopub.status.busy": "2024-10-28T15:52:23.755810Z", + "iopub.status.idle": "2024-10-28T15:52:24.493530Z", + "shell.execute_reply": "2024-10-28T15:52:24.492519Z", + "shell.execute_reply.started": "2024-10-28T15:52:23.756591Z" + }, + "trusted": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Classification Report:\n", + " precision recall f1-score support\n", + "\n", + " 0 0.89 0.84 0.86 38\n", + " 1 0.90 0.97 0.93 64\n", + " 2 0.95 0.90 0.93 63\n", + "\n", + " accuracy 0.92 165\n", + " macro avg 0.91 0.91 0.91 165\n", + "weighted avg 0.92 0.92 0.91 165\n", + "\n" + ] + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAoAAAAIjCAYAAACTRapjAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAABr/UlEQVR4nO3dd1gUV9sG8HtpS69KU0FERLDGDlhigj02MHZFRWPsipUkdiOW2GOJRhGNNYrG3ogl1lhjjYo9KiqK0qSf7w8/9s0KKKsss2HuX6654p45O/PMMIuPz5w5qxBCCBARERGRbOhJHQARERERFS4mgEREREQywwSQiIiISGaYABIRERHJDBNAIiIiIplhAkhEREQkM0wAiYiIiGSGCSARERGRzDABJCIiIpIZJoD00W7evInGjRvDysoKCoUCW7duLdDt3717FwqFAitXrizQ7f6Xffrpp/j000+lDkNyuV0bEyZMgEKhkC6oIkbu5zP7Gvvhhx/e21fu54r+W5gAFhG3bt1C3759UaZMGRgbG8PS0hJ+fn6YN28eXr9+rdV9BwUF4dKlS/j++++xevVq1KhRQ6v7K0w9evSAQqGApaVlrufx5s2bUCgU+f4L4m2PHj3ChAkTcOHChQKItvBkZWVh1apVaNSoEYoVKwZDQ0PY29ujcePGWLp0KVJTU6UOUas0/bmtXLlSdZ1kL/b29mjYsCF2796t3WDzITk5GRMmTMChQ4ekDkWNtj9/RHLGBLAI2LlzJypVqoSNGzeiZcuWWLBgAcLCwuDi4oKRI0diyJAhWtv369evceLECQQHB2PgwIHo2rUrSpYsWaD7cHV1xevXr9GtW7cC3W5+GRgYIDk5Gdu3b8+xbs2aNTA2Nv7gbT969AgTJ07UOAHct28f9u3b98H7/RivX79G8+bNERQUhOTkZIwYMQJLly7F6NGjYWxsjP79+6N///6SxAYA3333ndb/0fOhP7dJkyZh9erVWLVqFUaNGoVnz56hefPm2LFjh3YCzafk5GRMnDgx1wSwMM7nu2jz81fQpD5XRJowkDoA+jh37txBx44d4erqit9//x1OTk6qdQMGDEB0dDR27typtf0/e/YMAGBtba21fSgUCkl/ySuVSvj5+WHdunVo37692rq1a9eiRYsW2Lx5c6HEkpycDFNTUxgZGRXK/nIzbNgw7N27F3Pnzs3xj4vhw4fj5s2b2L9//zu3kZGRgaysLK0ch4GBAQwMdPNXW7NmzdQq5MHBwXBwcMC6devwxRdfSBhZ3qQ+n7r0+Xsfqc8VkSZYAfyPmzFjBhITE7F8+XK15C9b2bJl1f6SzsjIwOTJk+Hu7g6lUonSpUvjm2++yXHLrnTp0vjiiy9w9OhR1KpVC8bGxihTpgxWrVql6jNhwgS4uroCAEaOHAmFQoHSpUsDeHPrJvvP/5bbGJn9+/ejbt26sLa2hrm5OTw9PfHNN9+o1uc1BvD3339HvXr1YGZmBmtra7Ru3RrXrl3LdX/R0dHo0aMHrK2tYWVlhZ49eyI5OTnvE/uWzp07Y/fu3Xj58qWq7fTp07h58yY6d+6co/+LFy8wYsQIVKpUCebm5rC0tESzZs3w119/qfocOnQINWvWBAD07NlTdSsr+zg//fRTVKxYEWfPnkX9+vVhamqqOi9vjwEMCgqCsbFxjuNv0qQJbGxs8OjRo3wf67s8ePAAP//8M5o2bZpnZdnDw0OtAvjvMVRz585VXXtXr15FWloaxo0bh+rVq8PKygpmZmaoV68eDh48mGO7L1++RI8ePWBlZQVra2sEBQWp/Tyy5TUO65dffkH16tVhYmICW1tbdOzYEQ8ePFDrk33Or169ioYNG8LU1BQlSpTAjBkzVH3e93PThLW1NUxMTHIkDUlJSRg+fDhKlSoFpVIJT09P/PDDDxBCqPXL7+f5zJkzaNKkCYoVKwYTExO4ubmhV69eAN78fIoXLw4AmDhxoup4JkyYkOf5VCgUGDhwILZu3YqKFStCqVSiQoUK2LNnT45jPHToEGrUqAFjY2O4u7vjp59+0nisnDY+f9lSUlIwYcIElCtXDsbGxnByckJAQABu3bqVo+/SpUtV57pmzZo4ffq02vqPPVcPHz5Er1694ODgoOq3YsWK/J4mIo3wnyr/cdu3b0eZMmXg6+ubr/69e/dGREQE2rVrh+HDh+PUqVMICwvDtWvXsGXLFrW+0dHRaNeuHYKDgxEUFIQVK1agR48eqF69OipUqICAgABYW1tj2LBh6NSpE5o3bw5zc3ON4r9y5Qq++OILVK5cGZMmTYJSqUR0dDSOHTv2zvcdOHAAzZo1Q5kyZTBhwgS8fv0aCxYsgJ+fH86dO5cj+Wzfvj3c3NwQFhaGc+fO4eeff4a9vT2mT5+erzgDAgLw9ddfIzIyUvUX59q1a1G+fHlUq1YtR//bt29j69at+PLLL+Hm5oYnT57gp59+QoMGDXD16lU4OzvDy8sLkyZNwrhx4/DVV1+hXr16AKD2s3z+/DmaNWuGjh07omvXrnBwcMg1vnnz5uH3339HUFAQTpw4AX19ffz000/Yt28fVq9eDWdn53wd5/vs3r0bmZmZ6Nq1q8bvDQ8PR0pKCr766isolUrY2toiPj4eP//8Mzp16oQ+ffogISEBy5cvR5MmTfDnn3+iatWqAAAhBFq3bo2jR4/i66+/hpeXF7Zs2YKgoKB87fv777/H2LFj0b59e/Tu3RvPnj3DggULUL9+fZw/f16tgh0XF4emTZsiICAA7du3x6ZNmzB69GhUqlQJzZo1y9fPLS+vXr1CbGwshBB4+vQpFixYgMTERLXzKYRAq1atcPDgQQQHB6Nq1arYu3cvRo4ciYcPH2LOnDmqvvn5PD99+hSNGzdG8eLFMWbMGFhbW+Pu3buIjIwEABQvXhyLFy9Gv3790LZtWwQEBAAAKleu/M5jOXr0KCIjI9G/f39YWFhg/vz5CAwMxP3792FnZwcAOH/+PJo2bQonJydMnDgRmZmZmDRpkirhzC9tfP4AIDMzE1988QWioqLQsWNHDBkyBAkJCdi/fz8uX74Md3d31TbXrl2LhIQE9O3bFwqFAjNmzEBAQABu374NQ0PDjz5XT548QZ06dVQJY/HixbF7924EBwcjPj4eQ4cO1eicEb2XoP+sV69eCQCidevW+ep/4cIFAUD07t1brX3EiBECgPj9999Vba6urgKAOHLkiKrt6dOnQqlUiuHDh6va7ty5IwCImTNnqm0zKChIuLq65ohh/Pjx4t+X3Zw5cwQA8ezZszzjzt5HeHi4qq1q1arC3t5ePH/+XNX2119/CT09PdG9e/cc++vVq5faNtu2bSvs7Ozy3Oe/j8PMzEwIIUS7du3E559/LoQQIjMzUzg6OoqJEyfmeg5SUlJEZmZmjuNQKpVi0qRJqrbTp0/nOLZsDRo0EADEkiVLcl3XoEEDtba9e/cKAGLKlCni9u3bwtzcXLRp0+a9x6iJYcOGCQDiwoULau2pqani2bNnqiU2Nla1Lvv8WFpaiqdPn6q9LyMjQ6Smpqq1xcXFCQcHB7Wf2datWwUAMWPGDLX31qtXL8f5e/sau3v3rtDX1xfff/+92n4uXbokDAwM1Nqzz/mqVavUjs3R0VEEBgaq2t71c8tNeHi4AJBjUSqVYuXKlWp9s491ypQpau3t2rUTCoVCREdHCyHy/3nesmWLACBOnz6dZ3zPnj0TAMT48eNzrHv7fAohBABhZGSkikWIN58/AGLBggWqtpYtWwpTU1Px8OFDVdvNmzeFgYFBjm3mRtufvxUrVggAYvbs2Tn2nZWVpXofAGFnZydevHihWv/bb78JAGL79u0Fcq6Cg4OFk5OT2mdHCCE6duworKysRHJy8nvOFpFmeAv4Pyw+Ph4AYGFhka/+u3btAgCEhISotQ8fPhwAcowV9Pb2VlU3gDeVAk9PT9y+ffuDY35bduXlt99+Q1ZWVr7e8/jxY1y4cAE9evSAra2tqr1y5cpo1KiR6jj/7euvv1Z7Xa9ePTx//lx1DvOjc+fOOHToEGJiYvD7778jJiYm19tPwJtxS3p6bz5emZmZeP78uer29rlz5/K9T6VSiZ49e+arb+PGjdG3b19MmjQJAQEBMDY2xk8//ZTvfeVH9vl6u9K7a9cuFC9eXLVkDw34t8DAwByVH319fdU4wKysLLx48QIZGRmoUaOG2nnatWsXDAwM0K9fP7X3Dho06L0xR0ZGIisrC+3bt0dsbKxqcXR0hIeHR47bzebm5moVOSMjI9SqVatArvuFCxdi//792L9/P3755Rc0bNgQvXv3VlXjso9VX18fgwcPVnvv8OHDIYRQPTWc389z9mdsx44dSE9P/+hjyObv769WIatcuTIsLS1V5ykzMxMHDhxAmzZt1CrQZcuWRbNmzTTenzY+f5s3b0axYsVyvY7evpXboUMH2NjYqF5n/27Mz3XxvnMlhMDmzZvRsmVLCCHUrtMmTZrg1atXGv3eIMoPJoD/YZaWlgCAhISEfPW/d+8e9PT0ULZsWbV2R0dHWFtb4969e2rtLi4uObZhY2ODuLi4D4w4pw4dOsDPzw+9e/eGg4MDOnbsiI0bN74zGcyO09PTM8c6Ly8vxMbGIikpSa397WPJ/kWuybE0b94cFhYW2LBhA9asWYOaNWvmOJfZsrKyMGfOHHh4eECpVKJYsWIoXrw4Ll68iFevXuV7nyVKlNDoQYkffvgBtra2uHDhAubPnw97e/v3vufZs2eIiYlRLYmJiXn2zf7Hxtt9/Pz8VIlN48aNc32vm5tbru0RERGoXLkyjI2NYWdnh+LFi2Pnzp1q5+nevXtwcnLKkXjmdg287ebNmxBCwMPDQy1JLV68OK5du4anT5+q9S9ZsmSOv/wL6rqvVasW/P394e/vjy5dumDnzp3w9vbGwIEDkZaWBuDNsTo7O+f4h52Xl5dqffb/8/N5btCgAQIDAzFx4kQUK1YMrVu3Rnh4+EdP1fO+3w9Pnz7F69evc/2M5PW5eRdtfP5u3boFT0/PfD248TG/Q953rp49e4aXL19i6dKlOa7R7H8Avn2dEn0sjgH8D7O0tISzszMuX76s0fvyO/haX18/13bx1kB0TfaRmZmp9trExARHjhzBwYMHsXPnTuzZswcbNmzAZ599hn379uUZg6Y+5liyKZVKBAQEICIiArdv31YNks/N1KlTMXbsWPTq1QuTJ0+Gra0t9PT0MHTo0HxXOoE350cT58+fV/1FcenSJXTq1Om976lZs6Za8j9+/Pg8j618+fIAgMuXL6NKlSqq9uLFi8Pf3x/Am4ctcpPbsfzyyy/o0aMH2rRpg5EjR8Le3h76+voICwvLdRD+h8jKyoJCocDu3btzvQ7eTioL4lrJLz09PTRs2BDz5s3DzZs3UaFCBY238b7Ps0KhwKZNm3Dy5Els374de/fuRa9evTBr1iycPHlS43G72QrzPAHSfP7+7WOO933vzY6pa9eueY5rfd+YTCJNMQH8j/viiy+wdOlSnDhxAj4+Pu/s6+rqiqysLNy8eVNVTQDeDD5++fJlrrftPpSNjU2uT2i+XWUE3vwl+Pnnn+Pzzz/H7NmzMXXqVHz77bc4ePCgKql4+zgA4Pr16znW/f333yhWrBjMzMw+/iBy0blzZ6xYsQJ6enro2LFjnv02bdqEhg0bYvny5WrtL1++RLFixVSvC/JbA5KSktCzZ094e3vD19cXM2bMQNu2bVVPrOZlzZo1anOXlSlTJs++zZo1g76+PtasWYMuXbp8dMybNm1CmTJlEBkZqXYuxo8fr9bP1dUVUVFRSExMVEtYcrsG3ubu7g4hBNzc3FCuXLmPjhko2J9bRkYGgP9VVV1dXXHgwAEkJCSoVQH//vtv1frs/2vyea5Tpw7q1KmD77//HmvXrkWXLl2wfv169O7dWyvfXmFvbw9jY2NER0fnWJdbW34U9OfP3d0dp06dQnp6+nsf5NCm4sWLw8LCApmZmbn+ziPSBt4C/o8bNWoUzMzM0Lt3bzx58iTH+lu3bmHevHkA3txCAYC5c+eq9Zk9ezYAoEWLFgUWl7u7O169eoWLFy+q2h4/fpzjSeMXL17keG/2k5953aJycnJC1apVERERoZZkXr58Gfv27VMdpzY0bNgQkydPxo8//ghHR8c8++nr6+eoDPz66694+PChWlt2oppbsqyp0aNH4/79+4iIiMDs2bNRunRpBAUFvfdWn5+fn+q2pL+//zsTQBcXF/Tq1Qu7d+/Gjz/+mGsfTSpA2ZWRf7/n1KlTOHHihFq/5s2bIyMjA4sXL1a1ZWZmYsGCBe/dR0BAAPT19TFx4sQcsQkh8Pz583zHm62gfm7p6enYt28fjIyMVElc8+bNkZmZmeP8zpkzBwqFQjV+Lr+f57i4uBzH/fZnzNTUtECO59/09fXh7++PrVu3qk1DFB0d/cHfflLQn7/AwEDExsbmei1rq5KZG319fQQGBmLz5s253tHJnm+VqCCxAvgf5+7ujrVr16JDhw7w8vJC9+7dUbFiRaSlpeH48eP49ddf0aNHDwBAlSpVEBQUhKVLl+Lly5do0KAB/vzzT0RERKBNmzZo2LBhgcXVsWNHjB49Gm3btsXgwYORnJyMxYsXo1y5cmqDmSdNmoQjR46gRYsWcHV1xdOnT7Fo0SKULFkSdevWzXP7M2fORLNmzeDj44Pg4GDVNDBWVlbvvDX0sfT09PDdd9+9t98XX3yBSZMmoWfPnvD19cWlS5ewZs2aHMmVu7s7rK2tsWTJElhYWMDMzAy1a9fOc7xcXn7//XcsWrQI48ePV02LER4ejk8//RRjx45Vm8fuY82dOxd37tzBoEGDsH79erRs2RL29vaIjY3FsWPHsH379nyNzQPenKfIyEi0bdsWLVq0wJ07d7BkyRJ4e3urjTNs2bIl/Pz8MGbMGNy9exfe3t6IjIzM13hKd3d3TJkyBaGhobh79y7atGkDCwsL3LlzB1u2bMFXX32FESNGaHQOPvTntnv3blUl7+nTp1i7di1u3ryJMWPGqMb0tmzZEg0bNsS3336Lu3fvokqVKti3bx9+++03DB06VPUwQX4/zxEREVi0aBHatm0Ld3d3JCQkYNmyZbC0tFQlkSYmJvD29saGDRtQrlw52NraomLFiqhYsaJG5+VtEyZMwL59++Dn54d+/fqpEtuKFSt+0NcfFvTnr3v37li1ahVCQkLw559/ol69ekhKSsKBAwfQv39/tG7dWuMYP9S0adNw8OBB1K5dG3369IG3tzdevHiBc+fO4cCBA7n+Y5nooxTyU8ekJTdu3BB9+vQRpUuXFkZGRsLCwkL4+fmJBQsWiJSUFFW/9PR0MXHiROHm5iYMDQ1FqVKlRGhoqFofId5MA9OiRYsc+3l7+pG8poERQoh9+/aJihUrCiMjI+Hp6Sl++eWXHNMkREVFidatWwtnZ2dhZGQknJ2dRadOncSNGzdy7OPtKTcOHDgg/Pz8hImJibC0tBQtW7YUV69eVeuTvb+3p5nJnpbjzp07eZ5TIdSnochLXtNQDB8+XDg5OQkTExPh5+cnTpw4kev0Lb/99pvw9vZWTY2RfZwNGjQQFSpUyHWf/95OfHy8cHV1FdWqVRPp6elq/YYNGyb09PTEiRMn3nkMmsrIyBDh4eHis88+E7a2tsLAwEAUK1ZMfP7552LJkiXi9evXqr7vukaysrLE1KlThaurq1AqleKTTz4RO3bsyHUaoefPn4tu3boJS0tLYWVlJbp16ybOnz//3mlgsm3evFnUrVtXmJmZCTMzM1G+fHkxYMAAcf36dVWfvM55bvHk9XPLTW7TwBgbG4uqVauKxYsXq6YcyZaQkCCGDRsmnJ2dhaGhofDw8BAzZ87M0S8/n+dz586JTp06CRcXF6FUKoW9vb344osvxJkzZ9S2dfz4cVG9enVhZGSkNiVMXlObDBgwIMdxurq6iqCgILW2qKgo8cknnwgjIyPh7u4ufv75ZzF8+HBhbGyc5/nKVhifv+TkZPHtt9+qzqGjo6No166duHXrVp7b//d5+PfUOR97rp48eSIGDBggSpUqpYrl888/F0uXLn3nOSD6EAohCrHOTUREstemTRtcuXIFN2/elDoUItniGEAiItKafz9gBLyZlmfXrl1qX2VIRIWPFUAiItIaJycn9OjRA2XKlMG9e/ewePFipKam4vz58/Dw8JA6PCLZ4kMgRESkNU2bNsW6desQExMDpVIJHx8fTJ06lckfkcRYASQiIiKSGY4BJCIiIpIZJoBEREREMsMEkIiIiEhmiuRDIF/9ekXqEIhymN6ivNQhEBHpNBtTfcn2bfLJQK1t+/X53L86U0qsABIRERHJTJGsABIRERFpRCGvmhgTQCIiIiKFQuoICpW80l0iIiIiYgWQiIiISG63gOV1tERERETECiARERERxwASERERUZHGCiARERERxwASERERUVHGBJCIiIhIodDeoqGHDx+ia9eusLOzg4mJCSpVqoQzZ86o1gshMG7cODg5OcHExAT+/v64efOmRvtgAkhERESk0NPeooG4uDj4+fnB0NAQu3fvxtWrVzFr1izY2Nio+syYMQPz58/HkiVLcOrUKZiZmaFJkyZISUnJ9344BpCIiIhIR0yfPh2lSpVCeHi4qs3NzU31ZyEE5s6di++++w6tW7cGAKxatQoODg7YunUrOnbsmK/9sAJIREREpMVbwKmpqYiPj1dbUlNTcw1j27ZtqFGjBr788kvY29vjk08+wbJly1Tr79y5g5iYGPj7+6varKysULt2bZw4cSLfh8sEkIiIiEiLwsLCYGVlpbaEhYXl2vf27dtYvHgxPDw8sHfvXvTr1w+DBw9GREQEACAmJgYA4ODgoPY+BwcH1br84C1gIiIiIi1OAxMaGoqQkBC1NqVSmWvfrKws1KhRA1OnTgUAfPLJJ7h8+TKWLFmCoKCgAouJFUAiIiIiLVIqlbC0tFRb8koAnZyc4O3trdbm5eWF+/fvAwAcHR0BAE+ePFHr8+TJE9W6/GACSERERKQj08D4+fnh+vXram03btyAq6srgDcPhDg6OiIqKkq1Pj4+HqdOnYKPj0++98NbwEREREQ6YtiwYfD19cXUqVPRvn17/Pnnn1i6dCmWLl0KAFAoFBg6dCimTJkCDw8PuLm5YezYsXB2dkabNm3yvR8mgEREREQ68lVwNWvWxJYtWxAaGopJkybBzc0Nc+fORZcuXVR9Ro0ahaSkJHz11Vd4+fIl6tatiz179sDY2Djf+1EIIYQ2DkBKX/16ReoQiHKY3qK81CEQEek0G1N9yfZtUm+c1rb9+o9JWtv2h9KNdJeIiIiICg1vARMRERHpyC3gwiKvoyUiIiIiVgCJiIiIWAEkIiIioiKNFUAiIiIiPc0mbP6vYwWQiIiISGZYASQiIiKS2RhAJoBEREREGn5n73+dvNJdIiIiImIFkIiIiEhut4DldbRERERExAogEREREccAEhEREVGRJmkFUAiBBw8ewN7eHsbGxlKGQkRERHLGMYCFRwiBsmXL4sGDB1KGQURERCQrkiaAenp68PDwwPPnz6UMg4iIiOROodDeooMkr3dOmzYNI0eOxOXLl6UOhYiIiORKoae9RQdJ/hRw9+7dkZycjCpVqsDIyAgmJiZq61+8eCFRZERERERFk+QJ4Ny5c6UOgYiIiOROR2/VaovkCWBQUJDUIRARERHJik7cmL516xa+++47dOrUCU+fPgUA7N69G1euXJE4MiIiIpIFmY0BlDyqw4cPo1KlSjh16hQiIyORmJgIAPjrr78wfvx4iaMjIiIiKnokTwDHjBmDKVOmYP/+/TAyMlK1f/bZZzh58qSEkREREZFscBqYwnXp0iW0bds2R7u9vT1iY2MliIiIiIioaJM8AbS2tsbjx49ztJ8/fx4lSpSQICIiIiKSHY4BLFwdO3bE6NGjERMTA4VCgaysLBw7dgwjRoxA9+7dpQ6PiIiI5IAJYOGaOnUqypcvj1KlSiExMRHe3t6oX78+fH198d1330kdHhEREVGRI/k8gEZGRli2bBnGjh2Ly5cvIzExEZ988gk8PDykDo2IiIjkQkcf1tAWyRPAbC4uLnBxcZE6DCIiIqIiT5IEMCQkJN99Z8+ercVIiIiIiKCzY/W0RZIE8Pz582qvz507h4yMDHh6egIAbty4AX19fVSvXl2K8IiIiIiKNEkSwIMHD6r+PHv2bFhYWCAiIgI2NjYAgLi4OPTs2RP16tWTIjwiIiKSG5mNAZS83jlr1iyEhYWpkj8AsLGxwZQpUzBr1iwJIyMiIiIqmiR/CCQ+Ph7Pnj3L0f7s2TMkJCRIEBERERHJjszGAEp+tG3btkXPnj0RGRmJf/75B//88w82b96M4OBgBAQESB0eERERyYHMvgtY8grgkiVLMGLECHTu3Bnp6ekAAAMDAwQHB2PmzJkSR0dERERU9EiaAGZmZuLMmTP4/vvvMXPmTNy6dQsA4O7uDjMzMylDIyIiIhlR6GilTlskTQD19fXRuHFjXLt2DW5ubqhcubKU4RARERHJguRjACtWrIjbt29LHQYRERHJmEKh0NqiiyRPAKdMmYIRI0Zgx44dePz4MeLj49UWIiIiIipYkj8E0rx5cwBAq1at1LJkIQQUCgUyMzOlCo2IiIjkQjcLdVojeQL4728FISIiIiLtkzwBbNCggdQhEBERkczp6lg9bZE8AQSAly9fYvny5bh27RoAoEKFCujVqxesrKwkjoyIiIjkQG4JoOQPgZw5cwbu7u6YM2cOXrx4gRcvXmD27Nlwd3fHuXPnpA6PiIiIqMiRvAI4bNgwtGrVCsuWLYOBwZtwMjIy0Lt3bwwdOhRHjhyROEIiIiIq6uRWAZQ8ATxz5oxa8ge8+Sq4UaNGoUaNGhJGRkRERFQ0SX4L2NLSEvfv38/R/uDBA1hYWEgQEREREcmN3CaClrwC2KFDBwQHB+OHH36Ar68vAODYsWMYOXIkOnXqJHF0RV+DMjZo4G4LOzNDAMCj+FTsvPoMl2MSYWqoj1YVisPb0Ry2poZITM3A+YcJ2Hb5KV5nZEkcOcnJ5o3rEblpPR4/eggAKFOmLHp91Q++detLHBnJFa9J+q+TPAH84YcfoFAo0L17d2RkZAAADA0N0a9fP0ybNk3i6Iq+uNfpiLz0BE8T0wAAvqWt0d+vFCbvvw0FAGsTQ2z6KwaP41Nha2qErtWdYG1igJ9O/CNt4CQr9g4OGDBoGEq6uAIAdm7filHDBmLV+s0o4+4hcXQkR7wmiyDdLNRpjUIIIaQOAgCSk5Nx69YtAIC7uztMTU0/eFtf/XqloMKSpTmtPbHpryc4dvdljnXVS1qiV60SGLTlGrJ04sr575jeorzUIRQpjRvUwcChI9GqbaDUoRAB4DVZEGxM9SXbt1Xn1Vrb9qu13bS27Q8leQUwm6mpKSpVqoT4+Hjs27cPnp6e8PLykjosWVEAqFHKEkb6erj9/HWufUwM9ZCSkcXkjySTmZmJ3/fvxevXr1GpchWpwyHiNVlE6OpYPW2RPAFs37496tevj4EDB+L169eoUaMG7t69CyEE1q9fj8BA/ktK20pYKjH6czcY6ukhNSMLi48/wOOE1Bz9zI300cKrOP64HSdBlCR30TdvoE9QJ6SlpcHExBTTZ82Hm3tZqcMiGeM1Sf9lkj8FfOTIEdSrVw8AsGXLFggh8PLlS8yfPx9Tpkx57/tTU1MRHx+vtmSmp2k77CIlJiENk/fdRljUbRy+9QI9a5WAk4VSrY+xgR4G1XXB4/hUbL/yVKJISc5cS5fGqvWRWL5qPQK+7IBJ477BnVvRUodFMsZrsmiR21PAkieAr169gq2tLQBgz549CAwMhKmpKVq0aIGbN2++9/1hYWGwsrJSWy5sWabtsIuUTCHwLCkN91+mYMvlp/jnZQo+97BVrVca6GFIPVekZGRh0fEHyOTtX5KAoaERSrm4orx3BfQfHIKy5TyxYZ32xuwQvQ+vyaKFCWAhK1WqFE6cOIGkpCTs2bMHjRs3BgDExcXB2Nj4ve8PDQ3Fq1ev1JaqbftoO+wiTaEADPTfXLDGBnoYWt8VGVkCC4/dRwYH/5GOEEIgLS1d6jCIVHhN0n+J5GMAhw4dii5dusDc3Byurq749NNPAby5NVypUqX3vl+pVEKpVL9dqW9opI1Qi6S2Fe1xOSYRL5LTYWygh1ouVihX3AzzjtxTJX9G+npYceo+jA30Yfz/V0xCagaYClJhWTR/Nnz86sPByQnJSUnYt3sHzp35E3MXsdpP0uA1WfToaqVOWyRPAPv3749atWrhwYMHaNSoEfT03hQly5Qpk68xgPRxLIwN0LNWCVgZG+B1ehYevkrBvCP3cO1pEsoVN0UZuzfT8XzfvJza+0J33sDzZP5LlwpH3IsXmDh2DJ7HPoO5uQXcPcph7qJlqF3HV+rQSKZ4TdJ/nc7MA1iQOA8g6SLOA0hE9G5SzgNoF7ROa9t+HqF732wmSQUwJCQEkydPhpmZGUJCQt7Zd/bs2YUUFREREZE8SJIAnj9/Hunp6ao/50Vu9+OJiIhIGnLLOSRJAA8ePJjrn4mIiIhI+ySfBgZ48+h8bGwsnj9/LnUoREREJEO6Mg/ghAkTcry/fPn/jSFPSUnBgAEDYGdnB3NzcwQGBuLJkycaH6+kCWBMTAy6d+8OGxsbODg4wN7eHjY2NujVq9cHHQwRERHRh9CVBBAAKlSogMePH6uWo0ePqtYNGzYM27dvx6+//orDhw/j0aNHCAgI0Hgfkk0DEx8fD19fXyQmJqJnz54oX748hBC4evUq1q1bh6NHj+LcuXMwNzeXKkQiIiKiQmdgYABHR8cc7a9evcLy5cuxdu1afPbZZwCA8PBweHl54eTJk6hTp07+91Fg0Wpo3rx50NfXx5UrV1C8eHG1dd999x38/Pwwf/58fPPNNxJFSERERLKhxWdAUlNTkZqaqtaW2xdZZLt58yacnZ1hbGwMHx8fhIWFwcXFBWfPnkV6ejr8/f1VfcuXLw8XFxecOHFCowRQslvAO3fuxDfffJMj+QMAe3t7hIaGYvv27RJERkRERFRwwsLCYGVlpbaEhYXl2rd27dpYuXIl9uzZg8WLF+POnTuoV68eEhISEBMTAyMjI1hbW6u9x8HBATExMRrFJFkF8MaNG/D1zXvGdF9fX4wYMaIQIyIiIiK50uY0MKGhoTnmPc6r+tesWTPVnytXrozatWvD1dUVGzduhImJSYHFJFkFMD4+PkcG+2/W1taIj48vvICIiIiItECpVMLS0lJtySsBfJu1tTXKlSuH6OhoODo6Ii0tDS9fvlTr8+TJk1zHDL6LZAmgEEL1vb+5USgUKILfUkdEREQ6SJeeAv63xMRE3Lp1C05OTqhevToMDQ0RFRWlWn/9+nXcv38fPj4+Gm1XslvAQgiUK1cuzxPD5I+IiIjkZsSIEWjZsiVcXV3x6NEjjB8/Hvr6+ujUqROsrKwQHByMkJAQ2NrawtLSEoMGDYKPj49GD4AAEiaA4eHhUu2aiIiISI2ufBXcP//8g06dOuH58+coXrw46tati5MnT6oemp0zZw709PQQGBiI1NRUNGnSBIsWLdJ4PwpRBEttX/16ReoQiHKY3qL8+zsREcmYjam+ZPt27huptW0/+knziZq1TSe+Co6IiIiICo9kt4CJiIiIdIZu3AEuNKwAEhEREckMK4BEREQke7ryEEhh0akKoBCC078QERERaZlOJICrVq1CpUqVYGJiAhMTE1SuXBmrV6+WOiwiIiKSCV2dCFpbJL8FPHv2bIwdOxYDBw6En58fAODo0aP4+uuvERsbi2HDhkkcIREREVHRInkCuGDBAixevBjdu3dXtbVq1QoVKlTAhAkTmAASERGR1ulqpU5bJE8AHz9+DF9f3xztvr6+ePz4sQQRERERkezIK/+Tfgxg2bJlsXHjxhztGzZsgIeHhwQRERERERVtklcAJ06ciA4dOuDIkSOqMYDHjh1DVFRUrokhERERUUGT2y1gySuAgYGBOHXqFIoVK4atW7di69atKFasGP7880+0bdtW6vCIiIiIihzJK4AAUL16dfzyyy9Sh0FEREQyxQogERERERVpklUA9fT03pttKxQKZGRkFFJEREREJFdyqwBKlgBu2bIlz3UnTpzA/PnzkZWVVYgREREREcmDZAlg69atc7Rdv34dY8aMwfbt29GlSxdMmjRJgsiIiIhIbuRWAdSJMYCPHj1Cnz59UKlSJWRkZODChQuIiIiAq6ur1KERERGRHCi0uOggSRPAV69eYfTo0ShbtiyuXLmCqKgobN++HRUrVpQyLCIiIqIiTbJbwDNmzMD06dPh6OiIdevW5XpLmIiIiKgwyO0WsGQJ4JgxY2BiYoKyZcsiIiICERERufaLjIws5MiIiIiIijbJEsDu3bvLLtsmIiIi3SS3nESyBHDlypVS7ZqIiIhI1nTiq+CIiIiIpCSzAqBuTANDRERERIWHFUAiIiKSPY4BJCIiIpIZmeV/vAVMREREJDesABIREZHsye0WMCuARERERDLDCiARERHJnswKgKwAEhEREckNK4BEREQke3p68ioBsgJIREREJDOsABIREZHsyW0MIBNAIiIikj1OA0NERERERRorgERERCR7MisAsgJIREREJDesABIREZHscQwgERERERVprAASERGR7LECSERERERFGiuAREREJHsyKwAyASQiIiLiLWAiIiIiKtJYASQiIiLZk1kBkBVAIiIiIrlhBZCIiIhkj2MAiYiIiKhIYwWQiIiIZE9mBUBWAImIiIjkhhVAIiIikj2OASQiIiKiIo0VQCIiIpI9mRUAmQASERER8RYwERERERVprAASERGR7MmsAFg0E8AfWnpJHQJRDg4+g6UOgUhN3OkfpQ6BiCRSJBNAIiIiIk1wDCARERERFWmsABIREZHsyawAyAogERERkdywAkhERESyxzGARERERDKjUGhv+RjTpk2DQqHA0KFDVW0pKSkYMGAA7OzsYG5ujsDAQDx58kSj7TIBJCIiItJBp0+fxk8//YTKlSurtQ8bNgzbt2/Hr7/+isOHD+PRo0cICAjQaNtMAImIiEj2FAqF1pYPkZiYiC5dumDZsmWwsbFRtb969QrLly/H7Nmz8dlnn6F69eoIDw/H8ePHcfLkyXxvnwkgERERkRalpqYiPj5ebUlNTX3newYMGIAWLVrA399frf3s2bNIT09Xay9fvjxcXFxw4sSJfMfEBJCIiIhkT5sVwLCwMFhZWaktYWFhecayfv16nDt3Ltc+MTExMDIygrW1tVq7g4MDYmJi8n28fAqYiIiISItCQ0MREhKi1qZUKnPt++DBAwwZMgT79++HsbGx1mJiAkhERESyp81ZYJRKZZ4J39vOnj2Lp0+folq1aqq2zMxMHDlyBD/++CP27t2LtLQ0vHz5Uq0K+OTJEzg6OuY7JiaARERERDri888/x6VLl9TaevbsifLly2P06NEoVaoUDA0NERUVhcDAQADA9evXcf/+ffj4+OR7P0wAiYiISPZ0ZSJoCwsLVKxYUa3NzMwMdnZ2qvbg4GCEhITA1tYWlpaWGDRoEHx8fFCnTp1874cJIBEREcmejuR/+TJnzhzo6ekhMDAQqampaNKkCRYtWqTRNpgAEhEREemwQ4cOqb02NjbGwoULsXDhwg/eJhNAIiIikj1duQVcWDgPIBEREZHMsAJIREREsiezAiArgERERERywwogERERyZ6ezEqArAASERERyQwrgERERCR7MisAMgEkIiIi4jQwRERERFSksQJIREREsqcnrwIgK4BEREREcsMKIBEREckexwASERERUZHGCiARERHJnswKgKwAEhEREckNK4BEREQkewrIqwTIBJCIiIhkj9PAEBEREVGRxgogERERyZ7cpoHRiQRw06ZN2LhxI+7fv4+0tDS1defOnZMoKiIiIqKiSfJbwPPnz0fPnj3h4OCA8+fPo1atWrCzs8Pt27fRrFkzqcMjIiIiGVAotLfoIskTwEWLFmHp0qVYsGABjIyMMGrUKOzfvx+DBw/Gq1evpA6PiIiIqMiRPAG8f/8+fH19AQAmJiZISEgAAHTr1g3r1q2TMjQiIiKSCT2FQmuLLpI8AXR0dMSLFy8AAC4uLjh58iQA4M6dOxBCSBkaERERUZEkeQL42WefYdu2bQCAnj17YtiwYWjUqBE6dOiAtm3bShwdERERyYHcxgBK/hTw0qVLkZWVBQAYMGAA7OzscPz4cbRq1Qp9+/aVODoiIiKSA04DU8j09PSgp/e/QmTHjh3RsWNHCSMiIiIiKtokvwUMAH/88Qe6du0KHx8fPHz4EACwevVqHD16VOLIiIiISA7kdgtY8gRw8+bNaNKkCUxMTHD+/HmkpqYCAF69eoWpU6dKHB0RERFR0SN5AjhlyhQsWbIEy5Ytg6Ghoardz8+P3wJCREREhYLTwBSy69evo379+jnarays8PLly8IPiIiIiKiIkzwBdHR0RHR0dI72o0ePokyZMhJERERERHKj0OKiiyRPAPv06YMhQ4bg1KlTUCgUePToEdasWYMRI0agX79+UodHREREVORIPg3MmDFjkJWVhc8//xzJycmoX78+lEolRowYgUGDBkkdHhEREckA5wEsZAqFAt9++y1GjhyJ6OhoJCYmwtvbG+bm5lKHRkRERDKhJ6/8T/oEMJuRkRG8vb2lDoOIiIioyJM8AUxKSsK0adMQFRWFp0+fqr4WLtvt27clioyIiIjkgreAC1nv3r1x+PBhdOvWDU5OTrL7ARAREREVNskTwN27d2Pnzp3w8/OTOhQiIiKSKbnVnySfBsbGxga2trZSh0FEREQkG5IngJMnT8a4ceOQnJwsdShEREQkUwqFQmuLLsrXLeBt27ble4OtWrXSKIBZs2bh1q1bcHBwQOnSpdW+DxgAvw+YiIiIqIDlKwFs06ZNvjamUCiQmZmpUQD53TYRERGRtnAewFy8PTVLQRo/frzWtk1ERESUH7p6q1ZbJH8KONuZM2dw7do1AIC3tzeqV68ucURERERERdMHJYBJSUk4fPgw7t+/j7S0NLV1gwcP1mhb//zzDzp16oRjx47B2toaAPDy5Uv4+vpi/fr1KFmy5IeESERERJRv8qr/fUACeP78eTRv3hzJyclISkqCra0tYmNjYWpqCnt7e40TwN69eyM9PR3Xrl2Dp6cnAOD69evo2bMnevfujT179mgaIhERERG9g8bTwAwbNgwtW7ZEXFwcTExMcPLkSdy7dw/Vq1fHDz/8oHEAhw8fxuLFi1XJHwB4enpiwYIFOHLkiMbbIyIiItKUnkKhtUUXaZwAXrhwAcOHD4eenh709fWRmpqKUqVKYcaMGfjmm280DqBUqVJIT0/P0Z6ZmQlnZ2eNt0dERERE76ZxAmhoaAg9vTdvs7e3x/379wEAVlZWePDggcYBzJw5E4MGDcKZM2dUbWfOnMGQIUM+qKJIREREpCmFQnuLLtJ4DOAnn3yC06dPw8PDAw0aNMC4ceMQGxuL1atXo2LFihoH0KNHDyQnJ6N27dowMHgTTkZGBgwMDNCrVy/06tVL1ffFixcab5+IiIiI1GmcAE6dOhUJCQkAgO+//x7du3dHv3794OHhgRUrVmgcwNy5czV+DxEREVFB4jyA71GjRg3Vn+3t7T/6Kd2goKA817148QK2trYftX0iIiIiUqfxGMDCsG/fPrRv3x4lSpSQOhQiIiKSAY4BfA83N7d3lklv3779QYHcu3cPK1asQEREBOLi4tCsWTOsWrXqg7ZFHyd8+VIcjNqPe3duQ6k0RuWqn2Dg0OEoXdpN6tBIJpyLW2HKkNZo7FcBpsaGuPUgFn0n/IJzV+/DwEAPE/q3RJO6FeBW0g7xiSn4/dTfGDt/Gx4/eyV16CQz69euQUT4csTGPkM5z/IY881YVKpcWeqw6APo6nQt2qJxAjh06FC11+np6Th//jz27NmDkSNHarSttLQ0REZG4ueff8axY8fg7++Pf/75B+fPn0elSpU0DY0KyLkzp/Flh87wrlARmZmZWLRgDgZ9HYyNkTtgYmoqdXhUxFlbmOD3lSE4fPom2gxchGdxiSjrUhxx8ckAAFNjI1T1KoVpy3bj4o2HsLE0xQ8j2+HXuX1Rt8sMiaMnOdmzexd+mBGG78ZPRKVKVbBmdQT69Q3Gbzv2wM7OTurwiN5JIYQQBbGhhQsX4syZMwgPD89X/0GDBmHdunXw8PBA165d0bFjR9jZ2cHQ0BB//fUXvL29PziW+JSsD34v5RT34gUaN/TDTytWoVr1mlKH85/l4KPZt+TI1eTBreBTpQz8g+fm+z3VvV1wdM0olGs2Fg9i4rQXXBETd/pHqUP4T+vS8UtUqFgJ33w3DgCQlZWFxp83QKfO3RDc5yuJo/tvMv6gL6gtGP0jr2pt24sCPjyn0ZYCGwPYrFkzbN68Od/9Fy9ejL59+2Lfvn0YMGAA/7WkwxIT3zz1bWlpJXEkJActGlTCuav3sWZGL9yLCsOJdaPRs63vO99jaWGCrKwsvEx4XUhRktylp6Xh2tUrqOPzv2tTT08Pder44uJf5yWMjCh/CiwB3LRpk0ZP7K5evRp//vknnJyc0KFDB+zYsQOZmZkFFQ4VkKysLMyeEYYqVauhrEc5qcMhGXArUQx9vqyH6PvP0Kr/Qiz79ShmjWqHLi1r59pfaWSAKYNbY+Oes0hISinkaEmu4l7GITMzM0fxws7ODrGxsRJFRR9DoVBobdFFHzQR9L8PRgiBmJgYPHv2DIsWLcr3djp16oROnTrhzp07WLlyJQYMGIDk5GRkZWXh6tWr+b4FnJqaitTUVPU2YQilUpnvWChvM6ZOwq1bN7Fs5RqpQyGZ0NNT4NzV+xj/43YAwF/X/0GFsk7o064u1mw/pdbXwEAPv8wIhkKhwOCpG6QIl4joP0njCmDr1q3VloCAAIwfPx6XL1/GV19pPubBzc0NEydOxN27d/HLL78gMDAQXbt2RcmSJTF48PvHTIWFhcHKykptmT1zmsZxUE4zpk7GH0cOY/GyCDg4OEodDslETGw8rt2OUWv7+04MSjnaqLUZGOhhzfRguDjZ4It+P7L6R4XKxtoG+vr6eP78uVr78+fPUaxYMYmioo+hp8VFF2lcAZwwYYIWwnhTem3SpAmaNGmCFy9eYNWqVfl6oCQ0NBQhISFqbanCUCsxyoUQAjPDpuDQ7wewZHkESpQsKXVIJCMnLtxGOVd7tTYPF3vcf/y/r4LMTv7cXYqj6Vfz8eJVUmGHSTJnaGQEL+8KOHXyBD773B/AmyEzp06dQMdOXSWOjuj9NE5M9fX18fTp0xztz58/h76+foEEZWtri6FDh+Kvv/56b1+lUglLS0u1hbd/P870qZOwe9d2TJ42E6ZmZoiNfYbY2GdISWGFhbRvwS+/o1YlN4zs1RhlShVDh6Y10CvQDz9tOALgTfK3dmZvVPN2Qc9vI6Cvp4CDnQUc7CxgaFAwv4OI8qNbUE9EbtqIbVu34PatW5gyaQJev36NNm0DpA6NPgDHAL5HXrPGpKamwsjI6KMDIult3rgeAPB1sPrX9I2bNBUtW7eVIiSSkbNX76PD8GWYNKgVvvmqGe4+fI6RMzdj/e4zAADn4tZo+embiXb/3BCq9t7Gvefhj7M3Cz1mkqemzZoj7sULLPpxPmJjn8GzvBcW/fQz7HgL+D9JT0fytMWLF2Px4sW4e/cuAKBChQoYN24cmjVrBgBISUnB8OHDsX79eqSmpqJJkyZYtGgRHBwcNNpPvucBnD9/PgBg2LBhmDx5MszNzVXrMjMzceTIEdy9exfnz0v/+DvnASRdxHkASddwHkDSNVLOAzj0t7+1tu25rcvnu+/27duhr68PDw8PCCEQERGBmTNn4vz586hQoQL69euHnTt3YuXKlbCyssLAgQOhp6eHY8eOaRRTvhNAN7c3XwN27949lCxZUu12r5GREUqXLo1Jkyahdu3cp2ooTEwASRcxASRdwwSQdI2UCWDINu0lgLNb5T8BzI2trS1mzpyJdu3aoXjx4li7di3atWsHAPj777/h5eWFEydOoE6dOvneZr5P9Z07dwAADRs2RGRkJGxsbN7zDiIiIiLKbco6pVL53mcWMjMz8euvvyIpKQk+Pj44e/Ys0tPT4e/vr+pTvnx5uLi4aC8BzHbw4EFN3/JecXFxWL58Oa5duwYA8PLyQq9evTSaWJqIiIjoQ2nzYY2wsDBMnDhRrW38+PF5zqxy6dIl+Pj4ICUlBebm5tiyZQu8vb1x4cIFGBkZwdraWq2/g4MDYmJict1WXjR+CjgwMBDTp0/P0T5jxgx8+eWXmm4OR44cgZubG+bPn4+4uDjExcVhwYIFcHNzw5EjRzTeHhEREZEuCQ0NxatXr9SW0NDQPPt7enriwoULOHXqFPr164egoCBcvVqw31WscQXwyJEjuWaszZo1w6xZszQOYMCAAWjfvj0WL16sGleYmZmJ/v37Y8CAAbh06ZLG2yQiIiLShDafAs7P7d5/MzIyQtmyZQEA1atXx+nTpzFv3jx06NABaWlpePnypVoV8MmTJ3B01OwLGzSuACYmJuY63YuhoSHi4+M13Ryio6MxfPhwtYdK9PX1ERISgujoaI23R0RERFSUZGVlITU1FdWrV4ehoSGioqJU665fv4779+/Dx8dHo21qnABWqlQJGzbk/M7N9evX5/v7e/+tWrVqqrF//3bt2jVUqVJF4+0RERERaUqh0N6iidDQUNXUepcuXUJoaCgOHTqELl26wMrKCsHBwQgJCcHBgwdx9uxZ9OzZEz4+Pho9AAJ8wC3gsWPHIiAgALdu3cJnn30GAIiKisLatWuxadMmTTeHwYMHY8iQIYiOjlYFf/LkSSxcuBDTpk3DxYsXVX0rV66s8faJiIiI3kdPR76x4+nTp+jevTseP34MKysrVK5cGXv37kWjRo0AAHPmzIGenh4CAwPVJoLWVL7nAfy3nTt3YurUqbhw4QJMTExQpUoVjB8/Hra2tqhYsaJG29LTe3cRUqFQQAgBhUKBzMzMfG2T8wCSLuI8gKRrOA8g6Rop5wEcs+uG1rY9rXk5rW37Q33QqW7RogVatGgBAIiPj8e6deswYsQInD17Nt9JWrbs+QWJiIiIpKLxmLj/uA/OtY8cOYLly5dj8+bNcHZ2RkBAABYuXKjxdlxdXT80BCIiIiL6ABolvDExMZg2bRo8PDzw5ZdfwtLSEqmpqdi6dSumTZuGmjVrflAQq1evhp+fH5ydnXHv3j0AwNy5c/Hbb7990PaIiIiINKErD4EUlnwngC1btoSnpycuXryIuXPn4tGjR1iwYMFHB7B48WKEhISgefPmePnypeoWsrW1NebOnfvR2yciIiIidflOAHfv3o3g4GBMnDgRLVq0UJu372MsWLAAy5Ytw7fffqu2zRo1anASaCIiIioUegqF1hZdlO8E8OjRo0hISED16tVRu3Zt/Pjjj4iNjf3oAO7cuYNPPvkkR7tSqURSUtJHb5+IiIiI1OU7AaxTpw6WLVuGx48fo2/fvli/fj2cnZ2RlZWF/fv3IyEh4YMCcHNzw4ULF3K079mzB15eXh+0TSIiIiJNcAzge5iZmaFXr144evQoLl26hOHDh2PatGmwt7dHq1atNA4gJCQEAwYMwIYNGyCEwJ9//onvv/8eoaGhGDVqlMbbIyIiItKUnkJ7iy76qCkXPT09MWPGDISFhWH79u1YsWKFxtvo3bs3TExM8N133yE5ORmdO3eGs7Mz5s2bh44dO35MeERERESUiw/6JhBtSU5ORmJiIuzt7T9qO/wmENJF/CYQ0jX8JhDSNVJ+E8ik/dFa2/a4RmW1tu0PpRMTX2dkZODAgQNYvXo1TExMAACPHj1CYmKixJERERERFT0S5tpv3Lt3D02bNsX9+/eRmpqKRo0awcLCAtOnT0dqaiqWLFkidYhERERUxOnqwxraInkFcMiQIahRowbi4uJU1T8AaNu2LaKioiSMjIiIiKhokrwC+Mcff+D48eMwMjJSay9dujQePnwoUVREREQkJ7r6tK62SF4BzMrKUn3927/9888/sLCwkCAiIiIioqJN8gSwcePGat/5q1AokJiYiPHjx6N58+bSBUZERESyodDif7pI8lvAs2bNQpMmTeDt7Y2UlBR07twZN2/eRLFixbBu3TqpwyMiIiIZkNstYMkTwJIlS+Kvv/7C+vXrcfHiRSQmJiI4OBhdunRReyiEiIiIiAqG5AkgABgYGKBr165Sh0FEREQyxQpgIdi2bVu++37I9wsTERERUd4kSQDbtGmTr34KhSLXJ4SJiIiICpJCZjNBS5IAZmXxu3qJiIiIpKITYwCJiIiIpCS3MYCSzQN44sQJ7NixQ61t1apVcHNzg729Pb766iukpqZKFB0RERFR0SVZAjhp0iRcuXJF9frSpUsIDg6Gv78/xowZg+3btyMsLEyq8IiIiEhGFArtLbpIsgTwwoUL+Pzzz1Wv169fj9q1a2PZsmUICQnB/PnzsXHjRqnCIyIiIhnRUyi0tugiyRLAuLg4ODg4qF4fPnwYzZo1U72uWbMmHjx4IEVoREREREWaZAmgg4MD7ty5AwBIS0vDuXPnUKdOHdX6hIQEGBoaShUeERERyYieQnuLLpIsAWzevDnGjBmDP/74A6GhoTA1NUW9evVU6y9evAh3d3epwiMiIiIqsiSbBmby5MkICAhAgwYNYG5ujoiICBgZGanWr1ixAo0bN5YqPCIiIpIRHR2qpzWSJYDFihXDkSNH8OrVK5ibm0NfX19t/a+//gpzc3OJoiMiIiIquiSfCNrKyirXdltb20KOhIiIiORKD/IqAUo2BpCIiIiIpCF5BZCIiIhIahwDSERERCQzujpdi7bwFjARERGRzLACSERERLKnq1/Zpi2sABIRERHJDCuAREREJHsyKwCyAkhEREQkN6wAEhERkexxDCARERERFWmsABIREZHsyawAyASQiIiISG63ROV2vERERESyxwogERERyZ5CZveAWQEkIiIikhlWAImIiEj25FX/YwWQiIiISHZYASQiIiLZ40TQRERERFSksQJIREREsiev+h8TQCIiIiLZfRMIbwETERERyQwrgERERCR7nAiaiIiIiIo0VgCJiIhI9uRWEZPb8RIRERHJHiuAREREJHscA0hERERERRorgERERCR78qr/sQJIREREJDusABIREZHsyW0MIBNAokJy/4+5UodApMam+UypQyBS83rfSMn2LbdbonI7XiIiIiKdFRYWhpo1a8LCwgL29vZo06YNrl+/rtYnJSUFAwYMgJ2dHczNzREYGIgnT55otB8mgERERCR7CoVCa4smDh8+jAEDBuDkyZPYv38/0tPT0bhxYyQlJan6DBs2DNu3b8evv/6Kw4cP49GjRwgICNBoP7wFTERERKQj9uzZo/Z65cqVsLe3x9mzZ1G/fn28evUKy5cvx9q1a/HZZ58BAMLDw+Hl5YWTJ0+iTp06+doPK4BEREQkewotLqmpqYiPj1dbUlNT8xXXq1evAAC2trYAgLNnzyI9PR3+/v6qPuXLl4eLiwtOnDiR7+NlAkhERESkRWFhYbCyslJbwsLC3vu+rKwsDB06FH5+fqhYsSIAICYmBkZGRrC2tlbr6+DggJiYmHzHxFvAREREJHvanAUmNDQUISEham1KpfK97xswYAAuX76Mo0ePFnhMTACJiIiItEipVOYr4fu3gQMHYseOHThy5AhKliypand0dERaWhpevnypVgV88uQJHB0d87193gImIiIi2dODQmuLJoQQGDhwILZs2YLff/8dbm5uauurV68OQ0NDREVFqdquX7+O+/fvw8fHJ9/7YQWQiIiIZE9XvghkwIABWLt2LX777TdYWFioxvVZWVnBxMQEVlZWCA4ORkhICGxtbWFpaYlBgwbBx8cn308AA0wAiYiIiHTG4sWLAQCffvqpWnt4eDh69OgBAJgzZw709PQQGBiI1NRUNGnSBIsWLdJoP0wAiYiISPYUGt6q1RYhxHv7GBsbY+HChVi4cOEH74djAImIiIhkhhVAIiIikj1dGQNYWFgBJCIiIpIZVgCJiIhI9jSdruW/jhVAIiIiIplhBZCIiIhkT25jAJkAEhERkezJLQHkLWAiIiIimWEFkIiIiGRPVyaCLiysABIRERHJDCuAREREJHt68ioAsgJIREREJDesABIREZHscQwgERERERVprAASERGR7MltHkAmgERERCR7vAVMREREREUaK4BEREQke5wGhoiIiIiKNFYAiYiISPY4BpCIiIiIijRWAImIiEj25DYNDCuARERERDLDCiARERHJnswKgEwAiYiIiPRkdg+Yt4CJiIiIZIYVQCIiIpI9edX/WAEkIiIikh1WAImIiIhkVgJkBZCIiIhIZlgBJCIiItnjV8ERERERUZHGCiARERHJnsymAWQCSERERCSz/I+3gImIiIjkhhVAIiIiIpmVAFkBJCIiIpIZVgCJiIhI9uQ2DYzOJICbNm3Cxo0bcf/+faSlpamtO3funERRERERERU9OnELeP78+ejZsyccHBxw/vx51KpVC3Z2drh9+zaaNWsmdXhERERUxCkU2lt0kU4kgIsWLcLSpUuxYMECGBkZYdSoUdi/fz8GDx6MV69eSR0eERERUZGiEwng/fv34evrCwAwMTFBQkICAKBbt25Yt26dlKERERGRDCi0uOginUgAHR0d8eLFCwCAi4sLTp48CQC4c+cOhBBShkZERERyILMMUCcSwM8++wzbtm0DAPTs2RPDhg1Do0aN0KFDB7Rt21bi6IiIiIiKFp14Cnjp0qXIysoCAAwYMAB2dnY4fvw4WrVqhb59+0ocHRERERV1nAZGAnp6etDT+18xsmPHjujYsaOEEREREREVXZIlgBcvXkTFihWhp6eHixcvvrNv5cqVCykqIiIikiNdna5FWyRLAKtWrYqYmBjY29ujatWqUCgUuT7woVAokJmZKUGEREREREWTZAngnTt3ULx4cdWfiYiIiKQiswKgdAmgq6trrn8mIiIiIu3SiYdAAODmzZs4ePAgnj59qnoiONu4ceMkioqIiIhkQWYlQJ1IAJctW4Z+/fqhWLFicHR0hOJfIzEVCgUTQCIiItIqTgMjgSlTpuD777/H6NGjpQ6FiIiIqMjTiQQwLi4OX375pdRhEBERkUzJbRoYnfgquC+//BL79u2TOgwiIiIiWdCJCmDZsmUxduxYnDx5EpUqVYKhoaHa+sGDB0sUGREREcmBzAqAUIjcZl8uZG5ubnmuUygUuH37tkbbi0/Jen8nokKWmsHrknSLS8AcqUMgUvN630jJ9n35n0StbbtiSXOtbftD6UQFkBNBExERkaRkVgLUiTGARERERFR4dKICKITApk2b8pwIOjIyUqLI5Cl8+VIcjNqPe3duQ6k0RuWqn2Dg0OEoXTrvW/VEhWl1+DL89ONcfNmpK4aMCJU6HJKBb7v54rtufmpt1x88R9XgFXBxsMT11X1zfV+Xyb8h8o8bhREifSTOAyiBoUOH4qeffkLDhg3h4OCgNhE0Fb5zZ07jyw6d4V2hIjIzM7FowRwM+joYGyN3wMTUVOrwSOauXbmEbZG/wt2jnNShkMxcufsMLUb/qnqdkfmmWPHPswSU7rBIrW+v5pUx7Mta2HuaQ5xIN+lEArh69WpERkaiefPmUodCABYsXqb2evykMDRu6Idr166gWvWaEkVFBCQnJ2Hid6Mx6ruJiFj+k9ThkMxkZAo8iUvK0Z6VlbO9lZ8HNh/5G0kp6YUVHn0kudWedGIMoJWVFcqUKSN1GJSHxMQEAIClpZXEkZDczZ42Bb5166NmbR+pQyEZKlvCGrfX9cPViD4IH9MCpYpb5NrvEw8HVC3rgIg9lwo5QvoYCi0uukgnEsAJEyZg4sSJeP36tdSh0FuysrIwe0YYqlSthrK85UYSOrB3F278fQ19Bw6TOhSSodN/P8ZXM3ej1TebMHj+fpR2sMKB2Z1gbmKYo29Q00q4di8WJ68+kiBSKgqOHDmCli1bwtnZGQqFAlu3blVbL4TAuHHj4OTkBBMTE/j7++PmzZsa7UMnEsD27dsjLi4O9vb2qFSpEqpVq6a2vEtqairi4+PVltTU1EKKvOibMXUSbt26ie9nzJI6FJKxJzGPMe+HaRj3/XQolUqpwyEZ2nf6DiL/uIHLd57hwNm7aPPdZliZGyOwQXm1fsZGBujQ0IvVv/8iHSoBJiUloUqVKli4cGGu62fMmIH58+djyZIlOHXqFMzMzNCkSROkpKTkex86MQYwKCgIZ8+eRdeuXTV+CCQsLAwTJ05Uaxvz7TiEfje+oMOUnRlTJ+OPI4exdMVqODg4Sh0Oydj1a1cR9+I5grv87zvDMzMz8de5M4jcuA6/nzgPfX19CSMkuXmVlIrof17A3dlarb1tvXIwVRpizYEr0gRGRUKzZs3QrFmzXNcJITB37lx89913aN26NQBg1apVcHBwwNatW9GxY8d87UMnEsCdO3di7969qFu3rsbvDQ0NRUhIiFpbqshZkqf8E0JgZtgUHPr9AJYsj0CJkiWlDolkrkatOli1Yata29SJ38K1dBl0CQpm8keFzszYEG5O1oiJuqrW3qNpJew8GY3YVxzS9F+jzWlgUlNTc9ydVCqVH3RH486dO4iJiYG/v7+qzcrKCrVr18aJEyfynQDqxC3gUqVKwdLS8oPeq1QqYWlpqbbwFtHHmT51Enbv2o7J02bC1MwMsbHPEBv7TKPSMlFBMjUzQ5myHmqLsYkpLK2sUKash9ThkQyE9fkUdSuVhIuDJep4O2PDhDbIzBLYePCaqk8ZZ2vUrVQK4bsvShgp6aKwsDBYWVmpLWFhYR+0rZiYGACAg4ODWruDg4NqXX7oRAVw1qxZGDVqFJYsWYLSpUtLHY7sbd64HgDwdXCQWvu4SVPRsnVbKUIiIpJUieLmWPVNS9haGCP21Wscv/IPGgxZo1bpC2pSCQ9jE3Dg7F3pAqUPps1pYHK7Wyl1sUonEsCuXbsiOTkZ7u7uMDU1haGh+i3cFy9eSBSZPJ3+69r7OxFJ7MelK6UOgWSk+9Qd7+0zPvwPjA//oxCiof+aD73dmxtHxzdj8p88eQInJydV+5MnT1C1atV8b0cnEsC5c+dKHQIRERHJmK7O1/c2Nzc3ODo6IioqSpXwxcfH49SpU+jXr1++t6MTCWBQUND7OxERERFpiw5lgImJiYiOjla9vnPnDi5cuABbW1u4uLhg6NChmDJlCjw8PODm5oaxY8fC2dkZbdq0yfc+dCIBBN5M6bB161Zcu/bm9mOFChXQqlUrPt1HREREsnLmzBk0bNhQ9Tp7/GBQUBBWrlyJUaNGISkpCV999RVevnyJunXrYs+ePTA2Ns73PhRCCFHgkWsoOjoazZs3x8OHD+Hp6QkAuH79OkqVKoWdO3fC3d1do+3Fp2RpI0yij5KaweuSdItLwBypQyBS83rfSMn2ffOJ9qbu8XAw0dq2P5ROTAMzePBguLu748GDBzh37hzOnTuH+/fvw83NDYMHD5Y6PCIiIqIiRSduAR8+fBgnT56Era2tqs3Ozg7Tpk2Dn5+fhJERERGRHGhzGhhdpBMVQKVSiYSEhBztiYmJMDIykiAiIiIioqJLJxLAL774Al999RVOnToFIQSEEDh58iS+/vprtGrVSurwiIiIqIhTaHHRRTqRAM6fPx/u7u7w8fGBsbExjI2N4efnh7Jly2LevHlSh0dERERUpOjEGEBra2v89ttviI6OVk0D4+XlhbJly0ocGREREcmCrpbqtEQnEsBsZcuWRdmyZZGZmYlLly4hLi4ONjY2UodFRERERZxCZhmgTtwCHjp0KJYvXw7gzYTQDRo0QLVq1VCqVCkcOnRI2uCIiIiIihidSAA3bdqEKlWqAAC2b9+O27dv4++//8awYcPw7bffShwdERERFXUKhfYWXaQTCWBsbCwcHR0BALt27UL79u1Rrlw59OrVC5cuXZI4OiIiIqKiRScSQAcHB1y9ehWZmZnYs2cPGjVqBABITk7mdwETERGR1sltGhideAikZ8+eaN++PZycnKBQKODv7w8AOHXqFMqXLy9xdERERERFi04kgBMmTEDFihXx4MEDfPnll1AqlQAAfX19jBkzRuLoiIiIqMjT1VKdluhEAggA7dq1y9EWFBQkQSRERERERZvOJIBRUVGIiorC06dPkZWVpbZuxYoVEkVFREREciC3eQB1IgGcOHEiJk2ahBo1aqjGARIREREVFrmlHjqRAC5ZsgQrV65Et27dpA6FiIiIqMjTiQQwLS0Nvr6+UodBREREMiWzAqBuzAPYu3dvrF27VuowiIiIiGRBJyqAKSkpWLp0KQ4cOIDKlSvD0NBQbf3s2bMlioyIiIjkgGMAJXDx4kVUrVoVAHD58mVpgyEiIiIq4nQiATx48KDUIRAREZGsyasEKGkCGBAQ8N4+CoUCmzdvLoRoiIiIiORB0gTQyspKyt0TERERAeAYwEIVHh4u5e6JiIiIAMjtBrCOTANDRERERIVHJx4CISIiIpKS3G4BswJIREREJDOsABIREZHsKWQ2CpAVQCIiIiKZYQWQiIiISF4FQFYAiYiIiOSGFUAiIiKSPZkVAJkAEhEREXEaGCIiIiIq0lgBJCIiItnjNDBEREREVKSxAkhEREQkrwIgK4BEREREcsMKIBEREcmezAqArAASERERyQ0rgERERCR7cpsHkAkgERERyR6ngSEiIiKiIo0VQCIiIpI9ud0CZgWQiIiISGaYABIRERHJDBNAIiIiIpnhGEAiIiKSPY4BJCIiIqIijRVAIiIikj25zQPIBJCIiIhkj7eAiYiIiKhIYwWQiIiIZE9mBUBWAImIiIjkhhVAIiIiIpmVAFkBJCIiIpIZVgCJiIhI9uQ2DQwrgEREREQywwogERERyR7nASQiIiKiIo0VQCIiIpI9mRUAmQASERERyS0D5C1gIiIiIplhAkhERESyp9Difx9i4cKFKF26NIyNjVG7dm38+eefBXq8TACJiIiIdMiGDRsQEhKC8ePH49y5c6hSpQqaNGmCp0+fFtg+mAASERGR7CkU2ls0NXv2bPTp0wc9e/aEt7c3lixZAlNTU6xYsaLAjpcJIBEREZEWpaamIj4+Xm1JTU3NtW9aWhrOnj0Lf39/VZuenh78/f1x4sSJAoupSD4FbGnMvLYgpKamIiwsDKGhoVAqlVKHUwTwuvxYvCYL1ut9I6UOoUjgdVk0GGsxI5owJQwTJ05Uaxs/fjwmTJiQo29sbCwyMzPh4OCg1u7g4IC///67wGJSCCFEgW2NipT4+HhYWVnh1atXsLS0lDocIl6TpJN4XdL7pKam5qj4KZXKXP/B8OjRI5QoUQLHjx+Hj4+Pqn3UqFE4fPgwTp06VSAxFckKIBEREZGuyCvZy02xYsWgr6+PJ0+eqLU/efIEjo6OBRYT70kRERER6QgjIyNUr14dUVFRqrasrCxERUWpVQQ/FiuARERERDokJCQEQUFBqFGjBmrVqoW5c+ciKSkJPXv2LLB9MAGkPCmVSowfP56Dmkln8JokXcTrkgpahw4d8OzZM4wbNw4xMTGoWrUq9uzZk+PBkI/Bh0CIiIiIZIZjAImIiIhkhgkgERERkcwwASQiIiKSGSaABAD49NNPMXToUNnslz6MQqHA1q1bpQ6DqMi6e/cuFAoFLly4IHUoVMQxAZRYjx49oFAoMG3aNLX2rVu3QvEh3yD9LytXroRCoYBCoYC+vj5sbGxQu3ZtTJo0Ca9evVLrGxkZicmTJ3/U/ui/7dmzZ+jXrx9cXFygVCrh6OiIJk2a4NixY1KHlqd169ZBX18fAwYMkDoU0gE9evRAmzZtpA7jo5QqVQqPHz9GxYoVpQ6FijgmgDrA2NgY06dPR1xcXIFv29LSEo8fP8Y///yD48eP46uvvsKqVatQtWpVPHr0SNXP1tYWFhYWBb5/ABBCICMjQyvbzszMRFZWlla2LTeBgYE4f/48IiIicOPGDWzbtg2ffvopnj9/LnVoeVq+fDlGjRqFdevWISUlRepwiD6avr4+HB0dYWDAWdpIu5gA6gB/f384OjoiLCzsnf02b96MChUqQKlUonTp0pg1a9Z7t61QKODo6AgnJyd4eXkhODgYx48fR2JiIkaNGqXq9/at2EWLFsHDwwPGxsZwcHBAu3btVOtSU1MxePBg2Nvbw9jYGHXr1sXp06dV6w8dOgSFQoHdu3ejevXqUCqVOHr0KJKSktC9e3eYm5vDyckp1/hTU1MxYsQIlChRAmZmZqhduzYOHTqkWr9y5UpYW1tj27Zt8Pb2hlKpxP379997HujdXr58iT/++APTp09Hw4YN4erqilq1aiE0NBStWrXK830PHjxA+/btYW1tDVtbW7Ru3Rp3795V6/Pzzz/Dy8sLxsbGKF++PBYtWqRal327a/369fD19YWxsTEqVqyIw4cPvzfmO3fu4Pjx4xgzZgzKlSuHyMhItfXZ18rWrVtV13KTJk3w4MEDVZ8JEyagatWqWL16NUqXLg0rKyt07NgRCQkJqj5ZWVkICwuDm5sbTExMUKVKFWzatEm1PjMzE8HBwar1np6emDdv3nvjJ+369NNPMXjwYIwaNQq2trZwdHTEhAkTVOuFEJgwYYKq4u3s7IzBgwer1sfFxaF79+6wsbGBqakpmjVrhps3b6rWZ19fO3bsgKenJ0xNTdGuXTskJycjIiICpUuXho2NDQYPHozMzEzV+0qXLo2pU6eiV69esLCwgIuLC5YuXapa//YtYF5fpDWCJBUUFCRat24tIiMjhbGxsXjw4IEQQogtW7aIf/94zpw5I/T09MSkSZPE9evXRXh4uDAxMRHh4eF5bjs8PFxYWVnlum7IkCHCwsJCZGRkCCGEaNCggRgyZIgQQojTp08LfX19sXbtWnH37l1x7tw5MW/ePNV7Bw8eLJydncWuXbvElStXRFBQkLCxsRHPnz8XQghx8OBBAUBUrlxZ7Nu3T0RHR4vnz5+Lfv36CRcXF3HgwAFx8eJF8cUXXwgLCwvVfoUQonfv3sLX11ccOXJEREdHi5kzZwqlUilu3LihOiZDQ0Ph6+srjh07Jv7++2+RlJSk6Wmnt6Snpwtzc3MxdOhQkZKSkmc/AGLLli1CCCHS0tKEl5eX6NWrl7h48aK4evWq6Ny5s/D09BSpqalCCCF++eUX4eTkJDZv3ixu374tNm/eLGxtbcXKlSuFEELcuXNHABAlS5YUmzZtElevXhW9e/cWFhYWIjY29p0xjx07VrRr104IIcSCBQvEZ599prY++1qpUaOGOH78uDhz5oyoVauW8PX1VfUZP368MDc3FwEBAeLSpUviyJEjwtHRUXzzzTeqPlOmTBHly5cXe/bsEbdu3RLh4eFCqVSKQ4cOqc7DuHHjxOnTp8Xt27fFL7/8IkxNTcWGDRvyefapoGT/PhXize80S0tLMWHCBHHjxg0REREhFAqF2LdvnxBCiF9//VVYWlqKXbt2iXv37olTp06JpUuXqrbVqlUr4eXlJY4cOSIuXLggmjRpIsqWLSvS0tKEEP+7vho1aiTOnTsnDh8+LOzs7ETjxo1F+/btxZUrV8T27duFkZGRWL9+vWq7rq6uwtbWVixcuFDcvHlThIWFCT09PfH3338LIf73mTh//rwQgtcXaQ8TQIn9+xdWnTp1RK9evYQQORPAzp07i0aNGqm9d+TIkcLb2zvPbb8rAVy8eLEAIJ48eSKEUE8AN2/eLCwtLUV8fHyO9yUmJgpDQ0OxZs0aVVtaWppwdnYWM2bMEEL8LwHcunWrqk9CQoIwMjISGzduVLU9f/5cmJiYqPZ77949oa+vLx4+fKi2z88//1yEhoaqjgmAuHDhQp7HTR9m06ZNwsbGRhgbGwtfX18RGhoq/vrrL7U+/04AV69eLTw9PUVWVpZqfWpqqjAxMRF79+4VQgjh7u4u1q5dq7aNyZMnCx8fHyHE//6ymzZtmmp9enq6KFmypJg+fXqesWZmZopSpUqprrFnz54JIyMjcfv2bVWf7Gvl5MmTqrZr164JAOLUqVNCiDcJoKmpqdq1PnLkSFG7dm0hhBApKSnC1NRUHD9+XG3/wcHBolOnTnnGN2DAABEYGJjnetKOtxPAunXrqq2vWbOmGD16tBBCiFmzZoly5cqpErp/u3HjhgAgjh07pmqLjY0VJiYmqt9h2ddXdHS0qk/fvn2FqampSEhIULU1adJE9O3bV/Xa1dVVdO3aVfU6KytL2Nvbi8WLFwshciaAueH1RQWBt4B1yPTp0xEREYFr167lWHft2jX4+fmptfn5+eHmzZtqtxfyS/z/F8Dk9qBJo0aN4OrqijJlyqBbt25Ys2YNkpOTAQC3bt1Cenq6WiyGhoaoVatWjrhr1Kih+vOtW7eQlpaG2rVrq9psbW3h6empen3p0iVkZmaiXLlyMDc3Vy2HDx/GrVu3VP2MjIxQuXJljY+Z3i0wMBCPHj3Ctm3b0LRpUxw6dAjVqlXDypUrc+3/119/ITo6GhYWFqqfla2tLVJSUnDr1i0kJSXh1q1bCA4OVvt5TpkyRe3nCUDtC84NDAxQo0aNXD8H2fbv34+kpCQ0b94cAFCsWDE0atQIK1asUOtnYGCAmjVrql6XL18e1tbWatsuXbq02vhXJycnPH36FAAQHR2N5ORkNGrUSO0YVq1apXYMCxcuRPXq1VG8eHGYm5tj6dKlHJqgA97+PfHvn+2XX36J169fo0yZMujTpw+2bNmiGqt87do1GBgYqP2+srOzg6enp9q1Y2pqCnd3d9VrBwcHlC5dGubm5mpt2fvMLa7sYTpv9/k3Xl+kDRxlqkPq16+PJk2aIDQ0FD169NDqvq5duwZLS0vY2dnlWGdhYYFz587h0KFD2LdvH8aNG4cJEyaojfPLDzMzM436JyYmQl9fH2fPnoW+vr7aun//QjUxMfnoJ6Qpd8bGxmjUqBEaNWqEsWPHonfv3hg/fnyu12NiYiKqV6+ONWvW5FhXvHhxJCYmAgCWLVum9hcpgBw/X00tX74cL168gImJiaotKysLFy9exMSJE6Gnl/9/2xoaGqq9VigUqgeLso9h586dKFGihFq/7O99Xb9+PUaMGIFZs2bBx8cHFhYWmDlzJk6dOvVBx0YF510/21KlSuH69es4cOAA9u/fj/79+2PmzJn5Gn/6ru2/a5/5iettvL5IW5gA6php06ahatWqapUxAPDy8soxHcexY8dQrlw5jf8yffr0KdauXYs2bdrk+RelgYEB/P394e/vj/Hjx8Pa2hq///47mjRpAiMjIxw7dgyurq4AgPT0dJw+ffqd8/m5u7vD0NAQp06dgouLC4A3g6xv3LiBBg0aAAA++eQTZGZm4unTp6hXr55Gx0Ta4e3tnee8f9WqVcOGDRtgb28PS0vLHOutrKzg7OyM27dvo0uXLu/cz8mTJ1G/fn0AQEZGBs6ePYuBAwfm2vf58+f47bffsH79elSoUEHVnpmZibp162Lfvn1o2rSpaltnzpxBrVq1AADXr1/Hy5cv4eXl9d5jB6D2oFH2dfq2Y8eOwdfXF/3791e1vV3hJN1kYmKCli1bomXLlhgwYADKly+PS5cuwcvLCxkZGTh16hR8fX0BvLnurl+/Dm9v70KNkdcXaQsTQB1TqVIldOnSBfPnz1drHz58OGrWrInJkyejQ4cOOHHiBH788Ue1JypzI4RATEwMhBB4+fIlTpw4galTp8LKyirH3IPZduzYgdu3b6N+/fqwsbHBrl27kJWVBU9PT5iZmaFfv34YOXIkbG1t4eLighkzZiA5ORnBwcF5xmFubo7g4GCMHDkSdnZ2sLe3x7fffquWgJYrVw5dunRB9+7dMWvWLHzyySd49uwZoqKiULlyZbRo0UKDM0maeP78Ob788kv06tULlStXhoWFBc6cOYMZM2agdevWub6nS5cumDlzJlq3bo1JkyahZMmSuHfvHiIjIzFq1CiULFkSEydOxODBg2FlZYWmTZsiNTUVZ86cQVxcHEJCQlTbWrhwITw8PODl5YU5c+YgLi4OvXr1ynW/q1evhp2dHdq3b5+jEty8eXMsX75clQAaGhpi0KBBmD9/PgwMDDBw4EDUqVNHlRC+j4WFBUaMGIFhw4YhKysLdevWxatXr3Ds2DFYWloiKCgIHh4eWLVqFfbu3Qs3NzesXr0ap0+fhpubW772QdJYuXIlMjMzUbt2bZiamuKXX36BiYkJXF1dYWdnh9atW6NPnz746aefYGFhgTFjxqBEiRJ5fh60hdcXaQsTQB00adIkbNiwQa2tWrVq2LhxI8aNG4fJkyfDyckJkyZNeu+t4vj4eDg5OUGhUMDS0hKenp4ICgrCkCFDcq3aAIC1tTUiIyMxYcIEpKSkwMPDA+vWrVNVW6ZNm4asrCx069YNCQkJqFGjBvbu3QsbG5t3xjJz5kwkJiaiZcuWsLCwwPDhw3NMSB0eHo4pU6Zg+PDhePjwIYoVK4Y6dergiy++eM9Zo49hbm6O2rVrY86cOapxnqVKlUKfPn3wzTff5PoeU1NTHDlyBKNHj0ZAQAASEhJQokQJfP7556prq3fv3jA1NcXMmTMxcuRImJmZoVKlSjmqxdOmTcO0adNw4cIFlC1bFtu2bUOxYsVy3e+KFSvQtm3bXIcBBAYGolu3boiNjVXFOHr0aHTu3BkPHz5EvXr1sHz5co3OzeTJk1G8eHGEhYXh9u3bsLa2RrVq1VTnpW/fvjh//jw6dOgAhUKBTp06oX///ti9e7dG+6HCZW1tjWnTpiEkJASZmZmoVKkStm/frhoWEx4ejiFDhuCLL75AWloa6tevj127duW4fattvL5IWxQi+2kAIqJCdvfuXbi5ueH8+fOoWrVqgW575cqVGDp0KF6+fFmg2yUiKgr4FDARERGRzDABJCIiIpIZ3gImIiIikhlWAImIiIhkhgkgERERkcwwASQiIiKSGSaARERERDLDBJCIiIhIZpgAEpHO6tGjB9q0aaN6/emnn77zO6e15dChQ1AoFJxUmoiKDCaARKSxHj16QKFQQKFQwMjICGXLlsWkSZOQkZGh1f1GRkZi8uTJ+erLpI2IKG/8LmAi+iBNmzZFeHg4UlNTsWvXLgwYMACGhoYIDQ1V65eWlgYjI6MC2aetrW2BbIeISO5YASSiD6JUKuHo6AhXV1f069cP/v7+2LZtm+q27ffffw9nZ2d4enoCAB48eID27dvD2toatra2aN26Ne7evavaXmZmJkJCQmBtbQ07OzuMGjUKb89T//Yt4NTUVIwePRqlSpWCUqlE2bJlsXz5cty9excNGzYEANjY2EChUKBHjx4AgKysLISFhcHNzQ0mJiaoUqUKNm3apLafXbt2oVy5cjAxMUHDhg3V4iQiKgqYABJRgTAxMUFaWhoAICoqCtevX8f+/fuxY8cOpKeno0mTJrCwsMAff/yBY8eOwdzcHE2bNlW9Z9asWVi5ciVWrFiBo0eP4sWLF9iyZcs799m9e3esW7cO8+fPx7Vr1/DTTz/B3NwcpUqVwubNmwEA169fx+PHjzFv3jwAQFhYGFatWoUlS5bgypUrGDZsGLp27YrDhw8DeJOoBgQEoGXLlrhw4QJ69+6NMWPGaOu0ERFJgreAieijCCEQFRWFvXv3YtCgQXj27BnMzMzw888/q279/vLLL8jKysLPP/8MhUIBAAgPD4e1tTUOHTqExo0bY+7cuQgNDUVAQAAAYMmSJdi7d2+e+71x4wY2btyI/fv3w9/fHwBQpkwZ1frs28X29vawtrYG8KZiOHXqVBw4cAA+Pj6q9xw9ehQ//fQTGjRogMWLF8Pd3R2zZs0CAHh6euLSpUuYPn16AZ41IiJpMQEkog+yY8cOmJubIz09HVlZWejcuTMmTJiAAQMGoFKlSmrj/v766y9ER0fDwsJCbRspKSm4desWXr16hcePH6N27dqqdQYGBqhRo0aO28DZLly4AH19fTRo0CDfMUdHRyM5ORmNGjVSa09LS8Mnn3wCALh27ZpaHABUySIRUVHBBJCIPkjDhg2xePFiGBkZwdnZGQYG//t1YmZmptY3MTER1atXx5o1a3Jsp3jx4h+0fxMTE43fk5iYCADYuXMnSpQoobZOqVR+UBxERP9FTACJ6IOYmZmhbNmy+epbrVo1bNiwAfb29rC0tMy1j5OTE06dOoX69esDADIyMnD27FlUq1Yt1/6VKlVCVlYWDh8+rLoF/G/ZFcjMzExVm7e3N5RKJe7fv59n5dDLywvbtm1Tazt58uT7D5KI6D+ED4EQkdZ16dIFxYoVQ+vWrfHHH3/gzp07OHToEAYPHox//vkHADBkyBBMmzYNW7duxd9//43+/fu/cw6/0qVLIygoCL169cLWrVtV29y4cSMAwNXVFQqFAjt27MCzZ8+QmJgICwsLjBgxAsOGDUNERARu3bqFc+fOYcGCBYiIiAAAfP3117h58yZGjhyJ69evY+3atVi5cqW2TxERUaFiAkhEWmdqaoojR47AxcUFAQEB8PLyQnBwMFJSUlQVweHDh6Nbt24ICgqCj48PLCws0LZt23dud/HixWjXrh369++P8uXLo0+fPkhKSgIAlChRAhMnTsSYMWPg4OCAgQMHAgAmT56MsWPHIiwsDF5eXmjatCl27twJNzc3AICLiws2b96MrVu3okqVKliyZAmmTp2qxbNDRFT4FCKvEdZEREREVCSxAkhEREQkM0wAiYiIiGSGCSARERGRzDABJCIiIpIZJoBEREREMsMEkIiIiEhmmAASERERyQwTQCIiIiKZYQJIREREJDNMAImIiIhkhgkgERERkcz8HyfJxcA9DMVgAAAAAElFTkSuQmCC", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Accuracy: 0.9152\n", + "Precision: 0.9160\n", + "Recall: 0.9152\n", + "F1 Score: 0.9147\n" + ] + } + ], + "source": [ + "from sklearn.ensemble import GradientBoostingClassifier\n", + "\n", + "# Initialize GBM classifier\n", + "gbm_clf = GradientBoostingClassifier(random_state=42)\n", + "\n", + "# Train the model\n", + "gbm_clf.fit(X_train, y_train)\n", + "\n", + "# Predictions\n", + "y_pred = gbm_clf.predict(X_test)\n", + "\n", + "# Calculate metrics\n", + "accuracy_gbm = accuracy_score(y_test, y_pred)\n", + "precision_gbm = precision_score(y_test, y_pred, average='weighted')\n", + "recall_gbm = recall_score(y_test, y_pred, average='weighted')\n", + "f1_gbm = f1_score(y_test, y_pred, average='weighted')\n", + "\n", + "# Classification report\n", + "print(\"Classification Report:\")\n", + "print(classification_report(y_test, y_pred))\n", + "\n", + "# Confusion matrix\n", + "cm = confusion_matrix(y_test, y_pred)\n", + "plt.figure(figsize=(8, 6))\n", + "sns.heatmap(cm, annot=True, cmap='Blues', fmt='d', xticklabels=['No Disorder', 'Sleep Apnea', 'Insomnia'], yticklabels=['No Disorder', 'Sleep Apnea', 'Insomnia'])\n", + "plt.xlabel('Predicted')\n", + "plt.ylabel('Actual')\n", + "plt.title('Confusion Matrix - Gradient Boosting Machine')\n", + "plt.show()\n", + "\n", + "# Display metrics\n", + "print(f\"Accuracy: {accuracy_gbm:.4f}\")\n", + "print(f\"Precision: {precision_gbm:.4f}\")\n", + "print(f\"Recall: {recall_gbm:.4f}\")\n", + "print(f\"F1 Score: {f1_gbm:.4f}\")\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "> K Neighbors Classifier" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:24.495398Z", + "iopub.status.busy": "2024-10-28T15:52:24.494958Z", + "iopub.status.idle": "2024-10-28T15:52:24.819921Z", + "shell.execute_reply": "2024-10-28T15:52:24.818805Z", + "shell.execute_reply.started": "2024-10-28T15:52:24.495351Z" + }, + "trusted": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Classification Report:\n", + " precision recall f1-score support\n", + "\n", + " 0 0.92 0.87 0.89 38\n", + " 1 0.88 0.95 0.92 64\n", + " 2 0.97 0.92 0.94 63\n", + "\n", + " accuracy 0.92 165\n", + " macro avg 0.92 0.91 0.92 165\n", + "weighted avg 0.92 0.92 0.92 165\n", + "\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Accuracy: 0.9212\n", + "Precision: 0.9231\n", + "Recall: 0.9212\n", + "F1 Score: 0.9213\n" + ] + } + ], + "source": [ + "from sklearn.neighbors import KNeighborsClassifier\n", + "\n", + "# Initialize KNN classifier (example using k=5)\n", + "knn_clf = KNeighborsClassifier(n_neighbors=5)\n", + "\n", + "# Train the model\n", + "knn_clf.fit(X_train, y_train)\n", + "\n", + "# Predictions\n", + "y_pred = knn_clf.predict(X_test)\n", + "\n", + "# Calculate metrics\n", + "accuracy_knn = accuracy_score(y_test, y_pred)\n", + "precision_knn = precision_score(y_test, y_pred, average='weighted')\n", + "recall_knn = recall_score(y_test, y_pred, average='weighted')\n", + "f1_knn = f1_score(y_test, y_pred, average='weighted')\n", + "\n", + "# Classification report\n", + "print(\"Classification Report:\")\n", + "print(classification_report(y_test, y_pred))\n", + "\n", + "# Confusion matrix\n", + "cm = confusion_matrix(y_test, y_pred)\n", + "plt.figure(figsize=(8, 6))\n", + "sns.heatmap(cm, annot=True, cmap='Greens', fmt='d', xticklabels=['No Disorder', 'Sleep Apnea', 'Insomnia'], yticklabels=['No Disorder', 'Sleep Apnea', 'Insomnia'])\n", + "plt.xlabel('Predicted')\n", + "plt.ylabel('Actual')\n", + "plt.title('Confusion Matrix - K-Nearest Neighbors')\n", + "plt.show()\n", + "\n", + "# Display metrics\n", + "print(f\"Accuracy: {accuracy_knn:.4f}\")\n", + "print(f\"Precision: {precision_knn:.4f}\")\n", + "print(f\"Recall: {recall_knn:.4f}\")\n", + "print(f\"F1 Score: {f1_knn:.4f}\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Model Comparison" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:24.822107Z", + "iopub.status.busy": "2024-10-28T15:52:24.821557Z", + "iopub.status.idle": "2024-10-28T15:52:25.227991Z", + "shell.execute_reply": "2024-10-28T15:52:25.226750Z", + "shell.execute_reply.started": "2024-10-28T15:52:24.822035Z" + }, + "trusted": true + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "from sklearn.metrics import roc_curve, auc\n", + "\n", + "# Initialize figure\n", + "fig_roc = plt.figure(figsize=(10, 8))\n", + "models = ['Gradient Boosting Machine', 'K-Nearest Neighbors', 'Logistic Regression', 'XGBoost']\n", + "\n", + "# Plot ROC curve for each model\n", + "for idx, model in enumerate([gbm_clf, knn_clf, model_lr, model_xgb]):\n", + " if model == knn_clf:\n", + " y_scores = model.predict_proba(X_test)\n", + " fpr, tpr, _ = roc_curve(y_test, y_scores[:, 1], pos_label=1)\n", + " else:\n", + " y_scores = model.predict_proba(X_test)[:, 1]\n", + " fpr, tpr, _ = roc_curve(y_test, y_scores, pos_label=1)\n", + "\n", + " roc_auc = auc(fpr, tpr)\n", + "\n", + " # Plot ROC curve\n", + " plt.plot(fpr, tpr, lw=2, label=f'{models[idx]} (AUC = {roc_auc:.2f})')\n", + "\n", + "# Plot ROC curve for random guessing\n", + "plt.plot([0, 1], [0, 1], linestyle='--', lw=2, color='r', label='Random Guessing')\n", + "\n", + "# Set plot labels and title\n", + "plt.xlabel('False Positive Rate')\n", + "plt.ylabel('True Positive Rate')\n", + "plt.title('ROC Curve')\n", + "plt.legend(loc='lower right')\n", + "plt.grid()\n", + "\n", + "# Show plot\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Saving Model" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T15:52:25.230167Z", + "iopub.status.busy": "2024-10-28T15:52:25.229539Z", + "iopub.status.idle": "2024-10-28T15:52:25.249494Z", + "shell.execute_reply": "2024-10-28T15:52:25.248437Z", + "shell.execute_reply.started": "2024-10-28T15:52:25.230115Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "# Save the model to a file\n", + "import pickle\n", + "with open(\"Model_Prediction.sav\", \"wb\") as f:\n", + " pickle.dump(model_xgb,f)" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": { + "execution": { + "iopub.execute_input": "2024-10-28T16:18:17.328817Z", + "iopub.status.busy": "2024-10-28T16:18:17.327892Z", + "iopub.status.idle": "2024-10-28T16:18:17.334261Z", + "shell.execute_reply": "2024-10-28T16:18:17.333146Z", + "shell.execute_reply.started": "2024-10-28T16:18:17.328775Z" + }, + "trusted": true + }, + "outputs": [], + "source": [ + "with open('preprocessor.sav', 'wb') as f:\n", + " pickle.dump(preprocessor, f)" + ] + } + ], + "metadata": { + "kaggle": { + "accelerator": "none", + "dataSources": [ + { + "datasetId": 3321433, + "sourceId": 6491929, + "sourceType": "datasetVersion" + } + ], + "dockerImageVersionId": 30786, + "isGpuEnabled": false, + "isInternetEnabled": true, + "language": "python", + "sourceType": "notebook" + }, + "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": "3.10.14" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/Prediction Models/sleep_disorder_predictor/predict.py b/Prediction Models/sleep_disorder_predictor/predict.py new file mode 100644 index 00000000..a5394c9c --- /dev/null +++ b/Prediction Models/sleep_disorder_predictor/predict.py @@ -0,0 +1,25 @@ +from sleep_disorder_predictor.model import disease_get_prediction + +def get_prediction(Age, Sleep_Duration, + Heart_Rate, Daily_Steps, + Systolic, Diastolic,Occupation,Quality_of_Sleep,Gender, + Physical_Activity_Level, Stress_Level, BMI_Category): + + prediction = disease_get_prediction(Age, Sleep_Duration, + Heart_Rate, Daily_Steps, + Systolic, Diastolic,Occupation,Quality_of_Sleep,Gender, + Physical_Activity_Level, Stress_Level, BMI_Category) + + message = "" + + # Provide message based on the prediction value + if prediction==0: + message= "Insomnia" + elif prediction==1: + message = "No disorder" + elif prediction==2: + message = "Sleep Apnea" + else: + message="Invalid details." + + return message+"\n\nRecommendation - To prevent sleep disorders, maintain a balanced lifestyle with regular exercise, a healthy diet, and stress management. Stick to a consistent sleep schedule, limit caffeine and alcohol, and create a relaxing bedtime routine." \ No newline at end of file diff --git a/Prediction Models/sleep_disorder_predictor/readme.md b/Prediction Models/sleep_disorder_predictor/readme.md new file mode 100644 index 00000000..e08639f7 --- /dev/null +++ b/Prediction Models/sleep_disorder_predictor/readme.md @@ -0,0 +1,114 @@ +# Sleep Disorder Predictor + +## Overview + +The Sleep Disorder Predictor project aims to predict sleep disorders using a comprehensive dataset that includes various health and lifestyle parameters. The model leverages machine learning techniques to provide insights into potential sleep issues, including insomnia and sleep apnea. + +## Dataset Overview + +The Sleep Health and Lifestyle Dataset covers a wide range of variables related to sleep and daily habits. It includes details such as gender, age, occupation, sleep duration, quality of sleep, physical activity level, stress levels, BMI category, blood pressure, heart rate, daily steps, and the presence or absence of sleep disorders. + +### Key Features of the Dataset + +- **Comprehensive Sleep Metrics**: Explore sleep duration, quality, and factors influencing sleep patterns. +- **Lifestyle Factors**: Analyze physical activity levels, stress levels, and BMI categories. +- **Cardiovascular Health**: Examine blood pressure and heart rate measurements. +- **Sleep Disorder Analysis**: Identify the occurrence of sleep disorders such as insomnia and sleep apnea. + +### Dataset Columns + +- **Person ID**: An identifier for each individual. +- **Gender**: The gender of the person (Male/Female). +- **Age**: The age of the person in years. +- **Occupation**: The occupation or profession of the person. +- **Sleep Duration (hours)**: The number of hours the person sleeps per day. +- **Quality of Sleep (scale: 1-10)**: A subjective rating of the quality of sleep, ranging from 1 to 10. +- **Physical Activity Level (minutes/day)**: The number of minutes the person engages in physical activity daily. +- **Stress Level (scale: 1-10)**: A subjective rating of the stress level experienced by the person, ranging from 1 to 10. +- **BMI Category**: The BMI category of the person (e.g., Underweight, Normal, Overweight). +- **Blood Pressure (systolic/diastolic)**: The blood pressure measurement of the person, indicated as systolic pressure over diastolic pressure. +- **Heart Rate (bpm)**: The resting heart rate of the person in beats per minute. +- **Daily Steps**: The number of steps the person takes per day. +- **Sleep Disorder**: The presence or absence of a sleep disorder in the person (None, Insomnia, Sleep Apnea). + +### Details about Sleep Disorder Column + +- **None**: The individual does not exhibit any specific sleep disorder. +- **Insomnia**: The individual experiences difficulty falling asleep or staying asleep, leading to inadequate or poor-quality sleep. +- **Sleep Apnea**: The individual suffers from pauses in breathing during sleep, resulting in disrupted sleep patterns and potential health risks. + +## Project Workflow + +1. **Data Preprocessing**: + + - Handling missing values. + - Feature scaling and normalization. + +2. **Exploratory Data Analysis (EDA)**: + + - Analyzing data distribution, correlations, and visualizing patterns. + +3. **Data Balancing**: + + - Addressing class imbalance using techniques like SMOTE. + +4. **Model Building**: + + - Training multiple models including Logistic Regression, XGBoost, Random Forest, etc. + +5. **Model Evaluation**: + - Evaluating model performance using metrics like Accuracy, Precision, Recall, F1-score, and ROC-AUC. + +## Technologies Used + +- **Programming Language**: Python +- **Libraries**: + - Data Analysis: `pandas`, `numpy` + - Visualization: `matplotlib`, `seaborn`, `plotly` + - Machine Learning: `scikit-learn`, `imbalanced-learn`, `xgboost` +- **Environment**: Jupyter Notebook for code execution and visualization + +## Model Evaluation + +Models were evaluated using multiple metrics, including: + +- **Accuracy**: Percentage of correct predictions. +- **Precision**: Ratio of correctly predicted positive observations to total predicted positives. +- **Recall**: Ratio of correctly predicted positive observations to all actual positives. +- **F1-Score**: Weighted average of Precision and Recall. +- **ROC-AUC**: Area under the Receiver Operating Characteristic curve, indicating the model’s ability to distinguish between classes. + +## Usage + +You can use the model to predict sleep disorders by calling the `get_prediction` function with appropriate parameters. Example usage in Python: + +```python +from sleep_disorder_predictor.model import get_prediction + +result = get_prediction( + Age=30, + Sleep_Duration=7.5, + Heart_Rate=70, + Daily_Steps=8000, + Systolic=120, + Diastolic=80, + Occupation='Engineer', + Quality_of_Sleep=4, + Gender='Male', + Physical_Activity_Level=3, + Stress_Level=2, + BMI_Category='Normal' +) +print(result) +``` + +## Recommendations + +To prevent sleep disorders, consider the following lifestyle changes: + +- **Regular Exercise**: Engage in physical activities for at least 30 minutes most days of the week. +- **Healthy Diet**: Maintain a balanced diet rich in fruits, vegetables, whole grains, and lean proteins. +- **Stress Management**: Practice relaxation techniques such as meditation, yoga, or deep breathing exercises. +- **Consistent Sleep Schedule**: Go to bed and wake up at the same time every day, even on weekends. +- **Limit Caffeine and Alcohol**: Reduce intake of stimulants and depressants, especially close to bedtime. +- **Create a Relaxing Bedtime Routine**: Wind down with calming activities before sleep, such as reading or taking a warm bath. diff --git a/Prediction Models/sleep_disorder_predictor/requirements.txt b/Prediction Models/sleep_disorder_predictor/requirements.txt new file mode 100644 index 00000000..24fffe65 --- /dev/null +++ b/Prediction Models/sleep_disorder_predictor/requirements.txt @@ -0,0 +1,9 @@ +numpy +pandas +matplotlib +seaborn +plotly +scikit-learn +imbalanced-learn +xgboost +streamlit diff --git a/Prediction Models/sleep_disorder_predictor/saved_models/Model_Prediction.sav b/Prediction Models/sleep_disorder_predictor/saved_models/Model_Prediction.sav new file mode 100644 index 00000000..7b018b1d Binary files /dev/null and b/Prediction Models/sleep_disorder_predictor/saved_models/Model_Prediction.sav differ diff --git a/Prediction Models/sleep_disorder_predictor/saved_models/preprocessor.sav b/Prediction Models/sleep_disorder_predictor/saved_models/preprocessor.sav new file mode 100644 index 00000000..fd584ace Binary files /dev/null and b/Prediction Models/sleep_disorder_predictor/saved_models/preprocessor.sav differ