Upload 3 files

diabetes.csv

@@ -0,0 +1,391 @@
+patient_number,cholesterol,glucose,hdl_chol,chol_hdl_ratio,age,gender,height,weight,bmi,systolic_bp,diastolic_bp,waist,hip,waist_hip_ratio,diabetes
+1,193,77,49,"3,9",19,female,61,119,"22,5",118,70,32,38,"0,84",No diabetes
+2,146,79,41,"3,6",19,female,60,135,"26,4",108,58,33,40,"0,83",No diabetes
+3,217,75,54,4,20,female,67,187,"29,3",110,72,40,45,"0,89",No diabetes
+4,226,97,70,"3,2",20,female,64,114,"19,6",122,64,31,39,"0,79",No diabetes
+5,164,91,67,"2,4",20,female,70,141,"20,2",122,86,32,39,"0,82",No diabetes
+6,170,69,64,"2,7",20,female,64,161,"27,6",108,70,37,40,"0,93",No diabetes
+7,149,77,49,3,20,female,62,115,21,105,82,31,37,"0,84",No diabetes
+8,164,71,63,"2,6",20,male,72,145,"19,7",108,78,29,36,"0,81",No diabetes
+9,230,112,64,"3,6",20,male,67,159,"24,9",100,90,31,39,"0,79",No diabetes
+10,179,105,60,3,20,female,58,170,"35,5",140,100,34,46,"0,74",No diabetes
+11,174,105,117,"1,5",20,male,70,187,"26,8",132,86,37,41,"0,9",No diabetes
+12,193,106,63,"3,1",20,female,68,274,"41,7",165,110,49,58,"0,84",No diabetes
+13,132,99,34,"3,9",21,female,65,169,"28,1",112,62,39,43,"0,91",No diabetes
+14,203,84,75,"2,7",21,female,63,142,"25,2",125,85,28,39,"0,72",No diabetes
+15,135,88,47,"2,9",21,male,69,155,"22,9",110,68,31,39,"0,79",No diabetes
+16,187,84,64,"2,9",21,female,63,158,28,138,88,39,43,"0,91",No diabetes
+17,244,89,92,"2,7",21,male,71,163,"22,7",116,76,34,39,"0,87",No diabetes
+18,193,75,49,"3,9",21,female,61,220,"41,6",130,82,40,52,"0,77",No diabetes
+19,165,76,46,"3,6",22,female,63,114,"20,2",112,78,28,35,"0,8",No diabetes
+20,172,70,36,"4,8",22,female,64,148,"25,4",90,48,35,38,"0,92",No diabetes
+21,217,81,60,"3,6",22,female,71,223,"31,1",120,75,46,50,"0,92",No diabetes
+22,223,75,85,"2,6",22,female,62,137,"25,1",120,70,28,35,"0,8",No diabetes
+23,136,81,51,"2,7",22,female,66,160,"25,8",105,85,35,40,"0,88",No diabetes
+24,175,91,42,"4,2",23,female,65,235,"39,1",110,80,44,50,"0,88",No diabetes
+25,230,86,37,"6,2",23,male,71,277,"38,6",150,99,50,49,"1,02",No diabetes
+26,147,78,42,"3,5",23,female,61,185,35,127,71,43,47,"0,91",No diabetes
+27,229,91,43,"5,3",23,male,72,180,"24,4",110,78,34,41,"0,83",No diabetes
+28,179,75,36,5,23,female,65,183,"30,4",120,80,43,45,"0,96",No diabetes
+29,185,76,58,"3,2",23,male,76,164,20,124,78,32,40,"0,8",No diabetes
+30,164,86,40,"4,1",23,female,69,245,"36,2",126,75,44,47,"0,94",No diabetes
+31,228,66,45,"5,1",24,female,61,113,"21,3",100,70,33,38,"0,87",No diabetes
+32,199,87,63,"3,2",25,male,66,118,19,120,78,32,34,"0,94",No diabetes
+33,134,101,36,"3,7",25,female,63,245,"43,4",142,78,47,58,"0,81",No diabetes
+34,169,104,58,"2,9",25,female,60,154,"30,1",140,95,40,42,"0,95",No diabetes
+35,227,98,66,"3,4",25,male,71,162,"22,6",123,82,35,39,"0,9",No diabetes
+36,149,138,50,3,26,female,62,174,"31,8",148,92,38,46,"0,83",No diabetes
+37,155,58,69,"2,2",26,male,73,174,23,110,76,30,35,"0,86",No diabetes
+38,179,90,60,3,26,female,60,130,"25,4",138,84,32,40,"0,8",No diabetes
+39,283,83,74,"3,8",26,male,72,227,"30,8",158,104,41,44,"0,93",No diabetes
+40,228,79,37,"6,2",26,male,72,259,"35,1",122,90,48,49,"0,98",No diabetes
+41,220,60,66,"3,3",26,male,70,150,"21,5",136,88,33,39,"0,85",Diabetes
+42,170,76,60,"2,8",27,female,63,119,"21,1",122,86,28,37,"0,76",No diabetes
+43,201,100,46,"4,4",27,female,65,145,"24,1",121,75,32,35,"0,91",No diabetes
+44,238,75,36,"6,6",27,female,60,170,"33,2",130,80,35,41,"0,85",No diabetes
+45,190,92,44,"4,3",27,female,65,210,"34,9",150,106,39,47,"0,83",No diabetes
+46,203,94,62,"3,3",27,female,67,209,"32,7",140,80,34,43,"0,79",No diabetes
+47,226,100,65,"3,5",27,male,69,289,"42,7",130,100,48,51,"0,94",No diabetes
+48,204,62,70,"2,9",27,female,67,185,29,110,90,35,44,"0,8",No diabetes
+49,166,77,68,"2,4",27,male,72,141,"19,1",110,58,33,38,"0,87",No diabetes
+50,241,92,40,6,27,female,63,179,"31,7",120,75,40,42,"0,95",No diabetes
+51,164,94,58,"2,8",28,female,67,180,"28,2",128,94,39,43,"0,91",No diabetes
+52,214,111,59,"3,6",28,male,68,204,31,130,90,40,41,"0,98",No diabetes
+53,151,74,47,"3,2",28,male,69,130,"19,2",135,75,29,35,"0,83",No diabetes
+54,184,99,36,"5,1",28,male,67,154,"24,1",124,94,35,38,"0,92",No diabetes
+55,168,69,45,"3,7",28,female,63,200,"35,4",111,65,42,46,"0,91",No diabetes
+56,146,77,60,"2,4",28,female,64,126,"21,6",120,90,28,32,"0,88",No diabetes
+57,189,96,47,4,28,female,64,200,"34,3",136,52,38,45,"0,84",No diabetes
+58,132,83,40,"3,3",28,female,68,225,"34,2",136,86,41,52,"0,79",No diabetes
+59,179,77,50,"3,6",29,male,68,170,"25,8",122,68,38,39,"0,97",No diabetes
+60,135,88,34,4,29,female,65,123,"20,5",118,61,26,37,"0,7",No diabetes
+61,163,69,48,"3,4",29,female,62,99,"18,1",125,60,30,36,"0,83",No diabetes
+62,204,71,55,"3,7",29,female,64,120,"20,6",110,70,33,38,"0,87",No diabetes
+63,165,97,24,"6,9",29,female,64,218,"37,4",112,68,46,48,"0,96",No diabetes
+64,181,101,44,"4,1",29,male,68,180,"27,4",130,78,38,42,"0,9",No diabetes
+65,194,269,38,"5,1",29,female,69,167,"24,7",120,70,33,40,"0,83",Diabetes
+66,158,74,64,"2,5",30,female,62,142,26,108,68,32,34,"0,94",No diabetes
+67,160,82,41,"3,9",30,female,63,143,"25,3",172,124,33,40,"0,83",No diabetes
+68,181,77,46,"3,9",30,female,66,257,"41,5",162,108,47,55,"0,85",No diabetes
+69,144,81,28,"5,1",30,male,72,165,"22,4",118,78,31,38,"0,82",No diabetes
+70,182,74,44,"4,1",30,female,62,125,"22,9",132,80,31,39,"0,79",No diabetes
+71,145,84,54,"2,7",30,female,65,165,"27,5",102,56,33,42,"0,79",No diabetes
+72,195,92,41,"4,8",30,male,69,191,"28,2",161,112,46,49,"0,94",No diabetes
+73,207,75,44,"4,7",30,male,72,180,"24,4",118,62,35,41,"0,85",No diabetes
+74,192,124,31,"5,6",30,male,72,250,"33,9",142,79,43,51,"0,84",No diabetes
+75,183,69,51,"3,6",31,female,66,190,"30,7",125,70,41,47,"0,87",No diabetes
+76,176,92,55,"3,2",31,female,62,145,"26,5",110,72,36,42,"0,86",No diabetes
+77,163,83,57,"2,9",31,female,65,120,20,136,86,29,40,"0,73",No diabetes
+78,188,77,45,"4,2",31,female,67,227,"35,5",122,70,47,53,"0,89",No diabetes
+79,209,89,43,"4,9",31,female,67,160,"25,1",108,58,30,44,"0,68",No diabetes
+80,179,77,72,"2,5",31,male,66,145,"23,4",131,79,33,38,"0,87",No diabetes
+81,293,85,94,"3,1",31,female,67,200,"31,3",110,90,41,42,"0,98",No diabetes
+82,305,91,44,"6,9",31,male,71,211,"29,4",100,60,40,45,"0,89",No diabetes
+83,191,155,58,"3,3",31,female,62,237,"43,3",140,87,53,56,"0,95",Diabetes
+84,155,81,70,"2,2",32,female,65,151,"25,1",120,68,33,40,"0,83",No diabetes
+85,179,85,52,"3,4",32,female,62,179,"32,7",140,96,37,47,"0,79",No diabetes
+86,176,90,34,"5,2",32,female,63,252,"44,6",100,72,45,58,"0,78",No diabetes
+87,244,101,36,"6,8",32,male,70,212,"30,4",132,90,39,44,"0,89",No diabetes
+88,213,83,47,"4,5",33,female,65,157,"26,1",130,90,37,41,"0,9",No diabetes
+89,217,87,40,"5,4",33,female,62,186,34,140,90,42,46,"0,91",No diabetes
+90,151,85,48,"3,1",33,male,69,308,"45,5",110,90,52,58,"0,9",No diabetes
+91,168,82,44,"3,8",33,female,66,118,19,98,66,29,35,"0,83",No diabetes
+92,231,84,91,"2,5",33,male,69,163,"24,1",140,70,35,38,"0,92",No diabetes
+93,262,93,43,"6,1",33,female,63,170,"30,1",110,68,33,46,"0,72",No diabetes
+94,179,70,52,"3,4",34,male,72,170,"23,1",138,82,31,39,"0,79",No diabetes
+95,300,65,59,"5,1",34,female,65,160,"26,6",120,60,40,47,"0,85",No diabetes
+96,248,94,69,"3,6",34,male,71,190,"26,5",132,86,36,42,"0,86",No diabetes
+97,217,88,40,"5,4",34,male,73,219,"28,9",145,100,41,42,"0,98",No diabetes
+98,224,71,42,"5,3",34,female,60,165,"32,2",135,80,34,46,"0,74",No diabetes
+99,171,85,61,"2,8",34,female,63,164,29,120,80,34,43,"0,79",No diabetes
+100,174,90,36,"4,8",34,male,71,210,"29,3",142,92,37,43,"0,86",No diabetes
+101,194,86,67,"2,9",35,male,66,159,"25,7",115,64,31,35,"0,89",No diabetes
+102,150,80,38,"3,9",35,male,73,179,"23,6",138,92,32,37,"0,86",No diabetes
+103,337,85,62,"5,4",35,male,72,189,"25,6",124,84,36,44,"0,82",No diabetes
+104,239,97,55,"4,3",35,male,74,170,"21,8",122,62,32,38,"0,84",No diabetes
+105,218,126,32,"6,8",35,male,69,169,25,139,90,39,41,"0,95",No diabetes
+106,122,82,43,"2,8",36,female,71,183,"25,5",110,80,41,45,"0,91",No diabetes
+107,225,83,42,"5,4",36,male,67,192,"30,1",149,89,40,42,"0,95",No diabetes
+108,160,71,44,"3,6",36,female,64,185,"31,8",110,80,39,45,"0,87",No diabetes
+109,191,76,30,"6,4",36,male,69,183,27,100,66,36,40,"0,9",No diabetes
+110,199,153,77,"2,6",36,female,66,255,"41,2",118,66,47,52,"0,9",No diabetes
+111,197,92,46,"4,3",36,female,64,136,"23,3",128,80,32,37,"0,86",No diabetes
+112,179,81,35,"5,1",36,female,63,125,"22,1",110,76,33,36,"0,92",No diabetes
+113,186,74,76,"2,4",36,male,69,150,"22,1",138,82,31,38,"0,82",No diabetes
+114,178,78,59,3,36,male,70,161,"23,1",130,79,34,40,"0,85",No diabetes
+115,224,85,30,"7,5",36,male,69,205,"30,3",150,99,37,41,"0,9",No diabetes
+116,194,81,36,"5,4",36,male,64,126,"21,6",110,76,30,34,"0,88",No diabetes
+117,347,197,42,"8,3",36,male,70,277,"39,7",140,86,51,49,"1,04",No diabetes
+118,245,119,26,"9,4",36,male,66,179,"28,9",150,92,37,42,"0,88",Diabetes
+119,227,75,44,"5,2",37,male,59,170,"34,3",140,84,34,39,"0,87",No diabetes
+120,192,89,30,"6,4",37,male,71,195,"27,2",136,96,36,43,"0,84",No diabetes
+121,215,64,84,"2,6",37,female,59,148,"29,9",140,100,32,42,"0,76",No diabetes
+122,214,67,47,"4,6",37,female,64,145,"24,9",108,76,34,42,"0,81",No diabetes
+123,243,52,59,"4,1",37,female,64,233,40,110,82,49,57,"0,86",No diabetes
+124,156,86,34,"4,6",37,female,67,212,"33,2",122,74,48,51,"0,94",No diabetes
+125,179,85,50,"3,6",37,male,66,136,"21,9",190,94,33,39,"0,85",No diabetes
+126,209,91,36,"5,8",37,male,70,262,"37,6",130,94,42,48,"0,88",No diabetes
+127,232,87,30,"7,7",37,male,68,252,"38,3",140,95,43,47,"0,91",No diabetes
+128,212,88,36,"5,9",37,female,64,160,"27,5",124,82,37,45,"0,82",No diabetes
+129,199,130,48,"4,1",37,female,61,203,"38,4",136,84,42,51,"0,82",No diabetes
+130,145,85,29,5,38,female,60,125,"24,4",132,82,31,35,"0,89",No diabetes
+131,206,90,38,"5,4",38,female,69,167,"24,7",138,90,36,47,"0,77",No diabetes
+132,147,86,34,"4,3",38,male,69,205,"30,3",130,96,39,41,"0,95",No diabetes
+133,302,81,57,"5,3",38,female,67,222,"34,8",128,82,41,51,"0,8",No diabetes
+134,138,95,40,"3,5",38,female,60,138,"26,9",140,90,31,39,"0,79",No diabetes
+135,215,128,34,"6,3",38,female,58,195,"40,8",102,68,42,50,"0,84",No diabetes
+136,159,88,43,"3,7",38,male,68,169,"25,7",138,79,34,40,"0,85",No diabetes
+137,268,90,48,"5,6",38,female,63,181,"32,1",142,100,38,46,"0,83",No diabetes
+138,251,118,38,"6,6",38,female,64,248,"42,6",110,80,49,58,"0,84",No diabetes
+139,216,155,30,"7,2",38,male,68,145,22,110,60,34,37,"0,92",No diabetes
+140,203,299,43,"4,7",38,female,69,288,"42,5",136,83,48,55,"0,87",Diabetes
+141,181,83,44,"4,1",39,female,66,255,"41,2",140,98,46,54,"0,85",No diabetes
+142,239,85,63,"3,8",39,male,60,144,"28,1",162,90,33,42,"0,79",No diabetes
+143,200,56,51,"3,9",40,female,62,105,"19,2",125,64,26,33,"0,79",No diabetes
+144,211,98,40,"5,3",40,female,68,179,"27,2",110,76,37,43,"0,86",No diabetes
+145,152,103,32,"4,8",40,female,52,187,"48,6",148,82,38,49,"0,78",No diabetes
+146,173,83,37,"4,7",40,female,62,130,"23,8",122,76,37,38,"0,97",No diabetes
+147,215,72,42,"5,1",40,male,70,189,"27,1",180,122,37,39,"0,95",No diabetes
+148,219,105,63,"3,5",40,female,62,153,28,106,82,36,44,"0,82",No diabetes
+149,180,76,46,"3,9",40,female,64,146,"25,1",128,82,37,43,"0,86",No diabetes
+150,214,77,48,"4,5",40,male,72,222,"30,1",120,84,40,44,"0,91",No diabetes
+151,171,92,54,"3,2",40,male,71,214,"29,8",138,94,41,39,"1,05",No diabetes
+152,183,79,46,4,40,female,59,165,"33,3",135,84,37,43,"0,86",No diabetes
+153,184,92,36,"5,1",40,female,63,285,"50,5",142,98,50,60,"0,83",No diabetes
+154,180,84,69,"2,6",40,female,68,264,"40,1",142,98,43,54,"0,8",No diabetes
+155,191,74,33,"5,8",40,male,72,270,"36,6",136,70,45,49,"0,92",No diabetes
+156,218,87,38,"5,7",40,male,73,200,"26,4",120,76,38,41,"0,93",No diabetes
+157,169,85,51,"3,3",40,female,65,180,30,106,82,40,44,"0,91",No diabetes
+158,267,133,34,"7,9",40,female,59,204,"41,2",118,69,40,47,"0,85",Diabetes
+159,234,78,54,"4,3",41,male,67,183,"28,7",122,96,38,40,"0,95",No diabetes
+160,206,112,33,"6,2",41,female,62,184,"33,7",104,80,39,44,"0,89",No diabetes
+161,184,79,39,"4,7",41,male,69,154,"22,7",136,96,34,39,"0,87",No diabetes
+162,178,64,52,"3,4",41,female,65,188,"31,3",130,76,35,46,"0,76",No diabetes
+163,179,80,92,"1,9",41,female,72,118,16,144,112,28,36,"0,78",No diabetes
+164,225,84,82,"2,7",41,male,71,156,"21,8",150,80,31,40,"0,78",No diabetes
+165,189,84,46,"4,1",41,female,63,153,"27,1",130,80,32,40,"0,8",No diabetes
+166,199,76,52,"3,8",41,female,63,197,"34,9",120,78,41,48,"0,85",No diabetes
+167,241,86,63,"3,8",41,female,59,139,"28,1",112,72,29,39,"0,74",No diabetes
+168,170,106,42,4,41,female,61,110,"20,8",103,64,29,30,"0,97",No diabetes
+169,269,59,66,"4,1",41,male,67,191,"29,9",130,73,38,41,"0,93",No diabetes
+170,269,73,34,"7,9",41,female,62,160,"29,3",126,90,39,41,"0,95",No diabetes
+171,270,73,40,"6,8",42,male,66,185,"29,9",146,94,39,41,"0,95",No diabetes
+172,172,101,46,"3,7",42,female,65,165,"27,5",118,68,33,45,"0,73",No diabetes
+173,193,77,45,"4,3",42,female,75,186,"23,2",125,90,37,46,"0,8",No diabetes
+174,199,81,36,"5,5",42,female,67,235,"36,8",178,100,47,52,"0,9",No diabetes
+175,177,101,36,"4,9",42,female,65,174,29,146,94,37,40,"0,93",No diabetes
+176,191,81,53,"3,6",42,female,61,156,"29,5",138,84,36,42,"0,86",No diabetes
+177,208,122,51,"4,1",42,female,62,141,"25,8",118,78,33,40,"0,83",No diabetes
+178,188,84,46,"4,1",43,female,66,152,"24,5",122,80,37,41,"0,9",No diabetes
+179,243,74,42,"5,8",43,female,64,239,41,128,90,48,53,"0,91",No diabetes
+180,173,85,58,3,43,female,69,210,31,130,75,44,47,"0,94",No diabetes
+181,162,76,40,"4,1",43,male,67,216,"33,8",100,70,41,44,"0,93",No diabetes
+182,322,87,92,"3,5",43,female,56,120,"26,9",120,98,32,41,"0,78",No diabetes
+183,254,84,52,"4,9",43,female,62,145,"26,5",125,70,31,38,"0,82",No diabetes
+184,160,100,36,"4,4",43,female,64,140,24,180,110,37,40,"0,93",No diabetes
+185,192,109,44,"4,4",43,female,64,325,"55,8",141,79,53,62,"0,85",No diabetes
+186,197,120,37,"5,3",43,male,71,179,25,146,98,37,44,"0,84",No diabetes
+187,237,87,41,"5,8",43,female,64,181,"31,1",104,90,36,46,"0,78",No diabetes
+188,190,84,44,"4,3",43,female,62,163,"29,8",135,88,40,45,"0,89",No diabetes
+189,190,228,57,"3,3",43,female,65,198,"32,9",110,64,40,49,"0,82",Diabetes
+190,202,84,33,"6,1",44,male,68,157,"23,9",125,80,33,37,"0,89",No diabetes
+191,244,101,39,"6,3",44,male,71,168,"23,4",140,89,36,39,"0,92",No diabetes
+192,168,101,59,"2,8",44,female,64,160,"27,5",130,88,40,43,"0,93",No diabetes
+193,260,67,46,"5,7",44,female,62,159,"29,1",140,94,36,43,"0,84",No diabetes
+194,214,87,35,"6,1",44,female,64,190,"32,6",140,75,38,44,"0,86",No diabetes
+195,207,187,46,"4,5",44,female,67,201,"31,5",150,74,46,49,"0,94",Diabetes
+196,203,71,78,"2,6",45,male,66,115,"18,6",135,88,30,34,"0,88",No diabetes
+197,189,80,40,"4,7",45,male,69,190,"28,1",140,75,39,44,"0,89",No diabetes
+198,216,109,86,"2,5",45,female,67,147,23,140,102,32,38,"0,84",No diabetes
+199,233,92,39,6,45,female,64,167,"28,7",124,86,39,44,"0,89",No diabetes
+200,177,87,49,"3,6",45,male,69,166,"24,5",160,80,34,40,"0,85",No diabetes
+201,191,83,88,"2,2",45,female,67,151,"23,6",130,90,33,38,"0,87",No diabetes
+202,142,155,25,"5,7",45,male,69,204,"30,1",165,115,40,43,"0,93",No diabetes
+203,219,130,44,5,45,male,67,218,"34,1",172,110,41,45,"0,91",Diabetes
+204,190,107,32,"5,9",46,male,72,205,"27,8",145,88,46,49,"0,94",No diabetes
+205,203,82,56,"3,6",46,female,62,121,"22,1",118,59,29,38,"0,76",No diabetes
+206,207,102,43,"4,8",46,female,63,179,"31,7",212,114,38,46,"0,83",No diabetes
+207,242,108,53,"4,6",46,female,62,183,"33,5",130,86,37,45,"0,82",No diabetes
+208,183,81,60,"3,1",47,female,66,186,30,140,97,39,44,"0,89",No diabetes
+209,234,65,76,"3,1",47,male,67,230,36,137,100,45,46,"0,98",No diabetes
+210,118,95,39,3,47,female,64,123,"21,1",140,76,30,36,"0,83",No diabetes
+211,266,82,54,"4,9",47,male,68,142,"21,6",118,78,35,39,"0,9",No diabetes
+212,223,90,48,"4,6",47,female,65,232,"38,6",120,86,46,54,"0,85",No diabetes
+213,245,120,39,"6,3",47,female,63,156,"27,6",142,102,35,39,"0,9",Diabetes
+214,173,225,31,"5,6",47,male,73,260,"34,3",150,98,42,47,"0,89",Diabetes
+215,172,117,56,"3,1",48,female,63,170,"30,1",130,82,35,42,"0,83",No diabetes
+216,190,74,50,"3,8",48,male,68,100,"15,2",120,85,27,33,"0,82",No diabetes
+217,134,105,42,"3,2",48,male,70,173,"24,8",178,120,36,40,"0,9",No diabetes
+218,268,85,51,"5,3",48,male,70,120,"17,2",150,105,32,35,"0,91",No diabetes
+219,209,87,34,"6,1",48,female,63,121,"21,4",111,62,32,38,"0,84",No diabetes
+220,201,81,87,"2,3",48,female,68,146,"22,2",145,95,32,41,"0,78",No diabetes
+221,204,89,56,"3,6",48,male,68,196,"29,8",170,96,38,42,"0,9",No diabetes
+222,307,87,58,"5,3",49,male,67,181,"28,3",120,80,41,42,"0,98",No diabetes
+223,189,75,72,"2,6",49,female,62,205,"37,5",120,80,40,49,"0,82",No diabetes
+224,160,196,33,"4,8",49,male,71,266,"37,1",150,98,49,45,"1,09",Diabetes
+225,237,233,58,"4,1",49,female,62,189,"34,6",130,90,43,47,"0,91",Diabetes
+226,158,91,48,"3,3",50,male,71,180,"25,1",136,90,36,40,"0,9",No diabetes
+227,255,78,38,"6,7",50,female,65,183,"30,4",130,100,37,43,"0,86",No diabetes
+228,196,115,62,"3,2",50,male,67,140,"21,9",176,110,35,37,"0,95",No diabetes
+229,185,67,59,"3,1",50,female,64,228,"39,1",142,90,42,54,"0,78",No diabetes
+230,293,115,54,"5,4",50,male,71,170,"23,7",131,75,34,39,"0,87",No diabetes
+231,188,88,51,"3,7",50,female,61,147,"27,8",160,66,34,41,"0,83",No diabetes
+232,174,173,34,"5,1",50,male,70,263,"37,7",159,99,51,64,"0,8",No diabetes
+233,158,91,31,"5,1",50,male,70,215,"30,8",138,89,40,45,"0,89",No diabetes
+234,181,255,26,7,50,male,71,320,"44,6",140,86,56,49,"1,14",Diabetes
+235,140,385,31,"4,5",50,male,69,172,"25,4",138,66,37,41,"0,9",Diabetes
+236,192,85,69,"2,8",51,male,65,146,"24,3",130,110,33,36,"0,92",No diabetes
+237,284,89,54,"5,3",51,female,63,154,"27,3",140,100,32,43,"0,74",No diabetes
+238,222,82,87,"2,6",51,female,66,110,"17,8",150,110,28,37,"0,76",No diabetes
+239,249,81,28,"8,9",51,female,65,200,"33,3",122,90,43,46,"0,93",No diabetes
+240,212,79,49,"4,3",51,female,65,145,"24,1",230,120,38,42,"0,9",No diabetes
+241,215,110,36,6,51,female,67,282,"44,2",142,78,52,59,"0,88",Diabetes
+242,218,182,54,4,51,female,66,215,"34,7",139,69,42,53,"0,79",Diabetes
+243,443,185,23,"19,3",51,female,70,235,"33,7",158,98,43,48,"0,9",Diabetes
+244,218,68,46,"4,7",52,female,62,170,"31,1",142,79,40,43,"0,93",No diabetes
+245,171,97,69,"2,5",52,male,71,159,"22,2",125,72,33,39,"0,85",No diabetes
+246,255,83,90,"2,8",52,male,70,120,"17,2",170,110,30,33,"0,91",No diabetes
+247,182,85,43,"4,2",52,male,68,139,"21,1",130,90,29,35,"0,83",No diabetes
+248,206,83,68,3,52,male,69,153,"22,6",140,98,36,40,"0,9",No diabetes
+249,261,101,83,"3,1",52,female,64,198,34,152,92,42,49,"0,86",No diabetes
+250,204,57,74,"2,8",52,male,75,142,"17,7",140,90,31,35,"0,89",No diabetes
+251,196,120,67,"2,9",52,female,62,147,"26,9",144,94,34,42,"0,81",Diabetes
+252,219,78,67,"3,3",53,female,64,179,"30,7",135,100,39,47,"0,83",No diabetes
+253,273,94,49,"5,6",53,female,64,174,"29,9",160,96,34,43,"0,79",No diabetes
+254,225,74,36,"6,3",53,female,63,182,"32,2",126,80,38,46,"0,83",No diabetes
+255,185,84,52,"3,6",53,female,61,145,"27,4",147,72,37,40,"0,93",No diabetes
+256,242,297,34,"7,1",53,male,69,216,"31,9",142,96,43,45,"0,96",Diabetes
+257,296,369,46,"6,4",53,male,69,173,"25,5",138,94,35,39,"0,9",Diabetes
+258,228,76,53,"4,3",54,male,66,170,"27,4",121,62,36,41,"0,88",No diabetes
+259,194,87,65,3,54,male,69,129,19,170,96,30,37,"0,81",No diabetes
+260,216,79,46,"4,7",54,female,65,138,23,132,80,33,39,"0,85",No diabetes
+261,240,96,57,"4,2",54,female,65,175,"29,1",152,100,37,43,"0,86",No diabetes
+262,148,193,14,"10,6",54,female,67,165,"25,8",140,65,42,42,1,No diabetes
+263,271,103,90,3,55,female,63,114,"20,2",180,105,30,37,"0,81",No diabetes
+264,204,94,54,"3,8",55,female,66,202,"32,6",140,90,43,47,"0,91",No diabetes
+265,174,93,77,"2,3",55,male,70,140,"20,1",118,86,32,33,"0,97",No diabetes
+266,157,74,47,"3,3",55,female,66,219,"35,3",150,82,43,52,"0,83",No diabetes
+267,263,89,40,"6,6",55,female,63,202,"35,8",108,72,45,50,"0,9",No diabetes
+268,160,122,41,"3,9",55,female,67,223,"34,9",136,83,43,48,"0,9",No diabetes
+269,179,236,63,"2,8",55,male,75,186,"23,2",122,74,38,38,1,Diabetes
+270,208,95,32,"6,5",56,male,68,183,"27,8",131,75,36,39,"0,92",No diabetes
+271,129,110,42,"3,1",56,male,74,151,"19,4",140,75,34,38,"0,89",No diabetes
+272,219,173,31,"7,1",56,female,65,197,"32,8",100,50,41,50,"0,82",Diabetes
+273,404,206,33,"12,2",56,male,69,159,"23,5",162,88,38,39,"0,97",Diabetes
+274,138,81,45,"3,1",57,male,73,164,"21,6",148,81,31,37,"0,84",No diabetes
+275,173,80,57,3,57,male,71,145,"20,2",124,64,31,36,"0,86",No diabetes
+276,209,176,55,"3,8",57,female,61,150,"28,3",115,68,36,39,"0,92",Diabetes
+277,228,92,37,"6,2",58,female,61,256,"48,4",190,92,49,57,"0,86",No diabetes
+278,227,85,26,"8,7",58,male,70,211,"30,3",144,82,38,43,"0,88",No diabetes
+279,201,106,53,"3,8",58,male,66,215,"34,7",186,102,46,44,"1,05",No diabetes
+280,251,94,36,7,58,female,63,154,"27,3",174,75,38,41,"0,93",No diabetes
+281,211,48,34,"6,2",58,male,67,177,"27,7",162,78,38,43,"0,88",No diabetes
+282,115,239,36,"3,2",58,male,69,200,"29,5",125,69,30,37,"0,81",Diabetes
+283,204,113,35,"5,8",59,male,73,187,"24,7",148,76,38,37,"1,03",No diabetes
+284,215,97,46,"4,7",59,female,63,176,"31,2",140,70,34,44,"0,77",No diabetes
+285,221,126,48,"4,6",59,female,62,177,"32,4",130,78,39,45,"0,87",No diabetes
+286,220,95,58,"3,8",59,female,66,138,"22,3",138,80,32,38,"0,84",No diabetes
+287,193,248,24,8,59,female,66,189,"30,5",140,90,38,45,"0,84",Diabetes
+288,195,108,46,"4,2",59,female,67,172,"26,9",150,102,38,43,"0,88",Diabetes
+289,219,112,73,3,59,male,66,170,"27,4",146,92,37,40,"0,93",Diabetes
+290,289,267,38,"7,6",59,male,68,169,"25,7",142,79,36,38,"0,95",Diabetes
+291,198,92,62,"3,2",60,male,70,163,"23,4",126,78,36,40,"0,9",No diabetes
+292,192,56,42,"4,6",60,female,62,134,"24,5",130,70,31,40,"0,78",No diabetes
+293,242,82,54,"4,5",60,female,65,156,26,130,90,39,45,"0,87",No diabetes
+294,235,102,42,"5,6",60,male,69,186,"27,5",148,98,40,42,"0,95",No diabetes
+295,277,119,62,"4,5",60,female,61,128,"24,2",140,86,33,39,"0,85",No diabetes
+296,162,90,46,"3,5",60,female,63,121,"21,4",110,64,32,34,"0,94",No diabetes
+297,318,270,108,"2,9",60,female,65,167,"27,8",132,72,38,44,"0,86",No diabetes
+298,279,270,40,7,60,female,68,224,"34,1",174,90,48,50,"0,96",Diabetes
+299,128,223,24,"5,3",60,male,67,196,"30,7",110,68,42,43,"0,98",Diabetes
+300,203,90,51,4,60,female,59,123,"24,8",130,72,36,41,"0,88",Diabetes
+301,143,91,37,"3,9",61,female,65,220,"36,6",160,92,40,50,"0,8",No diabetes
+302,300,103,44,"6,8",61,female,67,169,"26,5",138,78,40,44,"0,91",No diabetes
+303,206,94,44,"4,7",61,female,63,199,"35,2",180,96,41,47,"0,87",No diabetes
+304,182,85,37,"4,9",61,female,69,174,"25,7",176,86,49,43,"1,14",No diabetes
+305,198,86,66,3,61,male,74,152,"19,5",138,76,33,38,"0,87",No diabetes
+306,211,225,29,"7,3",61,female,63,144,"25,5",190,100,40,42,"0,95",Diabetes
+307,265,330,34,"7,8",61,male,74,191,"24,5",170,88,39,41,"0,95",Diabetes
+308,204,128,61,"3,3",62,male,68,180,"27,4",141,81,38,41,"0,93",No diabetes
+309,169,95,29,"5,8",62,male,66,251,"40,5",118,72,50,47,"1,06",No diabetes
+310,236,102,36,"6,6",62,male,76,160,"19,5",150,80,35,39,"0,9",No diabetes
+311,235,109,59,4,62,female,63,290,"51,4",175,80,55,62,"0,89",Diabetes
+312,196,206,41,"4,8",62,female,65,196,"32,6",178,90,46,51,"0,9",Diabetes
+313,180,92,34,"5,3",63,male,69,169,25,145,72,35,39,"0,9",No diabetes
+314,194,54,57,"3,4",63,male,70,181,26,184,76,37,42,"0,88",No diabetes
+315,194,80,34,"5,7",63,male,73,175,"23,1",131,88,34,39,"0,87",No diabetes
+316,212,82,68,"3,1",63,male,70,161,"23,1",180,110,37,40,"0,93",No diabetes
+317,293,87,120,"2,4",63,female,64,179,"30,7",142,80,47,45,"1,04",No diabetes
+318,194,95,36,"5,4",63,female,58,210,"43,9",140,100,44,53,"0,83",No diabetes
+319,277,88,45,"6,2",63,female,64,223,"38,3",220,100,45,54,"0,83",No diabetes
+320,157,91,34,"4,6",63,male,69,166,"24,5",106,82,39,38,"1,03",No diabetes
+321,283,145,39,"7,3",63,female,61,200,"37,8",190,110,44,48,"0,92",Diabetes
+322,215,119,44,"3,9",63,female,63,158,28,160,68,34,42,"0,81",Diabetes
+323,342,251,48,"7,1",63,female,65,201,"33,4",178,88,45,46,"0,98",Diabetes
+324,202,81,55,"3,7",64,female,62,167,"30,5",190,118,44,47,"0,94",No diabetes
+325,255,100,34,"7,5",64,male,68,227,"34,5",134,74,44,47,"0,94",No diabetes
+326,181,177,24,"7,5",64,male,71,225,"31,4",130,66,44,47,"0,94",Diabetes
+327,249,90,28,"8,9",64,male,68,183,"27,8",138,80,44,41,"1,07",Diabetes
+328,249,197,44,"5,7",64,female,63,159,"28,2",151,85,33,41,"0,8",Diabetes
+329,219,106,50,"4,4",65,female,63,233,"41,3",140,90,40,53,"0,75",No diabetes
+330,229,95,74,"3,1",65,female,62,151,"27,6",125,64,37,42,"0,88",No diabetes
+331,212,97,45,"4,7",65,female,61,187,"35,3",158,94,43,47,"0,91",No diabetes
+332,170,67,33,"5,2",65,male,69,182,"26,9",140,65,42,39,"1,08",No diabetes
+333,159,172,28,"5,7",65,male,70,181,26,142,81,43,49,"0,88",Diabetes
+334,224,341,33,"6,8",65,male,67,197,"30,9",160,80,42,43,"0,98",Diabetes
+335,263,82,92,"2,9",66,female,66,121,"19,5",104,64,31,33,"0,94",No diabetes
+336,184,76,42,"4,4",66,male,74,185,"23,8",130,75,40,41,"0,98",No diabetes
+337,281,92,41,"6,9",66,female,62,185,"33,8",158,88,48,44,"1,09",No diabetes
+338,221,120,83,"2,7",66,female,64,130,"22,3",110,64,31,38,"0,82",No diabetes
+339,188,174,24,"7,8",66,male,68,210,"31,9",160,78,45,48,"0,94",No diabetes
+340,246,104,62,4,66,female,66,189,"30,5",200,94,45,46,"0,98",Diabetes
+341,204,173,37,"5,5",66,male,67,146,"22,9",138,78,36,48,"0,75",Diabetes
+342,78,93,12,"6,5",67,male,67,119,"18,6",110,50,33,38,"0,87",No diabetes
+343,206,85,46,"4,5",67,male,67,178,"27,9",119,68,37,41,"0,9",No diabetes
+344,174,125,44,4,67,male,68,198,"30,1",119,72,36,43,"0,84",No diabetes
+345,254,121,39,"6,5",67,male,68,167,"25,4",161,118,36,39,"0,92",Diabetes
+346,198,118,46,"4,3",68,female,63,124,22,130,70,32,38,"0,84",No diabetes
+347,143,371,46,"3,1",68,male,67,158,"24,7",138,82,37,43,"0,86",No diabetes
+348,207,77,46,"4,5",68,male,55,130,"30,2",199,115,29,33,"0,88",No diabetes
+349,236,111,82,"2,9",68,female,61,119,"22,5",142,96,29,37,"0,78",No diabetes
+350,260,68,60,"4,3",69,female,59,179,"36,1",158,98,45,48,"0,94",No diabetes
+351,242,74,55,"4,4",70,female,66,200,"32,3",140,65,41,47,"0,87",No diabetes
+352,186,97,50,"3,7",70,male,67,178,"27,9",148,88,42,41,"1,02",No diabetes
+353,182,206,43,"4,2",70,male,69,214,"31,6",158,90,45,48,"0,94",Diabetes
+354,289,111,50,"5,8",70,female,60,220,43,126,80,51,54,"0,94",Diabetes
+355,231,70,110,"2,1",71,female,63,155,"27,5",150,78,33,41,"0,8",No diabetes
+356,199,85,59,"3,4",71,male,69,171,"25,2",136,86,38,40,"0,95",No diabetes
+357,228,115,61,"3,7",71,female,63,244,"43,2",170,92,48,51,"0,94",No diabetes
+358,213,203,75,"2,8",71,female,63,165,"29,2",150,80,34,42,"0,81",Diabetes
+359,204,120,44,"4,6",72,male,65,167,"27,8",140,72,45,46,"0,98",No diabetes
+360,205,83,42,"4,9",72,female,61,180,34,170,90,39,47,"0,83",No diabetes
+361,213,76,40,"5,3",72,female,59,137,"27,7",130,60,40,40,1,No diabetes
+362,207,71,41,5,72,male,70,180,"25,8",138,88,39,40,"0,98",Diabetes
+363,235,106,37,"6,4",73,male,65,183,"30,4",134,78,43,46,"0,93",No diabetes
+364,237,118,45,"5,3",73,female,64,174,"29,9",162,75,38,44,"0,86",Diabetes
+365,306,92,56,"5,5",74,male,69,184,"27,2",140,72,39,41,"0,95",No diabetes
+366,223,88,42,"5,3",74,female,62,165,"30,2",250,100,41,46,"0,89",No diabetes
+367,296,262,60,"4,9",74,female,63,183,"32,4",159,99,42,48,"0,88",Diabetes
+368,205,79,32,"6,4",75,male,69,204,"30,1",136,90,44,42,"1,05",No diabetes
+369,254,342,37,"6,9",75,male,68,210,"31,9",151,87,44,45,"0,98",Diabetes
+370,159,100,54,"2,9",76,male,66,188,"30,3",116,53,40,41,"0,98",No diabetes
+371,196,82,58,"3,4",76,male,65,154,"25,6",158,78,37,41,"0,9",No diabetes
+372,173,131,69,"2,5",76,female,61,102,"19,3",160,60,31,33,"0,94",No diabetes
+373,219,112,73,3,76,male,64,105,18,125,82,29,33,"0,88",No diabetes
+374,209,113,65,"3,2",76,female,60,143,"27,9",156,78,35,40,"0,88",Diabetes
+375,215,80,100,"2,2",78,male,65,109,"18,1",170,88,33,34,"0,97",No diabetes
+376,210,81,81,"2,6",78,male,66,145,"23,4",110,70,38,39,"0,97",No diabetes
+377,224,98,44,"5,1",78,female,63,160,"28,3",150,81,36,45,"0,8",No diabetes
+378,195,171,29,"6,7",78,male,66,172,"27,8",130,82,40,40,1,No diabetes
+379,235,91,37,"6,4",79,female,65,134,"22,3",142,70,34,38,"0,89",No diabetes
+380,292,235,55,"5,3",79,male,70,165,"23,7",170,90,39,41,"0,95",Diabetes
+381,157,92,47,"3,3",80,male,71,212,"29,6",156,88,47,48,"0,98",No diabetes
+382,252,161,87,"2,9",80,female,62,162,"29,6",160,100,44,41,"1,07",Diabetes
+383,271,121,40,"6,8",81,female,64,158,"27,1",146,76,36,43,"0,84",No diabetes
+384,240,88,49,"4,9",82,female,63,170,"30,1",180,86,41,46,"0,89",No diabetes
+385,255,112,34,"7,5",82,male,66,163,"26,3",179,89,37,43,"0,86",No diabetes
+386,227,105,44,"5,2",83,female,59,125,"25,2",150,90,35,40,"0,88",No diabetes
+387,226,279,52,"4,3",84,female,60,192,"37,5",144,88,41,48,"0,85",Diabetes
+388,301,90,118,"2,6",89,female,61,115,"21,7",218,90,31,41,"0,76",No diabetes
+389,232,184,114,2,91,female,61,127,24,170,82,35,38,"0,92",Diabetes
+390,165,94,69,"2,4",92,female,62,217,"39,7",160,82,51,51,1,No diabetes

model.ipynb

@@ -0,0 +1,1029 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Importing modules and Loading dataset.\n",
+    "This section contains importing the important python modules. Also, the dataset to be used, in this case the   \n",
+    "\n"
+   ],
+   "metadata": {
+    "id": "r5yZ0Codo2rF"
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": true,
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "id": "Xfbj4kG4UwcC"
+   },
+   "outputs": [],
+   "source": [
+    "# importing python module.\n",
+    "import pandas as pd\n",
+    "from lightgbm.sklearn import LGBMClassifier\n",
+    "from sklearn.preprocessing import RobustScaler, OrdinalEncoder\n",
+    "from sklearn.model_selection import train_test_split, StratifiedShuffleSplit\n",
+    "from xgboost.sklearn import XGBClassifier\n",
+    "from sklearn.metrics import f1_score\n",
+    "\n",
+    "import warnings\n",
+    "warnings.filterwarnings(\"ignore\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "   patient_number  cholesterol  glucose  hdl_chol chol_hdl_ratio  age  gender  \\\n0               1          193       77        49            3,9   19  female   \n1               2          146       79        41            3,6   19  female   \n2               3          217       75        54              4   20  female   \n3               4          226       97        70            3,2   20  female   \n4               5          164       91        67            2,4   20  female   \n\n   height  weight   bmi  systolic_bp  diastolic_bp  waist  hip  \\\n0      61     119  22,5          118            70     32   38   \n1      60     135  26,4          108            58     33   40   \n2      67     187  29,3          110            72     40   45   \n3      64     114  19,6          122            64     31   39   \n4      70     141  20,2          122            86     32   39   \n\n  waist_hip_ratio     diabetes  \n0            0,84  No diabetes  \n1            0,83  No diabetes  \n2            0,89  No diabetes  \n3            0,79  No diabetes  \n4            0,82  No diabetes  ",
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>patient_number</th>\n      <th>cholesterol</th>\n      <th>glucose</th>\n      <th>hdl_chol</th>\n      <th>chol_hdl_ratio</th>\n      <th>age</th>\n      <th>gender</th>\n      <th>height</th>\n      <th>weight</th>\n      <th>bmi</th>\n      <th>systolic_bp</th>\n      <th>diastolic_bp</th>\n      <th>waist</th>\n      <th>hip</th>\n      <th>waist_hip_ratio</th>\n      <th>diabetes</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>193</td>\n      <td>77</td>\n      <td>49</td>\n      <td>3,9</td>\n      <td>19</td>\n      <td>female</td>\n      <td>61</td>\n      <td>119</td>\n      <td>22,5</td>\n      <td>118</td>\n      <td>70</td>\n      <td>32</td>\n      <td>38</td>\n      <td>0,84</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>146</td>\n      <td>79</td>\n      <td>41</td>\n      <td>3,6</td>\n      <td>19</td>\n      <td>female</td>\n      <td>60</td>\n      <td>135</td>\n      <td>26,4</td>\n      <td>108</td>\n      <td>58</td>\n      <td>33</td>\n      <td>40</td>\n      <td>0,83</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>217</td>\n      <td>75</td>\n      <td>54</td>\n      <td>4</td>\n      <td>20</td>\n      <td>female</td>\n      <td>67</td>\n      <td>187</td>\n      <td>29,3</td>\n      <td>110</td>\n      <td>72</td>\n      <td>40</td>\n      <td>45</td>\n      <td>0,89</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>226</td>\n      <td>97</td>\n      <td>70</td>\n      <td>3,2</td>\n      <td>20</td>\n      <td>female</td>\n      <td>64</td>\n      <td>114</td>\n      <td>19,6</td>\n      <td>122</td>\n      <td>64</td>\n      <td>31</td>\n      <td>39</td>\n      <td>0,79</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>164</td>\n      <td>91</td>\n      <td>67</td>\n      <td>2,4</td>\n      <td>20</td>\n      <td>female</td>\n      <td>70</td>\n      <td>141</td>\n      <td>20,2</td>\n      <td>122</td>\n      <td>86</td>\n      <td>32</td>\n      <td>39</td>\n      <td>0,82</td>\n      <td>No diabetes</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# loading dataset with pandas\n",
+    "dia = pd.read_csv(\"./dataset/diabetes.csv\")\n",
+    "\n",
+    "dia.head()"
+   ],
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 357
+    },
+    "id": "yx869JONUwcJ",
+    "outputId": "ccdf4d8b-adf1-40b1-fe75-bc8a0dccfa6c"
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 390 entries, 0 to 389\n",
+      "Data columns (total 16 columns):\n",
+      " #   Column           Non-Null Count  Dtype \n",
+      "---  ------           --------------  ----- \n",
+      " 0   patient_number   390 non-null    int64 \n",
+      " 1   cholesterol      390 non-null    int64 \n",
+      " 2   glucose          390 non-null    int64 \n",
+      " 3   hdl_chol         390 non-null    int64 \n",
+      " 4   chol_hdl_ratio   390 non-null    object\n",
+      " 5   age              390 non-null    int64 \n",
+      " 6   gender           390 non-null    object\n",
+      " 7   height           390 non-null    int64 \n",
+      " 8   weight           390 non-null    int64 \n",
+      " 9   bmi              390 non-null    object\n",
+      " 10  systolic_bp      390 non-null    int64 \n",
+      " 11  diastolic_bp     390 non-null    int64 \n",
+      " 12  waist            390 non-null    int64 \n",
+      " 13  hip              390 non-null    int64 \n",
+      " 14  waist_hip_ratio  390 non-null    object\n",
+      " 15  diabetes         390 non-null    object\n",
+      "dtypes: int64(11), object(5)\n",
+      "memory usage: 48.9+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "# wrangling datasets with pandas\n",
+    "dia.info()"
+   ],
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "rftvNRifUwcL",
+    "outputId": "d0799384-e171-4bc9-c149-873c22252711"
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "       patient_number  cholesterol     glucose    hdl_chol         age  \\\ncount      390.000000   390.000000  390.000000  390.000000  390.000000   \nmean       195.500000   207.230769  107.338462   50.266667   46.774359   \nstd        112.727548    44.666005   53.798188   17.279069   16.435911   \nmin          1.000000    78.000000   48.000000   12.000000   19.000000   \n25%         98.250000   179.000000   81.000000   38.000000   34.000000   \n50%        195.500000   203.000000   90.000000   46.000000   44.500000   \n75%        292.750000   229.000000  107.750000   59.000000   60.000000   \nmax        390.000000   443.000000  385.000000  120.000000   92.000000   \n\n           height      weight  systolic_bp  diastolic_bp       waist  \\\ncount  390.000000  390.000000   390.000000    390.000000  390.000000   \nmean    65.951282  177.407692   137.133333     83.289744   37.869231   \nstd      3.918867   40.407824    22.859528     13.498192    5.760947   \nmin     52.000000   99.000000    90.000000     48.000000   26.000000   \n25%     63.000000  150.250000   122.000000     75.000000   33.000000   \n50%     66.000000  173.000000   136.000000     82.000000   37.000000   \n75%     69.000000  200.000000   148.000000     90.000000   41.000000   \nmax     76.000000  325.000000   250.000000    124.000000   56.000000   \n\n              hip  \ncount  390.000000  \nmean    42.992308  \nstd      5.664342  \nmin     30.000000  \n25%     39.000000  \n50%     42.000000  \n75%     46.000000  \nmax     64.000000  ",
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>patient_number</th>\n      <th>cholesterol</th>\n      <th>glucose</th>\n      <th>hdl_chol</th>\n      <th>age</th>\n      <th>height</th>\n      <th>weight</th>\n      <th>systolic_bp</th>\n      <th>diastolic_bp</th>\n      <th>waist</th>\n      <th>hip</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>count</th>\n      <td>390.000000</td>\n      <td>390.000000</td>\n      <td>390.000000</td>\n      <td>390.000000</td>\n      <td>390.000000</td>\n      <td>390.000000</td>\n      <td>390.000000</td>\n      <td>390.000000</td>\n      <td>390.000000</td>\n      <td>390.000000</td>\n      <td>390.000000</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>195.500000</td>\n      <td>207.230769</td>\n      <td>107.338462</td>\n      <td>50.266667</td>\n      <td>46.774359</td>\n      <td>65.951282</td>\n      <td>177.407692</td>\n      <td>137.133333</td>\n      <td>83.289744</td>\n      <td>37.869231</td>\n      <td>42.992308</td>\n    </tr>\n    <tr>\n      <th>std</th>\n      <td>112.727548</td>\n      <td>44.666005</td>\n      <td>53.798188</td>\n      <td>17.279069</td>\n      <td>16.435911</td>\n      <td>3.918867</td>\n      <td>40.407824</td>\n      <td>22.859528</td>\n      <td>13.498192</td>\n      <td>5.760947</td>\n      <td>5.664342</td>\n    </tr>\n    <tr>\n      <th>min</th>\n      <td>1.000000</td>\n      <td>78.000000</td>\n      <td>48.000000</td>\n      <td>12.000000</td>\n      <td>19.000000</td>\n      <td>52.000000</td>\n      <td>99.000000</td>\n      <td>90.000000</td>\n      <td>48.000000</td>\n      <td>26.000000</td>\n      <td>30.000000</td>\n    </tr>\n    <tr>\n      <th>25%</th>\n      <td>98.250000</td>\n      <td>179.000000</td>\n      <td>81.000000</td>\n      <td>38.000000</td>\n      <td>34.000000</td>\n      <td>63.000000</td>\n      <td>150.250000</td>\n      <td>122.000000</td>\n      <td>75.000000</td>\n      <td>33.000000</td>\n      <td>39.000000</td>\n    </tr>\n    <tr>\n      <th>50%</th>\n      <td>195.500000</td>\n      <td>203.000000</td>\n      <td>90.000000</td>\n      <td>46.000000</td>\n      <td>44.500000</td>\n      <td>66.000000</td>\n      <td>173.000000</td>\n      <td>136.000000</td>\n      <td>82.000000</td>\n      <td>37.000000</td>\n      <td>42.000000</td>\n    </tr>\n    <tr>\n      <th>75%</th>\n      <td>292.750000</td>\n      <td>229.000000</td>\n      <td>107.750000</td>\n      <td>59.000000</td>\n      <td>60.000000</td>\n      <td>69.000000</td>\n      <td>200.000000</td>\n      <td>148.000000</td>\n      <td>90.000000</td>\n      <td>41.000000</td>\n      <td>46.000000</td>\n    </tr>\n    <tr>\n      <th>max</th>\n      <td>390.000000</td>\n      <td>443.000000</td>\n      <td>385.000000</td>\n      <td>120.000000</td>\n      <td>92.000000</td>\n      <td>76.000000</td>\n      <td>325.000000</td>\n      <td>250.000000</td>\n      <td>124.000000</td>\n      <td>56.000000</td>\n      <td>64.000000</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dia.describe()"
+   ],
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 364
+    },
+    "id": "mPXcxzuwUwcN",
+    "outputId": "a1107ea3-215d-4400-e6ff-2d8fd7ff8b55"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Wrangling dataset."
+   ],
+   "metadata": {
+    "id": "S2hRdWcPqcrP"
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "outputs": [],
+   "source": [
+    "dia.chol_hdl_ratio = round(dia.cholesterol / dia.hdl_chol,2)"
+   ],
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "id": "DCl3woxiUwcO"
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "   patient_number  cholesterol  glucose  hdl_chol  chol_hdl_ratio  age  \\\n0               1          193       77        49            3.94   19   \n1               2          146       79        41            3.56   19   \n2               3          217       75        54            4.02   20   \n3               4          226       97        70            3.23   20   \n4               5          164       91        67            2.45   20   \n\n   gender  height  weight   bmi  systolic_bp  diastolic_bp  waist  hip  \\\n0  female      61     119  22,5          118            70     32   38   \n1  female      60     135  26,4          108            58     33   40   \n2  female      67     187  29,3          110            72     40   45   \n3  female      64     114  19,6          122            64     31   39   \n4  female      70     141  20,2          122            86     32   39   \n\n  waist_hip_ratio     diabetes  \n0            0,84  No diabetes  \n1            0,83  No diabetes  \n2            0,89  No diabetes  \n3            0,79  No diabetes  \n4            0,82  No diabetes  ",
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>patient_number</th>\n      <th>cholesterol</th>\n      <th>glucose</th>\n      <th>hdl_chol</th>\n      <th>chol_hdl_ratio</th>\n      <th>age</th>\n      <th>gender</th>\n      <th>height</th>\n      <th>weight</th>\n      <th>bmi</th>\n      <th>systolic_bp</th>\n      <th>diastolic_bp</th>\n      <th>waist</th>\n      <th>hip</th>\n      <th>waist_hip_ratio</th>\n      <th>diabetes</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>193</td>\n      <td>77</td>\n      <td>49</td>\n      <td>3.94</td>\n      <td>19</td>\n      <td>female</td>\n      <td>61</td>\n      <td>119</td>\n      <td>22,5</td>\n      <td>118</td>\n      <td>70</td>\n      <td>32</td>\n      <td>38</td>\n      <td>0,84</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>146</td>\n      <td>79</td>\n      <td>41</td>\n      <td>3.56</td>\n      <td>19</td>\n      <td>female</td>\n      <td>60</td>\n      <td>135</td>\n      <td>26,4</td>\n      <td>108</td>\n      <td>58</td>\n      <td>33</td>\n      <td>40</td>\n      <td>0,83</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>217</td>\n      <td>75</td>\n      <td>54</td>\n      <td>4.02</td>\n      <td>20</td>\n      <td>female</td>\n      <td>67</td>\n      <td>187</td>\n      <td>29,3</td>\n      <td>110</td>\n      <td>72</td>\n      <td>40</td>\n      <td>45</td>\n      <td>0,89</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>226</td>\n      <td>97</td>\n      <td>70</td>\n      <td>3.23</td>\n      <td>20</td>\n      <td>female</td>\n      <td>64</td>\n      <td>114</td>\n      <td>19,6</td>\n      <td>122</td>\n      <td>64</td>\n      <td>31</td>\n      <td>39</td>\n      <td>0,79</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>164</td>\n      <td>91</td>\n      <td>67</td>\n      <td>2.45</td>\n      <td>20</td>\n      <td>female</td>\n      <td>70</td>\n      <td>141</td>\n      <td>20,2</td>\n      <td>122</td>\n      <td>86</td>\n      <td>32</td>\n      <td>39</td>\n      <td>0,82</td>\n      <td>No diabetes</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dia.head()"
+   ],
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 357
+    },
+    "id": "QNlQedszUwcP",
+    "outputId": "63231eb5-798a-4c07-8aae-851004ab3787"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [],
+   "metadata": {
+    "collapsed": false,
+    "id": "SFHdSj2YUwcQ"
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "outputs": [],
+   "source": [
+    "dia.waist_hip_ratio= round(dia.waist/dia.hip,2)"
+   ],
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "id": "ovJyqVa2UwcX"
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "   patient_number  cholesterol  glucose  hdl_chol  chol_hdl_ratio  age  \\\n0               1          193       77        49            3.94   19   \n1               2          146       79        41            3.56   19   \n2               3          217       75        54            4.02   20   \n3               4          226       97        70            3.23   20   \n4               5          164       91        67            2.45   20   \n\n   gender  height  weight   bmi  systolic_bp  diastolic_bp  waist  hip  \\\n0  female      61     119  22,5          118            70     32   38   \n1  female      60     135  26,4          108            58     33   40   \n2  female      67     187  29,3          110            72     40   45   \n3  female      64     114  19,6          122            64     31   39   \n4  female      70     141  20,2          122            86     32   39   \n\n   waist_hip_ratio     diabetes  \n0             0.84  No diabetes  \n1             0.82  No diabetes  \n2             0.89  No diabetes  \n3             0.79  No diabetes  \n4             0.82  No diabetes  ",
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>patient_number</th>\n      <th>cholesterol</th>\n      <th>glucose</th>\n      <th>hdl_chol</th>\n      <th>chol_hdl_ratio</th>\n      <th>age</th>\n      <th>gender</th>\n      <th>height</th>\n      <th>weight</th>\n      <th>bmi</th>\n      <th>systolic_bp</th>\n      <th>diastolic_bp</th>\n      <th>waist</th>\n      <th>hip</th>\n      <th>waist_hip_ratio</th>\n      <th>diabetes</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>193</td>\n      <td>77</td>\n      <td>49</td>\n      <td>3.94</td>\n      <td>19</td>\n      <td>female</td>\n      <td>61</td>\n      <td>119</td>\n      <td>22,5</td>\n      <td>118</td>\n      <td>70</td>\n      <td>32</td>\n      <td>38</td>\n      <td>0.84</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>146</td>\n      <td>79</td>\n      <td>41</td>\n      <td>3.56</td>\n      <td>19</td>\n      <td>female</td>\n      <td>60</td>\n      <td>135</td>\n      <td>26,4</td>\n      <td>108</td>\n      <td>58</td>\n      <td>33</td>\n      <td>40</td>\n      <td>0.82</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>217</td>\n      <td>75</td>\n      <td>54</td>\n      <td>4.02</td>\n      <td>20</td>\n      <td>female</td>\n      <td>67</td>\n      <td>187</td>\n      <td>29,3</td>\n      <td>110</td>\n      <td>72</td>\n      <td>40</td>\n      <td>45</td>\n      <td>0.89</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>226</td>\n      <td>97</td>\n      <td>70</td>\n      <td>3.23</td>\n      <td>20</td>\n      <td>female</td>\n      <td>64</td>\n      <td>114</td>\n      <td>19,6</td>\n      <td>122</td>\n      <td>64</td>\n      <td>31</td>\n      <td>39</td>\n      <td>0.79</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>164</td>\n      <td>91</td>\n      <td>67</td>\n      <td>2.45</td>\n      <td>20</td>\n      <td>female</td>\n      <td>70</td>\n      <td>141</td>\n      <td>20,2</td>\n      <td>122</td>\n      <td>86</td>\n      <td>32</td>\n      <td>39</td>\n      <td>0.82</td>\n      <td>No diabetes</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dia.head()"
+   ],
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 357
+    },
+    "id": "PWqYDcnYUwcZ",
+    "outputId": "d0e278d1-d7ed-4503-ee2b-5f94661e56e5"
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "outputs": [],
+   "source": [
+    "dia.bmi = pd.to_numeric(dia.bmi.str.replace(\",\",\".\"))"
+   ],
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "id": "CXAX15VHUwce"
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "   patient_number  cholesterol  glucose  hdl_chol  chol_hdl_ratio  age  \\\n0               1          193       77        49            3.94   19   \n1               2          146       79        41            3.56   19   \n2               3          217       75        54            4.02   20   \n3               4          226       97        70            3.23   20   \n4               5          164       91        67            2.45   20   \n\n   gender  height  weight   bmi  systolic_bp  diastolic_bp  waist  hip  \\\n0  female      61     119  22.5          118            70     32   38   \n1  female      60     135  26.4          108            58     33   40   \n2  female      67     187  29.3          110            72     40   45   \n3  female      64     114  19.6          122            64     31   39   \n4  female      70     141  20.2          122            86     32   39   \n\n   waist_hip_ratio     diabetes  \n0             0.84  No diabetes  \n1             0.82  No diabetes  \n2             0.89  No diabetes  \n3             0.79  No diabetes  \n4             0.82  No diabetes  ",
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>patient_number</th>\n      <th>cholesterol</th>\n      <th>glucose</th>\n      <th>hdl_chol</th>\n      <th>chol_hdl_ratio</th>\n      <th>age</th>\n      <th>gender</th>\n      <th>height</th>\n      <th>weight</th>\n      <th>bmi</th>\n      <th>systolic_bp</th>\n      <th>diastolic_bp</th>\n      <th>waist</th>\n      <th>hip</th>\n      <th>waist_hip_ratio</th>\n      <th>diabetes</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>193</td>\n      <td>77</td>\n      <td>49</td>\n      <td>3.94</td>\n      <td>19</td>\n      <td>female</td>\n      <td>61</td>\n      <td>119</td>\n      <td>22.5</td>\n      <td>118</td>\n      <td>70</td>\n      <td>32</td>\n      <td>38</td>\n      <td>0.84</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>146</td>\n      <td>79</td>\n      <td>41</td>\n      <td>3.56</td>\n      <td>19</td>\n      <td>female</td>\n      <td>60</td>\n      <td>135</td>\n      <td>26.4</td>\n      <td>108</td>\n      <td>58</td>\n      <td>33</td>\n      <td>40</td>\n      <td>0.82</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>217</td>\n      <td>75</td>\n      <td>54</td>\n      <td>4.02</td>\n      <td>20</td>\n      <td>female</td>\n      <td>67</td>\n      <td>187</td>\n      <td>29.3</td>\n      <td>110</td>\n      <td>72</td>\n      <td>40</td>\n      <td>45</td>\n      <td>0.89</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>226</td>\n      <td>97</td>\n      <td>70</td>\n      <td>3.23</td>\n      <td>20</td>\n      <td>female</td>\n      <td>64</td>\n      <td>114</td>\n      <td>19.6</td>\n      <td>122</td>\n      <td>64</td>\n      <td>31</td>\n      <td>39</td>\n      <td>0.79</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>164</td>\n      <td>91</td>\n      <td>67</td>\n      <td>2.45</td>\n      <td>20</td>\n      <td>female</td>\n      <td>70</td>\n      <td>141</td>\n      <td>20.2</td>\n      <td>122</td>\n      <td>86</td>\n      <td>32</td>\n      <td>39</td>\n      <td>0.82</td>\n      <td>No diabetes</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dia.head()"
+   ],
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 357
+    },
+    "id": "Y9Rg5DkoUwcf",
+    "outputId": "de5133be-4736-4098-c94c-300eaac58f7d"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "dia.weight.describe()"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "PglRQVOhWq6F",
+    "outputId": "9e50d452-d5c4-41f0-a632-f148bb85c44f"
+   },
+   "execution_count": 11,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "count    390.000000\nmean     177.407692\nstd       40.407824\nmin       99.000000\n25%      150.250000\n50%      173.000000\n75%      200.000000\nmax      325.000000\nName: weight, dtype: float64"
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "patient_number     0\ncholesterol        0\nglucose            0\nhdl_chol           0\nchol_hdl_ratio     0\nage                0\ngender             0\nheight             0\nweight             0\nbmi                0\nsystolic_bp        0\ndiastolic_bp       0\nwaist              0\nhip                0\nwaist_hip_ratio    0\ndiabetes           0\ndtype: int64"
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dia.isnull().sum()"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "dia.head()"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 357
+    },
+    "id": "GY9af0LOoUrQ",
+    "outputId": "5cb087ef-8459-40e3-c65d-515007489006"
+   },
+   "execution_count": 13,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "   patient_number  cholesterol  glucose  hdl_chol  chol_hdl_ratio  age  \\\n0               1          193       77        49            3.94   19   \n1               2          146       79        41            3.56   19   \n2               3          217       75        54            4.02   20   \n3               4          226       97        70            3.23   20   \n4               5          164       91        67            2.45   20   \n\n   gender  height  weight   bmi  systolic_bp  diastolic_bp  waist  hip  \\\n0  female      61     119  22.5          118            70     32   38   \n1  female      60     135  26.4          108            58     33   40   \n2  female      67     187  29.3          110            72     40   45   \n3  female      64     114  19.6          122            64     31   39   \n4  female      70     141  20.2          122            86     32   39   \n\n   waist_hip_ratio     diabetes  \n0             0.84  No diabetes  \n1             0.82  No diabetes  \n2             0.89  No diabetes  \n3             0.79  No diabetes  \n4             0.82  No diabetes  ",
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>patient_number</th>\n      <th>cholesterol</th>\n      <th>glucose</th>\n      <th>hdl_chol</th>\n      <th>chol_hdl_ratio</th>\n      <th>age</th>\n      <th>gender</th>\n      <th>height</th>\n      <th>weight</th>\n      <th>bmi</th>\n      <th>systolic_bp</th>\n      <th>diastolic_bp</th>\n      <th>waist</th>\n      <th>hip</th>\n      <th>waist_hip_ratio</th>\n      <th>diabetes</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>193</td>\n      <td>77</td>\n      <td>49</td>\n      <td>3.94</td>\n      <td>19</td>\n      <td>female</td>\n      <td>61</td>\n      <td>119</td>\n      <td>22.5</td>\n      <td>118</td>\n      <td>70</td>\n      <td>32</td>\n      <td>38</td>\n      <td>0.84</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>146</td>\n      <td>79</td>\n      <td>41</td>\n      <td>3.56</td>\n      <td>19</td>\n      <td>female</td>\n      <td>60</td>\n      <td>135</td>\n      <td>26.4</td>\n      <td>108</td>\n      <td>58</td>\n      <td>33</td>\n      <td>40</td>\n      <td>0.82</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>217</td>\n      <td>75</td>\n      <td>54</td>\n      <td>4.02</td>\n      <td>20</td>\n      <td>female</td>\n      <td>67</td>\n      <td>187</td>\n      <td>29.3</td>\n      <td>110</td>\n      <td>72</td>\n      <td>40</td>\n      <td>45</td>\n      <td>0.89</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>226</td>\n      <td>97</td>\n      <td>70</td>\n      <td>3.23</td>\n      <td>20</td>\n      <td>female</td>\n      <td>64</td>\n      <td>114</td>\n      <td>19.6</td>\n      <td>122</td>\n      <td>64</td>\n      <td>31</td>\n      <td>39</td>\n      <td>0.79</td>\n      <td>No diabetes</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>164</td>\n      <td>91</td>\n      <td>67</td>\n      <td>2.45</td>\n      <td>20</td>\n      <td>female</td>\n      <td>70</td>\n      <td>141</td>\n      <td>20.2</td>\n      <td>122</td>\n      <td>86</td>\n      <td>32</td>\n      <td>39</td>\n      <td>0.82</td>\n      <td>No diabetes</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ]
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "s= (dia.dtypes == \"object\")\n",
+    "obj_col= list(s[s].index)"
+   ],
+   "metadata": {
+    "id": "cKtpXdi6pwdJ"
+   },
+   "execution_count": 14,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "obj_col"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "_jnwJCli1cA6",
+    "outputId": "563aa279-aae2-4d4e-d5c8-f8d668946539"
+   },
+   "execution_count": 15,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "['gender', 'diabetes']"
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ]
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "orde = OrdinalEncoder()\n",
+    "dia[obj_col] = orde.fit_transform(dia[obj_col])"
+   ],
+   "metadata": {
+    "id": "KvSeVC8K2FvU"
+   },
+   "execution_count": 16,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "dia.head()"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 270
+    },
+    "id": "bY5dg9H53eVS",
+    "outputId": "27963a81-6560-455f-8d8d-10240bc5dc33"
+   },
+   "execution_count": 17,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "   patient_number  cholesterol  glucose  hdl_chol  chol_hdl_ratio  age  \\\n0               1          193       77        49            3.94   19   \n1               2          146       79        41            3.56   19   \n2               3          217       75        54            4.02   20   \n3               4          226       97        70            3.23   20   \n4               5          164       91        67            2.45   20   \n\n   gender  height  weight   bmi  systolic_bp  diastolic_bp  waist  hip  \\\n0     0.0      61     119  22.5          118            70     32   38   \n1     0.0      60     135  26.4          108            58     33   40   \n2     0.0      67     187  29.3          110            72     40   45   \n3     0.0      64     114  19.6          122            64     31   39   \n4     0.0      70     141  20.2          122            86     32   39   \n\n   waist_hip_ratio  diabetes  \n0             0.84       1.0  \n1             0.82       1.0  \n2             0.89       1.0  \n3             0.79       1.0  \n4             0.82       1.0  ",
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>patient_number</th>\n      <th>cholesterol</th>\n      <th>glucose</th>\n      <th>hdl_chol</th>\n      <th>chol_hdl_ratio</th>\n      <th>age</th>\n      <th>gender</th>\n      <th>height</th>\n      <th>weight</th>\n      <th>bmi</th>\n      <th>systolic_bp</th>\n      <th>diastolic_bp</th>\n      <th>waist</th>\n      <th>hip</th>\n      <th>waist_hip_ratio</th>\n      <th>diabetes</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>193</td>\n      <td>77</td>\n      <td>49</td>\n      <td>3.94</td>\n      <td>19</td>\n      <td>0.0</td>\n      <td>61</td>\n      <td>119</td>\n      <td>22.5</td>\n      <td>118</td>\n      <td>70</td>\n      <td>32</td>\n      <td>38</td>\n      <td>0.84</td>\n      <td>1.0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>146</td>\n      <td>79</td>\n      <td>41</td>\n      <td>3.56</td>\n      <td>19</td>\n      <td>0.0</td>\n      <td>60</td>\n      <td>135</td>\n      <td>26.4</td>\n      <td>108</td>\n      <td>58</td>\n      <td>33</td>\n      <td>40</td>\n      <td>0.82</td>\n      <td>1.0</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>217</td>\n      <td>75</td>\n      <td>54</td>\n      <td>4.02</td>\n      <td>20</td>\n      <td>0.0</td>\n      <td>67</td>\n      <td>187</td>\n      <td>29.3</td>\n      <td>110</td>\n      <td>72</td>\n      <td>40</td>\n      <td>45</td>\n      <td>0.89</td>\n      <td>1.0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>226</td>\n      <td>97</td>\n      <td>70</td>\n      <td>3.23</td>\n      <td>20</td>\n      <td>0.0</td>\n      <td>64</td>\n      <td>114</td>\n      <td>19.6</td>\n      <td>122</td>\n      <td>64</td>\n      <td>31</td>\n      <td>39</td>\n      <td>0.79</td>\n      <td>1.0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>164</td>\n      <td>91</td>\n      <td>67</td>\n      <td>2.45</td>\n      <td>20</td>\n      <td>0.0</td>\n      <td>70</td>\n      <td>141</td>\n      <td>20.2</td>\n      <td>122</td>\n      <td>86</td>\n      <td>32</td>\n      <td>39</td>\n      <td>0.82</td>\n      <td>1.0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ]
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "X = dia.drop([\"patient_number\", \"diabetes\"], axis= 1)\n",
+    "y= dia.diabetes"
+   ],
+   "metadata": {
+    "id": "ZbHayB553gRB"
+   },
+   "execution_count": 18,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "scale = RobustScaler()\n",
+    "scaled_x = scale.fit_transform(X, y=y)"
+   ],
+   "metadata": {
+    "id": "GpABdNvA3_8-"
+   },
+   "execution_count": 19,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "scaled_x"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "qgImunKB4r2i",
+    "outputId": "76b3b342-70c9-4aee-b3b6-1c21b9aac379"
+   },
+   "execution_count": 20,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "array([[-0.2       , -0.48598131,  0.14285714, ..., -0.625     ,\n        -0.57142857, -0.41025641],\n       [-1.14      , -0.41121495, -0.23809524, ..., -0.5       ,\n        -0.28571429, -0.61538462],\n       [ 0.28      , -0.56074766,  0.38095238, ...,  0.375     ,\n         0.42857143,  0.1025641 ],\n       ...,\n       [ 1.96      ,  0.        ,  3.42857143, ..., -0.75      ,\n        -0.14285714, -1.23076923],\n       [ 0.58      ,  3.51401869,  3.23809524, ..., -0.25      ,\n        -0.57142857,  0.41025641],\n       [-0.76      ,  0.14953271,  1.0952381 , ...,  1.75      ,\n         1.28571429,  1.23076923]])"
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ]
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(scaled_x, y, test_size= 0.2, random_state=42)"
+   ],
+   "metadata": {
+    "id": "ZECN7XuJ4uAR"
+   },
+   "execution_count": 21,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "outputs": [],
+   "source": [
+    "split = StratifiedShuffleSplit(n_splits=4, random_state=42 )\n",
+    "\n",
+    "for train_index, test_index in split.split(scaled_x, y):\n",
+    "    strat_X, strat_test = scaled_x[train_index], scaled_x[test_index]\n",
+    "    strat_y, strat_ytest = y[train_index], y[test_index]"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "X_train"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "Zo2R6TH55gTW",
+    "outputId": "b12de013-4626-4a0e-aaac-f16281bd50b6"
+   },
+   "execution_count": 23,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "array([[-0.22      , -1.27102804, -0.19047619, ..., -0.75      ,\n        -0.28571429, -1.02564103],\n       [-0.44      ,  0.41121495, -0.0952381 , ...,  0.125     ,\n         0.        ,  0.20512821],\n       [ 0.18      , -0.41121495,  0.14285714, ...,  0.125     ,\n         0.        ,  0.20512821],\n       ...,\n       [-1.48      ,  0.74766355, -0.19047619, ..., -0.375     ,\n        -0.57142857,  0.1025641 ],\n       [ 0.66      ,  0.78504673,  1.71428571, ..., -1.        ,\n        -0.71428571, -1.02564103],\n       [ 2.68      , -0.18691589,  0.76190476, ..., -0.125     ,\n         0.28571429, -0.61538462]])"
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ]
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "lgbm_model = LGBMClassifier(n_estimators=200, max_depth=-2, random_state=42)"
+   ],
+   "metadata": {
+    "id": "S9cGQrMp5iug"
+   },
+   "execution_count": 24,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "lgbm_model.fit(X_train, y_train)"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "SWj3o6Cg6nUD",
+    "outputId": "b64a97a4-1f1d-46c3-c11e-e429feedd6db"
+   },
+   "execution_count": 25,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "LGBMClassifier(max_depth=-2, n_estimators=200, random_state=42)"
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ]
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "y_pred=lgbm_model.predict(X_test)"
+   ],
+   "metadata": {
+    "id": "8LFEmpW16yNk"
+   },
+   "execution_count": 26,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "f1_score(y_pred, y_test)"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "I1pWPR0x6_r9",
+    "outputId": "4ecaee82-9c32-4ca2-f71a-c376ea853419"
+   },
+   "execution_count": 27,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "0.9354838709677419"
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ]
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "xg_model= XGBClassifier(n_estimators=200, max_depth=4, scale_pos_weight=5.5)"
+   ],
+   "metadata": {
+    "id": "e6JqauyE7Luq"
+   },
+   "execution_count": 28,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[23:22:04] WARNING: C:/Users/Administrator/workspace/xgboost-win64_release_1.4.0/src/learner.cc:1095: Starting in XGBoost 1.3.0, the default evaluation metric used with the objective 'binary:logistic' was changed from 'error' to 'logloss'. Explicitly set eval_metric if you'd like to restore the old behavior.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n              colsample_bynode=1, colsample_bytree=1, gamma=0, gpu_id=-1,\n              importance_type='gain', interaction_constraints='',\n              learning_rate=0.300000012, max_delta_step=0, max_depth=4,\n              min_child_weight=1, missing=nan, monotone_constraints='()',\n              n_estimators=200, n_jobs=4, num_parallel_tree=1, random_state=0,\n              reg_alpha=0, reg_lambda=1, scale_pos_weight=5.5, subsample=1,\n              tree_method='exact', validate_parameters=1, verbosity=None)"
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "xg_model.fit(X_train, y_train)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "outputs": [],
+   "source": [
+    "xg_pred = xg_model.predict(X_test)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "0.943089430894309"
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "f1_score(y_test, xg_pred)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Stratified Shuffle Test"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "outputs": [],
+   "source": [
+    "lgbm_strat = LGBMClassifier(n_estimators=200, learning_rate=0.0099, max_depth=-2, )"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "LGBMClassifier(learning_rate=0.0099, max_depth=-2, n_estimators=200)"
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "lgbm_strat.fit(strat_X, strat_y)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "outputs": [],
+   "source": [
+    "strat_pred = lgbm_strat.predict(strat_test)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "0.955223880597015"
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "f1_score(strat_pred, strat_ytest)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "\n",
+    "def predict(var_name):\n",
+    "    pred = [var_name]\n",
+    "    np_pred = np.array(pred)\n",
+    "    score = lgbm_strat.predict(np_pred)\n",
+    "    return score"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "1.0    330\n0.0     60\nName: diabetes, dtype: int64"
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dia.diabetes.value_counts()"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "5.5"
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "330/60"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "outputs": [],
+   "source": [
+    "xgb= XGBClassifier(max_depth=7, n_estimators=1000, scale_pos_weight=5.5)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[00:36:49] WARNING: C:/Users/Administrator/workspace/xgboost-win64_release_1.4.0/src/learner.cc:1095: Starting in XGBoost 1.3.0, the default evaluation metric used with the objective 'binary:logistic' was changed from 'error' to 'logloss'. Explicitly set eval_metric if you'd like to restore the old behavior.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n              colsample_bynode=1, colsample_bytree=1, gamma=0, gpu_id=-1,\n              importance_type='gain', interaction_constraints='',\n              learning_rate=0.300000012, max_delta_step=0, max_depth=7,\n              min_child_weight=1, missing=nan, monotone_constraints='()',\n              n_estimators=1000, n_jobs=4, num_parallel_tree=1, random_state=0,\n              reg_alpha=0, reg_lambda=1, scale_pos_weight=5.5, subsample=1,\n              tree_method='exact', validate_parameters=1, verbosity=None)"
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "xgb.fit(strat_X, strat_y)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "outputs": [],
+   "source": [
+    "y=xgb.predict(strat_test)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "0.955223880597015"
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "f1_score(y, strat_ytest)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "outputs": [],
+   "source": [
+    "import sqlite3"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "outputs": [],
+   "source": [
+    "conn = sqlite3.connect(\"diabetes.db\")\n",
+    "c = conn.cursor()"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "('patient_number',\n 'cholesterol',\n 'glucose',\n 'hdl_chol',\n 'chol_hdl_ratio',\n 'age',\n 'gender',\n 'height',\n 'weight',\n 'bmi',\n 'systolic_bp',\n 'diastolic_bp',\n 'waist',\n 'hip',\n 'waist_hip_ratio',\n 'diabetes')"
+     },
+     "execution_count": 47,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "col= tuple(dia.columns)\n",
+    "col"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "outputs": [],
+   "source": [
+    "conn.commit()"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "outputs": [],
+   "source": [
+    "dia.to_sql(name=\"diabetes.db\", con=conn, if_exists= \"replace\", index=False)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  },
+  "colab": {
+   "provenance": []
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

model.py

@@ -0,0 +1,60 @@
+# importing python libraries
+import pandas as pd
+import pickle as pkl
+from lightgbm.sklearn import LGBMClassifier
+from sklearn.model_selection import StratifiedShuffleSplit
+from sklearn.preprocessing import RobustScaler, OrdinalEncoder
+from sklearn.metrics import f1_score
+
+import warnings
+warnings.filterwarnings("ignore")
+
+# loading diabetes data into variable data
+data = pd.read_csv("./dataset/diabetes.csv")
+
+# wrangling dataset.
+data.chol_hdl_ratio = round(data.cholesterol / data.hdl_chol, 2)
+data.waist_hip_ratio = round(data.waist / data.hip, 2)
+
+# correcting comma separated number to decimal separated number.
+data.bmi = pd.to_numeric(data.bmi.str.replace(",", "."))
+
+print(data.head())
+# encoding columns with object values using Ordinal Encoding
+s = (data.dtypes == "object")
+obj_col = s[s].index
+
+print("Ordinal Encoding")
+orde = OrdinalEncoder()
+data[obj_col] = orde.fit_transform(data[obj_col])
+
+print("Splitting features and target.")
+# dropping off target and unnecessary columns (diabetes and patient number columns)
+X = data.drop(["patient_number", "diabetes"], axis=1)
+y = data.diabetes
+
+print("Robust Scaling on X, y.")
+# scaling data using RobustScaler
+scale = RobustScaler()
+scaled_X = scale.fit_transform(X, y)
+
+print("Stratified Split.")
+# StratifiedShuffleSplit on Data
+split = StratifiedShuffleSplit(n_splits=4, random_state=42)
+
+for train_index, test_index in split.split(scaled_X, y):
+    X_train, X_test = scaled_X[train_index], scaled_X[test_index]
+    y_train, y_test = y[train_index], y[test_index]
+
+# Loading LightGBM classifier to be used for training model
+lgbm = LGBMClassifier(n_estimators=200, max_depth=-2, random_state=42)
+lgbm.fit(X_train, y_train)
+pred = lgbm.predict(X_test)
+
+f1 = f1_score(pred, y_test)
+print(f"F1 Score for LightGBM: {f1}.")
+
+# Using pickle to save model
+lightgbm = open("../deployment/lightgbm.pickle", "wb")
+pkl.dump(lgbm, lightgbm)
+lightgbm.close()