model1

knnsm

data about canser disease

first :

import classes that we need and read file

second :

search about information of data to understand it and treat with

third :

cleaning data to prepare it
1- searching about duplicates find "8" that are dropped
2- searching about null values and not found
3- searching about missing values and they were "16" values "?" in one column "Bare Nuclei"
** convert it into nan values
** calculate column median and replace it
4- searching about datatypes and "Bare Nuclei" column was "object" type so we convert it into numeric that was "float"😢 then converting to "int46"
all datatypes were "int64"
5- dropping useless column "id"

now data is ready 👏👏

fourth :

visualizing data in univaratie and multivaratie then make corr about relationship between each colum and others

fifth :

modeling data to make predication using knn model in:
**test1 : accuracy was 0.9807692307692307
**test2 : accuracy was 0.9663461538461539🤷‍♀️

finishing data finally💃