Diabetes Challenge! Machine Learning in Health

#1

I got only 68% accuracy and I have tried value of k from 15 to 25 all.But still it is 68% .
My code link is https://ide.codingblocks.com/s/146185
plz help!!

#2

Normalize dataset both training and testing. But for normalising use mean and std dev of training data for testing data too as we want to normalise both train and test data with the same mean and same std dev.
Also you can drop some (more than one) unimportant feature columns. As of now try dropping features randomly. So give it a hit and try approach for dropping features.

#3

But why to drop features as output is dependent on all six features here .
And how will nomalization effect accuracy ?
I didn’t understand Plz make me clear of it

#4

Sir i have normalized both training and testing set but this time accuracy reduces to 34%.I am doing wrong .plz help!!!

#5

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.

#6

plz modify my code .I am unable to increase accuracy

#7

My doubt is still not cleared