Difficulty in quiz problem

#1

not able to understand this quiz , I need some hints

#2

what should be the querypoint in knn function

#3

Hi, this challenge states that you are given a training dataset with features like pregnancies,insulin along with their labels etc. Using these as your features ,like x1,x2 … , you have to apply knn on the query points or testing data. The querypoints or testing data is available as test dataset which you can download. The query points also has the same features , like pregnancies etc, and using them you have to apply knn algo. The distance would be between the querypoint(testing points) and the training data. Both of them are given.

#4

I have used the same knn function as shown in the video,

#5

I have used the same knn function as shown in the video, and I have used x_train and y_train intead of x nd y and test case as querypoint, and I am getting 34%accuracy, Now , plz tell me what to do for improving the accuracy ad i have used k=5

#6

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.

#7

how to increase the accuracy sir, I have not received the appropriate answer

#8

How much accuracy are you getting? To increase your accuracy, keep the value of k greater than 15 and check for every value till 25. Also normalise both training and testing data and fill the NA enteries in the data with mean. Also try to drop some features. By dropping some feature columns you can increase the accuracy. As of now try dropping random features and note your accuracy. There is no need to drop more than 2-3 features.