Question
You are working on a classification problem. For validation purposes, you’ve randomly sampled the training data set into train and validation. You are confident that your model will work incredibly well on unseen data since your validation accuracy is high. However, you get shocked after getting poor test accuracy. What went wrong?
Answers
In case of classification problem, we should always use stratified sampling instead of random sampling. A random sampling doesn’t takes into consideration the proportion of target classes. On the contrary, stratified sampling helps to maintain the distribution of target variable in the resultant distributed samples also.
    Your Comment




  • Contributors: *,


Search
Can you Answer!!
  • Q Jawaharlal Nehru Port is located in which state?
  • Q How do you find the maximum number from an array without comparing and sorting?
  • Q Which robotic lander achieved a controlled touchdown on the comet 67p/Churyumov-Gerasimenko?
  • Q Differentiate between XP and Windows 2000
  • Q How WinRunner handles varying window labels?
  • Q What changes are needed to make the following prg to compile? import java.util.*; class Ques{ public static void main (String args[]) { String s1 = "abc"; String s2 = "def"; Vector v = new Vector(); v.add(s1); v.add(s2); String s3 = v.elementAt(0) + v.elementAt(1); System.out.println(s3); } } A) Declare Ques as public B) Cast v.elementAt(0) to a String C) Cast v.elementAt(1) to an Object. D) Import java.lang
  • Q Describe the Floral formula of Schistochilaceae ?
  • Q What is pl/sql table ?
  • Q What is the first line on Mel Blanc's tombstone
  • Q What if a Namenode has no data
  • Q Which among the following gas is most responsible for global warming?