This is a companion discussion topic for the original entry at https://dphi.tech/challenges/288
Hi, i have some queries in the dataset, what are ID1 and ID2? and what are entries in food preferences?
I also have the same query , regarding ID1 and ID2. What are they ?
The ID1 and ID2 columns are just identifiers for the rows, the numbers do not have any specific meaning.
Wont they contribute to the output?
That is for you to decide. Does an ID column provide useful information about what the target column value should be? You must check for yourself and decide whether to keep or remove those columns in your final model.
How to measure accuracy, Test.csv doesn’t have label “Healthy”, Or we have to just do submissions and accuracy will be measured by Dphi at backend
The food preferences column is a string containing various food types that these subjects prefer. Let’s say someone prefers fastfood, someone prefers fastfood and beverages,someone prefers salad and spicy food.
Labels are not given for the testing set on purpose. The score based on your predictions is calculated automatically by us.