Handle Missing and Categorical Data SNOWPRO-ADVANCED-DATA-SCIENTIST Practice Questions (Page 4)

Questions 16–20

1. 16foundation · easy

   Which encoding method creates one binary column for each unique category, with a 1 indicating the presence of that category and 0 otherwise?

   • ALabel encoding
   • BFrequency encoding
   • COne-hot encoding
   • DOrdinal encoding
   Reveal Solution Discussion Select an answer first
2. 17foundation · easy

   Which encoding technique replaces each category with the proportion of rows that belong to that category?

   • AFrequency encoding
   • BOrdinal encoding
   • COne-hot encoding
   • DTarget encoding
   Reveal Solution Discussion Select an answer first
4. 18foundation · easy

   Which imputation technique uses other features in the dataset to predict missing values, often by training a model on the observed cases?

   • AMode imputation
   • BMean imputation
   • CListwise deletion
   • DModel-based imputation
   Reveal Solution Discussion Select an answer first
5. 19application · medium

   A data scientist is building a model to predict whether a user will click on an ad. The dataset has a 'browser' feature with 10 unique values, and a 'user_agent' feature with 50,000 unique values. The team plans to use a logistic regression model. What is the most appropriate encoding strategy?

   • ATarget encode both 'browser' and 'user_agent'.
   • BOne-hot encode both 'browser' and 'user_agent'.
   • CLabel encode both 'browser' and 'user_agent'.
   • DOne-hot encode 'browser' and frequency encode 'user_agent'.
   Reveal Solution Discussion Select an answer first
6. 20application · medium

   A data scientist at a retail bank is preparing a churn-prediction dataset. The 'income' column has 12% missing values. Analysis shows that missingness is strongly correlated with the 'loan_default' flag: customers who defaulted are far more likely to have missing income. The team plans to build a logistic regression model. What is the most appropriate first step?

   • AAdd a binary 'income_missing' indicator and then apply multiple imputation.
   • BPerform mean imputation on 'income' because the missingness is low at 12%.
   • CDelete all rows with missing income because the missingness is MNAR.
   • DReplace missing income with the median income of the entire dataset.
   Reveal Solution Discussion Select an answer first