Engineer Features for Models SNOWPRO-ADVANCED-DATA-SCIENTIST Practice Questions (Page 4)

Questions 16–20

1. 16foundation · easy

   Which of the following is a common automated feature engineering library?

   • AFeaturetools
   • BPandas
   • CScikit-learn
   • DTensorFlow
   Reveal Solution Discussion Select an answer first
2. 17foundation · easy

   Which encoding method assigns a unique integer to each category of an ordinal variable?

   • AMin-max scaling
   • BLabel encoding
   • CTarget encoding
   • DOne-hot encoding
   Reveal Solution Discussion Select an answer first
4. 18application · medium

   A data scientist is building a model to predict credit risk. The 'age' feature has a non-linear relationship with risk, where risk is high for very young and very old applicants but lower in the middle. The scientist is using a logistic regression model. Which transformation of 'age' would best capture this relationship?

   • AApply Min-Max scaling to 'age' and use it as-is.
   • BCreate a squared term 'age^2' and include it alongside 'age'.
   • CReplace 'age' with its rank among all samples.
   • DBin 'age' into 5 equal-width bins and use them as ordinal features.
   Reveal Solution Discussion Select an answer first
5. 19application · medium

   A data scientist is training a neural network on a dataset where one feature, 'income', has a heavily right-skewed distribution with a few extreme outliers. The network is struggling to learn from this feature. Which transformation should be applied to 'income' before feeding it to the network?

   • AApply a log transformation to 'income'.
   • BDiscretize 'income' into 10 equal-frequency bins and use the bin index.
   • CApply StandardScaler to 'income' without any other transformation.
   • DApply Min-Max scaling to 'income' without any other transformation.
   Reveal Solution Discussion Select an answer first
6. 20foundation · easy

   For which model type is one-hot encoding typically more suitable than label encoding for nominal categorical variables?

   • AGradient boosting machines
   • BRandom forests
   • CLinear models
   • DDecision trees
   Reveal Solution Discussion Select an answer first