Data Science Data Wrangling and Preprocessing 5

Question 1

When concatenating training feature engineering, fitting an encoder on the full dataset before train/test split causes what problem?

Accepted Answer

Data leakage

Answer

Fitting any preprocessing on the combined data lets test information influence training, which is data leakage.

Question 2

A target variable has 95% class A and 5% class B. Which preprocessing technique addresses this imbalance?

Accepted Answer

Resampling such as SMOTE or undersampling

Answer

Oversampling the minority class (e.g., SMOTE) or undersampling the majority class rebalances skewed class distributions.

Question 3

Why should imputation of missing values inside a cross-validation loop be done within each fold rather than once beforehand?

Accepted Answer

To avoid leaking information across folds

Answer

Imputing before splitting lets statistics from validation folds leak into training, inflating performance estimates.

Question 4

Two highly correlated numeric features (r=0.98) are kept in a linear model. What issue does this raise?

Accepted Answer

Multicollinearity

Answer

Highly correlated predictors cause multicollinearity, making coefficient estimates unstable and hard to interpret.

Question 5

A free-text 'notes' column needs to become model features. Which preprocessing step is most appropriate first?

Accepted Answer

Text vectorization (e.g., TF-IDF or tokenization)

Answer

Raw text must be tokenized and vectorized (e.g., TF-IDF) into numeric features before most models can use it.

Data Science Practice Test