Data Science Data Cleaning and Preparation 4

Question 1

In pandas, df['col'].fillna(method='ffill') does what?

Accepted Answer

Fills missing values with the previous valid value

Answer

Forward fill propagates the last valid observation forward.

Question 2

Which describes 'data leakage' during preparation?

Accepted Answer

Information from the test set influences training preprocessing

Answer

Leakage occurs when test-set information leaks into training, e.g. fitting a scaler on all data.

Question 3

To avoid leakage, a StandardScaler should be fit on:

Accepted Answer

The training set only, then applied to test data

Answer

Fit scalers on training data and transform test data with those parameters.

Question 4

Binning a continuous 'age' column into groups like 'child', 'adult', 'senior' is called:

Accepted Answer

Discretization

Answer

Converting continuous values into discrete bins is discretization.

Question 5

Which is a sign of a poorly structured ('untidy') dataset?

Accepted Answer

Multiple variables stored in a single column

Answer

Tidy data needs one variable per column; cramming several into one breaks that.

Data Science Practice Test