Data Science Data Cleaning and Preparation 3

Question 1

The interquartile range (IQR) method is commonly used to detect:

Accepted Answer

Outliers

Answer

Missing values

Answer

Duplicates

Answer

Encoding errors

Question 2

Min-max scaling transforms a feature to which range by default?

Accepted Answer

[0, 1]

Answer

[-1, 1]

Answer

[0, 100]

Answer

Mean 0, std 1

Question 3

Z-score standardization produces data with:

Accepted Answer

Mean of 0 and standard deviation of 1

Answer

Range of 0 to 1

Answer

All positive integers

Answer

No missing values

Question 4

Which encoding creates a separate binary column for each category value?

Accepted Answer

One-hot encoding

Answer

Ordinal encoding

Answer

Mean imputation

Answer

Log transform

Question 5

Why scale features before training a k-nearest-neighbors model?

Accepted Answer

Distance calculations are sensitive to feature magnitude

Answer

KNN cannot handle categorical labels

Answer

Scaling removes missing values

Answer

It increases the number of neighbors

Question 6

Applying a log transform to a right-skewed feature primarily aims to:

Accepted Answer

Reduce skew and compress large values

Answer

Add missing values

Answer

Convert text to numbers

Answer

Remove duplicates

Question 7

Removing a data point with age = 250 from a human dataset is best described as:

Accepted Answer

Handling an invalid/implausible value

Answer

Normalizing

Answer

Encoding

Answer

Sampling