MS-DS Master of Data science FREE MS-DS Master of Data science Data Wrangling and Preprocessing Questions and Answers 3

Question 1

What is the key difference between StandardScaler and RobustScaler in scikit-learn?

Accepted Answer

RobustScaler uses median and IQR making it less sensitive to outliers

Answer

RobustScaler centers data using the median and scales using the interquartile range, making it robust to outliers unlike StandardScaler which uses mean and standard deviation.

Question 2

Which technique is used to detect and handle duplicate records that are not exact matches but refer to the same entity?

Accepted Answer

Record linkage or fuzzy matching

Answer

Record linkage and fuzzy matching algorithms identify approximate duplicates by comparing similarity scores across fields like names and addresses.

Question 3

When applying a pipeline in scikit-learn, why should you fit the preprocessor only on training data and then transform both training and test data?

Accepted Answer

To prevent data leakage from the test set into the model

Answer

Fitting on training data only ensures that no information from the test set influences the preprocessing parameters, preventing data leakage that would give overly optimistic performance estimates.

Question 4

What problem does the Synthetic Minority Over-sampling Technique (SMOTE) address in data preprocessing?

Accepted Answer

Class imbalance by generating synthetic minority class samples

Answer

SMOTE generates synthetic examples of the minority class by interpolating between existing minority samples, helping balance the class distribution for better model training.

Question 5

Which pandas method would you use to apply different aggregation functions to different columns after a groupby operation?

Accepted Answer

agg() with a dictionary mapping columns to functions

Answer

The agg() method accepts a dictionary where keys are column names and values are the aggregation functions to apply to each respective column.

MS-DS Master of Data science Practice Test

MS-DS Master of Data science Practice Test

MS-DS Master of Data science FREE MS-DS Master of Data science Data Wrangling and Preprocessing Questions and Answers 3