Data Cleaning and Standardization PCAD-31 Practice Questions (Page 3)

Questions 11–15

1. 11foundation · easy

   Why is standardizing categorical values important in data cleaning?

   • ATo ensure consistent representation, such as 'Male' vs. 'male'
   • BTo remove duplicate rows
   • CTo scale the values to a common range
   • DTo convert categorical values to numerical values
   Reveal Solution Discussion Select an answer first
2. 12application · medium

   A data analyst receives a dataset from a web form. The 'email' column contains values like 'user@example.com', 'USER@EXAMPLE.COM', and 'user@example.com '. The 'phone' column contains values like '(555) 123-4567' and '555-123-4567'. The analyst needs to identify duplicate customers. What is the most critical issue to address before deduplication?

   • ASort the dataset by the email column to visually identify duplicates.
   • BApply min-max scaling to the email and phone columns.
   • CStandardize the email and phone columns by trimming whitespace and converting to a consistent case and format.
   • DRemove all rows with missing values in the email column.
   Reveal Solution Discussion Select an answer first
4. 13application · medium

   A financial analyst is building a linear regression model to predict loan default. The dataset includes 'credit_score' (ranging from 300 to 850) and 'annual_income' (ranging from $15,000 to $500,000). The analyst wants to interpret the model coefficients directly to understand the relative importance of each feature. Which preprocessing step is most appropriate?

   • AApply z-score standardization to both features so they have a mean of 0 and a standard deviation of 1.
   • BApply min-max scaling to both features to bring them into a [0, 1] range.
   • CLeave the features as-is because linear regression does not require scaling.
   • DRemove outliers from both features using the IQR method.
   Reveal Solution Discussion Select an answer first
5. 14application · medium

   A multinational e-commerce company collects customer addresses. The 'country' column contains 'USA', 'U.S.A.', 'United States', and 'US'. The 'zip_code' column contains '10001' and '10001-1234'. The analyst needs to aggregate sales by country. What is the most appropriate preprocessing step?

   • AMap all country name variants to a single canonical value (e.g., 'US') and standardize zip codes to a consistent format.
   • BRemove the 'zip_code' column because it is not needed for country-level aggregation.
   • CGroup by the 'country' column as-is, since the variations are minor.
   • DApply one-hot encoding to the 'country' column before aggregation.
   Reveal Solution Discussion Select an answer first
6. 15foundation · easy

   In a dataset of customer records, a column for 'age' contains the value -5. How should this value be classified?

   • AErroneous data
   • BOutlier
   • CMissing value
   • DDuplicate
   Reveal Solution Discussion Select an answer first