D497 DTMG 3221
Data Wrangling
3.0 Credits
Objective Assessment Review (Qns &
Ans)
2025
©2025
, Question 1:
An organization receives raw logs from various systems in which date
formats, currency symbols, and case sensitivity vary widely. Which
technique is most critical to standardize these inconsistencies during data
wrangling?
- A. Manually reviewing each record
- B. Using regular expressions combined with parsing libraries
- C. Aggregating all entries and then sorting alphabetically
- D. Dropping all columns that exhibit inconsistencies
Correct ANS: B. Using regular expressions combined with parsing
libraries
Rationale:
Regular expressions and specialized parsing libraries (e.g., Python’s
`dateutil` for dates) offer flexible, automated methods to detect and
convert inconsistent formats into standard representations—essential for
high-quality data cleansing.
---
Question 2:
When handling missing values in a high-dimensional dataset, which
imputation technique leverages patterns in the data by using similar
records to estimate missing values?
- A. Mean or median imputation
- B. K-nearest neighbors (KNN) imputation
- C. Dropping all incomplete rows
- D. Imputation using constant zeros
Correct ANS: B. K-nearest neighbors (KNN) imputation
Rationale:
KNN imputation uses the similarity between records to estimate missing
values, which often produces more realistic estimates compared to
simple mean or median substitutions, particularly in complex datasets.
©2025
, ---
Question 3:
A data engineer is merging several datasets from different sources,
where the same variables are labeled differently (e.g., “Date,”
“timestamp,” “dt”). Which concept is most crucial to ensure a successful
integration?
- A. Data deduplication
- B. Schema mapping
- C. Data encryption
- D. Aggregation
Correct ANS: B. Schema mapping
Rationale:
Schema mapping involves aligning column names, data types, and
structures across datasets, enabling a coherent merged dataset. This
process is especially important when integrating heterogeneous data
sources from different origins.
---
Question 4:
To extract and structure information from semi‑structured data formats
such as XML or JSON in a big data context, which approach is most
appropriate?
- A. Manual data entry
- B. Utilizing specialized parsers (e.g., xml.etree or json libraries)
- C. Converting the files into plain text
- D. Relying solely on spreadsheet software
Correct ANS: B. Utilizing specialized parsers (e.g., xml.etree or json
libraries)
Rationale:
Specialized parsing libraries automatically extract and convert structured
©2025
Data Wrangling
3.0 Credits
Objective Assessment Review (Qns &
Ans)
2025
©2025
, Question 1:
An organization receives raw logs from various systems in which date
formats, currency symbols, and case sensitivity vary widely. Which
technique is most critical to standardize these inconsistencies during data
wrangling?
- A. Manually reviewing each record
- B. Using regular expressions combined with parsing libraries
- C. Aggregating all entries and then sorting alphabetically
- D. Dropping all columns that exhibit inconsistencies
Correct ANS: B. Using regular expressions combined with parsing
libraries
Rationale:
Regular expressions and specialized parsing libraries (e.g., Python’s
`dateutil` for dates) offer flexible, automated methods to detect and
convert inconsistent formats into standard representations—essential for
high-quality data cleansing.
---
Question 2:
When handling missing values in a high-dimensional dataset, which
imputation technique leverages patterns in the data by using similar
records to estimate missing values?
- A. Mean or median imputation
- B. K-nearest neighbors (KNN) imputation
- C. Dropping all incomplete rows
- D. Imputation using constant zeros
Correct ANS: B. K-nearest neighbors (KNN) imputation
Rationale:
KNN imputation uses the similarity between records to estimate missing
values, which often produces more realistic estimates compared to
simple mean or median substitutions, particularly in complex datasets.
©2025
, ---
Question 3:
A data engineer is merging several datasets from different sources,
where the same variables are labeled differently (e.g., “Date,”
“timestamp,” “dt”). Which concept is most crucial to ensure a successful
integration?
- A. Data deduplication
- B. Schema mapping
- C. Data encryption
- D. Aggregation
Correct ANS: B. Schema mapping
Rationale:
Schema mapping involves aligning column names, data types, and
structures across datasets, enabling a coherent merged dataset. This
process is especially important when integrating heterogeneous data
sources from different origins.
---
Question 4:
To extract and structure information from semi‑structured data formats
such as XML or JSON in a big data context, which approach is most
appropriate?
- A. Manual data entry
- B. Utilizing specialized parsers (e.g., xml.etree or json libraries)
- C. Converting the files into plain text
- D. Relying solely on spreadsheet software
Correct ANS: B. Utilizing specialized parsers (e.g., xml.etree or json
libraries)
Rationale:
Specialized parsing libraries automatically extract and convert structured
©2025
