,Exam Blueprint & Instructions
WGU D599 Task 1: Data Profiling and Cleaning | Complete Revised Report, Python Code & Data Analysis | 2026/2027 Updated
Part I · Exam Questions (1-200) with Complete Solutions
1. Data Profiling Fundamentals & Exploratory Data Analysis (22 q) ....5
2. Data Quality Issues: Missing Values, Outliers & Duplicates (23 q) ....6
3. Data Cleaning Techniques: Imputation & Transformation (22 q) ....7
4. Python Implementation: pandas, numpy & Data Wrangling (22 q) ....8
5. Data Types, Encoding & Feature Engineering (22 q) ....9
6. Data Validation & Consistency Checks (22 q) . . . . 10
7. WGU D599 Task 1 Report Requirements & Documentation (22 q) . . . . 11
8. Visualization: Missingness Matrix & Distribution Plots (22 q) . . . . 12
9. Business Implications, Data Governance & Recommendations (23 q) . . . . 13
Instructions:
• 200 original questions with complete solutions for WGU D599 Task 1.
• Covers data profiling, cleaning, pandas, validation, visualization.
• Python uses pandas, numpy, missingno, sklearn per WGU standards.
• Correct answers and detailed rationales follow each item immediately.
• Original study material with complete solutions, not actual WGU assessment.
,SECTION ONE: QUESTIONS 1-200
Choose the single best answer. Correct answers and complete solutions follow each item.
Data Profiling Fundamentals & Exploratory Data Analysis
Question 1. In WGU D599 Task 1, what is the correct approach for encoding categorical
variables with OneHotEncoder or LabelEncoder while avoiding data leakage?
A. Drop all rows with any missing values without analysis, losing 60% data and biasing results
B. Ignore outliers and duplicate data, proceeding directly to modeling without profiling or
documentation
C. Convert data types without validation and encode categoricals on full dataset causing data
leakage
D. Encode categoricals with OneHotEncoder for nominal and OrdinalEncoder for ordinal, fit only
on training data to prevent leakage
CORRECT ANSWER: D. Encode categoricals with OneHotEncoder for nominal and OrdinalEncoder for
ordinal, fit only on training data to prevent leakage
RATIONALE: For WGU D599 Task 1 data profiling and cleaning, encoding categorical variables with
OneHotEncoder or LabelEncoder while avoiding data leakage requires correct methodology. Correct (D):
Encode categoricals with OneHotEncoder for nominal and OrdinalEncoder for ordinal, fit only on
training data to prevent leakage. This ensures data quality, reproducibility, and WGU rubric
compliance (Python code, data analysis, report). Incorrect options cause data loss, leakage, or
rubric failure.
Question 2. When implementing handling missing data via mean/median imputation, forward
fill, or dropping based on business context in Python, which code avoids errors?
A. Omit documentation of profiling steps, cleaning decisions, and business impact from WGU D599
Task 1 report
B. Identify missingness with df.isnull().sum() and missingno; impute based on mechanism
(MCAR/MAR) and business logic, document justification
C. Ignore outliers and duplicate data, proceeding directly to modeling without profiling or
documentation
D. Convert data types without validation and encode categoricals on full dataset causing data
leakage
CORRECT ANSWER: B. Identify missingness with df.isnull().sum() and missingno; impute based
on mechanism (MCAR/MAR) and business logic, document justification
RATIONALE: For WGU D599 Task 1 data profiling and cleaning, handling missing data via mean/median
imputation, forward fill, or dropping based on business context requires correct methodology.
Correct (B): Identify missingness with df.isnull().sum() and missingno; impute based on mechanism
(MCAR/MAR) and business logic, document justification. This ensures data quality, reproducibility,
and WGU rubric compliance (Python code, data analysis, report). Incorrect options cause data loss,
leakage, or rubric failure.
Question 3. A student observes explaining difference between data profiling and data
cleaning in data analysis workflow in dataset. What should be done?
A. Drop all rows with any missing values without analysis, losing 60% data and biasing results
B. Correct D599 Task 1 methodology: explaining difference between data profiling and data
cleaning in data anal with Python data wrangling, validation, and rubric-compliant report
C. Omit documentation of profiling steps, cleaning decisions, and business impact from WGU D599
, Task 1 report
D. Ignore outliers and duplicate data, proceeding directly to modeling without profiling or
documentation
CORRECT ANSWER: B. Correct D599 Task 1 methodology: explaining difference between data
profiling and data cleaning in data anal with Python data wrangling, validation, and rubric-
compliant report
RATIONALE: For WGU D599 Task 1 data profiling and cleaning, explaining difference between data
profiling and data cleaning in data analysis workflow requires correct methodology. Correct (B):
Correct D599 Task 1 methodology: explaining difference between data profiling and data cleaning in
data anal with Python data wrangling, validation, and rubric-compliant report. This ensures data
quality, reproducibility, and WGU rubric compliance (Python code, data analysis, report). Incorrect
options cause data loss, leakage, or rubric failure.
Question 4. Which Python snippet correctly implements removing duplicate rows with
drop_duplicates() and validating uniqueness of key identifiers?
A. Omit documentation of profiling steps, cleaning decisions, and business impact from WGU D599
Task 1 report
B. Drop all rows with any missing values without analysis, losing 60% data and biasing results
C. Ignore outliers and duplicate data, proceeding directly to modeling without profiling or
documentation
D. Use df.duplicated() and drop_duplicates() to remove exact duplicates, validate key
uniqueness, report count removed
CORRECT ANSWER: D. Use df.duplicated() and drop_duplicates() to remove exact duplicates,
validate key uniqueness, report count removed
RATIONALE: For WGU D599 Task 1 data profiling and cleaning, removing duplicate rows with
drop_duplicates() and validating uniqueness of key identifiers requires correct methodology. Correct
(D): Use df.duplicated() and drop_duplicates() to remove exact duplicates, validate key uniqueness,
report count removed. This ensures data quality, reproducibility, and WGU rubric compliance (Python
code, data analysis, report). Incorrect options cause data loss, leakage, or rubric failure.
Question 5. What is the primary purpose of detecting outliers using IQR method and Z-score
and deciding to cap, transform, or remove in data profiling?
A. Convert data types without validation and encode categoricals on full dataset causing data
leakage
B. Omit documentation of profiling steps, cleaning decisions, and business impact from WGU D599
Task 1 report
C. Ignore outliers and duplicate data, proceeding directly to modeling without profiling or
documentation
D. Detect outliers via IQR (Q1-1.5*IQR, Q3+1.5*IQR) and Z-score; decide to cap, transform, or
keep based on domain, document in report
CORRECT ANSWER: D. Detect outliers via IQR (Q1-1.5*IQR, Q3+1.5*IQR) and Z-score; decide to
cap, transform, or keep based on domain, document in report
RATIONALE: For WGU D599 Task 1 data profiling and cleaning, detecting outliers using IQR method and
Z-score and deciding to cap, transform, or remove requires correct methodology. Correct (D): Detect
outliers via IQR (Q1-1.5*IQR, Q3+1.5*IQR) and Z-score; decide to cap, transform, or keep based on
domain, document in report. This ensures data quality, reproducibility, and WGU rubric compliance
(Python code, data analysis, report). Incorrect options cause data loss, leakage, or rubric failure.
WGU D599 Task 1: Data Profiling and Cleaning | Complete Revised Report, Python Code & Data Analysis | 2026/2027 Updated
Part I · Exam Questions (1-200) with Complete Solutions
1. Data Profiling Fundamentals & Exploratory Data Analysis (22 q) ....5
2. Data Quality Issues: Missing Values, Outliers & Duplicates (23 q) ....6
3. Data Cleaning Techniques: Imputation & Transformation (22 q) ....7
4. Python Implementation: pandas, numpy & Data Wrangling (22 q) ....8
5. Data Types, Encoding & Feature Engineering (22 q) ....9
6. Data Validation & Consistency Checks (22 q) . . . . 10
7. WGU D599 Task 1 Report Requirements & Documentation (22 q) . . . . 11
8. Visualization: Missingness Matrix & Distribution Plots (22 q) . . . . 12
9. Business Implications, Data Governance & Recommendations (23 q) . . . . 13
Instructions:
• 200 original questions with complete solutions for WGU D599 Task 1.
• Covers data profiling, cleaning, pandas, validation, visualization.
• Python uses pandas, numpy, missingno, sklearn per WGU standards.
• Correct answers and detailed rationales follow each item immediately.
• Original study material with complete solutions, not actual WGU assessment.
,SECTION ONE: QUESTIONS 1-200
Choose the single best answer. Correct answers and complete solutions follow each item.
Data Profiling Fundamentals & Exploratory Data Analysis
Question 1. In WGU D599 Task 1, what is the correct approach for encoding categorical
variables with OneHotEncoder or LabelEncoder while avoiding data leakage?
A. Drop all rows with any missing values without analysis, losing 60% data and biasing results
B. Ignore outliers and duplicate data, proceeding directly to modeling without profiling or
documentation
C. Convert data types without validation and encode categoricals on full dataset causing data
leakage
D. Encode categoricals with OneHotEncoder for nominal and OrdinalEncoder for ordinal, fit only
on training data to prevent leakage
CORRECT ANSWER: D. Encode categoricals with OneHotEncoder for nominal and OrdinalEncoder for
ordinal, fit only on training data to prevent leakage
RATIONALE: For WGU D599 Task 1 data profiling and cleaning, encoding categorical variables with
OneHotEncoder or LabelEncoder while avoiding data leakage requires correct methodology. Correct (D):
Encode categoricals with OneHotEncoder for nominal and OrdinalEncoder for ordinal, fit only on
training data to prevent leakage. This ensures data quality, reproducibility, and WGU rubric
compliance (Python code, data analysis, report). Incorrect options cause data loss, leakage, or
rubric failure.
Question 2. When implementing handling missing data via mean/median imputation, forward
fill, or dropping based on business context in Python, which code avoids errors?
A. Omit documentation of profiling steps, cleaning decisions, and business impact from WGU D599
Task 1 report
B. Identify missingness with df.isnull().sum() and missingno; impute based on mechanism
(MCAR/MAR) and business logic, document justification
C. Ignore outliers and duplicate data, proceeding directly to modeling without profiling or
documentation
D. Convert data types without validation and encode categoricals on full dataset causing data
leakage
CORRECT ANSWER: B. Identify missingness with df.isnull().sum() and missingno; impute based
on mechanism (MCAR/MAR) and business logic, document justification
RATIONALE: For WGU D599 Task 1 data profiling and cleaning, handling missing data via mean/median
imputation, forward fill, or dropping based on business context requires correct methodology.
Correct (B): Identify missingness with df.isnull().sum() and missingno; impute based on mechanism
(MCAR/MAR) and business logic, document justification. This ensures data quality, reproducibility,
and WGU rubric compliance (Python code, data analysis, report). Incorrect options cause data loss,
leakage, or rubric failure.
Question 3. A student observes explaining difference between data profiling and data
cleaning in data analysis workflow in dataset. What should be done?
A. Drop all rows with any missing values without analysis, losing 60% data and biasing results
B. Correct D599 Task 1 methodology: explaining difference between data profiling and data
cleaning in data anal with Python data wrangling, validation, and rubric-compliant report
C. Omit documentation of profiling steps, cleaning decisions, and business impact from WGU D599
, Task 1 report
D. Ignore outliers and duplicate data, proceeding directly to modeling without profiling or
documentation
CORRECT ANSWER: B. Correct D599 Task 1 methodology: explaining difference between data
profiling and data cleaning in data anal with Python data wrangling, validation, and rubric-
compliant report
RATIONALE: For WGU D599 Task 1 data profiling and cleaning, explaining difference between data
profiling and data cleaning in data analysis workflow requires correct methodology. Correct (B):
Correct D599 Task 1 methodology: explaining difference between data profiling and data cleaning in
data anal with Python data wrangling, validation, and rubric-compliant report. This ensures data
quality, reproducibility, and WGU rubric compliance (Python code, data analysis, report). Incorrect
options cause data loss, leakage, or rubric failure.
Question 4. Which Python snippet correctly implements removing duplicate rows with
drop_duplicates() and validating uniqueness of key identifiers?
A. Omit documentation of profiling steps, cleaning decisions, and business impact from WGU D599
Task 1 report
B. Drop all rows with any missing values without analysis, losing 60% data and biasing results
C. Ignore outliers and duplicate data, proceeding directly to modeling without profiling or
documentation
D. Use df.duplicated() and drop_duplicates() to remove exact duplicates, validate key
uniqueness, report count removed
CORRECT ANSWER: D. Use df.duplicated() and drop_duplicates() to remove exact duplicates,
validate key uniqueness, report count removed
RATIONALE: For WGU D599 Task 1 data profiling and cleaning, removing duplicate rows with
drop_duplicates() and validating uniqueness of key identifiers requires correct methodology. Correct
(D): Use df.duplicated() and drop_duplicates() to remove exact duplicates, validate key uniqueness,
report count removed. This ensures data quality, reproducibility, and WGU rubric compliance (Python
code, data analysis, report). Incorrect options cause data loss, leakage, or rubric failure.
Question 5. What is the primary purpose of detecting outliers using IQR method and Z-score
and deciding to cap, transform, or remove in data profiling?
A. Convert data types without validation and encode categoricals on full dataset causing data
leakage
B. Omit documentation of profiling steps, cleaning decisions, and business impact from WGU D599
Task 1 report
C. Ignore outliers and duplicate data, proceeding directly to modeling without profiling or
documentation
D. Detect outliers via IQR (Q1-1.5*IQR, Q3+1.5*IQR) and Z-score; decide to cap, transform, or
keep based on domain, document in report
CORRECT ANSWER: D. Detect outliers via IQR (Q1-1.5*IQR, Q3+1.5*IQR) and Z-score; decide to
cap, transform, or keep based on domain, document in report
RATIONALE: For WGU D599 Task 1 data profiling and cleaning, detecting outliers using IQR method and
Z-score and deciding to cap, transform, or remove requires correct methodology. Correct (D): Detect
outliers via IQR (Q1-1.5*IQR, Q3+1.5*IQR) and Z-score; decide to cap, transform, or keep based on
domain, document in report. This ensures data quality, reproducibility, and WGU rubric compliance
(Python code, data analysis, report). Incorrect options cause data loss, leakage, or rubric failure.
