
Explanation:
The Error count statistic specifically tracks missing, malformed, or anomalous values in each column, making it the optimal choice for detecting odd or missing values. The Profile statistic provides general statistical summaries but doesn't focus on data quality issues. The Std deviation measures data variability but doesn't identify missing or malformed values. The Type statistic only shows data types without indicating data quality problems. The community discussion shows 100% consensus on option C, with the highest upvoted comment (9 upvotes) clearly explaining that Error count is designed for this exact purpose - identifying missing values and values that don't conform to expected data types.
Ultimate access to all questions.
You are profiling data in Azure Machine Learning studio and need to identify columns with anomalous or missing values.
Which statistic should you analyze?
A
Profile
B
Std deviation
C
Error count
D
Type
No comments yet.