You have a large amount of data from which you want to build a model. Although many of the records of data are complete, there are substantial amounts of records which contain missing data. The…

Question

Options

• AFiller node
• BFilter node
• CSelect node
• DAggregate node

• A
  3% (1)
• B
  8% (3)
• C
  87% (34)
• D
  3% (1)

Explanation

Select node (C) is correct because it allows you to define a condition that determines which records (rows) are kept or excluded from the data stream - for example, excluding any record where a field value is null or missing.

Filler node (A) is wrong because it does the opposite: instead of removing incomplete records, it replaces missing values with substitutes (e.g., mean imputation), keeping all records in the stream.

Filter node (B) is a common trap - it operates on fields (columns), not records. It renames, reorders, or removes entire columns, not individual rows with missing data.

Aggregate node (D) is wrong because it summarizes groups of records into statistics (sums, averages, etc.) and has nothing to do with filtering out incomplete data.

Memory tip: Think "Select = Survivors" - the Select node decides which records survive and pass through. If you need to drop rows, Select is your tool; if you need to drop columns, that's Filter.

No community discussion yet for this question.