A data scientist is standardizing a large data set that contains website addresses. A specific string inside some of the web addresses needs to be extracted. Which of the following is the best…

Question

Options

• ARegular expressions
• BNamed-entity recognition
• CLarge language model
• DFind and replace

• A
  90% (35)
• B
  5% (2)
• C
  3% (1)
• D
  3% (1)

Explanation

Regular expressions (regex) are purpose-built for pattern matching and extraction within strings, making them ideal for pulling specific substrings from URLs - they're fast, precise, and require no external models or manual effort. Named-entity recognition (B) is an NLP technique designed to identify real-world entities like names and places in natural language text, not for pattern-based string extraction in structured data like URLs. A large language model (C) would be a massive overkill - computationally expensive, non-deterministic, and unnecessary when a simple pattern rule suffices. Find and replace (D) can locate and swap text but doesn't extract a substring into a new field, and it lacks the flexibility to handle variable patterns across thousands of records.

Memory tip: Think of regex as a Swiss Army knife for strings - whenever an exam mentions extracting, matching, or validating patterns in text data (emails, URLs, phone numbers), regex is almost always the answer.

No community discussion yet for this question.