A category column has text values, and the algorithm needs numbers. What do you apply?
Why C is the answer
One-hot encoding
Encoding converts categories into numeric features.
In detail
- One-hot encoding turns categories into numbers.
- Many categories create many columns.
Use case
An illustrative scenario, not a real incident.
A column holds red, blue and green. One-hot encoding creates a numeric column for each.
See it in different ways
flowchart LR A["Raw data in S3"] --> B["Clean and transform"] B --> C["Feature engineering"] C --> D["Check quality and bias"] D --> E["Training set"]
mindmap
root((Data preparation))
Missing values
Impute
Categories
One-hot encoding
Ranges
Scaling
Imbalance
Resampling
Class weights
Leakage
Remove future datamindmap
root(("Color column"))
n1["One-hot columns"]
n2["is_red"]
n3["is_blue"]
n4["is_green"]Key point: Encoding turns categories into numbers.
Why the other options are wrong
- A. Dropout on the output layer of the network
- Dropout is regularization.
- B. Early stopping during the first training epoch
- Early stopping is about training length.
- D. A larger batch size for the training job
- Batch size does not encode anything.