Working with Numerical Data: Test Your Knowledge

1. Which of the following techniques is not a form of feature engineering?

   Binning

   Hyperparameter tuning

   Bucketing

   Normalizing

2. You are training a model on infant health data. One of your features is birth_weight. You would like to normalize these birth_weight values to train the model more efficiently. Which of the following normalization techniques would likely be the best choice?

   Clipping

   Linear scaling

   Log scaling

   Z-score scaling

3. True or False: Binning is a technique for transforming categorical data into numerical data.

   True

   False

4. Your training data for a shoe recommendation model contains the feature shoe_size, which should contain values between 6 and 16. The following table shows the shoe_size values for six examples in the dataset:

   Example	shoe_size
   1	8.5
   2	9
   3	N/A
   4	105
   5	11
   6	9

   Which examples should you consider scrubbing from the dataset prior to training? (Choose all that apply.)

   Choose as many answers as you see fit.

   Example 1

   Either Example 2 or Example 6

   Example 3

   Example 4

   Example 5

5. Fill in the blank in the following sentence:
   During feature engineering, synthetic features can be created to ___.

   Replace missing feature values

   Supplement human-labeled data with machine-labeled data

   Model non-linear relationships between two features

   Pre-train the model

Submit answers