Feature stores concept in MLOps - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load features from a feature store client.

MLOps

features = feature_store_client.[1]('user_features')

Drag options to blanks, or click blank then click option'

Aget_features

Bdelete_features

Cupdate_features

Dsave_features

Attempts:

3 left

💡 Hint

Common Mistakes

Using save_features instead of get_features will try to save data, not load it.

delete_features removes data, not loads it.

The method get_features is used to retrieve features from the feature store.

2fill in blank

medium

Complete the code to write features into the feature store.

MLOps

feature_store_client.[1](features_df, 'transaction_features')

Drag options to blanks, or click blank then click option'

Afetch_features

Bload_features

Cwrite_features

Dremove_features

Attempts:

3 left

💡 Hint

Common Mistakes

Using load_features would try to read, not write.

fetch_features is for retrieving, not saving.

The method write_features is used to save or write features into the feature store.

3fill in blank

hard

Fix the error in the code to retrieve a feature vector by its key.

MLOps

feature_vector = feature_store_client.get_feature_vector([1]='user_123')

Drag options to blanks, or click blank then click option'

Akey

Bfeature_id

Cvector_key

Dfeature_key

Attempts:

3 left

💡 Hint

Common Mistakes

Using feature_id or feature_key causes errors because those are not valid parameter names.

vector_key is not recognized by the method.

The correct parameter name to specify the key for the feature vector is key.

4fill in blank

hard

Fill both blanks to create a feature store client and connect to the store.

MLOps

client = FeatureStoreClient([1]='[2]')

Drag options to blanks, or click blank then click option'

Aurl

Bapi_key

Cendpoint

Dtoken

Attempts:

3 left

💡 Hint

Common Mistakes

Using api_key or token as the parameter name instead of endpoint.

Confusing the URL with the API key.

The client is created by specifying the endpoint parameter with the URL of the feature store.

5fill in blank

hard

Fill all three blanks to define a feature group with name, version, and description.

MLOps

feature_group = FeatureGroup(name='[1]', version=[2], description='[3]')

Drag options to blanks, or click blank then click option'

Auser_activity

B1

CStores user activity features

Dtransaction_data

Attempts:

3 left

💡 Hint

Common Mistakes

Using transaction_data as the name when the description is about user activity.

Putting version as a string instead of a number.

The feature group is named 'user_activity', version is 1, and the description explains it stores user activity features.