3. Register Entities

Registering entities represented in Credit Default dataset¶

In FeatureByte, an entity models real-world objects and ideas. These entities often correspond to keys in database tables.

Taking our loan applications scenario as an example, we can view "Client", "New Application", "Prior Application", and "Loan" as entities.

To help FeatureByte identify these entities in the data and the columns that represent them, we'll be creating and tagging these entities in this tutorial.

In [7]:

            
                Copied!
                
import featurebyte as fb

# Set your profile to the tutorial environment
fb.use_profile("tutorial")

catalog_name = "Credit Default Dataset SDK Tutorial"
catalog = fb.Catalog.activate(catalog_name)
import featurebyte as fb

# Set your profile to the tutorial environment
fb.use_profile("tutorial")

catalog_name = "Credit Default Dataset SDK Tutorial"
catalog = fb.Catalog.activate(catalog_name)

17:53:44 | INFO     | Using profile: tutorial
17:53:44 | INFO     | Using configuration file at: /Users/gxav/.featurebyte/config.yaml
17:53:44 | INFO     | Active profile: tutorial (https://tutorials.featurebyte.com/api/v1)
17:53:44 | INFO     | SDK version: 3.3.1
17:53:44 | INFO     | No catalog activated.
17:53:44 | INFO     | Catalog activated: Credit Default Dataset SDK Tutorial
16:05:47 | INFO     | Catalog activated: Grocery Dataset Tutorial

Identify Entities in Your Data and Decide their Serving Name¶

When creating an entity, you'll need to define its serving name. This name acts as a unique identifier, particularly during preview or serving requests.

In [8]:

            
                Copied!
                
                    
                    
                
                

        
catalog.create_entity(name="New Application", serving_names=["SK_ID_CURR"])
catalog.create_entity(name="Client", serving_names=["ClientID"])
catalog.create_entity(name="BureauReportedCredit", serving_names=["SK_ID_BUREAU"])
catalog.create_entity(name="PriorApplication", serving_names=["APPLICATION_ID"])
catalog.create_entity(name="Installment", serving_names=["INSTALMENT_ID"])
catalog.create_entity(name="Loan", serving_names=["LOAN_ID"])
catalog.create_entity(name="New Application", serving_names=["SK_ID_CURR"])
catalog.create_entity(name="Client", serving_names=["ClientID"])
catalog.create_entity(name="BureauReportedCredit", serving_names=["SK_ID_BUREAU"])
catalog.create_entity(name="PriorApplication", serving_names=["APPLICATION_ID"])
catalog.create_entity(name="Installment", serving_names=["INSTALMENT_ID"])
catalog.create_entity(name="Loan", serving_names=["LOAN_ID"])

Out[8]:

Entity

name	Loan
created_at	2025-12-04 09:53:46
updated_at	None
description	None
serving_names	['LOAN_ID']
catalog_name	Credit Default Dataset SDK Tutorial

Tag Columns Representing Entities¶

Now that we've established the entities, it's time to guide FeatureByte in mapping these entities to the actual data in our tables.

In [9]:

            
                Copied!
                
                    
                    
                
                

        
application = catalog.get_table("NEW_APPLICATION")
application["ClientID"].as_entity("Client")
application["SK_ID_CURR"].as_entity("New Application")

client_profile = catalog.get_table("CLIENT_PROFILE")
client_profile["ClientID"].as_entity("Client")

bureau = catalog.get_table("BUREAU")
bureau["ClientID"].as_entity("Client")
bureau["SK_ID_BUREAU"].as_entity("BureauReportedCredit")

previous_application = catalog.get_table("PREVIOUS_APPLICATION")
previous_application["ClientID"].as_entity("Client")
previous_application["APPLICATION_ID"].as_entity("PriorApplication")

loan_status = catalog.get_table("LOAN_STATUS")
loan_status["LOAN_ID"].as_entity("Loan")
loan_status['APPLICATION_ID'].as_entity("PriorApplication")

installments_payments = catalog.get_table("INSTALLMENTS_PAYMENTS")
installments_payments["INSTALMENT_ID"].as_entity("Installment")
installments_payments["APPLICATION_ID"].as_entity("PriorApplication")

credit_card_balance = catalog.get_table("CREDIT_CARD_MONTHLY_BALANCE")
credit_card_balance["ClientID"].as_entity("Client")
application = catalog.get_table("NEW_APPLICATION")
application["ClientID"].as_entity("Client")
application["SK_ID_CURR"].as_entity("New Application")

client_profile = catalog.get_table("CLIENT_PROFILE")
client_profile["ClientID"].as_entity("Client")

bureau = catalog.get_table("BUREAU")
bureau["ClientID"].as_entity("Client")
bureau["SK_ID_BUREAU"].as_entity("BureauReportedCredit")

previous_application = catalog.get_table("PREVIOUS_APPLICATION")
previous_application["ClientID"].as_entity("Client")
previous_application["APPLICATION_ID"].as_entity("PriorApplication")

loan_status = catalog.get_table("LOAN_STATUS")
loan_status["LOAN_ID"].as_entity("Loan")
loan_status['APPLICATION_ID'].as_entity("PriorApplication")

installments_payments = catalog.get_table("INSTALLMENTS_PAYMENTS")
installments_payments["INSTALMENT_ID"].as_entity("Installment")
installments_payments["APPLICATION_ID"].as_entity("PriorApplication")

credit_card_balance = catalog.get_table("CREDIT_CARD_MONTHLY_BALANCE")
credit_card_balance["ClientID"].as_entity("Client")

Review Entities Relationships¶

Now, if we list the tables as we did in the previous tutorial, we'll notice that entities have been assigned to each table.

In [10]:

            
                Copied!
                
display(catalog.list_tables())
display(catalog.list_tables())

	id	name	type	status	entities	created_at
0	69315a03b3208c06f266c51c	CREDIT_CARD_MONTHLY_BALANCE	time_series_table	PUBLIC_DRAFT	[Client]	2025-12-04T09:53:08.220000
1	69315a02b3208c06f266c51b	LOAN_STATUS	scd_table	PUBLIC_DRAFT	[Loan, PriorApplication]	2025-12-04T09:53:06.475000
2	69315a00b3208c06f266c51a	PREVIOUS_APPLICATION	event_table	PUBLIC_DRAFT	[PriorApplication, Client]	2025-12-04T09:53:04.927000
3	693159feb3208c06f266c519	INSTALLMENTS_PAYMENTS	event_table	PUBLIC_DRAFT	[Installment, PriorApplication]	2025-12-04T09:53:03.192000
4	693159fdb3208c06f266c518	BUREAU	event_table	PUBLIC_DRAFT	[Client, BureauReportedCredit]	2025-12-04T09:53:01.457000
5	693159fbb3208c06f266c517	CLIENT_PROFILE	scd_table	PUBLIC_DRAFT	[Client]	2025-12-04T09:52:59.647000
6	693159f9b3208c06f266c516	NEW_APPLICATION	dimension_table	PUBLIC_DRAFT	[New Application, Client]	2025-12-04T09:52:57.630000

We can also list entities separately:

In [11]:

            
                Copied!
                
display(catalog.list_entities())
display(catalog.list_entities())

	id	name	serving_names	created_at
0	69315a2adb89f9149ba1ef3a	Loan	[LOAN_ID]	2025-12-04T09:53:46.811000
1	69315a2adb89f9149ba1ef39	Installment	[INSTALMENT_ID]	2025-12-04T09:53:46.488000
2	69315a29db89f9149ba1ef38	PriorApplication	[APPLICATION_ID]	2025-12-04T09:53:46.169000
3	69315a29db89f9149ba1ef37	BureauReportedCredit	[SK_ID_BUREAU]	2025-12-04T09:53:45.816000
4	69315a29db89f9149ba1ef36	Client	[ClientID]	2025-12-04T09:53:45.477000
5	69315a28db89f9149ba1ef35	New Application	[SK_ID_CURR]	2025-12-04T09:53:45.141000

And let's examine the relationships between entities, which FeatureByte has conveniently outlined for us:

In [12]:

            
                Copied!
                
display(catalog.list_relationships())
display(catalog.list_relationships())

	id	relationship_type	entity	related_entity	relation_table	relation_table_type	enabled	created_at	updated_at
0	69315a30da8963295e76f9a2	child_parent	Installment	PriorApplication	INSTALLMENTS_PAYMENTS	event_table	True	2025-12-04T09:53:52.503000	None
1	69315a2fda8963295e76f99a	child_parent	Loan	PriorApplication	LOAN_STATUS	scd_table	True	2025-12-04T09:53:51.579000	None
2	69315a2eda8963295e76f994	child_parent	PriorApplication	Client	PREVIOUS_APPLICATION	event_table	True	2025-12-04T09:53:50.588000	None
3	69315a2dda8963295e76f98c	child_parent	BureauReportedCredit	Client	BUREAU	event_table	True	2025-12-04T09:53:49.708000	None
4	69315a2cda8963295e76f984	child_parent	New Application	Client	NEW_APPLICATION	dimension_table	True	2025-12-04T09:53:48.123000	None

That's it for most important data modeling concepts in FeatureByte. In next tutorials we will look into concepts related to data cleaning and feature engineering.

For more details about concepts we discussed in this tutorial, feel free to explore:¶

More info on Entities