7. Create Observation Tables

Create Observation Table¶

An Observation Set is a collection that combines specific moments in history (timestamps) with related entity key values, used to determine feature values for those moments. Think of it as the backbone of a training dataset.

An Observation Table is its representation in the feature store.

You can either:

upload an Observation Table from a parquet or csv file
create it from a View,
or create it from a Source Table.

This guide explains how to configure Observation Tables from a Source Table and link them to our Credit Default context and use case.

We will create Applications up to March 2025: Credit Default Observations for training up to March 2025.

For an example how to upload an Observation Table or create it from a view, check out the Grocery SDK Tutorial. The tutorial also covers how to add Target values when your target has been registered with a logical approach.

In [1]:

            
                Copied!
                
import featurebyte as fb
import pandas as pd

# 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
import pandas as pd

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

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

16:59:37 | INFO     | SDK version: 3.2.0.dev66
INFO    :featurebyte:SDK version: 3.2.0.dev66
16:59:37 | INFO     | No catalog activated.
INFO    :featurebyte:No catalog activated.
16:59:37 | INFO     | Using profile: staging
INFO    :featurebyte:Using profile: staging
16:59:37 | INFO     | Using configuration file at: /Users/gxav/.featurebyte/config.yaml
INFO    :featurebyte:Using configuration file at: /Users/gxav/.featurebyte/config.yaml
16:59:37 | INFO     | Active profile: staging (https://staging.featurebyte.com/api/v1)
INFO    :featurebyte:Active profile: staging (https://staging.featurebyte.com/api/v1)
16:59:37 | INFO     | SDK version: 3.2.0.dev66
INFO    :featurebyte:SDK version: 3.2.0.dev66
16:59:37 | INFO     | No catalog activated.
INFO    :featurebyte:No catalog activated.
16:59:37 | INFO     | Catalog activated: Credit Default Dataset SDK Tutorial
INFO    :featurebyte.api.catalog:Catalog activated: Credit Default Dataset SDK Tutorial
16:06:21 | WARNING  | Remote SDK version (1.1.0.dev7) is different from local (1.1.0.dev1). Update local SDK to avoid unexpected behavior.
16:06:21 | INFO     | No catalog activated.
16:06:21 | INFO     | Catalog activated: Grocery Dataset Tutorial

Locate Source Table¶

In [2]:

            
                Copied!
                
                    
                    
                
                

        
ds = catalog.get_data_source()
DATABASE_NAME = "DEMO_DATASETS"
SCHEMA_NAME = "CREDIT_DEFAULT"

training_observations = ds.get_source_table(
    database_name=DATABASE_NAME,
    schema_name=SCHEMA_NAME,
    table_name="OBSERVATIONS_WITH_TARGET",
)
ds = catalog.get_data_source()
DATABASE_NAME = "DEMO_DATASETS"
SCHEMA_NAME = "CREDIT_DEFAULT"

training_observations = ds.get_source_table(
    database_name=DATABASE_NAME,
    schema_name=SCHEMA_NAME,
    table_name="OBSERVATIONS_WITH_TARGET",
)

Locate the Target, Context and Use Case, the observation tables will be linked to¶

In [3]:

            
                Copied!
                
context_name = "New Loan Application"
target_name = "Loan_Default"
use_case_name = "Loan Default by client"

usecase = catalog.get_use_case(use_case_name)
context_name = "New Loan Application"
target_name = "Loan_Default"
use_case_name = "Loan Default by client"

usecase = catalog.get_use_case(use_case_name)

Create Applications up to March 2025 table¶

In [4]:

            
                Copied!
                
                    
                    
                
                

        
observation_train_table_name = "Applications up to March 2025"

observation_train_table = training_observations.create_observation_table(
    name=observation_train_table_name,
    sample_rows=None,
    sample_from_timestamp="2019-04-01",
    sample_to_timestamp="2025-04-01",
    context_name=context_name,
    primary_entities=["New Application"],
    target_column=target_name,
)
observation_train_table.update_purpose(fb.Purpose.TRAINING)

# link it to the use case
usecase.add_observation_table(observation_train_table_name)
observation_train_table_name = "Applications up to March 2025"

observation_train_table = training_observations.create_observation_table(
    name=observation_train_table_name,
    sample_rows=None,
    sample_from_timestamp="2019-04-01",
    sample_to_timestamp="2025-04-01",
    context_name=context_name,
    primary_entities=["New Application"],
    target_column=target_name,
)
observation_train_table.update_purpose(fb.Purpose.TRAINING)

# link it to the use case
usecase.add_observation_table(observation_train_table_name)

Done! |████████████████████████████████████████| 100% in 18.3s (0.06%/s)        
Done! |████████████████████████████████████████| 100% in 15.2s (0.07%/s)

List observation tables in catalog¶

In [5]:

            
                Copied!
                
catalog.list_observation_tables()
catalog.list_observation_tables()

Out[5]:

	id	name	type	shape	feature_store_name	created_at
0	68ef627ae645921d591abdd9	Applications up to March 2025	source_table	[307511, 3]	playground	2025-10-15T08:59:47.822000

Concepts in this tutorial¶

SDK reference for¶

In [ ]: