8. Create Lookup Feature

Create Lookup features¶

We've learned how to define a target and materialize data using observation tables. Now, let's dive into basic feature engineering.

The most straightforward features we can craft with FeatureByte are known as lookup features. These are either direct columns taken from the source table or simple computations that don't require any aggregations.

In [1]:

import featurebyte as fb

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

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

11:12:12 | INFO     | SDK version: 3.2.0.dev66
INFO    :featurebyte:SDK version: 3.2.0.dev66
11:12:12 | INFO     | No catalog activated.
INFO    :featurebyte:No catalog activated.
11:12:12 | INFO     | Using profile: staging
INFO    :featurebyte:Using profile: staging
11:12:12 | INFO     | Using configuration file at: /Users/gxav/.featurebyte/config.yaml
INFO    :featurebyte:Using configuration file at: /Users/gxav/.featurebyte/config.yaml
11:12:12 | INFO     | Active profile: staging (https://staging.featurebyte.com/api/v1)
INFO    :featurebyte:Active profile: staging (https://staging.featurebyte.com/api/v1)
11:12:12 | INFO     | SDK version: 3.2.0.dev66
INFO    :featurebyte:SDK version: 3.2.0.dev66
11:12:12 | INFO     | No catalog activated.
INFO    :featurebyte:No catalog activated.
11:12:12 | INFO     | Catalog activated: Grocery Dataset SDK Tutorial
INFO    :featurebyte.api.catalog:Catalog activated: Grocery Dataset SDK Tutorial
16:07:20 | INFO     | Using configuration file at: /Users/gxav/.featurebyte/config.yaml
16:07:20 | INFO     | Active profile: tutorial (https://tutorials.featurebyte.com/api/v1)
16:07:20 | WARNING  | Remote SDK version (1.1.0.dev7) is different from local (1.1.0.dev1). Update local SDK to avoid unexpected behavior.
16:07:20 | INFO     | No catalog activated.
16:07:20 | INFO     | Catalog activated: Grocery Dataset Tutorial

In [2]:

# Get view from GROCERYCUSTOMER scd table.
grocerycustomer_view = catalog.get_view("GROCERYCUSTOMER")

# Get view from GROCERYCUSTOMER scd table. grocerycustomer_view = catalog.get_view("GROCERYCUSTOMER")

Create Lookup feature¶

In [3]:

# Create lookup feature from DateOfBirth column for customer entity.
customer_dateofbirth = grocerycustomer_view["DateOfBirth"].as_feature("CUSTOMER_DateOfBirth")

# Create lookup feature from DateOfBirth column for customer entity. customer_dateofbirth = grocerycustomer_view["DateOfBirth"].as_feature("CUSTOMER_DateOfBirth")

Derive Age at the point-in-time of the request observation¶

In [4]:

# Derive Age from the point-in-time and the date of birth.
customer_age = (
    (fb.RequestColumn.point_in_time() - customer_dateofbirth).dt.day / 365.25
).floor()
# Name feature
customer_age.name = "CUSTOMER_Age"

# Derive Age from the point-in-time and the date of birth. customer_age = ( (fb.RequestColumn.point_in_time() - customer_dateofbirth).dt.day / 365.25 ).floor() # Name feature customer_age.name = "CUSTOMER_Age"

In [5]:

# Transform age into a 5 year age band.
customer_age_band = (
    ((customer_age + 1) / 5).ceil() - 1
) * 5
customer_age_band = (
    customer_age_band.astype(str)
     + "-" + (customer_age_band + 4).astype(str)
)
# Name feature
customer_age_band.name = "CUSTOMER_Age_band"

# Transform age into a 5 year age band. customer_age_band = ( ((customer_age + 1) / 5).ceil() - 1 ) * 5 customer_age_band = ( customer_age_band.astype(str) + "-" + (customer_age_band + 4).astype(str) ) # Name feature customer_age_band.name = "CUSTOMER_Age_band"

Preview feature¶

We will use observation table we created in previous tutorial here.

In [6]:

# Check the primary entity of the feature'
customer_age.primary_entity

# Check the primary entity of the feature' customer_age.primary_entity

Out[6]:

[<featurebyte.api.entity.Entity at 0x14ec45cb0>
 {
   'name': 'customer',
   'created_at': '2025-10-15T03:06:58.482000',
   'updated_at': '2025-10-15T03:07:01.153000',
   'description': None,
   'serving_names': [
     'GROCERYCUSTOMERGUID'
   ],
   'catalog_name': 'Grocery Dataset SDK Tutorial'
 }]

In [7]:

# Get observation table: 'Preview Table with 10 items'
preview_table = catalog.get_observation_table("Preview Table with 10 items")

# Get observation table: 'Preview Table with 10 items' preview_table = catalog.get_observation_table("Preview Table with 10 items")

In [8]:

# Preview CUSTOMER_Age
customer_age.preview(preview_table)

# Preview CUSTOMER_Age customer_age.preview(preview_table)

Out[8]:

	POINT_IN_TIME	GROCERYINVOICEITEMGUID	CUSTOMER_Age
0	2022-07-14 18:12:49	a3245668-aeba-4259-87e1-1b99a1e7391c	45
1	2022-09-12 16:29:49	f7de9fec-9e01-4478-8b2e-5a17427a53c1	31
2	2023-03-18 09:43:40	7ec0da36-b85f-47cf-873e-461b5c2b1cbf	30
3	2022-12-01 13:28:57	600a7549-9f3e-42f9-8408-e3996d6c4750	50
4	2023-05-14 15:41:46	e904b0bc-b342-4491-a7d9-216489b6ac01	54
5	2022-10-30 09:08:11	5ee681b9-583c-4968-88bb-993704a6c54e	85
6	2022-10-03 12:02:23	f25a7864-4e0d-43bb-8191-0ffdf56b5a21	60
7	2023-01-08 15:40:02	879de04d-36ef-49a3-b1f7-a96495100dbe	41
8	2023-04-07 13:41:35	f017e72e-1645-4fbe-988e-a9c09920c506	21
9	2022-12-12 10:27:30	9526bbd7-3b85-4bd5-99d7-2eecda85ada2	52

In [9]:

# Preview CUSTOMER_Age_band
customer_age_band.preview(preview_table)

# Preview CUSTOMER_Age_band customer_age_band.preview(preview_table)

Out[9]:

	POINT_IN_TIME	GROCERYINVOICEITEMGUID	CUSTOMER_Age_band
0	2022-07-14 18:12:49	a3245668-aeba-4259-87e1-1b99a1e7391c	45-49
1	2022-09-12 16:29:49	f7de9fec-9e01-4478-8b2e-5a17427a53c1	30-34
2	2023-03-18 09:43:40	7ec0da36-b85f-47cf-873e-461b5c2b1cbf	30-34
3	2022-12-01 13:28:57	600a7549-9f3e-42f9-8408-e3996d6c4750	50-54
4	2023-05-14 15:41:46	e904b0bc-b342-4491-a7d9-216489b6ac01	50-54
5	2022-10-30 09:08:11	5ee681b9-583c-4968-88bb-993704a6c54e	85-89
6	2022-10-03 12:02:23	f25a7864-4e0d-43bb-8191-0ffdf56b5a21	60-64
7	2023-01-08 15:40:02	879de04d-36ef-49a3-b1f7-a96495100dbe	40-44
8	2023-04-07 13:41:35	f017e72e-1645-4fbe-988e-a9c09920c506	20-24
9	2022-12-12 10:27:30	9526bbd7-3b85-4bd5-99d7-2eecda85ada2	50-54

In [10]:

# Save features to catalog 
customer_age.save()
customer_age_band.save()

# Save features to catalog customer_age.save() customer_age_band.save()

Done! |████████████████████████████████████████| 100% in 6.1s (0.17%/s)         
Done! |████████████████████████████████████████| 100% in 6.1s (0.17%/s)         
Done! |████████████████████████████████████████| 100% in 6.1s (0.17%/s)         
Done! |████████████████████████████████████████| 100% in 6.1s (0.17%/s)         

In [11]:

# Add description
customer_age.update_description("Age of the customer.")
customer_age_band.update_description("Age Band of the customer.")

# Add description customer_age.update_description("Age of the customer.") customer_age_band.update_description("Age Band of the customer.")

Check feature definition files (same as definition files we discussed in target tutorial)¶

In [12]:

customer_age.definition

customer_age.definition

Out[12]:

# Generated by SDK version: 3.2.0.dev66
from bson import ObjectId
from featurebyte import SCDTable
from featurebyte.api.request_column import RequestColumn

request_col = RequestColumn.point_in_time()

# scd_table name: "GROCERYCUSTOMER"
scd_table = SCDTable.get_by_id(ObjectId("68ef0d6293cce39d676ca317"))
scd_view = scd_table.get_view(
    view_mode="manual",
    drop_column_names=["record_available_at", "CurrentRecord"],
    column_cleaning_operations=[],
)
grouped = scd_view.as_features(
    column_names=["DateOfBirth"],
    feature_names=["CUSTOMER_DateOfBirth"],
    offset=None,
)
feat = grouped["CUSTOMER_DateOfBirth"]
feat_1 = ((request_col - feat).dt.day / 365.25).floor()
feat_1.name = "CUSTOMER_Age"
output = feat_1
output.save(_id=ObjectId("68ef110cd0ec86dc5121f298"))

In [13]:

customer_age_band.definition

customer_age_band.definition

Out[13]:

# Generated by SDK version: 3.2.0.dev66
from bson import ObjectId
from featurebyte import SCDTable
from featurebyte.api.request_column import RequestColumn

request_col = RequestColumn.point_in_time()

# scd_table name: "GROCERYCUSTOMER"
scd_table = SCDTable.get_by_id(ObjectId("68ef0d6293cce39d676ca317"))
scd_view = scd_table.get_view(
    view_mode="manual",
    drop_column_names=["record_available_at", "CurrentRecord"],
    column_cleaning_operations=[],
)
grouped = scd_view.as_features(
    column_names=["DateOfBirth"],
    feature_names=["CUSTOMER_DateOfBirth"],
    offset=None,
)
feat = grouped["CUSTOMER_DateOfBirth"]
feat_1 = ((request_col - feat).dt.day / 365.25).floor()
feat_1.name = "CUSTOMER_Age"
feat_2 = ((((feat_1 + 1) / 5).ceil() - 1) * 5).astype(str) + "-"
feat_3 = ((((feat_1 + 1) / 5).ceil() - 1) * 5) + 4
feat_4 = feat_2 + feat_3.astype(str)
feat_4.name = "CUSTOMER_Age_band"
output = feat_4
output.save(_id=ObjectId("68ef110cd0ec86dc5121f2a2"))

Concepts in this tutorial¶

• More on features
• More on lookup features
• More about point-in-time

SDK reference for¶

• Feature
• ViewColumn.as_feature()
• RequestColumn.point_in_time
• Feature.preview()
• Feature.save()

In [ ]: