Deploy and Serve a Feature List for Model Predictions¶

Once you have a feature list ready, it's essential to serve these features effectively to make real-time or batch predictions using your machine learning model.

In this section, we'll take the feature list we previously crafted and explore two primary ways to serve its values:

REST API: Ideal for real-time predictions where you need instantaneous results. For instance, in applications where user interactions require immediate feedback based on model predictions.

Batch Processing: Best suited for scenarios where you have a bulk of data and don't require instant results.

Important Note for FeatureByte Enterprise Users¶

In Catalogs with Approval Flow enabled, moving features to production-ready status involves a comprehensive approval process.

This includes several evaluations, such as checking the feature's compliance with default cleaning operations and the feature job setting of its source tables. It also involves confirming the status of these tables and backtesting the feature job setting to prevent future training-serving inconsistencies. Additionally, essential details of the feature, particularly its feature definition file, are shared and subjected to a thorough review.

In [1]:

import featurebyte as fb
from datetime import datetime

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

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

import featurebyte as fb from datetime import datetime # Set your profile to the tutorial environment fb.use_profile("tutorial") catalog_name = "Grocery Dataset Tutorial" catalog = fb.Catalog.activate(catalog_name)

15:35:52 | INFO     | SDK version: 1.0.2.dev46
15:35:52 | INFO     | No catalog activated.
15:35:52 | INFO     | Using profile: tutorial
15:35:53 | INFO     | Using configuration file at: /Users/gxav/.featurebyte/config.yaml
15:35:53 | INFO     | Active profile: tutorial (https://tutorials.featurebyte.com/api/v1)
15:35:53 | INFO     | SDK version: 1.0.2.dev46
15:35:53 | INFO     | No catalog activated.
15:35:53 | INFO     | Catalog activated: Grocery Dataset Tutorial

List feature lists in Catalog¶

In [2]:

catalog.list_feature_lists()

catalog.list_feature_lists()

Out[2]:

	id	name	num_feature	status	deployed	readiness_frac	online_frac	tables	entities	primary_entity	created_at
0	662b59023bbb17418af6e696	Customer x ProductGroup Simple FeatureList	9	DRAFT	False	0.0	0.0	[GROCERYCUSTOMER, GROCERYINVOICE, INVOICEITEMS...	[customer, productgroup]	[customer, productgroup]	2024-04-26T07:34:53.267000

Get a feature list from Catalog¶

In [3]:

simple_feature_list = catalog.get_feature_list("Customer x ProductGroup Simple FeatureList")

simple_feature_list = catalog.get_feature_list("Customer x ProductGroup Simple FeatureList")

Loading Feature(s) |████████████████████████████████████████| 9/9 [100%] in 0.5s

Deploy feature list¶

In [4]:

# Create a deployment
deployment = simple_feature_list.deploy(
  deployment_name="In-Store Customer x ProductGroup Spending 2w Spending - 9 features",
  make_production_ready=True,
)

# Create a deployment deployment = simple_feature_list.deploy( deployment_name="In-Store Customer x ProductGroup Spending 2w Spending - 9 features", make_production_ready=True, )

Done! |████████████████████████████████████████| 100% in 6.2s (0.16%/s)         
Done! |████████████████████████████████████████| 100% in 6.1s (0.17%/s)         

In [5]:

# Enable deployment
deployment.enable()

# Enable deployment deployment.enable()

Done! |████████████████████████████████████████| 100% in 1:37.4 (0.01%/s)       

In [6]:

# Check that the deployment is enabled
catalog.list_deployments()

# Check that the deployment is enabled catalog.list_deployments()

Out[6]:

	id	name	feature_list_name	feature_list_version	num_feature	enabled
0	662b5962d9a443d42ef26718	In-Store Customer x ProductGroup Spending 2w S...	Customer x ProductGroup Simple FeatureList	V240426	9	True

In [7]:

# Check status of the feature list
print("simple_feature_list.status:", simple_feature_list.status)

# Check status of the feature list print("simple_feature_list.status:", simple_feature_list.status)

simple_feature_list.status: DEPLOYED

Get template for online serving¶

In [8]:

# Get a python template for consuming the feature serving API
deployment.get_online_serving_code(language="python")

# Get a python template for consuming the feature serving API deployment.get_online_serving_code(language="python")

Out[8]:

from typing import Any, Dict

import pandas as pd
import requests


def request_features(entity_serving_names: Dict[str, Any]) -> pd.DataFrame:
    """
    Send POST request to online serving endpoint

    Parameters
    ----------
    entity_serving_names: Dict[str, Any]
        Entity serving name values to used for serving request

    Returns
    -------
    pd.DataFrame
    """
    response = requests.post(
        url="https://tutorials.featurebyte.com/api/v1/deployment/662b5962d9a443d42ef26718/online_features",
        headers={"Content-Type": "application/json", "active-catalog-id": "662b5752b408f15615a00d7d", "Authorization": "Bearer alZJY8HvLxoi_emU_eukghMpSMzxL0eQ4ufUSWxvsLk"},
        json={"entity_serving_names": entity_serving_names},
    )
    assert response.status_code == 200, response.json()
    return pd.DataFrame.from_dict(response.json()["features"])


request_features([{"GROCERYCUSTOMERGUID": "016d7230-8602-42ef-9861-c672f48fb010", "PRODUCTGROUP": "Gla\u00e7ons"}])

In [9]:

# Get shell script
deployment.get_online_serving_code(language="sh")

# Get shell script deployment.get_online_serving_code(language="sh")

Out[9]:

#!/bin/sh

curl -X POST \
    -H 'Content-Type: application/json' \
    -H 'active-catalog-id: 662b5752b408f15615a00d7d' \
    -H 'Authorization: Bearer alZJY8HvLxoi_emU_eukghMpSMzxL0eQ4ufUSWxvsLk' \
    -d '{"entity_serving_names": [{"GROCERYCUSTOMERGUID": "016d7230-8602-42ef-9861-c672f48fb010", "PRODUCTGROUP": "Gla\u00e7ons"}]}' \
    https://tutorials.featurebyte.com/api/v1/deployment/662b5962d9a443d42ef26718/online_features

Create batch request table¶

Although batch request is not suitable for our "In-Store" use case, let's run a batch request for all current customers for a campaign for "Fromages".

In [10]:

# Get view of current customer
customer_table = catalog.get_table("GROCERYCUSTOMER")
customer_view = customer_table.get_view(view_mode="manual")
cond = customer_view.CurrentRecord == True
current_customer_view = customer_view[cond]

# Get view of current customer customer_table = catalog.get_table("GROCERYCUSTOMER") customer_view = customer_table.get_view(view_mode="manual") cond = customer_view.CurrentRecord == True current_customer_view = customer_view[cond]

In [11]:

# Check primary entity of the deployed feature list to obtain its serving name
simple_feature_list.primary_entity

# Check primary entity of the deployed feature list to obtain its serving name simple_feature_list.primary_entity

Out[11]:

[<featurebyte.api.entity.Entity at 0x1546a4c80>
 {
   'name': 'customer',
   'created_at': '2024-04-26T07:28:15.128000',
   'updated_at': '2024-04-26T07:28:24.021000',
   'description': None,
   'serving_names': [
     'GROCERYCUSTOMERGUID'
   ],
   'catalog_name': 'Grocery Dataset Tutorial'
 },
 <featurebyte.api.entity.Entity at 0x154b793c0>
 {
   'name': 'productgroup',
   'created_at': '2024-04-26T07:28:17.313000',
   'updated_at': '2024-04-26T07:28:27.128000',
   'description': None,
   'serving_names': [
     'PRODUCTGROUP'
   ],
   'catalog_name': 'Grocery Dataset Tutorial'
 }]

In [12]:

# Add PRODUCTGROUP to the view with "Fromages" for a specific targeted campaign.
current_customer_view["PRODUCTGROUP"] = "Fromages"

# Add PRODUCTGROUP to the view with "Fromages" for a specific targeted campaign. current_customer_view["PRODUCTGROUP"] = "Fromages"

In [13]:

# Create batch request table from the view
batch_request_table = current_customer_view.create_batch_request_table(
    name="Current Customers for Fromages at " + datetime.now().strftime("%Y%m%d:%H%M"),
    columns=["GroceryCustomerGuid", "PRODUCTGROUP"],
    columns_rename_mapping={
        "GroceryCustomerGuid": "GROCERYCUSTOMERGUID",
    }
)

# Create batch request table from the view batch_request_table = current_customer_view.create_batch_request_table( name="Current Customers for Fromages at " + datetime.now().strftime("%Y%m%d:%H%M"), columns=["GroceryCustomerGuid", "PRODUCTGROUP"], columns_rename_mapping={ "GroceryCustomerGuid": "GROCERYCUSTOMERGUID", } )

Done! |████████████████████████████████████████| 100% in 12.5s (0.08%/s)        

In [14]:

# Get name of the batch request table
batch_request_table.name

# Get name of the batch request table batch_request_table.name

Out[14]:

'Current Customers for Fromages at 20240426:1537'

In [15]:

# List batch request tables in catalog
catalog.list_batch_request_tables()

# List batch request tables in catalog catalog.list_batch_request_tables()

Out[15]:

	id	name	type	shape	feature_store_name	created_at
0	662b59d4d9a443d42ef26719	Current Customers for Fromages at 20240426:1537	view	[500, 2]	playground	2024-04-26T07:38:03.469000

Compute batch feature table¶

In [16]:

# Get deployment and batch request table
deployment = catalog.get_deployment("In-Store Customer x ProductGroup Spending 2w Spending - 9 features")
batch_request_table = catalog.get_batch_request_table(batch_request_table.name)

# Get deployment and batch request table deployment = catalog.get_deployment("In-Store Customer x ProductGroup Spending 2w Spending - 9 features") batch_request_table = catalog.get_batch_request_table(batch_request_table.name)

In [17]:

# Compute batch features
batch_features = deployment.compute_batch_feature_table(
    batch_request_table=batch_request_table,
    batch_feature_table_name = 
    f"Customer Simple FeatureList for Spending forecast with {batch_request_table.name}"
)

# Compute batch features batch_features = deployment.compute_batch_feature_table( batch_request_table=batch_request_table, batch_feature_table_name = f"Customer Simple FeatureList for Spending forecast with {batch_request_table.name}" )

Done! |████████████████████████████████████████| 100% in 9.6s (0.10%/s)         

In [18]:

# List observation tables
catalog.list_batch_feature_tables()

# List observation tables catalog.list_batch_feature_tables()

Out[18]:

	id	name	feature_store_name	batch_request_table_name	shape	created_at
0	662b59e2d9a443d42ef2671a	Customer Simple FeatureList for Spending forec...	playground	Current Customers for Fromages at 20240426:1537	[500, 11]	2024-04-26T07:38:16.321000

In [19]:

# Convert to pandas 
batch_features.to_pandas()

# Convert to pandas batch_features.to_pandas()

Downloading table |████████████████████████████████████████| 500/500 [100%] in 0

Out[19]:

	GROCERYCUSTOMERGUID	PRODUCTGROUP	CUSTOMER_Age_band	CUSTOMER_Latest_invoice_Amount	CUSTOMER_Count_of_invoice_14d	CUSTOMER_Avg_of_invoice_Amount_14d	CUSTOMER_Std_of_invoice_Amount_14d	CUSTOMER_Latest_invoice_Amount_Z_Score_to_invoice_Amount_28d	CUSTOMER_vs_OVERALL_item_TotalCost_across_product_ProductGroups_26w	CUSTOMER_x_PRODUCTGROUP_Sum_of_item_TotalCost_14d	CUSTOMER_x_PRODUCTGROUP_Time_Since_Latest_Timestamp
0	3671f019-0bb3-46b0-be1b-17e7cf9c5239	Fromages	65-69	9.49	1.0	9.490000	0.000000	NaN	0.234423	0.00	1573.678678
1	a3dae335-faa3-46de-93c0-fbd7854e0da4	Fromages	60-64	32.12	1.0	32.120000	0.000000	1.000000	0.643859	9.65	212.580067
2	6a9598c3-26ba-4784-8551-9c20819c5690	Fromages	65-69	4.37	0.0	NaN	NaN	-1.000000	0.646209	0.00	1032.467289
3	29dc945d-1c9e-46a7-a5d7-ba6d24182195	Fromages	65-69	28.11	2.0	23.690000	4.420000	1.000000	0.507266	0.00	3451.564789
4	c63196a3-0226-4a7e-96b9-18d50953ec39	Fromages	20-24	6.18	0.0	NaN	NaN	NaN	0.628182	0.00	1770.345067
...	...	...	...	...	...	...	...	...	...	...	...
495	0716d17b-7117-4ef0-a9c5-f4a0595a08f6	Fromages	65-69	2.69	0.0	NaN	NaN	NaN	0.093593	0.00	NaN
496	f9920ddc-de54-4588-ad2f-f65a1a386138	Fromages	20-24	13.68	3.0	5.886667	5.513138	1.413593	0.601433	0.00	NaN
497	4c66085a-389d-4cfd-9ab8-e0b90bcf6acf	Fromages	80-84	13.47	0.0	NaN	NaN	NaN	0.423913	0.00	NaN
498	7e4e042b-6c14-4ba1-a74d-ecb70664fb2f	Fromages	20-24	1.88	0.0	NaN	NaN	NaN	0.208342	0.00	NaN
499	903378a9-5bb5-46d4-8598-292fbb5f664f	Fromages	20-24	2.59	0.0	NaN	NaN	NaN	0.305591	0.00	NaN

500 rows × 11 columns

In [20]:

# download parquet file
batch_features.download()

# download parquet file batch_features.download()

Downloading table |████████████████████████████████████████| 500/500 [100%] in 0

Out[20]:

PosixPath('BATCH_FEATURE_TABLE_662b59e29385e38271fc9a8d.parquet')

In [21]:

# delete if not needed any more
batch_features.delete()
batch_request_table.delete()

# delete if not needed any more batch_features.delete() batch_request_table.delete()

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

Manage Deployment¶

In [22]:

deployment = catalog.get_deployment("In-Store Customer x ProductGroup Spending 2w Spending - 9 features")

deployment = catalog.get_deployment("In-Store Customer x ProductGroup Spending 2w Spending - 9 features")

In [23]:

# get feature jobs status (this will produce meaningful results once multiple jobs have been run)
deployment.get_feature_jobs_status(job_history_window=12)

# get feature jobs status (this will produce meaningful results once multiple jobs have been run) deployment.get_feature_jobs_status(job_history_window=12)

Loading Feature(s) |████████████████████████████████████████| 9/9 [100%] in 0.7s

Out[23]:

Job statistics (last 12 hours)

	request_date	job_history_window	job_duration_tolerance
0	2024-04-26T07:38:47.995915	12	60

	feature_name	aggregation_hash
0	CUSTOMER_Avg_of_invoice_Amount_14d	ccbdbb50
1	CUSTOMER_Count_of_invoice_14d	decd9c4b
2	CUSTOMER_Latest_invoice_Amount	a8359d79
3	CUSTOMER_Latest_invoice_Amount_Z_Score_to_invoice_Amount_28d	a8359d79
4	CUSTOMER_Latest_invoice_Amount_Z_Score_to_invoice_Amount_28d	ccbdbb50
5	CUSTOMER_Latest_invoice_Amount_Z_Score_to_invoice_Amount_28d	e432ef49
6	CUSTOMER_Std_of_invoice_Amount_14d	e432ef49
7	CUSTOMER_vs_OVERALL_item_TotalCost_across_product_ProductGroups_26w	46496de4
8	CUSTOMER_vs_OVERALL_item_TotalCost_across_product_ProductGroups_26w	98e84952
9	CUSTOMER_x_PRODUCTGROUP_Sum_of_item_TotalCost_14d	da3173df
10	CUSTOMER_x_PRODUCTGROUP_Time_Since_Latest_Timestamp	80d7b6bd

	aggregation_hash	frequency(min)	completed_jobs	max_duration(s)	95 percentile	frac_late	exceed_period	failed_jobs	incomplete_jobs	time_since_last
0	a8359d79	60	0	NaN	NaN	NaN	0	0	12	NaT
1	decd9c4b	60	0	NaN	NaN	NaN	0	0	12	NaT
2	ccbdbb50	60	0	NaN	NaN	NaN	0	0	12	NaT
3	e432ef49	60	0	NaN	NaN	NaN	0	0	12	NaT
4	46496de4	60	0	NaN	NaN	NaN	0	0	12	NaT
5	98e84952	60	0	NaN	NaN	NaN	0	0	12	NaT
6	da3173df	60	0	NaN	NaN	NaN	0	0	12	NaT
7	80d7b6bd	60	0	NaN	NaN	NaN	0	0	12	NaT