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.

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)

16:46:03 | INFO     | Using configuration file at: /Users/viktor/.featurebyte/config.yaml
16:46:03 | INFO     | Active profile: tutorial (https://tutorials.featurebyte.com/api/v1)
16:46:04 | INFO     | SDK version: 0.6.0.dev121
16:46:04 | INFO     | No catalog activated.
16:46:04 | INFO     | 10 feature lists, 59 features deployed
16:46:04 | INFO     | Using profile: tutorial
16:46:04 | INFO     | Using configuration file at: /Users/viktor/.featurebyte/config.yaml
16:46:04 | INFO     | Active profile: tutorial (https://tutorials.featurebyte.com/api/v1)
16:46:04 | INFO     | SDK version: 0.6.0.dev121
16:46:04 | INFO     | No catalog activated.
16:46:05 | INFO     | 10 feature lists, 59 features deployed
16:46:05 | 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	6564b959d3f7244b7fc926a0	Customer Simple FeatureList	7	DRAFT	False	0.0	0.0	[GROCERYCUSTOMER, GROCERYINVOICE, INVOICEITEMS...	[customer]	[customer]	2023-11-27T15:44:36.966000

Get a feature list from Catalog¶

In [3]:

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

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

Loading Feature(s) |████████████████████████████████████████| 7/7 [100%] in 0.7s

Deploy feature list¶

In [4]:

# Create a deployment
deployment = simple_feature_list.deploy(
  deployment_name="Customer Spending forecast",
  make_production_ready=True,
)

# Create a deployment deployment = simple_feature_list.deploy( deployment_name="Customer Spending forecast", make_production_ready=True, )

Done! |████████████████████████████████████████| 100% in 6.5s (0.16%/s)         
Done! |████████████████████████████████████████| 100% in 3.3s (0.31%/s)         

In [5]:

# Enable deployment
deployment.enable()

# Enable deployment deployment.enable()

Done! |████████████████████████████████████████| 100% in 42.0s (0.02%/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	6564b9c77927bf2a9d6cca65	Customer Spending forecast	Customer Simple FeatureList	V231127	7	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/6564b9c77927bf2a9d6cca65/online_features",
        headers={"Content-Type": "application/json", "active-catalog-id": "6564b7da5cf4e2dd964abb60", "Authorization": "Bearer 2u5EXHbdmiHNjEC4Y-EXBBJV-yeBiS35I4kK7FMjsLI"},
        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"}])

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: 6564b7da5cf4e2dd964abb60' \
    -H 'Authorization: Bearer 2u5EXHbdmiHNjEC4Y-EXBBJV-yeBiS35I4kK7FMjsLI' \
    -d '{"entity_serving_names": [{"GROCERYCUSTOMERGUID": "016d7230-8602-42ef-9861-c672f48fb010"}]}' \
    https://tutorials.featurebyte.com/api/v1/deployment/6564b9c77927bf2a9d6cca65/online_features

Create batch request table¶

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 0x106f19880>
 {
   'name': 'customer',
   'created_at': '2023-11-27T15:39:09.477000',
   'updated_at': '2023-11-27T15:39:19.968000',
   'description': None,
   'serving_names': [
     'GROCERYCUSTOMERGUID'
   ],
   'catalog_name': 'Grocery Dataset Tutorial'
 }]

In [12]:

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

Done! |████████████████████████████████████████| 100% in 6.5s (0.16%/s)         

In [13]:

# Get name of the batch request table
batch_request_table.name

# Get name of the batch request table batch_request_table.name

Out[13]:

'Current Customers at 20231127:1647'

In [14]:

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

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

Out[14]:

	id	name	type	shape	feature_store_name	created_at
0	6564b9fa7927bf2a9d6cca66	Current Customers at 20231127:1647	view	[500, 1]	playground	2023-11-27T15:47:08.828000

Compute batch feature table¶

In [15]:

# Get deployment and batch request table
deployment = catalog.get_deployment("Customer Spending forecast")
batch_request_table = catalog.get_batch_request_table(batch_request_table.name)

# Get deployment and batch request table deployment = catalog.get_deployment("Customer Spending forecast") batch_request_table = catalog.get_batch_request_table(batch_request_table.name)

In [16]:

# 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 9.8s (0.10%/s)         

In [17]:

# List observation tables
catalog.list_batch_feature_tables()

# List observation tables catalog.list_batch_feature_tables()

Out[17]:

	id	name	feature_store_name	batch_request_table_name	shape	created_at
0	6564ba027927bf2a9d6cca67	Customer Simple FeatureList for Spending forec...	playground	Current Customers at 20231127:1647	[500, 8]	2023-11-27T15:47:19.526000

In [18]:

# Convert to pandas 
batch_features.to_pandas()

# Convert to pandas batch_features.to_pandas()

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

Out[18]:

	GROCERYCUSTOMERGUID	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
0	c4f35072-c0ae-48b4-9f61-4bd4c348e48a	60-64	10.09	0.0	NaN	NaN	NaN	0.740359
1	c003c0a7-73f3-41c8-be4e-a7b0ede84312	30-34	17.98	0.0	NaN	NaN	NaN	0.348179
2	1d15db25-a662-41d5-9bad-1079b1e443ed	40-44	6.00	0.0	NaN	NaN	-1.000000	0.663154
3	6a780e8d-0c03-4246-b08c-d76be43470bb	35-39	8.98	7.0	7.734286	7.824217	-0.026837	0.774803
4	716c079e-a98f-456c-af24-ed7b1d87b38d	85-89	5.76	0.0	NaN	NaN	1.000000	0.733773
...	...	...	...	...	...	...	...	...
495	1c35daf7-e880-403f-95ab-3a2f3295f303	60-64	10.12	2.0	6.535000	3.585000	0.464564	0.738185
496	d90fda3d-2dfb-4be0-bbcf-2b5c46c97e19	60-64	2.68	3.0	12.060000	11.073328	-1.246973	0.641640
497	f4c7dce9-ea7d-4af2-98c6-3630b7cd869d	70-74	32.73	1.0	32.730000	0.000000	1.221433	0.780169
498	62fd4b3d-a46c-4166-971e-3c2041d7d4d8	20-24	3.88	2.0	4.440000	0.560000	0.315371	0.451703
499	f8d62c21-4337-4a68-9063-ad3f8d16aa21	85-89	19.52	0.0	NaN	NaN	-1.034224	0.628090

500 rows × 8 columns

In [19]:

# download parquet file
batch_features.download()

# download parquet file batch_features.download()

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

Out[19]:

PosixPath('BATCH_FEATURE_TABLE_6564ba03083bd15e6cb1e755.parquet')

In [20]:

# 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 6.5s (0.16%/s)         
Done! |████████████████████████████████████████| 100% in 6.5s (0.16%/s)         

Manage Deployment¶

In [21]:

deployment = catalog.get_deployment("Customer Spending forecast")

deployment = catalog.get_deployment("Customer Spending forecast")

In [22]:

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

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

Loading Feature(s) |████████████████████████████████████████| 7/7 [100%] in 0.7s

Out[22]:

Job statistics (last 1 hours)

	request_date	job_history_window	job_duration_tolerance
0	2023-11-27T15:47:48.386771	1	60

	feature_name	aggregation_hash
0	CUSTOMER_Avg_of_invoice_Amount_14d	45351576
1	CUSTOMER_Count_of_invoice_14d	7cee376c
2	CUSTOMER_Latest_invoice_Amount	0ee300b2
3	CUSTOMER_Latest_invoice_Amount_Z_Score_to_invoice_Amount_28d	0ee300b2
4	CUSTOMER_Latest_invoice_Amount_Z_Score_to_invoice_Amount_28d	45351576
5	CUSTOMER_Latest_invoice_Amount_Z_Score_to_invoice_Amount_28d	31e54300
6	CUSTOMER_Std_of_invoice_Amount_14d	31e54300
7	CUSTOMER_vs_OVERALL_item_TotalCost_across_product_ProductGroups_26w	f831676d
8	CUSTOMER_vs_OVERALL_item_TotalCost_across_product_ProductGroups_26w	c5e9a3c5

	aggregation_hash	frequency(min)	completed_jobs	max_duration(s)	95 percentile	frac_late	exceed_period	failed_jobs	incomplete_jobs	time_since_last
0	0ee300b2	60	0	NaN	NaN	NaN	0	0	1	NaT
1	7cee376c	60	0	NaN	NaN	NaN	0	0	1	NaT
2	45351576	60	0	NaN	NaN	NaN	0	0	1	NaT
3	31e54300	60	0	NaN	NaN	NaN	0	0	1	NaT
4	f831676d	60	0	NaN	NaN	NaN	0	0	1	NaT
5	c5e9a3c5	60	0	NaN	NaN	NaN	0	0	1	NaT

In [23]:

# Disable deployment
deployment.disable()

# Disable deployment deployment.disable()

Done! |████████████████████████████████████████| 100% in 9.8s (0.10%/s)         

In [24]:

# The deployment is still part of the catalog but disabled
catalog.list_deployments()

# The deployment is still part of the catalog but disabled catalog.list_deployments()

Out[24]:

	id	name	feature_list_name	feature_list_version	num_feature	enabled
0	6564b9c77927bf2a9d6cca65	Customer Spending forecast	Customer Simple FeatureList	V231127	7	False

Concepts in this tutorial¶

• Feature list deployment
• REST API and batch serving
• Feature jobs

SDK reference for¶

• Deployment
• Batch Request Table
• Batch Feature Table
• FeatureList.deploy()
• Deployment.enable()
• Deployment.get_online_serving_code()
• Deployment.compute batch feature_table()
• Table.get_view() in a manual mode
• View.create_batch_request_table()
• SourceTable.create_batch_request_table()

In [ ]: