14. Compute Historical Feature Values

Compute historical feature values¶

Historical feature values are needed to train and test Machine Learning models.

Let's take the feature list we just created and compute feature values for a given observation table.

In [1]:

import featurebyte as fb

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

16:12:25 | WARNING  | Service endpoint is inaccessible: http://featurebyte-server:8088
16:12:25 | INFO     | Using profile: tutorial
16:12:25 | INFO     | Using configuration file at: /Users/gxav/.featurebyte/config.yaml
16:12:25 | INFO     | Active profile: tutorial (https://tutorials.featurebyte.com/api/v1)
16:12:25 | WARNING  | Remote SDK version (1.1.0.dev7) is different from local (1.1.0.dev1). Update local SDK to avoid unexpected behavior.
16:12:25 | INFO     | No catalog activated.
16:12:25 | 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	666958439767025aff191450	Customer x ProductGroup Simple FeatureList	9	DRAFT	False	0.0	0.0	[GROCERYCUSTOMER, GROCERYINVOICE, INVOICEITEMS...	[customer, productgroup]	[customer, productgroup]	2024-06-12T08:12:14.787000

Get 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 0.2s

Get an observation table¶

In [4]:

# List observation tables
catalog.list_observation_tables()

# List observation tables catalog.list_observation_tables()

Out[4]:

	id	name	type	shape	feature_store_name	created_at
0	66695726850bd33441fdc242	Preview Table with 10 items	view	[10, 2]	playground	2024-06-12T08:07:09.337000
1	6669570fddd5be620a410f7f	In_Store_Customer_x_ProductGroup_Spending_next...	observation_table	[1000, 4]	playground	2024-06-12T08:06:54.934000
2	666956fdddd5be620a410f7c	In_Store_Customer_x_ProductGroup_2023_1K	uploaded_file	[1000, 3]	playground	2024-06-12T08:06:33.543000

In [5]:

# Get observation table: 'In_Store_Customer_x_ProductGroup_Spending_next_2_weeks_2023_1K'
training_observations = catalog.get_observation_table(
    "In_Store_Customer_x_ProductGroup_Spending_next_2_weeks_2023_1K"
)

# Get observation table: 'In_Store_Customer_x_ProductGroup_Spending_next_2_weeks_2023_1K' training_observations = catalog.get_observation_table( "In_Store_Customer_x_ProductGroup_Spending_next_2_weeks_2023_1K" )

Compute historical features¶

In [6]:

# Create historical feature table
table_name =\
"Simple Training Simple Training for In_Store_Customer_x_ProductGroup_Spending_next_2_weeks_2023_1K"
training_data_table = simple_feature_list.compute_historical_feature_table(
    training_observations,
    historical_feature_table_name=table_name,
)

# Create historical feature table table_name =\ "Simple Training Simple Training for In_Store_Customer_x_ProductGroup_Spending_next_2_weeks_2023_1K" training_data_table = simple_feature_list.compute_historical_feature_table( training_observations, historical_feature_table_name=table_name, )

Done! |████████████████████████████████████████| 100% in 36.4s (0.03%/s)        

In [7]:

display(training_data_table.to_pandas())

display(training_data_table.to_pandas())

Downloading table |████████████████████████████████████████| 1000/1000 [100%] in

	GROCERYCUSTOMERGUID	POINT_IN_TIME	PRODUCTGROUP	CUSTOMER_x_PRODUCTGROUP_Sum_of_TotalCost_next_2_weeks	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	699efd7f-aba2-4515-9335-2c8040a94f9f	2023-12-11 08:51:22	Fromages	14.18	80-84	13.13	4.0	13.860000	3.720329	0.179880	0.683171	6.00	166.499167
1	125dfe7d-eac0-4eab-94d8-1cd008e1641c	2023-05-16 09:00:11	Laits	1.85	30-34	5.82	1.0	5.820000	0.000000	-1.000000	0.645410	NaN	2653.102500
2	326b6ccb-0891-49fe-acbf-31d06c6d9e67	2023-03-20 13:34:55	Céréales	0.00	35-39	24.79	1.0	24.790000	0.000000	1.414202	0.624311	NaN	532.296944
3	e42fa5f3-7737-4c6a-9ef4-856f113e60bd	2023-12-18 19:04:45	Fromages	9.00	25-29	4.76	4.0	12.860000	7.439772	-0.637723	0.649094	11.36	241.682222
4	dde029d7-ceca-4e44-aad0-38e22ba11b74	2023-09-08 15:00:07	Pains	3.49	40-44	22.71	6.0	10.605000	8.144472	0.930581	0.740797	2.50	50.218611
...	...	...	...	...	...	...	...	...	...	...	...	...	...
995	e883912f-82c4-4ca8-bfa9-0bdeb46dd4c5	2023-06-28 20:16:15	Céréales	0.00	70-74	3.00	1.0	3.000000	0.000000	NaN	0.724302	NaN	1994.139722
996	cc96d96e-5d02-48dd-b742-d2a0ef633c43	2023-03-07 10:00:46	Laits	2.00	55-59	30.21	NaN	NaN	NaN	NaN	0.655556	NaN	984.909444
997	1b82b9eb-cc54-4cc4-a7e3-9a7417faa8a5	2023-11-16 20:44:02	Laits	2.69	40-44	4.00	3.0	8.143333	2.931033	-1.413608	0.541741	NaN	1970.083056
998	c0ca0bda-e7f5-4748-9b14-0e7ba9a07a47	2023-04-06 14:58:43	Laits	2.32	65-69	17.20	10.0	20.122000	13.270356	-0.079666	0.808877	4.64	241.992500
999	a0588833-ba78-41a4-b36a-d36bcd68e27e	2023-09-16 13:40:19	Fromages	0.00	20-24	5.50	6.0	6.561667	2.902714	-0.493589	0.699924	NaN	1578.428611

1000 rows × 13 columns

In [8]:

### List historical feature tables from catalog
catalog.list_historical_feature_tables()

### List historical feature tables from catalog catalog.list_historical_feature_tables()

Out[8]:

	id	name	feature_store_name	observation_table_name	shape	created_at
0	6669586bec7bc32effdab7a4	Simple Training Simple Training for In_Store_C...	playground	In_Store_Customer_x_ProductGroup_Spending_next...	[1000, 13]	2024-06-12T08:12:57.839000

Concepts in this tutorial¶

• More on Historical feature serving

SDK reference for¶

• Historical feature table
• FeatureList.compute historical feature table()
• FeatureList.compute_historical_features() to compute directly a data frame