12. Create feature list

Create a feature list¶

Feature list is a collection of features which can be used for machine learning model.

Let's take some of features we created and bundle them into a feature list.

In [1]:

            
                Copied!
                
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)

22:02:03 | INFO     | Using configuration file at: /Users/gxav/.featurebyte/config.yaml
22:02:03 | INFO     | Active profile: tutorial (https://tutorials.featurebyte.com/api/v1)
22:02:03 | WARNING  | Remote SDK version (0.5.0.dev6) is different from local (0.5.0.dev1). Update local SDK to avoid unexpected behavior.
22:02:03 | INFO     | No catalog activated.
22:02:03 | INFO     | 6 feature lists, 31 features deployed
22:02:03 | INFO     | Using profile: tutorial
22:02:04 | INFO     | Using configuration file at: /Users/gxav/.featurebyte/config.yaml
22:02:04 | INFO     | Active profile: tutorial (https://tutorials.featurebyte.com/api/v1)
22:02:04 | WARNING  | Remote SDK version (0.5.0.dev6) is different from local (0.5.0.dev1). Update local SDK to avoid unexpected behavior.
22:02:04 | INFO     | No catalog activated.
22:02:04 | INFO     | 6 feature lists, 31 features deployed
22:02:05 | INFO     | Catalog activated: Grocery Dataset Tutorial

List all features we created so far¶

In [2]:

            
                Copied!
                
catalog.list_features()
catalog.list_features()

Out[2]:

	id	name	dtype	readiness	online_enabled	tables	primary_tables	entities	primary_entities	created_at
0	64ff1dc2183aab97b493af21	CUSTOMER_vs_OVERALL_item_TotalCost_across_prod...	FLOAT	DRAFT	False	[GROCERYINVOICE, INVOICEITEMS, GROCERYPRODUCT]	[INVOICEITEMS]	[customer]	[customer]	2023-09-11T14:01:53.167000
1	64ff1d9a2fa89ef7c7f4f5b8	CUSTOMER_Latest_invoice_Amount_Z_Score_to_invo...	FLOAT	DRAFT	False	[GROCERYINVOICE]	[GROCERYINVOICE]	[customer]	[customer]	2023-09-11T14:01:19.807000
2	64ff1d6a98b637caa7897494	CUSTOMER_Std_of_invoice_Amount_28d	FLOAT	DRAFT	False	[GROCERYINVOICE]	[GROCERYINVOICE]	[customer]	[customer]	2023-09-11T14:00:30.353000
3	64ff1d6a98b637caa7897493	CUSTOMER_Std_of_invoice_Amount_14d	FLOAT	DRAFT	False	[GROCERYINVOICE]	[GROCERYINVOICE]	[customer]	[customer]	2023-09-11T14:00:29.117000
4	64ff1d6a98b637caa7897492	CUSTOMER_Avg_of_invoice_Amount_28d	FLOAT	DRAFT	False	[GROCERYINVOICE]	[GROCERYINVOICE]	[customer]	[customer]	2023-09-11T14:00:27.834000
5	64ff1d6a98b637caa7897491	CUSTOMER_Avg_of_invoice_Amount_14d	FLOAT	DRAFT	False	[GROCERYINVOICE]	[GROCERYINVOICE]	[customer]	[customer]	2023-09-11T14:00:26.527000
6	64ff1d6a98b637caa789748f	CUSTOMER_Count_of_invoice_28d	FLOAT	DRAFT	False	[GROCERYINVOICE]	[GROCERYINVOICE]	[customer]	[customer]	2023-09-11T14:00:25.244000
7	64ff1d6a98b637caa789748d	CUSTOMER_Count_of_invoice_14d	FLOAT	DRAFT	False	[GROCERYINVOICE]	[GROCERYINVOICE]	[customer]	[customer]	2023-09-11T14:00:24.165000
8	64ff1d6a98b637caa789748c	CUSTOMER_Latest_invoice_Amount	FLOAT	DRAFT	False	[GROCERYINVOICE]	[GROCERYINVOICE]	[customer]	[customer]	2023-09-11T14:00:23.056000
9	64ff1d4682feedb4dc913349	CUSTOMER_Age_band	VARCHAR	DRAFT	False	[GROCERYCUSTOMER]	[GROCERYCUSTOMER]	[customer]	[customer]	2023-09-11T13:59:53.623000
10	64ff1d4182feedb4dc91333f	CUSTOMER_Age	INT	DRAFT	False	[GROCERYCUSTOMER]	[GROCERYCUSTOMER]	[customer]	[customer]	2023-09-11T13:59:43.782000

Get features from catalog¶

In [3]:

            
                Copied!
                
                    
                    
                
                

        
customer_age_band = catalog.get_feature("CUSTOMER_Age_band")
customer_latest_invoice_amount = catalog.get_feature("CUSTOMER_Latest_invoice_Amount")
customer_count_of_invoice_14d = catalog.get_feature("CUSTOMER_Count_of_invoice_14d")
customer_avg_of_invoice_amount_14d = catalog.get_feature("CUSTOMER_Avg_of_invoice_Amount_14d")
customer_std_of_invoice_amount_14d = catalog.get_feature("CUSTOMER_Std_of_invoice_Amount_14d")
customer_latest_invoice_amount_Z_score_to_invoice_amount_28d = catalog.get_feature(
    "CUSTOMER_Latest_invoice_Amount_Z_Score_to_invoice_Amount_28d"
)
customer_vs_overall_item_totalcost_across_product_productgroups_26w = catalog.get_feature(
    "CUSTOMER_vs_OVERALL_item_TotalCost_across_product_ProductGroups_26w"
)
customer_age_band = catalog.get_feature("CUSTOMER_Age_band")
customer_latest_invoice_amount = catalog.get_feature("CUSTOMER_Latest_invoice_Amount")
customer_count_of_invoice_14d = catalog.get_feature("CUSTOMER_Count_of_invoice_14d")
customer_avg_of_invoice_amount_14d = catalog.get_feature("CUSTOMER_Avg_of_invoice_Amount_14d")
customer_std_of_invoice_amount_14d = catalog.get_feature("CUSTOMER_Std_of_invoice_Amount_14d")
customer_latest_invoice_amount_Z_score_to_invoice_amount_28d = catalog.get_feature(
    "CUSTOMER_Latest_invoice_Amount_Z_Score_to_invoice_Amount_28d"
)
customer_vs_overall_item_totalcost_across_product_productgroups_26w = catalog.get_feature(
    "CUSTOMER_vs_OVERALL_item_TotalCost_across_product_ProductGroups_26w"
)

Create feature list¶

In [4]:

            
                Copied!
                
                    
                    
                
                

        
simple_feature_list = fb.FeatureList(
    [
        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
    ],
    name="Customer Simple FeatureList"
)
simple_feature_list = fb.FeatureList(
    [
        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
    ],
    name="Customer Simple FeatureList"
)

Preview feature list¶

In [5]:

            
                Copied!
                
# Check the primary entity of the feature list
simple_feature_list.primary_entity
# Check the primary entity of the feature list
simple_feature_list.primary_entity

Out[5]:

[<featurebyte.api.entity.Entity at 0x7fa8b001cac0>
 {
   'name': 'customer',
   'created_at': '2023-09-11T13:56:58.863000',
   'updated_at': '2023-09-11T13:57:16.943000',
   'description': None,
   'serving_names': [
     'GROCERYCUSTOMERGUID'
   ],
   'catalog_name': 'Grocery Dataset Tutorial'
 }]

In [6]:

            
                Copied!
                
# Get observation table: 'Preview Table with 10 Customers'
preview_table = catalog.get_observation_table(
    "Preview Table with 10 Customers"
).to_pandas()
# Get observation table: 'Preview Table with 10 Customers'
preview_table = catalog.get_observation_table(
    "Preview Table with 10 Customers"
).to_pandas()

Downloading table |████████████████████████████████████████| 10/10 [100%] in 0.1

In [7]:

            
                Copied!
                
# Preview simple_feature_list
simple_feature_list.preview(preview_table)
# Preview simple_feature_list
simple_feature_list.preview(preview_table)

Out[7]:

	POINT_IN_TIME	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	2022-07-21 12:50:21	dd0c74f0-9ba8-4ca9-bd84-8148095aa38a	50-54	19.35	1	19.350000	0.000000	1.696160	0.681454
1	2022-11-10 15:57:20	0401635c-e6ab-4525-bb5d-00aba7f6d0c4	30-34	62.55	2	38.645000	23.905000	1.706156	0.751135
2	2022-08-14 19:00:14	54d86ef6-f9b8-40e2-9162-a60bd1b705db	20-24	24.73	3	23.230000	8.492738	0.931491	0.417760
3	2022-07-12 08:02:04	4eb4ee84-ee13-4eec-9c26-61b6eb4ba35b	65-69	46.00	4	25.005000	14.659950	1.567570	0.769076
4	2022-12-13 08:15:49	1e866814-e5a6-475d-87e3-b53377cc005b	55-59	5.00	4	3.512500	1.064551	-0.367178	0.532345
5	2023-04-26 16:52:34	48072b52-39cf-452c-8531-02cc4d0fc32e	40-44	1.54	12	3.740000	5.472707	-0.521815	0.839560
6	2023-03-01 11:31:00	081f111a-598b-43ae-a28a-3a5dc3d2a091	60-64	5.08	3	3.983333	1.759968	-0.341443	0.704808
7	2023-01-19 16:33:33	f3415165-754c-40b6-af17-06ef952a3fa1	20-24	2.28	15	10.937333	15.656393	-0.585856	0.823894
8	2023-04-11 19:07:26	d0ea14bf-038a-4ae5-887e-e2d4d68dd8f6	40-44	3.80	6	6.605000	6.384240	-0.463131	0.866171
9	2023-04-10 08:24:27	69d8718e-8c4a-4264-8edf-e0ffc1ef4737	30-34	40.56	8	8.308750	12.339442	1.813072	0.856881

Save feature list¶

In [8]:

            
                Copied!
                
# Save feature list
simple_feature_list.save()
# Add description
simple_feature_list.update_description("Simple feature list for the customer")
# Save feature list
simple_feature_list.save()
# Add description
simple_feature_list.update_description("Simple feature list for the customer")

Done! |████████████████████████████████████████| 100% in 6.8s (0.15%/s)         
Loading Feature(s) |████████████████████████████████████████| 7/7 [100%] in 1.5s

Concepts in this tutorial¶

More on feature lists

SDK Reference for¶

In [ ]: