9. Create window aggregate features

Create window aggregate features¶

Next feature type we will consider is window aggregate feature. These are features generated by aggregating data within specific time frame.

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)

15:30:30 | INFO     | SDK version: 1.0.2.dev46
15:30:30 | INFO     | No catalog activated.
15:30:30 | INFO     | Using profile: tutorial
15:30:30 | INFO     | Using configuration file at: /Users/gxav/.featurebyte/config.yaml
15:30:30 | INFO     | Active profile: tutorial (https://tutorials.featurebyte.com/api/v1)
15:30:30 | INFO     | SDK version: 1.0.2.dev46
15:30:30 | INFO     | No catalog activated.
15:30:31 | INFO     | Catalog activated: Grocery Dataset Tutorial

In [2]:

# Set desired windows
windows = ['14d', '28d']

# Set desired windows windows = ['14d', '28d']

Do window aggregation from INVOICEITEMS¶

Let's start with some aggregations from the items view and create features for the interaction between Customer and Product Group.

In [3]:

# Get view from GROCERYPRODUCT dimension table.
groceryproduct_view = catalog.get_view("GROCERYPRODUCT")
# Get view from INVOICEITEMS item table.
invoiceitems_view = catalog.get_view("INVOICEITEMS")
# Join GROCERYPRODUCT view to INVOICEITEMS view.
invoiceitems_view = invoiceitems_view.join(groceryproduct_view, rsuffix="")

# Get view from GROCERYPRODUCT dimension table. groceryproduct_view = catalog.get_view("GROCERYPRODUCT") # Get view from INVOICEITEMS item table. invoiceitems_view = catalog.get_view("INVOICEITEMS") # Join GROCERYPRODUCT view to INVOICEITEMS view. invoiceitems_view = invoiceitems_view.join(groceryproduct_view, rsuffix="")

In [4]:

# Group GROCERYINVOICE view by customer entity (GroceryCustomerGuid) and productgroup entity (ProductGroup).
invoiceitems_view_by_customer_x_productgroup = invoiceitems_view.groupby(
    ['GroceryCustomerGuid', 'ProductGroup']
)

# Group GROCERYINVOICE view by customer entity (GroceryCustomerGuid) and productgroup entity (ProductGroup). invoiceitems_view_by_customer_x_productgroup = invoiceitems_view.groupby( ['GroceryCustomerGuid', 'ProductGroup'] )

In [5]:

# Get Sum of TotalCost for the customer x productgroup over time.
customer_productgroup_sum_of_totalcost_14d_28d = \
invoiceitems_view_by_customer_x_productgroup.aggregate_over(
    "TotalCost", method="sum",
    feature_names=[
        "CUSTOMER_x_PRODUCTGROUP_Sum_of_item_TotalCost"
        + "_" + w for w in windows
    ],
    fill_value=0,
    windows=windows
)

# Get Sum of TotalCost for the customer x productgroup over time. customer_productgroup_sum_of_totalcost_14d_28d = \ invoiceitems_view_by_customer_x_productgroup.aggregate_over( "TotalCost", method="sum", feature_names=[ "CUSTOMER_x_PRODUCTGROUP_Sum_of_item_TotalCost" + "_" + w for w in windows ], fill_value=0, windows=windows )

In [6]:

# Get Latest Interaction between Customer and ProductGroup
customer_x_productgroup_latest_timestamp = \
invoiceitems_view_by_customer_x_productgroup.aggregate_over(
    "Timestamp", method="latest",
    feature_names=["CUSTOMER_x_PRODUCTGROUP_Latest_Timestamp"],
    windows=[None]
)["CUSTOMER_x_PRODUCTGROUP_Latest_Timestamp"]

# Get Latest Interaction between Customer and ProductGroup customer_x_productgroup_latest_timestamp = \ invoiceitems_view_by_customer_x_productgroup.aggregate_over( "Timestamp", method="latest", feature_names=["CUSTOMER_x_PRODUCTGROUP_Latest_Timestamp"], windows=[None] )["CUSTOMER_x_PRODUCTGROUP_Latest_Timestamp"]

In [7]:

# Create recency feature: Time Since Latest Interaction between Customer and Product Group
customer_x_productgroup_time_since_latest_timestamp = (
    fb.RequestColumn.point_in_time()
    - customer_x_productgroup_latest_timestamp
).dt.hour
customer_x_productgroup_time_since_latest_timestamp.name = \
"CUSTOMER_x_PRODUCTGROUP_Time_Since_Latest_Timestamp"

# Create recency feature: Time Since Latest Interaction between Customer and Product Group customer_x_productgroup_time_since_latest_timestamp = ( fb.RequestColumn.point_in_time() - customer_x_productgroup_latest_timestamp ).dt.hour customer_x_productgroup_time_since_latest_timestamp.name = \ "CUSTOMER_x_PRODUCTGROUP_Time_Since_Latest_Timestamp"

Do window aggregation from GROCERYINVOICE¶

Now, let's do some aggregations on the invoices view for the Customer entity.

In [8]:

# Get view from GROCERYINVOICE event table.
groceryinvoice_view = catalog.get_view("GROCERYINVOICE")

# Get view from GROCERYINVOICE event table. groceryinvoice_view = catalog.get_view("GROCERYINVOICE")

In [9]:

# Group GROCERYINVOICE view by customer entity (GroceryCustomerGuid).
groceryinvoice_view_by_customer = groceryinvoice_view.groupby(['GroceryCustomerGuid'])

# Group GROCERYINVOICE view by customer entity (GroceryCustomerGuid). groceryinvoice_view_by_customer = groceryinvoice_view.groupby(['GroceryCustomerGuid'])

In [10]:

# Get Latest invoice Amount for the customer
customer_latest_invoice_amount = groceryinvoice_view_by_customer.aggregate_over(
    "Amount", method="latest",
    feature_names=["CUSTOMER_Latest_invoice_Amount"],
    windows=[None]
)["CUSTOMER_Latest_invoice_Amount"]

# Get Latest invoice Amount for the customer customer_latest_invoice_amount = groceryinvoice_view_by_customer.aggregate_over( "Amount", method="latest", feature_names=["CUSTOMER_Latest_invoice_Amount"], windows=[None] )["CUSTOMER_Latest_invoice_Amount"]

In [11]:

# Get Count of invoices for the customer
customer_count_of_invoice_14d_28d = groceryinvoice_view_by_customer.aggregate_over(
    method="count",
    feature_names=[
        "CUSTOMER_Count_of_invoice"
        + "_" + w for w in windows
    ],
    windows=windows
)

# Get Count of invoices for the customer customer_count_of_invoice_14d_28d = groceryinvoice_view_by_customer.aggregate_over( method="count", feature_names=[ "CUSTOMER_Count_of_invoice" + "_" + w for w in windows ], windows=windows )

In [12]:

# Get Avg of Amount for the customer over time.
customer_avg_of_invoice_amount_14d_28d = groceryinvoice_view_by_customer.aggregate_over(
    "Amount", method="avg",
    feature_names=[
        "CUSTOMER_Avg_of_invoice_Amount"
        + "_" + w for w in windows
    ],
    windows=windows
)

# Get Avg of Amount for the customer over time. customer_avg_of_invoice_amount_14d_28d = groceryinvoice_view_by_customer.aggregate_over( "Amount", method="avg", feature_names=[ "CUSTOMER_Avg_of_invoice_Amount" + "_" + w for w in windows ], windows=windows )

In [13]:

# Get Std of Amount for the customer over time.
customer_std_of_invoice_amount_14d_28d = groceryinvoice_view_by_customer.aggregate_over(
    "Amount", method="std",
    feature_names=[
        "CUSTOMER_Std_of_invoice_Amount"
        + "_" + w for w in windows
    ],
    windows=windows
)

# Get Std of Amount for the customer over time. customer_std_of_invoice_amount_14d_28d = groceryinvoice_view_by_customer.aggregate_over( "Amount", method="std", feature_names=[ "CUSTOMER_Std_of_invoice_Amount" + "_" + w for w in windows ], windows=windows )

Preview a feature group¶

For convenience, we can create a feature group to preview/save all features we just created.

In [14]:

feature_group = fb.FeatureGroup([
    customer_x_productgroup_time_since_latest_timestamp,
    customer_productgroup_sum_of_totalcost_14d_28d,
    customer_latest_invoice_amount,
    customer_count_of_invoice_14d_28d,
    customer_avg_of_invoice_amount_14d_28d,
    customer_std_of_invoice_amount_14d_28d,
])

feature_group = fb.FeatureGroup([ customer_x_productgroup_time_since_latest_timestamp, customer_productgroup_sum_of_totalcost_14d_28d, customer_latest_invoice_amount, customer_count_of_invoice_14d_28d, customer_avg_of_invoice_amount_14d_28d, customer_std_of_invoice_amount_14d_28d, ])

In [15]:

# Check the primary entity of the feature group. It should be the interaction Customer x ProductGroup.
feature_group.primary_entity

# Check the primary entity of the feature group. It should be the interaction Customer x ProductGroup. feature_group.primary_entity

Out[15]:

[<featurebyte.api.entity.Entity at 0x107a508c0>
 {
   '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 0x14a543240>
 {
   '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 [16]:

# 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 [17]:

# Preview feature_group
feature_group.preview(preview_table)

# Preview feature_group feature_group.preview(preview_table)

Out[17]:

	POINT_IN_TIME	GROCERYINVOICEITEMGUID	CUSTOMER_x_PRODUCTGROUP_Time_Since_Latest_Timestamp	CUSTOMER_x_PRODUCTGROUP_Sum_of_item_TotalCost_14d	CUSTOMER_x_PRODUCTGROUP_Sum_of_item_TotalCost_28d	CUSTOMER_Latest_invoice_Amount	CUSTOMER_Count_of_invoice_14d	CUSTOMER_Count_of_invoice_28d	CUSTOMER_Avg_of_invoice_Amount_14d	CUSTOMER_Avg_of_invoice_Amount_28d	CUSTOMER_Std_of_invoice_Amount_14d	CUSTOMER_Std_of_invoice_Amount_28d
0	2022-11-03 14:39:00	9faf5936-d4bb-4709-a530-c1624ec003a5	6314.067778	0.0	0.00	63.65	2	9	46.9650	23.980000	16.685000	19.449867
1	2022-08-16 15:37:21	6781acc6-652d-4867-a138-2d8adb278886	NaN	0.0	0.00	1.50	1	3	1.5000	10.873333	0.000000	11.031305
2	2022-10-05 14:30:03	fc4769cf-41d6-4fb0-9cfc-fe30502cfa18	360.176111	0.0	5.63	14.57	2	5	7.9150	16.126000	6.655000	10.164890
3	2023-03-19 15:22:18	dcdb7c98-dd62-4287-b432-bfe3a2317ebc	163.990000	9.0	9.00	85.74	2	3	60.1600	64.773333	25.580000	21.881270
4	2023-03-13 21:11:43	cfc620a2-0054-4b4b-99d5-040cf87cfe2d	414.501389	0.0	3.09	4.29	2	9	3.1400	13.368889	1.150000	11.359725
5	2022-11-18 10:07:49	ae2ccf38-4e5d-4c76-b1e5-04f12307e45b	NaN	0.0	0.00	9.24	3	6	28.6700	24.143333	33.102335	25.427108
6	2022-11-09 18:07:20	37122b82-478b-4d9e-b236-69629b592c0b	4448.626944	0.0	0.00	69.93	1	2	69.9300	80.980000	0.000000	11.050000
7	2023-02-15 21:10:22	5daf8edb-8625-4653-aaa0-9ac03df92017	1705.355000	0.0	0.00	24.04	2	3	35.8850	35.370000	11.845000	9.698787
8	2023-02-27 13:27:47	b807e05c-ff1c-4fb3-a760-e0e8ce29c859	316.402222	1.0	1.00	4.80	4	8	10.8925	8.286250	7.927192	6.802988
9	2023-04-19 15:25:05	8a60f455-aff1-4b4e-8c63-9ab89df2715d	503.857500	0.0	2.89	3.39	1	3	3.3900	10.223333	0.000000	5.149319

Save features into catalog¶

With feature groups we can do it in one call.

In [18]:

feature_group.save()

feature_group.save()

Done! |████████████████████████████████████████| 100% in 15.6s (0.06%/s)        
Done! |████████████████████████████████████████| 100% in 6.2s (0.16%/s)         
Loading Feature(s) |████████████████████████████████████████| 10/10 [100%] in 0.

Add description and see feature definition files¶

In [19]:

# Add description
customer_x_productgroup_time_since_latest_timestamp.update_description(
    "Time Since Latest interaction between the customer and the product group"
)
# See feature definition file
customer_x_productgroup_time_since_latest_timestamp.definition

# Add description customer_x_productgroup_time_since_latest_timestamp.update_description( "Time Since Latest interaction between the customer and the product group" ) # See feature definition file customer_x_productgroup_time_since_latest_timestamp.definition

Out[19]:

# Generated by SDK version: 1.0.2.dev46
from bson import ObjectId
from featurebyte import DimensionTable
from featurebyte import FeatureJobSetting
from featurebyte import ItemTable
from featurebyte.api.request_column import RequestColumn


# item_table name: "INVOICEITEMS", event_table name: "GROCERYINVOICE"
item_table = ItemTable.get_by_id(ObjectId("662b5778aa13c89fa14554e2"))
item_view = item_table.get_view(
    event_suffix=None,
    view_mode="manual",
    drop_column_names=["record_available_at"],
    column_cleaning_operations=[],
    event_drop_column_names=["record_available_at"],
    event_column_cleaning_operations=[],
    event_join_column_names=[
        "Timestamp",
        "GroceryInvoiceGuid",
        "GroceryCustomerGuid",
        "tz_offset",
    ],
)

# dimension_table name: "GROCERYPRODUCT"
dimension_table = DimensionTable.get_by_id(ObjectId("662b577aaa13c89fa14554e3"))
dimension_view = dimension_table.get_view(
    view_mode="manual", drop_column_names=[], column_cleaning_operations=[]
)
joined_view = item_view.join(
    dimension_view, on="GroceryProductGuid", how="left", rsuffix="", rprefix=""
)
grouped = joined_view.groupby(
    by_keys=["GroceryCustomerGuid", "ProductGroup"], category=None
).aggregate_over(
    value_column="Timestamp",
    method="latest",
    windows=[None],
    feature_names=["CUSTOMER_x_PRODUCTGROUP_Latest_Timestamp"],
    feature_job_setting=FeatureJobSetting(
        blind_spot="120s", frequency="3600s", time_modulo_frequency="120s"
    ),
    skip_fill_na=True,
)
feat = grouped["CUSTOMER_x_PRODUCTGROUP_Latest_Timestamp"]
request_col = RequestColumn.point_in_time()
feat_1 = (request_col - feat).dt.hour
feat_1.name = "CUSTOMER_x_PRODUCTGROUP_Time_Since_Latest_Timestamp"
output = feat_1
output.save(_id=ObjectId("662b5819da3f1a887399f98a"))

In [20]:

# Add description
customer_productgroup_sum_of_totalcost_14d = \
customer_productgroup_sum_of_totalcost_14d_28d["CUSTOMER_x_PRODUCTGROUP_Sum_of_item_TotalCost_14d"]
customer_productgroup_sum_of_totalcost_14d.update_description(
    "Total spent by the customer on the product group over a 14d period."
)
customer_productgroup_sum_of_totalcost_28d = \
customer_productgroup_sum_of_totalcost_14d_28d["CUSTOMER_x_PRODUCTGROUP_Sum_of_item_TotalCost_28d"]
customer_productgroup_sum_of_totalcost_28d.update_description(
    "Total spent by the customer on the product group over a 28d period."
)
# See feature definition file
customer_productgroup_sum_of_totalcost_28d.definition

# Add description customer_productgroup_sum_of_totalcost_14d = \ customer_productgroup_sum_of_totalcost_14d_28d["CUSTOMER_x_PRODUCTGROUP_Sum_of_item_TotalCost_14d"] customer_productgroup_sum_of_totalcost_14d.update_description( "Total spent by the customer on the product group over a 14d period." ) customer_productgroup_sum_of_totalcost_28d = \ customer_productgroup_sum_of_totalcost_14d_28d["CUSTOMER_x_PRODUCTGROUP_Sum_of_item_TotalCost_28d"] customer_productgroup_sum_of_totalcost_28d.update_description( "Total spent by the customer on the product group over a 28d period." ) # See feature definition file customer_productgroup_sum_of_totalcost_28d.definition

Out[20]:

# Generated by SDK version: 1.0.2.dev46
from bson import ObjectId
from featurebyte import DimensionTable
from featurebyte import FeatureJobSetting
from featurebyte import ItemTable


# item_table name: "INVOICEITEMS", event_table name: "GROCERYINVOICE"
item_table = ItemTable.get_by_id(ObjectId("662b5778aa13c89fa14554e2"))
item_view = item_table.get_view(
    event_suffix=None,
    view_mode="manual",
    drop_column_names=["record_available_at"],
    column_cleaning_operations=[],
    event_drop_column_names=["record_available_at"],
    event_column_cleaning_operations=[],
    event_join_column_names=[
        "Timestamp",
        "GroceryInvoiceGuid",
        "GroceryCustomerGuid",
        "tz_offset",
    ],
)

# dimension_table name: "GROCERYPRODUCT"
dimension_table = DimensionTable.get_by_id(ObjectId("662b577aaa13c89fa14554e3"))
dimension_view = dimension_table.get_view(
    view_mode="manual", drop_column_names=[], column_cleaning_operations=[]
)
joined_view = item_view.join(
    dimension_view, on="GroceryProductGuid", how="left", rsuffix="", rprefix=""
)
grouped = joined_view.groupby(
    by_keys=["GroceryCustomerGuid", "ProductGroup"], category=None
).aggregate_over(
    value_column="TotalCost",
    method="sum",
    windows=["28d"],
    feature_names=["CUSTOMER_x_PRODUCTGROUP_Sum_of_item_TotalCost_28d"],
    feature_job_setting=FeatureJobSetting(
        blind_spot="120s", frequency="3600s", time_modulo_frequency="120s"
    ),
    skip_fill_na=True,
)
feat = grouped["CUSTOMER_x_PRODUCTGROUP_Sum_of_item_TotalCost_28d"]
feat_1 = feat.copy()
feat_1[feat.isnull()] = 0
feat_1.name = "CUSTOMER_x_PRODUCTGROUP_Sum_of_item_TotalCost_28d"
output = feat_1
output.save(_id=ObjectId("662b5819da3f1a887399f986"))

In [21]:

# Add description
customer_latest_invoice_amount.update_description("Latest invoice Amount for the customer")
# See feature definition file
customer_latest_invoice_amount.definition

# Add description customer_latest_invoice_amount.update_description("Latest invoice Amount for the customer") # See feature definition file customer_latest_invoice_amount.definition

Out[21]:

# Generated by SDK version: 1.0.2.dev46
from bson import ObjectId
from featurebyte import ColumnCleaningOperation
from featurebyte import DisguisedValueImputation
from featurebyte import EventTable
from featurebyte import FeatureJobSetting
from featurebyte import ValueBeyondEndpointImputation


# event_table name: "GROCERYINVOICE"
event_table = EventTable.get_by_id(ObjectId("662b5775aa13c89fa14554e1"))
event_view = event_table.get_view(
    view_mode="manual",
    drop_column_names=["record_available_at"],
    column_cleaning_operations=[
        ColumnCleaningOperation(
            column_name="Amount",
            cleaning_operations=[
                DisguisedValueImputation(
                    imputed_value=None, disguised_values=[-99.0, -98.0]
                ),
                ValueBeyondEndpointImputation(
                    type="less_than", end_point=0.0, imputed_value=0.0
                ),
                ValueBeyondEndpointImputation(
                    type="greater_than", end_point=2000.0, imputed_value=2000.0
                ),
            ],
        )
    ],
)
grouped = event_view.groupby(
    by_keys=["GroceryCustomerGuid"], category=None
).aggregate_over(
    value_column="Amount",
    method="latest",
    windows=[None],
    feature_names=["CUSTOMER_Latest_invoice_Amount"],
    feature_job_setting=FeatureJobSetting(
        blind_spot="120s", frequency="3600s", time_modulo_frequency="120s"
    ),
    skip_fill_na=True,
)
feat = grouped["CUSTOMER_Latest_invoice_Amount"]
output = feat
output.save(_id=ObjectId("662b581ada3f1a887399f98b"))

In [22]:

# Add description
customer_count_of_invoice_14d = customer_count_of_invoice_14d_28d["CUSTOMER_Count_of_invoice_14d"]
customer_count_of_invoice_14d.update_description(
    "Count of invoice for the customer over a 14d period."
)
customer_count_of_invoice_28d = customer_count_of_invoice_14d_28d["CUSTOMER_Count_of_invoice_28d"]
customer_count_of_invoice_28d.update_description(
    "Count of invoice for the customer over a 28d period."
)
# See feature definition file
customer_count_of_invoice_28d.definition

# Add description customer_count_of_invoice_14d = customer_count_of_invoice_14d_28d["CUSTOMER_Count_of_invoice_14d"] customer_count_of_invoice_14d.update_description( "Count of invoice for the customer over a 14d period." ) customer_count_of_invoice_28d = customer_count_of_invoice_14d_28d["CUSTOMER_Count_of_invoice_28d"] customer_count_of_invoice_28d.update_description( "Count of invoice for the customer over a 28d period." ) # See feature definition file customer_count_of_invoice_28d.definition

Out[22]:

# Generated by SDK version: 1.0.2.dev46
from bson import ObjectId
from featurebyte import EventTable
from featurebyte import FeatureJobSetting


# event_table name: "GROCERYINVOICE"
event_table = EventTable.get_by_id(ObjectId("662b5775aa13c89fa14554e1"))
event_view = event_table.get_view(
    view_mode="manual",
    drop_column_names=["record_available_at"],
    column_cleaning_operations=[],
)
grouped = event_view.groupby(
    by_keys=["GroceryCustomerGuid"], category=None
).aggregate_over(
    value_column=None,
    method="count",
    windows=["28d"],
    feature_names=["CUSTOMER_Count_of_invoice_28d"],
    feature_job_setting=FeatureJobSetting(
        blind_spot="120s", frequency="3600s", time_modulo_frequency="120s"
    ),
    skip_fill_na=True,
)
feat = grouped["CUSTOMER_Count_of_invoice_28d"]
feat_1 = feat.copy()
feat_1[feat.isnull()] = 0
feat_1.name = "CUSTOMER_Count_of_invoice_28d"
output = feat_1
output.save(_id=ObjectId("662b581ada3f1a887399f98e"))

In [23]:

# Add description
customer_avg_of_invoice_amount_14d = customer_avg_of_invoice_amount_14d_28d["CUSTOMER_Avg_of_invoice_Amount_14d"]
customer_avg_of_invoice_amount_14d.update_description(
    "Avg of invoice Amount for the customer over a 14d period."
)
customer_avg_of_invoice_amount_28d = customer_avg_of_invoice_amount_14d_28d["CUSTOMER_Avg_of_invoice_Amount_28d"]
customer_avg_of_invoice_amount_28d.update_description(
    "Avg of invoice Amount for the customer over a 28d period."
)
# See feature definition file
customer_avg_of_invoice_amount_28d.definition

# Add description customer_avg_of_invoice_amount_14d = customer_avg_of_invoice_amount_14d_28d["CUSTOMER_Avg_of_invoice_Amount_14d"] customer_avg_of_invoice_amount_14d.update_description( "Avg of invoice Amount for the customer over a 14d period." ) customer_avg_of_invoice_amount_28d = customer_avg_of_invoice_amount_14d_28d["CUSTOMER_Avg_of_invoice_Amount_28d"] customer_avg_of_invoice_amount_28d.update_description( "Avg of invoice Amount for the customer over a 28d period." ) # See feature definition file customer_avg_of_invoice_amount_28d.definition

Out[23]:

# Generated by SDK version: 1.0.2.dev46
from bson import ObjectId
from featurebyte import ColumnCleaningOperation
from featurebyte import DisguisedValueImputation
from featurebyte import EventTable
from featurebyte import FeatureJobSetting
from featurebyte import ValueBeyondEndpointImputation


# event_table name: "GROCERYINVOICE"
event_table = EventTable.get_by_id(ObjectId("662b5775aa13c89fa14554e1"))
event_view = event_table.get_view(
    view_mode="manual",
    drop_column_names=["record_available_at"],
    column_cleaning_operations=[
        ColumnCleaningOperation(
            column_name="Amount",
            cleaning_operations=[
                DisguisedValueImputation(
                    imputed_value=None, disguised_values=[-99.0, -98.0]
                ),
                ValueBeyondEndpointImputation(
                    type="less_than", end_point=0.0, imputed_value=0.0
                ),
                ValueBeyondEndpointImputation(
                    type="greater_than", end_point=2000.0, imputed_value=2000.0
                ),
            ],
        )
    ],
)
grouped = event_view.groupby(
    by_keys=["GroceryCustomerGuid"], category=None
).aggregate_over(
    value_column="Amount",
    method="avg",
    windows=["28d"],
    feature_names=["CUSTOMER_Avg_of_invoice_Amount_28d"],
    feature_job_setting=FeatureJobSetting(
        blind_spot="120s", frequency="3600s", time_modulo_frequency="120s"
    ),
    skip_fill_na=True,
)
feat = grouped["CUSTOMER_Avg_of_invoice_Amount_28d"]
output = feat
output.save(_id=ObjectId("662b581ada3f1a887399f991"))

In [24]:

# Add description
customer_std_of_invoice_amount_14d = customer_std_of_invoice_amount_14d_28d["CUSTOMER_Std_of_invoice_Amount_14d"]
customer_std_of_invoice_amount_14d.update_description(
    "Std of invoice Amount for the customer over a 14d period."
)
customer_std_of_invoice_amount_28d = customer_std_of_invoice_amount_14d_28d["CUSTOMER_Std_of_invoice_Amount_28d"]
customer_std_of_invoice_amount_28d.update_description(
    "Std of invoice Amount for the customer over a 28d period."
)

# See feature definition file
customer_std_of_invoice_amount_28d.definition

# Add description customer_std_of_invoice_amount_14d = customer_std_of_invoice_amount_14d_28d["CUSTOMER_Std_of_invoice_Amount_14d"] customer_std_of_invoice_amount_14d.update_description( "Std of invoice Amount for the customer over a 14d period." ) customer_std_of_invoice_amount_28d = customer_std_of_invoice_amount_14d_28d["CUSTOMER_Std_of_invoice_Amount_28d"] customer_std_of_invoice_amount_28d.update_description( "Std of invoice Amount for the customer over a 28d period." ) # See feature definition file customer_std_of_invoice_amount_28d.definition

Out[24]:

# Generated by SDK version: 1.0.2.dev46
from bson import ObjectId
from featurebyte import ColumnCleaningOperation
from featurebyte import DisguisedValueImputation
from featurebyte import EventTable
from featurebyte import FeatureJobSetting
from featurebyte import ValueBeyondEndpointImputation


# event_table name: "GROCERYINVOICE"
event_table = EventTable.get_by_id(ObjectId("662b5775aa13c89fa14554e1"))
event_view = event_table.get_view(
    view_mode="manual",
    drop_column_names=["record_available_at"],
    column_cleaning_operations=[
        ColumnCleaningOperation(
            column_name="Amount",
            cleaning_operations=[
                DisguisedValueImputation(
                    imputed_value=None, disguised_values=[-99.0, -98.0]
                ),
                ValueBeyondEndpointImputation(
                    type="less_than", end_point=0.0, imputed_value=0.0
                ),
                ValueBeyondEndpointImputation(
                    type="greater_than", end_point=2000.0, imputed_value=2000.0
                ),
            ],
        )
    ],
)
grouped = event_view.groupby(
    by_keys=["GroceryCustomerGuid"], category=None
).aggregate_over(
    value_column="Amount",
    method="std",
    windows=["28d"],
    feature_names=["CUSTOMER_Std_of_invoice_Amount_28d"],
    feature_job_setting=FeatureJobSetting(
        blind_spot="120s", frequency="3600s", time_modulo_frequency="120s"
    ),
    skip_fill_na=True,
)
feat = grouped["CUSTOMER_Std_of_invoice_Amount_28d"]
output = feat
output.save(_id=ObjectId("662b581ada3f1a887399f993"))

Concepts in this tutorial¶

• Aggregate Features
• Window Aggregate Features

SDK reference for¶

• View.groupby()
• Groupby.aggregate_over()
• List of aggregate functions
• FeatureGroup
• FeatureGroup.save()

In [ ]:

In [ ]: