PRODUCT vs OVERALL item TotalCost across customer Genders 28d
SDK code to create PRODUCT_vs_OVERALL_item_TotalCost_across_customer_Genders_28d¶
Feature description:
Similarity between the product and all products measured by the Cosine Similarity between the Distribution representing the cumulative TotalCost of item, categorized by their respective customer's Gender, over 28d for both entities.
In [ ]:
Copied!
import featurebyte as fb
fb.use_profile("tutorial")
import featurebyte as fb
fb.use_profile("tutorial")
Activate catalog¶
In [ ]:
Copied!
catalog = fb.Catalog.activate("Grocery Dataset Tutorial")
catalog = fb.Catalog.activate("Grocery Dataset Tutorial")
Set windows for aggregation¶
In [ ]:
Copied!
windows = ['28d']
windows = ['28d']
Get view from table¶
In [ ]:
Copied!
# Get view from INVOICEITEMS item table.
invoiceitems_view = catalog.get_view("INVOICEITEMS")
# Get view from INVOICEITEMS item table.
invoiceitems_view = catalog.get_view("INVOICEITEMS")
In [ ]:
Copied!
# Get view from GROCERYCUSTOMER scd table.
grocerycustomer_view = catalog.get_view("GROCERYCUSTOMER")
# Get view from GROCERYCUSTOMER scd table.
grocerycustomer_view = catalog.get_view("GROCERYCUSTOMER")
Join views¶
In [ ]:
Copied!
# Join GROCERYCUSTOMER view to INVOICEITEMS view.
invoiceitems_view = invoiceitems_view.join(grocerycustomer_view, rsuffix="")
# Join GROCERYCUSTOMER view to INVOICEITEMS view.
invoiceitems_view = invoiceitems_view.join(grocerycustomer_view, rsuffix="")
Do window aggregation from INVOICEITEMS¶
See SDK reference for features
See SDK reference to groupby a view
See SDK reference to do aggregation over time
In [ ]:
Copied!
# Group INVOICEITEMS view by product entity (GroceryProductGuid) across different Genders.
invoiceitems_view_by_product_across_gender =\
invoiceitems_view.groupby(
['GroceryProductGuid'], category="Gender"
)
# Group INVOICEITEMS view by product entity (GroceryProductGuid) across different Genders.
invoiceitems_view_by_product_across_gender =\
invoiceitems_view.groupby(
['GroceryProductGuid'], category="Gender"
)
In [ ]:
Copied!
# Distribution representing the cumulative TotalCost of item, categorized by their respective
# customer's Gender, for the product over time.
feature_group =\
invoiceitems_view_by_product_across_gender.aggregate_over(
"TotalCost", method=fb.AggFunc.SUM,
feature_names=[
"PRODUCT_item_TotalCost_across_customer_Genders"
+ "_" + w for w in windows
],
windows=windows
)
# Get PRODUCT_item_TotalCost_across_customer_Genders_28d object from feature group.
product_item_totalcost_across_customer_genders_28d =\
feature_group["PRODUCT_item_TotalCost_across_customer_Genders_28d"]
# Distribution representing the cumulative TotalCost of item, categorized by their respective
# customer's Gender, for the product over time.
feature_group =\
invoiceitems_view_by_product_across_gender.aggregate_over(
"TotalCost", method=fb.AggFunc.SUM,
feature_names=[
"PRODUCT_item_TotalCost_across_customer_Genders"
+ "_" + w for w in windows
],
windows=windows
)
# Get PRODUCT_item_TotalCost_across_customer_Genders_28d object from feature group.
product_item_totalcost_across_customer_genders_28d =\
feature_group["PRODUCT_item_TotalCost_across_customer_Genders_28d"]
In [ ]:
Copied!
# Group INVOICEITEMS view across different Genders.
invoiceitems_view_by_overall_across_gender =\
invoiceitems_view.groupby(
[], category="Gender"
)
# Group INVOICEITEMS view across different Genders.
invoiceitems_view_by_overall_across_gender =\
invoiceitems_view.groupby(
[], category="Gender"
)
In [ ]:
Copied!
# Distribution representing the cumulative TotalCost of item, categorized by their respective
# customer's Gender, over time.
feature_group =\
invoiceitems_view_by_overall_across_gender.aggregate_over(
"TotalCost", method=fb.AggFunc.SUM,
feature_names=[
"OVERALL_item_TotalCost_across_customer_Genders"
+ "_" + w for w in windows
],
windows=windows
)
# Get OVERALL_item_TotalCost_across_customer_Genders_28d object from feature group.
overall_item_totalcost_across_customer_genders_28d =\
feature_group["OVERALL_item_TotalCost_across_customer_Genders_28d"]
# Distribution representing the cumulative TotalCost of item, categorized by their respective
# customer's Gender, over time.
feature_group =\
invoiceitems_view_by_overall_across_gender.aggregate_over(
"TotalCost", method=fb.AggFunc.SUM,
feature_names=[
"OVERALL_item_TotalCost_across_customer_Genders"
+ "_" + w for w in windows
],
windows=windows
)
# Get OVERALL_item_TotalCost_across_customer_Genders_28d object from feature group.
overall_item_totalcost_across_customer_genders_28d =\
feature_group["OVERALL_item_TotalCost_across_customer_Genders_28d"]
Derive Similarity feature across entities¶
In [ ]:
Copied!
# Derive Similarity feature from cosine similarity between
# PRODUCT_item_TotalCost_across_customer_Genders_28d
# and OVERALL_item_TotalCost_across_customer_Genders_28d
product_vs_overall_item_totalcost_across_customer_genders_28d =\
product_item_totalcost_across_customer_genders_28d.cd.cosine_similarity(
overall_item_totalcost_across_customer_genders_28d
)
# Give a name to new feature
product_vs_overall_item_totalcost_across_customer_genders_28d.name = \
"PRODUCT_vs_OVERALL_item_TotalCost_across_customer_Genders_28d"
# Derive Similarity feature from cosine similarity between
# PRODUCT_item_TotalCost_across_customer_Genders_28d
# and OVERALL_item_TotalCost_across_customer_Genders_28d
product_vs_overall_item_totalcost_across_customer_genders_28d =\
product_item_totalcost_across_customer_genders_28d.cd.cosine_similarity(
overall_item_totalcost_across_customer_genders_28d
)
# Give a name to new feature
product_vs_overall_item_totalcost_across_customer_genders_28d.name = \
"PRODUCT_vs_OVERALL_item_TotalCost_across_customer_Genders_28d"
Preview feature¶
Read on the feature primary entity concept
Read on the serving entity concept
In [ ]:
Copied!
#Check the primary entity of the feature'
product_vs_overall_item_totalcost_across_customer_genders_28d.primary_entity
#Check the primary entity of the feature'
product_vs_overall_item_totalcost_across_customer_genders_28d.primary_entity
In [ ]:
Copied!
#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 [ ]:
Copied!
#Preview PRODUCT_vs_OVERALL_item_TotalCost_across_customer_Genders_28d
product_vs_overall_item_totalcost_across_customer_genders_28d.preview(
preview_table
)
#Preview PRODUCT_vs_OVERALL_item_TotalCost_across_customer_Genders_28d
product_vs_overall_item_totalcost_across_customer_genders_28d.preview(
preview_table
)
Save feature¶
In [ ]:
Copied!
# Save feature
product_vs_overall_item_totalcost_across_customer_genders_28d.save()
# Save feature
product_vs_overall_item_totalcost_across_customer_genders_28d.save()
Add description and see feature definition file¶
In [ ]:
Copied!
# Add description
product_vs_overall_item_totalcost_across_customer_genders_28d.update_description(
"Similarity between the product and all products measured by the Cosine"
" Similarity between the Distribution representing the cumulative "
"TotalCost of item, categorized by their respective customer's Gender, "
"over 28d for both entities."
)
# See feature definition file
product_vs_overall_item_totalcost_across_customer_genders_28d.definition
# Add description
product_vs_overall_item_totalcost_across_customer_genders_28d.update_description(
"Similarity between the product and all products measured by the Cosine"
" Similarity between the Distribution representing the cumulative "
"TotalCost of item, categorized by their respective customer's Gender, "
"over 28d for both entities."
)
# See feature definition file
product_vs_overall_item_totalcost_across_customer_genders_28d.definition