CUSTOMER Avg ProductGroup Embedding 14d vs 182d

Aggregate embedding features over time¶

Another useful way of aggregating embedding vectors is aggregation over time.

This capability allows to compute average/max embeddings over various time windows, which can be useful for capturing change of grocery customer's basket over time, compute similarities between baskets at current time vs the past.

In [ ]:

import featurebyte as fb
fb.use_profile("tutorial")

import featurebyte as fb fb.use_profile("tutorial")

In [ ]:

catalog = fb.Catalog.activate("Grocery Dataset Tutorial")

catalog = fb.Catalog.activate("Grocery Dataset Tutorial")

Create UDF function¶

F_SBERT_EMBEDDING is a name of SQL function awailable in Data Warehouse, which calls deployed transformer model.

In [ ]:

embedding_udf = fb.UserDefinedFunction.create(
    name='embedding', 
    sql_function_name='F_SBERT_EMBEDDING',
    function_parameters=[fb.FunctionParameter(name="x", dtype=fb.enum.DBVarType.VARCHAR)],
    output_dtype=fb.enum.DBVarType.ARRAY,
    is_global=False,
)

embedding_udf = fb.UserDefinedFunction.create( name='embedding', sql_function_name='F_SBERT_EMBEDDING', function_parameters=[fb.FunctionParameter(name="x", dtype=fb.enum.DBVarType.VARCHAR)], output_dtype=fb.enum.DBVarType.ARRAY, is_global=False, )

Get views¶

In [ ]:

# Get view from GROCERYPRODUCT dimension table.
groceryproduct_view = catalog.get_view("GROCERYPRODUCT")
# Get view from INVOICEITEMS item table.
invoiceitems_view = catalog.get_view("INVOICEITEMS")

# Get view from GROCERYPRODUCT dimension table. groceryproduct_view = catalog.get_view("GROCERYPRODUCT") # Get view from INVOICEITEMS item table. invoiceitems_view = catalog.get_view("INVOICEITEMS")

Run embedding UDF on the ProductGroup column¶

In [ ]:

groceryproduct_view["ProductGroupEmbedding"] = embedding_udf(groceryproduct_view["ProductGroup"])

groceryproduct_view["ProductGroupEmbedding"] = embedding_udf(groceryproduct_view["ProductGroup"])

Join views¶

In [ ]:

# Join GROCERYPRODUCT view to INVOICEITEMS view.
invoiceitems_view = invoiceitems_view.join(groceryproduct_view, rsuffix="")

# Join GROCERYPRODUCT view to INVOICEITEMS view. invoiceitems_view = invoiceitems_view.join(groceryproduct_view, rsuffix="")

Create observation table¶

In [ ]:

observation_table = invoiceitems_view.create_observation_table(
    name="Preview tables with Invoice Items",
    sample_rows=10,
    columns=["Timestamp", "GroceryInvoiceItemGuid"],
    columns_rename_mapping={
        "Timestamp": "POINT_IN_TIME",
        "GroceryInvoiceItemGuid": "GROCERYINVOICEITEMGUID",
    },
)

observation_table = invoiceitems_view.create_observation_table( name="Preview tables with Invoice Items", sample_rows=10, columns=["Timestamp", "GroceryInvoiceItemGuid"], columns_rename_mapping={ "Timestamp": "POINT_IN_TIME", "GroceryInvoiceItemGuid": "GROCERYINVOICEITEMGUID", }, )

Create features from embedding column¶

In [ ]:

customer_avg_product_groups = invoiceitems_view.groupby("GroceryCustomerGuid").aggregate_over(
    "ProductGroupEmbedding",
    method=fb.AggFunc.AVG,
    feature_names=["CUSTOMER_Avg_of_ProductGroup_Embedding_14d", "CUSTOMER_Avg_of_ProductGroup_Embedding_183d"], 
    windows=["14d", "183d"]
)

customer_avg_product_groups_cosine = customer_avg_product_groups["CUSTOMER_Avg_of_ProductGroup_Embedding_14d"].vec.cosine_similarity(
    customer_avg_product_groups["CUSTOMER_Avg_of_ProductGroup_Embedding_183d"]
)
customer_avg_product_groups_cosine.name = "CUSTOMER_Consistency_of_Avg_of_ProductGroup_Embedding_14d_183d"

customer_avg_product_groups = invoiceitems_view.groupby("GroceryCustomerGuid").aggregate_over( "ProductGroupEmbedding", method=fb.AggFunc.AVG, feature_names=["CUSTOMER_Avg_of_ProductGroup_Embedding_14d", "CUSTOMER_Avg_of_ProductGroup_Embedding_183d"], windows=["14d", "183d"] ) customer_avg_product_groups_cosine = customer_avg_product_groups["CUSTOMER_Avg_of_ProductGroup_Embedding_14d"].vec.cosine_similarity( customer_avg_product_groups["CUSTOMER_Avg_of_ProductGroup_Embedding_183d"] ) customer_avg_product_groups_cosine.name = "CUSTOMER_Consistency_of_Avg_of_ProductGroup_Embedding_14d_183d"

In [ ]:

observation_table = catalog.get_observation_table("Preview tables with Invoice Items")
customer_avg_product_groups_cosine.preview(observation_table.to_pandas())

observation_table = catalog.get_observation_table("Preview tables with Invoice Items") customer_avg_product_groups_cosine.preview(observation_table.to_pandas())

Save feature and view definition file¶

In [ ]:

customer_avg_product_groups_cosine.save()

customer_avg_product_groups_cosine.save()

In [ ]:

# Add description
customer_avg_product_groups_cosine.update_description(
    "Similarity between average customer's baskets in 14 and 183 days periods"
)
# See feature definition file
customer_avg_product_groups_cosine.definition

# Add description customer_avg_product_groups_cosine.update_description( "Similarity between average customer's baskets in 14 and 183 days periods" ) # See feature definition file customer_avg_product_groups_cosine.definition

In [ ]: