Generating Features for Raw Event Data

feature_generation.py

import featuretools as ft

rawEventsDF = ... # load from data warehouse 

# 1-hot encode the raw event data
es = ft.EntitySet(id="events")    
es = es.entity_from_dataframe(entity_id="events", dataframe=rawDataDF)    
feature_matrix, defs = ft.dfs(entityset=es, target_entity="events", max_depth=1)
encodedDF, encoders = ft.encode_features(feature_matrix, defs)

# perform deep feature synthesis on the encoded data
es = ft.EntitySet(id="events")    
es = es.entity_from_dataframe(entity_id="events", dataframe=encodedDF)
es = es.normalize_entity(base_entity_id="events", new_entity_id="users", index="user_id")
generated_features, descriptors = ft.dfs(entityset=es, target_entity="users", max_depth=2)