featurebyte.Feature.cd.cosine_similarity¶
Description¶
Computes the cosine similarity with another Cross Aggregate feature.
Parameters¶
- other: Feature
Another dictionary feature.
Returns¶
- Feature
Another Cross Aggregate feature.
Examples¶
Create a similarity feature between two dictionary features:
>>> feature_1 = catalog.get_feature("CustomerProductGroupCounts_7d")
>>> feature_2 = catalog.get_feature("CustomerProductGroupCounts_90d")
>>> similarity = feature_1.cd.cosine_similarity(feature_2)
>>> similarity.name = "CustomerProductGroupCounts_7d_90d_similarity"
>>> features = fb.FeatureGroup([feature_1, feature_2, similarity])
>>> df = features.preview(pd.DataFrame([{"POINT_IN_TIME": "2022-04-15 10:00:00", "GROCERYCUSTOMERGUID": "2f4c1578-29d6-44b7-83da-7c5bfb981fa0"}]))
>>> df["CustomerProductGroupCounts_7d"].iloc[0]
'{"Chips et Tortillas":1,"Colas, Thés glacés et Sodas":3,"Crèmes et Chantilly":1,"Pains":1,"Œufs":1}'
Dictionary feature 2:
>>> df["CustomerProductGroupCounts_90d"].iloc[0]
'{"Biscuits apéritifs":1,"Biscuits":1,"Bonbons":1,"Chips et Tortillas":2,"Colas, Thés glacés et Sodas":12,"Confitures":1,"Crèmes et Chantilly":2,"Céréales":1,"Emballages et sacs":1,"Fromages":3,"Glaces et Sorbets":1,"Glaçons":1,"Laits":4,"Noix":1,"Pains":4,"Petit-déjeuner":2,"Viande Surgelée":1,"Œufs":1}'
Similarity feature: