Some embedding layer implementation using ivy library. Just for fun. It is based on NYCTaxiFare dataset from kaggle (cut down to 120,000 rows). Most of the feature extraction is similar to Jose Portilla’s.
Uses haversine formula to extract the feature of distance (km) from a given latitude and longtitude of pickup and dropoff locations.
Initial loss graph with lr = 0.01 and 50 epochs: