Closed rnowling closed 9 years ago
The classifiers in Clatern currently default to Euclidean distance. We can make distance an optional parameter that takes a function and provide functions for additional distance metrics such as the Manhattan (L1) and cosine distances.
The classifiers in Clatern currently default to Euclidean distance. We can make distance an optional parameter that takes a function and provide functions for additional distance metrics such as the Manhattan (L1) and cosine distances.