I've used euclidean metric instead of taxicab as I feel it makes more sense (taxicab has bizzare unintuitive effects for points far from the centroids).
pull/37/head
drevicko 7 years ago committed by GitHub
parent 8c70433312
commit 8d56a0b630

@ -52,7 +52,7 @@ class CentroidConversion(EmotionConversionPlugin):
dimensions = list(self.centroids.values())[0]
def distance(e1, e2):
return sum((e1[k] - e2.get(k, 0)) for k in dimensions)
return sum((e1[k] - e2.get(k, 0)**2) for k in dimensions)
emotion = ''
mindistance = 10000000000000000000000.0

Loading…
Cancel
Save