search

taki0112 / Vector_Similarity

Python, Java implementation of TS-SS called from "A Hybrid Geometric Approach for Measuring Similarity Level Among Documents and Document Clustering"
MIT License
297 stars 44 forks source link

Why euclidean and ts ss result exceeding 1? #7

Open thoriqadillah opened 1 year ago

thoriqadillah commented 1 year ago

I tried the java version. When I run the example from the code, the result as follows euclidean: 2.23606797749979 cosine similarity: 0.9999999999999998 ts ss: 4.6395825669994775E-4

I get that the cosine similarity is 0.99, because I expect it to be out of 1 or 100%. But why euclidean and ts ss exceed 100%. How to measure it then?

lynnwilliam commented 1 year ago

Ts ss and ecludian are not from 0 to 1. You can get from 0.00 to infinity. So the example is correct