Reputation: 8029
I am trying to get numbers out of some ordered lists, for example a list could be 'A B C D E', and the other: 'C B E A D H G F I J K'
So I have some trusted data, which is a set of ordered lists each associated with a String, and I am trying to evaluate which automated way is the best to retrieve the same lists given a string so that the list would match (or be as similar as possible to) the list of the same string in my trusted data.
I don't have a strong background in statistics, I was hoping you can refer to methods that I can use and links or resources that would help me understand how to implement them.
Upvotes: 1
Views: 100
Reputation: 3577
The solution would depend on your notion of similarity. One popular similarity measure is the Levenshtein distance (number of letter additions, deletions and modification required to obtain one string from another).
Upvotes: 1