langsim.py¶
This is the main module to be using.
We combine the final results using:
$$ sim_{overall} = \lambda_1 sim_{phon} + \lambda_2 sim_{script} + \lambda_3 sim_{gen} $$.
Module Documentation¶
-
langsim.sim_gen(l1, l2)¶ Parameters: - l1 –
- l2 –
Returns:
-
langsim.sim_gen_closest(l1)¶ Parameters: l1 – Returns:
-
langsim.sim_overall(l1, l2, lambda1=0.3333333333333333, lambda2=0.3333333333333333, lambda3=0.3333333333333333)¶ This is just pairwise similarity.
Parameters: - l1 –
- l2 –
- lambda1 –
- lambda2 –
- lambda3 –
Returns:
-
langsim.sim_overall_closest(l1, lambda1=0.3333333333333333, lambda2=0.3333333333333333, lambda3=0.3333333333333333)¶ Given a language, this gets a list of close languages.
Parameters: - l1 –
- lambda1 –
- lambda2 –
- lambda3 –
Returns:
-
langsim.sim_phon(l1, l2)¶ l1 and l2 are 3 letter ISO language codes.
Parameters: - l1 –
- l2 –
Returns:
-
langsim.sim_phon_closest(l1)¶ Should return a tuple: langs, closest.
Parameters: l1 – Returns: ?
-
langsim.sim_script(l1, l2)¶ l1 and l2 are Wikipedia language names (as found in wikidata.<lang> files)
Parameters: - l1 –
- l2 –
Returns:
-
langsim.sim_script_closest(l1)¶ Parameters: l1 – language name, wikiname? Returns: langdists, closest