calculate number and names of similar sounding words from a data frame

$ gem install text

Text::Levenshtein.distance('test', 'test')    # => 0
Text::Levenshtein.distance('test', 'tent')    # => 1

$ gem install levenshtein

String.module_eval do
   def similar?(other, threshold=2)
    distance = Text::Levenshtein.distance(self, other)
    distance <= threshold
  end
end

SELECT * FROM `stu_table` WHERE STRCMP(SOUNDEX(`stu_name`), SOUNDEX('Mrinmoy')) <= 0 

from jellyfish import soundex

print(soundex("two"))
print(soundex("to"))

T000
T000

def getSoundexList(dList):
    res = [soundex(x) for x in dList]   # iterate over each elem in the dataList
    # print(res)     # ['T000', 'F630', 'F630', 'D263', 'T000', 'D263']
    return res

dataList = ['two','fourth','forth','dessert','to','desert']    
print([x for x in sorted(getSoundexList(dataList))])

['D263', 'D263', 'F630', 'F630', 'T000', 'T000']

import fuzzy
soundex = fuzzy.Soundex(4)

print(soundex("to"))
print(soundex("two"))

T000
T000

from itertools import groupby

def getSoundexList(dList):
    return sorted([soundex(x) for x in dList])

dataList = ['two','fourth','forth','dessert','to','desert']    
print([list(g) for _, g in groupby(getSoundexList(dataList), lambda x: x)])

[['D263', 'D263'], ['F630', 'F630'], ['T000', 'T000']]

from operator import itemgetter

def getSoundexDict(dList):
    return sorted(dict_.items(), key=itemgetter(1))  # sorting the dict_ on val

dataList = ['two','fourth','forth','dessert','to','desert']
res = [soundex(x) for x in dataList]    # to get the val for each elem
dict_ = dict(list(zip(dataList, res)))  # dict_ with k,v as name/val

print([list(g) for _, g in groupby(getSoundexDict(dataList), lambda x: x[1])])

[[('dessert', 'D263'), ('desert', 'D263')], [('fourth', 'F630'), ('forth', 'F630')], [('two', 'T000'), ('to', 'T000')]]

cbind(df1['Word1'], do.call(rbind, lapply(df1$Word1, function(x) {
         i1 <- agrep(x, df2$Word2)
     data.frame(links = toString(df2$Word2[i1]) , counts = length(i1))})))