Search code examples
pythonnlptext-processing

How to identify Nouns in string and capitalize them?

I have simple plain text in lower case and no punctuation. Is there any library which can help changing the upper case like where Nouns are or where required? Like names after Mr. and so.? Any solution or guiding hint can be very helpful. for example: in english language in English .. in plain text, at several places are names. and several names needed to be capitalized. like 

mr. john is living in canada

to

Mr. John is living in Canada
Solution

  • Here is a workaround using nltk library to identify nouns using pos_tag feature:

    #Import nltk modules

import nltk
from nltk.tokenize import word_tokenize
from nltk.tag import pos_tag

text = "mr. john is living in canada"

#Define a function to extract nouns from the string

def ExtractNoun(sentence):
    sentence = nltk.word_tokenize(sentence)
    sentence = nltk.pos_tag(sentence)
    return sentence

sent = ExtractNoun(text)

#This will return a tuple of tokens and tags

print(sent)
[('mr.', 'NN'), ('john', 'NN'), ('is', 'VBZ'), ('living', 'VBG'), ('in', 'IN'), ('canada', 'NN')]

#Create a list of nouns

nn = [i[0] for i in sent if i[1] == 'NN']

#Capitalize the nouns which are matching with the list

text_cap = " ".join([x.capitalize() if x in nn else x for x in text.split()])
print(text_cap)

'Mr. John is living in Canada'

    Hope this works!!