Natural Language Processing with Python: A beginner's guide

def sentenceSegment(text):
    sentences = []
    start = 0
    for i in range(len(text)):
        if text[i] == '.' or text[i] == '!' or text[i] == '?':
            sentences.append(text[start:i+1].strip())
            start = i + 1
    return sentences
text = "Hello, NLP world!! In this example, we are going to do the basics of Text processing which will be used later."
print(sentenceSegment(text))

import string
def remove_punctuation(input_string):
    # Define a string of punctuation marks and symbols
    punctuations = string.punctuation
    
    # Remove the punctuation marks and symbols from the input string
    output_string = "".join(char for char in input_string if char not in punctuations)
    
    return output_string
text = "Hello, NLP world!! In this example, we are going to do the basics of Text processing which will be used later."
sentences = sentenceSegment(text)
puncRemovedText = remove_punctuation(text)
print(puncRemovedText)

def convertToLower(s):
  return s.lower()
text = "Hello, NLP world!! In this example, we are going to do the basics of Text processing which will be used later."
puncRemovedText = remove_punctuation(text)
lowerText = convertToLower(puncRemovedText)
print(lowerText)

#in this code, we are not using any libraries
#tokenize without using any function from string or any other function. 
#only using loops and if/else
def tokenize(s):
  words = [] #token words should be stored here
  i = 0
  word = ""
  while(i <len(s)):
    if (s[i] != " "):
      word = word+s[i]
    else:
        words.append(word)
        word = ""
    
    i = i + 1
  words.append(word)
  return words
text = "Hello, NLP world!! In this example, we are going to do the basics of Text processing which will be used later."
puncRemovedText = remove_punctuation(text)
lowerText = convertToLower(puncRemovedText)
tokenizedText = tokenize(lowerText)
print(tokenizedText)

 #remove stop words. 
 #For this code, wesimply assume all words of length less than or equal to 3 
 #MUST be removed.
def stopWordRemoval(words):
    j = 0
    while (j < len(words)):
        if(len(words[j]) < 3):
            words.remove(words[j])
        else:
            j = j + 1
        
    return words
text = "Hello, NLP world!! In this example, we are going to do the basics of Text processing which will be used later"
puncRemovedText = remove_punctuation(text)
lowerText = convertToLower(puncRemovedText)
tokenizedText = tokenize(lowerText)
cleaned = stopWordRemoval(tokenizedText)
print(cleaned)