nlp

1

 import nltk

from nltk.tokenize import word_tokenize

from nltk.stem import PorterStemmer, WordNetLemmatizer

from nltk import pos_tag, ne_chunk

nltk.download('punkt')

text = "Dinesh puri sir kiti bhari HOD ahet."

# Tokenization

tokens = word_tokenize(text)

print("Tokens:", tokens)

# Stemming

stemmer = PorterStemmer()

print("Stemmed:", [stemmer.stem(w) for w in tokens])

# Lemmatization

lemmatizer = WordNetLemmatizer()

print("Lemmatized:", [lemmatizer.lemmatize(w) for w in tokens])

# Chunking

chunks = ne_chunk(pos_tag(tokens))

print("Chunks:", chunks)

2

from nltk.tokenize import word_tokenize

def count_lines_words(file):

    with open(file, 'r') as f:

        text = f.read()

    print("Lines:", text.count('\n') + 1)

    print("Words:", len(word_tokenize(text)))

count_lines_words("nlp5.txt")

#pracitcal 3

from nltk.tokenize import word_tokenize

def count_articles(file):

    with open(file, 'r') as f:

        text = f.read().lower()

    words = word_tokenize(text)

    for a in ['a', 'an', 'the']:

        print(f"{a}: {words.count(a)}")

count_articles("nlp5.txt")

#practical 4

from nltk.tokenize import word_tokenize

from nltk.corpus import stopwords

def remove_stopwords(file):

    with open(file, 'r') as f:

        text = f.read()

    tokens = word_tokenize(text.lower())

    filtered = [w for w in tokens if w not in stopwords.words('english')]

    print("Filtered:", filtered)

remove_stopwords("nlp5.txt")

#practical 5

import re

from nltk.tokenize import word_tokenize

def apply_regex(file):

    with open(file, 'r') as f:

        text = f.read().lower()

    words = word_tokenize(text)

    patterns = {'a*': r'a*', 'a+': r'a+', 'a?': r'a?', 'upper': r'[A-Z]', 's_S': r'[Ss]'}

    for name, pat in patterns.items():

        matched = [w for w in words if re.search(pat, w)]

        print(f"{name}: {matched}")

apply_regex("nlp5.txt")

#practical 6

from nltk import word_tokenize, pos_tag

sentence = input("Enter a sentence: ")

tags = pos_tag(word_tokenize(sentence))

print("POS Tags:", tags)