Skip to main content

6-10

 Lab 6 

import nltk

#define the text

sentence = "I told the children I was going to tell them a story. They were excited"

#tokenize the text

tokens = nltk.word_tokenize(sentence)

#perform POS tagging

tags = nltk.pos_tag(tokens)

#define a chunk grammar named mychunk

chunk_grammar = """ mychunk: {<NNS.?>*<PRP.?>*<VBD?>}"""

#parse the grammar with regular expression parser

parser = nltk.RegexpParser(chunk_grammar)

#assign the chunk

tree = parser.parse(tags)

# Print the tree instead of drawing it

print(tree)



Lab 7 

!pip install nltk
import nltk
from nltk import CFG
from nltk.parse import ChartParser
cnf_grammar = CFG.fromstring("""
S -> NP VP
VP -> V NP | VP PP
PP -> P NP
V -> 'saw' | 'ate' | 'walked'
NP -> 'John' | 'Mary' | 'Bob' | Det N | NP PP
Det -> 'a' | 'an' | 'the'
N -> 'man' | 'dog' | 'cat' | 'telescope' | 'park'
P -> 'in' | 'on' | 'by' | 'with'
""")
parser = ChartParser(cnf_grammar)
sentence = "John saw a man with a telescope"
tokens = sentence.split()
parse_trees = list(parser.parse(tokens))
for tree in parse_trees:
    # Indent the line below to be part of the for loop
    tree.pretty_print()


Lab 8 

!pip install nltk
import nltk
nltk.download('punkt')
from nltk.util import ngrams
from collections import Counter
def extract_ngrams(text):
  tokens = nltk.word_tokenize(text)
  unigrams = list(tokens)
  bigrams = list(ngrams(tokens, 2))
  trigrams = list(ngrams(tokens, 3))
  return unigrams, bigrams, trigrams
def main():
  nltk.download('punkt') # Ensure necessary resources are downloaded
  text = "This is a sample text for n-gram extraction. N-grams are useful in NLP."
  unigrams, bigrams, trigrams = extract_ngrams(text)
  print("Unigrams:", unigrams)
  print("Bigrams:", bigrams)
  print("Trigrams:", trigrams)
if __name__ == "__main__":
  main()



Lab 9 


import nltk
import string
from nltk.corpus import stopwords
from sklearn.feature_extraction.text import TfidfVectorizer

nltk.download('punkt')

# Sample documents
documents = [
    "This is the first document.",
    "This document is the second document.",
    "And this is the third one.",
    "Is this the first document?",
]

# Tokenize and preprocess the documents
def preprocess_text(doc):
    tokens = nltk.word_tokenize(doc)
    tokens = [word for word in tokens if word not in string.punctuation]
    tokens = [word.lower() for word in tokens]
    stop_words = set(stopwords.words('english'))
    tokens = [word for word in tokens if word not in stop_words]
    # Join the tokens back into a single string
    preprocessed_doc = ' '.join(tokens)
    # Ensure the return statement is properly indented
    return preprocessed_doc

# Preprocess all documents
preprocessed_documents = [preprocess_text(doc) for doc in documents]

# Compute TF-IDF scores using scikit-learn
vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform(preprocessed_documents)

# Print TF-IDF matrix
print(tfidf_matrix.toarray())


Lab 10 

import nltk
from nltk.tokenize import word_tokenize
from nltk import pos_tag, ne_chunk

# Download necessary NLTK resources
nltk.download('punkt')
nltk.download('averaged_perceptron_tagger')
nltk.download('maxent_ne_chunker')
nltk.download('words')
# Download the specific resource for the chunker's model data
nltk.download('maxent_ne_chunker_tab')

def ner(text):
  words = word_tokenize(text)
  tagged_words = pos_tag(words)
  named_entities = ne_chunk(tagged_words)
  return named_entities

text = "Apple is a company based in California, United States. Steve Jobs was one of its founders."
named_entities = ner(text)
print(named_entities)

Comments

Popular posts from this blog

DL

June 09, 2025
 LAB 1(IMAGE CLASSIFICATION) import tensorflow as tf from tensorflow.keras import datasets, layers, models import matplotlib.pyplot as plt import numpy as np # Load CIFAR-10 dataset (train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data() train_images, test_images = train_images / 255.0, test_images / 255.0  # Normalize # Class names in CIFAR-10 class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',                 'dog', 'frog', 'horse', 'ship', 'truck'] # Plot some sample images plt.figure(figsize=(10,10)) for i in range(25):     plt.subplot(5,5,i+1)     plt.xticks([])     plt.yticks([])     plt.grid(False)     plt.imshow(train_images[i])     plt.xlabel(class_names[int(train_labels[i])]) plt.show() # Define CNN model model = models.Sequential() model.add(layers.Conv2D(32, (3,3), activation='relu', input_shape=(32, 32, 3))) model.add...
READ MORE

Comments

Post a Comment

Popular posts from this blog

Web

                         STRING   <?php $mystr="php is a server side scripting language"; echo "<strong> the given string is :</strong> $mystr <br>"; echo "<strong> the length of string is :</strong>".strlen($mystr)."<br>"; echo "<strong> the count of string is :</strong>".str_word_count($mystr)."<br>"; echo "<strong> the reverse of string is :</strong>".strrev($mystr)."<br>"; $substr="side"; echo "<strong> the position of string is '$substr' in the string is :</strong>".strpos($mystr,$substr);                     Files <?php $fname="file1.txt"; $fptr=fopen($fname,"r"); $content=fread($fptr,filesize($fname)); $fptw=fopen("file2.txt","w"); fwrite($fptw,$content); echo"<strong>the content copied in file2 is:</strong> <br>".$c...
Read more

Lab 1 ai

 Dfs.pl s[a,b). s(a,c). s(b,d). s(b,e). s(c,f). s(c,g). s(d,h). s(e,i). s(e,j). s(f,k). goal(f). goal(j). solve(Start,Solution):- breadthfirst([[Start]],Solution). breadthfirst([[Node | Path] ].[Node|Path]]:- goal(Node). breadthfirst([Path | Paths] Solution):- extend(Path,NewPaths), write(NewPaths), nl, conc(Paths,NewPaths, Paths1), breadthfirst(Paths1,Solution). extend([NodePath],NewPaths):- bagof([NewNode, Node | Path),(s(Node, NewNode),not(member(NewNode, [Node | Path]))),NewPaths),!. extend([]). conc([],L,L). Scanned with OKEN Scanner bfs.pl s(a,b). s(a,c). s(b,d). s(b,e). s(c,f). s(c,g). / s(d,h). s(e,i). s(e,j). s(f,k). goal(f). goal(j). member(X,[X|_]). member(X,_|Tail]):- member(X,Tail). solve(Node,Solution):- depthfirst([],Node,Solution). depthfirst(Path, Node,[Node | Path]):- goal(Node). depthfirst(Path,Node,Sol):- s(Node,Node1), not(member(Node1,Path)), depthfirst([Node | Path], Node1,Sol). Scanned with OKEN Scanner conc([X/L1],L2,[X|L3]):- write('conc'), write(X), w...
Read more
 def aStarAlgo(start_node, stop_node): open_set = set(start_node) closed_set = set() g={} parents = {} g[start_node] = 0 parents[start_node] = start_node while len(open_set) > 0: n = None for v in open_set: if n == None or g[v] + heuristic(v) <g[n] + heuristic(n): n=v if n stop_node or Graph_nodes[n] == None: pass else: for (m, weight) in get_neighbors(n): open_set.add(m) if m not in open_set and m not in closed_set: parents[m] = n g[m] = g[n] + weight else: if g[m]g[n] + weight: g[m] = g[n] + weight parents[m] = n if m in closed_set: closed_set.remove(m) open_set.add(m) if n == None: print('Path does not exist!") return None if n == stop_node: path = [] while parents[n] != n: path.append(n) n = parents[n] path.append(start_node) path.reverse() print('Path found: {}'.format(path)) return path open_set.remove(n) closed_set.add(n) print('Path does not exist!") return None def get_neighbors(v): if v in Graph_nodes: return Graph_nodes[v] else: return None de...
Read more