lab 3

 from gensim.models import Word2Vec

from nltk.tokenize import word_tokenize
import nltk
nltk.download('punkt_tab')
corpus = [
 "A patient with diabetes requires insulin injections.",
 "Medical professionals recommend exercise for heart health.",
 "Doctors use MRI scans to diagnose brain disorders.",
 "Antibiotics help fight bacterial infections.",
 "A doctor specializes in diagnosing and treating diseases."
]
tokens = [word_tokenize(s.lower()) for s in corpus]
model = Word2Vec(tokens, vector_size=50, window=3, min_count=1, sg=1)
print("Similar to 'doctor':", model.wv.most_similar("doctor", topn=5))

Comments

Post a Comment

Popular posts from this blog

lab 6

  from transformers import pipeline sentiment = pipeline( "sentiment-analysis" ) sentences = [   "I love this product! It works perfectly." ,   "This is the worst experience I've ever had." ,   "The weather is nice today." ] results = sentiment(sentences) for s, r in zip (sentences, results):     print ( f " {s} -> {r[ 'label' ]} ( {r[ 'score' ] :.2f } )" )
Read more

lab 5

  import gensim.downloader as api model = api.load( "glove-wiki-gigaword-50" ) def make_paragraph ( seed ):     sims = model.most_similar(seed, topn= 5 )     s = [w for w, _ in sims]     para = ( f "In the spirit of {seed} , one may explore {s[ 0 ]} , {s[ 1 ]} and {s[ 2 ]} . "             f "Through {s[ 3 ]} and {s[ 4 ]} , every journey becomes memorable." )     return s, para seed_word = "adventure" similar_words, paragraph = make_paragraph(seed_word) print ( "Similar words:" , similar_words) print ( "\nParagraph:\n" , paragraph)
Read more

lab 1

  ! pip install gensim nltk transformers torch matplotlib scikit-learn import gensim.downloader as api model = api.load( "glove-wiki-gigaword-50" ) w1, w2, w3 = "king" , "man" , "woman" vec = model[w1] - model[w2] + model[w3] word = model.most_similar([vec], topn= 1 )[ 0 ][ 0 ] print ( f " {w1} - {w2} + {w3} ≈ {word} " )
Read more