lab 2

 !pip install gensim nltk transformers torch matplotlib scikit-learn

import gensim.downloader as api
import numpy as np
from sklearn.decomposition import PCA
import matplotlib.pyplot as plt

model = api.load("glove-wiki-gigaword-50")

words = ["computer","internet","software","hardware","data",
         "robot","ai","network","cloud","algorithm"]

vecs = np.array([model[w] for w in words])
xy = PCA(2).fit_transform(vecs)    
plt.scatter(xy[:,0], xy[:,1])
for (x, y), w in zip(xy, words):
    plt.text(x+0.01, y+0.01, w)
plt.title("PCA – Technology words")
plt.xlabel("PC1"); plt.ylabel("PC2")
plt.show()
word = "computer"
print("Similar to", word, ":", model.most_similar(word, 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