from gensim.models import Word2Vec
import numpy as np

# Training Word2Vec on a corpus
sentences = [
    ["king", "rules", "kingdom"],
    ["queen", "rules", "kingdom"],
    ["man", "woman", "child"],
    ["doctor", "patient", "hospital"],
]

model = Word2Vec(sentences, vector_size=100, window=5, min_count=1)

# Similarity
similarity = model.wv.similarity("king", "queen")
print(f"king-queen similarity: {similarity:.3f}")  # high

# Analogy: king - man + woman = ?
result = model.wv.most_similar(
    positive=["king", "woman"],
    negative=["man"],
    topn=1
)
print(f"king - man + woman = {result[0][0]}")  # queen (hopefully)

NLP — Natural Language Processing בסיסי

NLP — Natural Language Processing בסיסי

NLP — Natural Language Processing בסיסי