import numpy as np
import urllib.request
import zipfile
import os

# Download a small GloVe embedding set (50 dimensions, ~70MB zipped)
glove_url = "http://nlp.stanford.edu/data/glove.6B.zip"
glove_zip_path = "glove.6B.zip"

if not os.path.exists(glove_zip_path):
    urllib.request.urlretrieve(glove_url, glove_zip_path)

# Extract the smallest file (glove.6B.50d.txt)
with zipfile.ZipFile(glove_zip_path, 'r') as z:
    if not os.path.exists("glove.6B.50d.txt"):
        z.extract("glove.6B.50d.txt")

# Load GloVe vectors into a dictionary
embeddings = {}
with open("glove.6B.50d.txt", encoding="utf-8") as f:
    for line in f:
        parts = line.strip().split()
        word = parts[0]
        vec = np.array(parts[1:], dtype=np.float32)
        embeddings[word] = vec

# Compute cosine similarity between two words
def cosine_similarity(x, y):
    return np.dot(x, y) / (np.linalg.norm(x) * np.linalg.norm(y))

word1, word2 = "king", "queen"
vec1 = embeddings[word1]
vec2 = embeddings[word2]
sim = cosine_similarity(vec1, vec2)
print(f"Cosine similarity between '{word1}' and '{word2}': {sim:.3f}")