Pythonで学ぶコサイン類似度とk-meansクラスタリング

import math

# Cosine similarity compares directions: 1 = same direction, 0 = unrelated.
def cosine(a, b):
    dot = sum(x * y for x, y in zip(a, b))
    return dot / (math.sqrt(sum(x * x for x in a)) * math.sqrt(sum(y * y for y in b)))

print("cos(doc1, doc2):", round(cosine([1, 2, 0], [2, 4, 0]), 3))
print("cos(doc1, doc3):", round(cosine([1, 2, 0], [0, 0, 3]), 3))

# k-means: assign points to the nearest centre, then move each centre to its points' mean.
points = [1, 2, 3, 10, 11, 12]
centres = [1.0, 2.0]
for step in range(1, 4):
    groups = [[], []]
    for p in points:
        nearest = min(range(len(centres)), key=lambda i: abs(p - centres[i]))
        groups[nearest].append(p)
    centres = [sum(g) / len(g) for g in groups]
    print(f"step {step}: centres={[round(c, 2) for c in centres]} groups={groups}")