电影推荐中NDCG指标代码

以下是使用Python计算电影推荐中NDCG指标的代码示例：

import numpy as np

def dcg_at_k(r, k):
    """Calculate DCG@K (Discounted Cumulative Gain)"""
    r = np.asfarray(r)[:k]
    if r.size:
        return np.sum(r / np.log2(np.arange(2, r.size + 2)))
    return 0.

def ndcg_at_k(r, k):
    """Calculate NDCG@K (Normalized Discounted Cumulative Gain)"""
    dcg_max = dcg_at_k(sorted(r, reverse=True), k)
    if not dcg_max:
        return 0.
    return dcg_at_k(r, k) / dcg_max

# Example usage:
# r = relevance scores of recommended movies, with higher scores indicating higher relevance
# k = number of recommended movies to consider for NDCG calculation

r = [3, 2, 3, 0, 1, 2]
k = 6

ndcg = ndcg_at_k(r, k)
print(f"NDCG@{k}: {ndcg}")

在代码中，`r` 是推荐电影的相关性得分列表，得分越高表示电影越相关。`k` 是用于计算 NDCG 的推荐电影数。该代码使用 `dcg_at_k` 函数计算 DCG@K，然后计算 NDCG@K 并返回结果。