def topk(topk_data: TopkData,
score_fn: Callable[[Dict[str, List[int]]], List[float]],
ks=[10, 36, 100]):
precisions, recalls = topk_evaluate(topk_data, score_fn, ks)
for k, precision, recall in zip(ks, precisions, recalls):
f1 = 2. * precision * recall / pr if (pr := precision + recall) else 0
print('[k=%d, precision=%.3f%%, recall=%.3f%%, f1=%.3f%%]' %
(k, 100. * precision, 100. * recall, 100. * f1),
end='')
def topk():
ks = [10, 36, 100]
precisions, recalls = topk_evaluate(
topk_data, lambda ui: fast_model(tf.constant(ui)).numpy(),
ks)
for k, precision, recall in zip(ks, precisions, recalls):
tf.print(
'[k=%d, precision=%.3f%%, recall=%.3f%%, f1=%.3f%%]' %
(k, 100 * precision, 100 * recall,
200 * precision * recall / (precision + recall)),
end='')
tf.print()
if W[i][j] != 0:
Wi[j] = W[i][j]
most_similar_items.append(set(x[0] for x in sorted(Wi.items(), key=lambda x: x[1], reverse=True)[:N]))
scores = [[0 for _ in range(n_item)] for _ in range(n_user)] # scores[u][i]是用户u对物品i的评分
for user_id in range(n_user):
user_item_set = train_user_items[user_id]
for i in user_item_set:
for j in most_similar_items[i]:
if j not in user_item_set:
scores[user_id][j] += W[i][j]
#for i in set(range(n_item)) - user_item_set:
# for j in user_item_set & most_similar_items[i]:
# scores[user_id][i] += W[i][j]
print('（耗时', time.time() - start_time, '秒）', sep='')
return scores
if __name__ == '__main__':
n_user, n_item, train_data, test_data, topk_data = data_process.pack(data_loader.ml1m, negative_sample_ratio=0)
W = _item_similarity(train_data, n_user, n_item)
scores = _user_item_score(train_data, n_user, n_item, W, N=10)
ks = [10, 36, 100]
precisions, recalls = topk_evaluate(topk_data, lambda uis: [scores[u][i] for u, i in uis], ks)
for k, precision, recall in zip(ks, precisions, recalls):
print('[k=%d, precision=%.3f%%, recall=%.3f%%, f1=%.3f%%]' %
(k, 100 * precision, 100 * recall, 200 * precision * recall / (precision + recall)))