recommenders-team/recommenders

[ASK] negative_feedback_sampler super slow

Open

#1,539 opened on 2021年9月26日

GitHub で見る
 (5 comments) (0 reactions) (0 assignees)Python (2,972 forks)batch import
help wanted

Repository metrics

Stars
 (17,706 stars)
PR merge metrics
 (平均マージ 6d 16h) (30d で 10 merged PRs)

説明

Hi, I got some questions about the usage of negative_feedback_sampler, my codes are as below:

from recommenders.datasets.pandas_df_utils import negative_feedback_sampler

df_feature = negative_feedback_sampler(df_feature_ori,col_user='userid',col_item='sku',col_label='label',ratio_neg_per_user=1)

df_feature_ori has about 623k rows, and 24 columns, but it really takes so long to process the negative_feedback_sampler, I wonder if I do it wrong or it's just normal situation. Any advice would be appreciated.

コントリビューターガイド