f4beaac559e00a3676d942dc7e8fea69efc01cfe,catalyst/metrics/mrr.py,,mrr,#,8
Before Change
The mrr score for each user.
k = min(outputs.size(1), k)
_, indices_for_sort = outputs.sort(descending=True, dim=-1)
true_sorted_by_preds = torch.gather(
targets, dim=-1, index=indices_for_sort
)
true_sorted_by_pred_shrink = true_sorted_by_preds[:, :k]
After Change
mrr_score (torch.Tensor):
The mrr score for each batch.
results = []
for k in topk:
results.append(torch.mean(reciprocal_rank(outputs, targets, k)))
return results
__all__ = ["reciprocal_rank", "mrr"]

In pattern: SUPERPATTERN
Frequency: 3
Non-data size: 7
Instances
Project Name: Scitator/catalyst
Commit Name: f4beaac559e00a3676d942dc7e8fea69efc01cfe
Time: 2020-11-30
Author: raveforlive@gmail.com
File Name: catalyst/metrics/mrr.py
Class Name:
Method Name: mrr
Project Name: nilmtk/nilmtk
Commit Name: f74a4a251d395b3e175f99845b01ece0e50a79c3
Time: 2014-08-24
Author: nipunreddevil@gmail.com
File Name: nilmtk/metergroup.py
Class Name: MeterGroup
Method Name: select_top_k
Project Name: Scitator/catalyst
Commit Name: f4beaac559e00a3676d942dc7e8fea69efc01cfe
Time: 2020-11-30
Author: raveforlive@gmail.com
File Name: catalyst/metrics/hitrate.py
Class Name:
Method Name: hitrate