Skip to content

fix train_only_size #652

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix train_only_size #652

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5f1042b
fix train_only_size
bos1988 Apr 16, 2023
7d35852
fix zero-candidate case
bos1988 Apr 21, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 6 additions & 5 deletions implicit/evaluation.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -187,16 +187,17 @@ cpdef leave_k_out_split(

# get only users with n + 1 interactions
candidate_mask = counts > K + 1
if sum(candidate_mask) == 0:
return ratings.tocsr(), csr_matrix(ratings.shape)
unique_candidate_users = unique_users[candidate_mask]

# keep a given subset of users _only_ in the training set.
if train_only_size > 0.0:
train_only_mask = ~np.isin(
unique_users, _choose(random_state, len(unique_users), train_only_size)
)
candidate_mask = train_only_mask & candidate_mask
adjusted_ratio = min(1, (1 - train_only_size) / (unique_candidate_users.shape[0] / (unique_users.shape[0] + 1)))
train_only_mask = _choose(random_state, len(unique_candidate_users), adjusted_ratio)
unique_candidate_users = unique_candidate_users[train_only_mask]

# get unique users who appear in the test set
unique_candidate_users = unique_users[candidate_mask]
full_candidate_mask = np.isin(users, unique_candidate_users)

# get all users, items and ratings that match specified requirements to be
Expand Down