lenskit.knn#

k-NN recommender models.

class lenskit.knn.ItemKNNScorer(nnbrs, min_nbrs=1, min_sim=1e-06, save_nbrs=None, feedback='explicit', block_size=250)#

Bases: Component, Trainable

Item-item nearest-neighbor collaborative filtering feedback. This item-item implementation is based on the description of item-based CF by Deshpande and Karypis [DK04] and hard-codes several design decisions found to work well in the previous Java-based LensKit code [ELKR11]. In explicit-feedback mode, its output is equivalent to that of the Java version.

Parameters:

nnbrs (int) – The maximum number of neighbors for scoring each item (None for unlimited)
min_nbrs (int) – The minimum number of neighbors for scoring each item
min_sim (float) – Minimum similarity threshold for considering a neighbor. Must be positive; if less than the smallest 32-bit normal (\(1.175 \times 10^{-38}\)), is clamped to that value.
save_nbrs (int | None) – The number of neighbors to save per item in the trained model (None for unlimited)
feedback (Literal['explicit', 'implicit']) – The type of input data to use (explicit or implicit). This affects data pre-processing and aggregation.
block_size (int)

items_: Vocabulary#: Vocabulary of item IDs.

item_means_: torch.Tensor | None#: Mean rating for each known item.

item_counts_: torch.Tensor#: Number of saved neighbors for each item.

sim_matrix_: torch.Tensor#: Similarity matrix (sparse CSR tensor).

users_: Vocabulary#: Vocabulary of user IDs.

rating_matrix_: torch.Tensor#: Normalized rating matrix to look up user ratings at prediction time.

property is_trained: bool#: Check if this model has already been trained.

train(data)#

Train a model.

The model-training process depends on save_nbrs and min_sim, but not on other algorithm parameters.

Parameters:

ratings – (user,item,rating) data for computing item similarities.
data (Dataset)

class lenskit.knn.UserKNNScorer(nnbrs, min_nbrs=1, min_sim=1e-06, feedback='explicit')#

Bases: Component, Trainable

User-user nearest-neighbor collaborative filtering with ratings. This user-user implementation is not terribly configurable; it hard-codes design decisions found to work well in the previous Java-based LensKit code.

Parameters:

nnbrs (int) – the maximum number of neighbors for scoring each item (None for unlimited).
min_nbrs (int) – The minimum number of neighbors for scoring each item.
min_sim (float) – Minimum similarity threshold for considering a neighbor. Must be positive; if less than the smallest 32-bit normal (\(1.175 \times 10^{-38}\)), is clamped to that value.
feedback (Literal['explicit', 'implicit']) –
Control how feedback should be interpreted. Specifies defaults for the other settings, which can be overridden individually; can be one of the following values:

explicit
Configure for explicit-feedback mode: use rating values, and predict using weighted averages. This is the default setting.

implicit
Configure for implicit-feedback mode: ignore rating values, and predict using the sums of similarities.

users_: Vocabulary#: The index of user IDs.

items_: Vocabulary#: The index of item IDs.

user_means_: torch.Tensor | None#: Mean rating for each known user.

user_vectors_: torch.Tensor#: Normalized rating matrix (CSR) to find neighbors at prediction time.

user_ratings_: csr_array#: Centered but un-normalized rating matrix (COO) to find neighbor ratings.

property is_trained: bool#: Check if this model has already been trained.

train(data)#

“Train” a user-user CF model. This memorizes the rating data in a format that is usable for future computations.

Parameters:

ratings (pandas.DataFrame) – (user, item, rating) data for collaborative filtering.
data (Dataset)

Return type:

Self

Modules

`item`	Item-based k-NN collaborative filtering.
`user`	User-based k-NN collaborative filtering.