PureSVDModel

class rectools.models.pure_svd.PureSVDModel(factors: int = 10, tol: float = 0, maxiter: Optional[int] = None, random_state: Optional[int] = None, verbose: int = 0)

Bases: VectorModel[PureSVDModelConfig]

PureSVD matrix factorization model.

See https://dl.acm.org/doi/10.1145/1864708.1864721

Parameters

• factors (int, default 10) – The number of latent factors to compute.

• tol (float, default 0) – Tolerance for singular values. Zero means machine precision.

• maxiter (int, optional, default None) – Maximum number of iterations.

• random_state (int, optional, default None) – Pseudorandom number generator state used to generate resamples.

• verbose (int, default 0) – Degree of verbose output. If 0, no output will be provided.

Inherited-members

Methods

dumps()	Serialize model to bytes.
fit(dataset, *args, **kwargs)	Fit model.
fit_partial(dataset, *args, **kwargs)	Fit model.
from_config(config)	Create model from config.
get_config([mode, simple_types])	Return model config.
get_params([simple_types, sep])	Return model parameters.
get_vectors()	Return user and item vector representations from fitted model.
load(f)	Load model from file.
loads(data)	Load model from bytes.
recommend(users, dataset, k, filter_viewed)	Recommend items for users.
recommend_to_items(target_items, dataset, k)	Recommend items for target items.
save(f)	Save model to file.

Attributes

i2i_dist
n_threads
recommends_for_cold
recommends_for_warm
u2i_dist

config_class

alias of PureSVDModelConfig

get_vectors() → Tuple[ndarray, ndarray]

Return user and item vector representations from fitted model.

Returns

User and item embeddings. Shapes are (n_users, n_factors) and (n_items, n_factors).

Return type

(np.ndarray, np.ndarray)