elliot.recommender.latent_factor_models.FM package

Submodules

elliot.recommender.latent_factor_models.FM.factorization_machine module

Module description:

class elliot.recommender.latent_factor_models.FM.factorization_machine.FM(data, config, params, *args, **kwargs)[source]

Bases: elliot.recommender.recommender_utils_mixin.RecMixin, elliot.recommender.base_recommender_model.BaseRecommenderModel

Factorization Machines

For further details, please refer to the paper

Parameters

  • factors – Number of factors of feature embeddings

  • lr – Learning rate

  • reg – Regularization coefficient

To include the recommendation model, add it to the config file adopting the following pattern:

models:
  FM:
    meta:
      save_recs: True
    epochs: 10
    batch_size: 512
    factors: 10
    lr: 0.001
    reg: 0.1
get_item_fragment()[source]
get_recommendations(k: int = 100)[source]
get_user_full_array(user)[source]
property name
predict(u: int, i: int)[source]
prepare_fm_transaction(batch)[source]
train()[source]

elliot.recommender.latent_factor_models.FM.factorization_machine_model module

Module description:

class elliot.recommender.latent_factor_models.FM.factorization_machine_model.Embedding(*args, **kwargs)[source]

Bases: tensorflow.python.keras.engine.base_layer.Layer

call(x0: tensorflow.python.framework.ops.Tensor, training=None) → tensorflow.python.framework.ops.Tensor[source]
get_config()[source]
class elliot.recommender.latent_factor_models.FM.factorization_machine_model.FactorizationMachineLayer(*args, **kwargs)[source]

Bases: tensorflow.python.keras.engine.base_layer.Layer

call(inputs: tensorflow.python.framework.ops.Tensor, training=False) → tensorflow.python.framework.ops.Tensor[source]
get_config()[source]
class elliot.recommender.latent_factor_models.FM.factorization_machine_model.FactorizationMachineModel(*args, **kwargs)[source]

Bases: tensorflow.python.keras.engine.training.Model

call(inputs, training=None, mask=None)[source]
get_recs(inputs, training=False, **kwargs)[source]

Get full predictions on the whole users/items matrix.

Returns

The matrix of predicted values.

get_top_k(preds, train_mask, k=100)[source]
predict(inputs, training=False, **kwargs)[source]

Get full predictions on the whole users/items matrix.

Returns

The matrix of predicted values.

train_step(batch)[source]
class elliot.recommender.latent_factor_models.FM.factorization_machine_model.Linear(*args, **kwargs)[source]

Bases: tensorflow.python.keras.engine.base_layer.Layer

call(x0: tensorflow.python.framework.ops.Tensor, training=None) → tensorflow.python.framework.ops.Tensor[source]
get_config()[source]
class elliot.recommender.latent_factor_models.FM.factorization_machine_model.MatrixFactorizationLayer(*args, **kwargs)[source]

Bases: tensorflow.python.keras.engine.base_layer.Layer

call(inputs: tensorflow.python.framework.ops.Tensor, training=False) → tensorflow.python.framework.ops.Tensor[source]
get_config()[source]

Module contents