elliot.recommender package

Subpackages

Submodules

elliot.recommender.base_recommender_model module

Module description:

class elliot.recommender.base_recommender_model.BaseRecommenderModel(data, config, params, *args, **kwargs)[source]

Bases: abc.ABC

autoset_params()[source]

Define Parameters as tuples: (variable_name, public_name, shortcut, default, reading_function, printing_function) Example:

self._params_list = [

(“_similarity”, “similarity”, “sim”, “cosine”, None, None), (“_user_profile_type”, “user_profile”, “up”, “tfidf”, None, None), (“_item_profile_type”, “item_profile”, “ip”, “tfidf”, None, None), (“_mlpunits”, “mlp_units”, “mlpunits”, “(1,2,3)”, lambda x: list(make_tuple(x)), lambda x: str(x).replace(“,”, “-“)),

]

get_base_params_shortcut()[source]
abstract get_loss()[source]
abstract get_params()[source]
get_params_shortcut()[source]
abstract get_recommendations(*args)[source]
abstract get_results()[source]
abstract train()[source]
elliot.recommender.base_recommender_model.init_charger(init)[source]

elliot.recommender.recommender_utils_mixin module

class elliot.recommender.recommender_utils_mixin.RecMixin[source]

Bases: object

evaluate(it=None, loss=0)[source]
get_best_arg()[source]
get_candidate_mask(validation=False)[source]
get_loss()[source]
get_params()[source]
get_recommendations(k: int = 100)[source]
get_results()[source]
get_single_recommendation(mask, k, predictions, offset, offset_stop)[source]
iterate(epochs)[source]
process_protocol(k, *args)[source]
restore_weights()[source]
train()[source]

Module contents

Module description: