alpenglow.utils package

Submodules

alpenglow.utils.AvailabilityFilter module

class alpenglow.utils.AvailabilityFilter.AvailabilityFilter(availability_data)

Bases: alpenglow.cpp.AvailabilityFilter

Python wrapper around alpenglow.cpp.AvailabilityFilter.

alpenglow.utils.DataShuffler module

class alpenglow.utils.DataShuffler.DataShuffler(seed=254938879, shuffle_mode=complete, input_file, output_file)

Bases: alpenglow.ParameterDefaults.ParameterDefaults

This class is for shuffling datasets.

Parameters

• seed (int) – The seed to initialize RNG-s. Should not be 0.

• shuffle_mode (string) – Possible values: complete, same_timestamp.

• input_file (string) – Input file name.

• output_file (string) – Output file name.

• data_format (string) – Input file format. Available values: online, online_id, online_id_noeval, online_attribute, offline, offlineTimestamp, category. See RecommenderData.cpp for details. Default: online_id.

run()

alpenglow.utils.DataframeData module

class alpenglow.utils.DataframeData.DataframeData(df, columns={})

Bases: alpenglow.cpp.DataframeData

Python wrapper around alpenglow.cpp.DataframeData.

alpenglow.utils.FactorModelReader module

alpenglow.utils.FactorModelReader.readEigenFactorModel(file)

alpenglow.utils.FactorModelReader.readFactorModel(file, dimensions)

alpenglow.utils.ParameterSearch module

class alpenglow.utils.ParameterSearch.DependentParameter(format_string, parameter_names=None)

Bases: object

eval(parameters)

class alpenglow.utils.ParameterSearch.ParameterSearch(model, Score)

Bases: object

Utility for evaluating online experiments with different hyperparameters. For a brief tutorial on using this class, see Five minute tutorial.

run(*run_paremeters, **run_kw_parameters)

set_parameter_values(parameter_name, parameter_values)

alpenglow.utils.ThreadedParameterSearch module

class alpenglow.utils.ThreadedParameterSearch.ThreadedParameterSearch(model, Score, threads=4, use_process_pool=True)

Bases: alpenglow.utils.ParameterSearch.ParameterSearch

Threaded version of alpenglow.utils.ParameterSearch.

run(*run_parameters, **run_kw_parameters)

Module contents