config.yml

# The base configuration of the benchmark

# Enable logging
log: True
# The name of each dataset in the directory on which the benchmark should be run
name: ["plausible"]
# A label for the resul directory
label: "_"
# The type of dataset, currently supported ".hdf5", and ".csv"
file_type: ".hdf5"
# The views to use in the banchmark, an empty value will result in using all the views
views:
# The path to the directory where the datasets are stored
pathf: "../data/"
# The niceness of the processes, useful to lower their priority
nice: 0
# The random state of the benchmark, useful for reproducibility
random_state: 42
# The number of parallel computing threads
nb_cores: 1
# Used to run the benchmark on the full dataset
full: False
# Used to be able to run more than one benchmark per minute
debug: False
# To add noise to the data, will add gaussian noise with noise_std
add_noise: False
noise_std: 0.0
# The directory in which the results will be stored
res_dir: "../results/"
# If an error occurs in a classifier, if track_tracebacks is set to True, the
# benchmark saves the traceback and continues, if it is set to False, it will
# stop the benchmark and raise the error
track_tracebacks: True

# If the dataset is multiclass, will use this multiclass-to-biclass method
multiclass_method: "oneVersusOne"
# The ratio number of test exmaples/number of train examples
split: 0.8
# The nubmer of folds in the cross validation process when hyper-paramter optimization is performed
nb_folds: 2
# The number of classes to select in the dataset
nb_class: 2
# The name of the classes to select in the dataset
classes:
# The type of algorithms to run during the benchmark (monoview and/or multiview)
type: ["monoview","multiview"]
# The name of the monoview algorithms to run, ["all"] to run all the available classifiers
algos_monoview: ["all"]
# The names of the multiview algorithms to run, ["all"] to run all the available classifiers
algos_multiview: ["all"]
# The number of times the benchamrk is repeated with different train/test
# split, to have more statistically significant results
stats_iter: 1
# The metrics that will be use din the result analysis
metrics: ["accuracy_score", "f1_score"]
# The metric that will be used in the hyper-parameter optimization process
metric_princ: "f1_score"
# The type of hyper-parameter optimization method
hps_type: "Random"
# The arguments of the hyper-parameter optimization method
hps_args:
  # The number of iteration of the optimization process
  n_iter: 4
  # If True, for multiview algoriithm, will use n_iter*n_views iterations to optimize.
  equivalent_draws: True


# The following arguments are classifier-specific, and are documented in each
# of the corresponding modules.