-
felix kleinert authored
default data handler and preprocessing support parameter use_multiprocessing. Parameter is set to False on DEBUG always. /close #297 on pipeline success
felix kleinert authoreddefault data handler and preprocessing support parameter use_multiprocessing. Parameter is set to False on DEBUG always. /close #297 on pipeline success
defaults.rst 1.74 KiB
Defaults
In this section, we explain which parameters are set by MLAir during the :py:`ExperimentSetup` if not specified by the user. This is important information for example if a new :ref:`Custom Data Handler` is implemented.
parameter | default | comment |
---|---|---|
batch_path | ||
batch_size | ||
bootstrap_path | ||
competitor_path | ||
competitors | ||
create_new_bootstraps | ||
create_new_model | ||
data_handler | ||
data_origin | ||
data_path | ||
debug |
|
MLAir checks if it is running in debug mode and stores this |
dimensions | ||
end | ||
epochs | ||
evaluate_bootstraps | ||
experiment_name | ||
experiment_path | ||
extreme_values | ||
extremes_on_right_tail_only | ||
forecast_path | ||
fraction_of_training | ||
hostname | ||
hpc_hosts | ||
interpolation_limit | ||
interpolation_method | ||
logging_path | ||
login_nodes | ||
model_class | ||
model_path | ||
neighbors | ||
number_of_bootstraps | ||
overwrite_local_data | ||
permute_data | ||
plot_list | ||
plot_path | ||
start | ||
stations | ||
statistics_per_var | ||
target_dim | ||
target_var | ||
test_start | ||
test_end | ||
test_min_length | ||
time_dim | ||
train_model | ||
train_end | ||
train_min_length | ||
train_start | ||
transformation | :py:`{}` | implement all further transformation functionality inside your custom data handler |
use_all_stations_on_all_data_sets | ||
use_multiprocessing | :py:`True` | is set to False if MLAir is running in debug mode |
upsampling | ||
val_end | ||
val_min_length | ||
val_start | ||
variables | ||
window_history_size | ||
window_lead_time |