return io_args, model_options
if __name__ == '__main__':
# process command line arguments
io_args, model_options = process_args()
sample_info_df = du.load_sample_info(model_options.training_data,
verbose=io_args.verbose)
# create results dir and subdir for experiment if they don't exist
experiment_dir = Path(io_args.results_dir, 'purity').resolve()
experiment_dir.mkdir(parents=True, exist_ok=True)
# save model options for this experiment
# (hyperparameters, preprocessing info, etc)
fu.save_model_options(experiment_dir, model_options,
classify=model_options.classify)
# create empty log file if it doesn't exist
log_columns = [
'training_data',
'shuffle_labels',
'skip_reason'
]
log_df = None
tcga_data = TCGADataModel(seed=model_options.seed,
subset_mad_genes=model_options.subset_mad_genes,
training_data=model_options.training_data,
load_compressed_data=model_options.use_compressed,
n_dim=model_options.n_dim,
sample_info_df=sample_info_df,
if __name__ == '__main__':
# process command line arguments
io_args, model_options = process_args()
sample_info_df = du.load_sample_info(model_options.training_data,
verbose=io_args.verbose)
# create results dir and subdir for experiment if they don't exist
experiment_dir = Path(io_args.results_dir, 'gene').resolve()
experiment_dir.mkdir(parents=True, exist_ok=True)
# save model options for this experiment
# (hyperparameters, preprocessing info, etc)
fu.save_model_options(experiment_dir, model_options)
# create empty log file if it doesn't exist
log_columns = ['gene', 'titration_ratio', 'shuffle_labels', 'skip_reason']
tcga_data = TCGADataModel(
seed=model_options.seed,
subset_mad_genes=model_options.subset_mad_genes,
training_data=model_options.training_data,
overlap_data_types=model_options.overlap_data_types,
sample_info_df=sample_info_df,
verbose=io_args.verbose,
debug=model_options.debug)
genes_df = tcga_data.load_gene_set(io_args.gene_set)
# we want to run mutation prediction experiments:
return io_args, model_options, sample_info_df
if __name__ == '__main__':
# process command line arguments
io_args, model_options, sample_info_df = process_args()
# create results dir and subdir for experiment if they don't exist
experiment_dir = Path(io_args.results_dir).resolve()
experiment_dir.mkdir(parents=True, exist_ok=True)
# save model options for this experiment
# (hyperparameters, preprocessing info, etc)
fu.save_model_options(experiment_dir, model_options, 'survival')
# create empty log file if it doesn't exist
log_columns = [
'cancer_type', 'training_data', 'shuffle_labels', 'skip_reason'
]
tcga_data = TCGADataModel(
seed=model_options.seed,
subset_mad_genes=model_options.subset_mad_genes,
training_data=model_options.training_data,
overlap_data_types=model_options.overlap_data_types,
load_compressed_data=(model_options.n_dim is not None),
standardize_input=(model_options.n_dim is not None
and model_options.training_data
in cfg.standardize_data_types),