pimkl.cli package

Submodules

pimkl.cli.analyse module

pimkl.cli.analyse.analyse(data_names, network_name, gene_sets_name, preprocess_dir, output_dir, class_label_file, model_name='EasyMKL', lam=0.2, k=5, number_of_folds=2, max_per_class=20, seed=0, max_processes=2)

pimkl.cli.analyse.kpca(data_names, network_name, gene_sets_name, preprocess_dir, output_dir, class_label_file, weights_csv_file, fold)

pimkl.cli.analyse.read_preprocessed(data_names, network_name, gene_sets_name, preprocess_dir)

pimkl.cli.cli module

Console script for pimkl.

pimkl.cli.preprocess module

Main module.

pimkl.cli.preprocess.assert_valid_names(*names)

pimkl.cli.preprocess.invalid_name(name)

pimkl.cli.preprocess.preprocess_data_and_inducers(data_csv_files, data_names, network_csv_file, network_name, gene_sets_gmt_file, gene_sets_name, preprocess_dir, match_samples)

Inducers, that is Laplacian matrices for geneset subnetworks, and data are preprocessed and written to file. Data and inducers are filtered for genes (per dataset) available in the data and the network and the union of genesets. Conditionally, also the data is filtered for matching samples over all datasets.

pimkl.cli.preprocess.read_data(filename, reader, gene_name_transformation=None)

pimkl.cli.preprocess.reader(filename)

Module contents