def normalize_gene_counts(data, method, threshold=None, target_identifier="", experiment_identifier=""):
# if exists -> get from db
processing_result = cn.bioconductor_normalization(data, method)
new_intern_identifier = identifier_generator.get_generated_guid_as_string()
hdf_storage.store_hdf(processing_result.frame, new_intern_identifier)
print("compressed pytable storage done")
package = mr.get_package_by_name_and_version(processing_result.package,
processing_result.version).public_identifier
dataset = dr.create_data_set(new_intern_identifier, package + "_" + target_identifier, "genes normalized dataset",
package_identifier=package,
experiment_identifier=experiment_identifier)
print("new dataset saved")
#er.link_dataset_to_experiment(experiment_identifier, dataset.public_identifier)
print("new dataset linked")
return dataset
def store_data_frame_to_hdf(df, identifier):
return hdf_storage.store_hdf(df, identifier)
