def _download_data_set(self):
make_sure_dir_exists(os.path.dirname(self.DATA_SET_FILE_PATH))
download_file_if_not_exists(self.DATA_SET_URL, self.DATA_SET_FILE_PATH,
self.DATA_SET_MD5_SUM)
download_file_if_not_exists(self.ANNOTATION_URL,
self.ANNOTATION_FILE_PATH,
self.ANNOTATION_MD5_SUM)
def _download_data_set(self):
make_sure_dir_exists(self.DATA_SET_DIR_NAME)
download_file_if_not_exists(self.PBMC_RNA_DATA_URL,
self.PBMC_RNA_DATA_FILE_PATH,
self.PBMC_RNA_DATA_MD5_SUM)
download_file_if_not_exists(self.PBMC_ADT_DATA_URL,
self.PBMC_ADT_DATA_FILE_PATH,
self.PBMC_ADT_DATA_MD5_SUM)
download_file_if_not_exists(self.PBMC_TRANSFORMED_ADT_DATA_URL,
self.PBMC_TRANSFORMED_ADT_DATA_FILE_PATH,
self.PBMC_TRANSFORMED_ADT_DATA_MD5_SUM)
download_file_if_not_exists(self.CBMC_RNA_DATA_URL,
self.CBMC_RNA_DATA_FILE_PATH,
self.CBMC_RNA_DATA_MD5_SUM)
download_file_if_not_exists(self.CBMC_ADT_DATA_URL,
self.CBMC_ADT_DATA_FILE_PATH,
self.CBMC_ADT_DATA_MD5_SUM)
download_file_if_not_exists(self.CBMC_TRANSFORMED_ADT_DATA_URL,
self.CBMC_TRANSFORMED_ADT_DATA_FILE_PATH,
self.CBMC_TRANSFORMED_ADT_DATA_MD5_SUM)
download_file_if_not_exists(self.CD8_RNA_DATA_URL,
self.CD8_RNA_DATA_FILE_PATH,
self.CD8_RNA_DATA_MD5_SUM)
download_file_if_not_exists(self.CD8_ADT_DATA_URL,
self.CD8_ADT_DATA_FILE_PATH,
self.CD8_ADT_DATA_MD5_SUM)
download_file_if_not_exists(self.CD8_TRANSFORMED_ADT_DATA_URL,
self.CD8_TRANSFORMED_ADT_DATA_FILE_PATH,
self.CD8_TRANSFORMED_ADT_DATA_MD5_SUM)
def save_model_and_outputs():
args.output_dir = os.path.abspath(args.output_dir)
make_sure_dir_exists(args.output_dir)
log("Saving output results to {}".format(args.output_dir))
if not args.ignore_model:
dump_gzip_pickle(model.get_full_state_dict(),
os.path.join(args.output_dir, "model.pkl.gz"))
if not args.ignore_output:
data_loader = DataLoader(dataset=data_set,
batch_size=args.batch_size,
num_workers=4,
collate_fn=collate_function,
shuffle=False,
drop_last=False)
all_outputs = get_output(model, data_loader)
if args.mean_only:
features = ["mean"]
for feature in ["mean", "r", "pi", "normal_mean_nodes"]:
if feature in all_outputs:
print("Saving %s ..." % feature)
output = all_outputs[feature]
output = pd.DataFrame(output.transpose(),
index=data_set.genes,
columns=data_set.cells)
output = output.round(3)
write_csv(
output,
os.path.join(args.output_dir,
"{}.csv.gz".format(feature)))
if args.debug:
import IPython
IPython.embed()
