diff --git a/run/extraModel/generate_bivar_data.py b/run/extraModel/generate_bivar_data.py index 87268a6..ee10cb3 100755 --- a/run/extraModel/generate_bivar_data.py +++ b/run/extraModel/generate_bivar_data.py @@ -4,12 +4,11 @@ from glob import glob from tqdm import tqdm, trange import logging -from multiprocessing import Pool from os.path import exists import shutil def process_sample(data_folder, sample_id, - default_pred, labeling=False, n_thread = 10): + default_pred, labeling=False): # recessive_folder = f'{data_folder}/recessive_matrix' # if not os.path.exists(recessive_folder): @@ -62,14 +61,11 @@ def process_sample(data_folder, sample_id, 'gene': gene, 'varIDs': list(gene_dict[gene])} for gene in gene_dict ] - print(f"Now starting to generate recessive feature matrix for {len(gene_dict)} genes, {feature_df.shape[0]} variants using {n_thread} threads.") - p = Pool(processes=n_thread) + print(f"Now starting to generate recessive feature matrix for {len(gene_dict)} genes, {feature_df.shape[0]} variants.") - with tqdm(total=len(params)) as pbar: - for result in p.imap_unordered(process_gene, params): - pbar.update() - p.close() - p.join() + for param in tqdm(params): + process_gene(param) + print("Recessive features for each gene finished, now putting together...") bivar_feature_mats = [] diff --git a/run/extraModel/main.py b/run/extraModel/main.py index 258aa73..c77c36d 100755 --- a/run/extraModel/main.py +++ b/run/extraModel/main.py @@ -16,15 +16,11 @@ parser.add_argument('-id', metavar='I', type=str, help = 'sample ID') -parser.add_argument('-n_cpu', type=int, default=10, - help = 'folders containing all extended final matrices') - args = parser.parse_args() #st_time = time() #prj_name = args.project sample_id = args.id -n_cpu = args.n_cpu out_folder = '/out/conf_4Model' @@ -60,7 +56,7 @@ def assign_ranking(df): return pred_df -def AIM(data_folder, sample_id, n_thread): +def AIM(data_folder, sample_id): feature_fn = f'/out/final_matrix/{sample_id}.csv' if not os.path.exists(feature_fn): @@ -88,7 +84,7 @@ def AIM(data_folder, sample_id, n_thread): generate_bivar_data.process_sample( data_folder = out_folder, sample_id = sample_id, default_pred = default_pred, - labeling=False, n_thread = n_thread) + labeling=False) recessive_feature_file = f"{out_folder}/recessive_matrix/{sample_id}.csv" if os.path.exists(recessive_feature_file): @@ -117,4 +113,4 @@ def AIM(data_folder, sample_id, n_thread): return #for sample_id in tqdm(sample_folders): -AIM(out_folder, sample_id, n_thread = n_cpu) +AIM(out_folder, sample_id)