def build_args_parser():
parser = argparse_ArgumentParser(
prog='rpcompletion',
description=
'Python wrapper to parse RP2 to generate rpSBML collection of unique and complete (cofactors) pathways'
)
parser = _add_arguments(parser)
return parser
def main():
parser = argparse_ArgumentParser("Input parameters")
parser.add_argument("--input_file_name",
default="input_toy.yaml",
help="Input parameters file name")
parser.add_argument("--graph_files_dir",
default="",
help="Graph files' folder path")
parser.add_argument("--out_dir_name",
default="/results",
help="Output directory name")
args = parser.parse_args()
with open(args.input_file_name, 'r') as f:
inputs = yaml_load(f, yaml_Loader)
# Override output directory name if same as gen
if args.out_dir_name or inputs['out_comp_nm'] == "/results/res":
if not os_path.exists(inputs['dir_nm'] + args.out_dir_name):
os_mkdir(inputs['dir_nm'] + args.out_dir_name)
inputs['out_comp_nm'] = args.out_dir_name + "/res"
inputs['graph_files_dir'] = ''
if args.graph_files_dir:
if not os_path.exists(inputs['dir_nm'] + args.graph_files_dir):
os_mkdir(inputs['dir_nm'] + args.graph_files_dir)
inputs['graph_files_dir'] = args.graph_files_dir
with open(inputs['dir_nm'] + inputs['out_comp_nm'] + "_input.yaml",
'w') as outfile:
yaml_dump(inputs, outfile, default_flow_style=False)
logging_basicConfig(filename=inputs['dir_nm'] + inputs['out_comp_nm'] +
"_logs.yaml",
level=logging_INFO)
start_time_read = time_time()
myGraph = read_graphs(inputs)
read_time = time_time() - start_time_read
myGraphName = inputs['dir_nm'] + inputs['graph_files_dir'] + "/res_myGraph"
with open(myGraphName, 'wb') as f:
pickle_dump(myGraph, f)
tot_time = time_time() - start_time
out_comp_nm = inputs['dir_nm'] + inputs['out_comp_nm']
# Write to yaml file instead
with open(out_comp_nm + '_runtime_performance.out', "a") as fid:
print("Read network time (s) = ",
read_time,
"[",
round(100 * float(read_time) / tot_time, 2),
"%]",
file=fid)
print("Total time (s) = ", tot_time, file=fid)
def parse_options():
'''Get and parse program input arguments.'''
arg_parser = argparse_ArgumentParser()
arg_parser.version = CONST.APP_VERSION
arg_parser.add_argument("file",
help=TEXT.OPT_FILE,
action='store',
nargs=1,
type=str)
arg_parser.add_argument("-v", "--version", action='version')
args = arg_parser.parse_args()
return vars(args)
def parse_options():
'''Get and parse program input arguments.'''
arg_parser = argparse_ArgumentParser()
arg_parser.version = CONST.APP_VERSION
arg_parser.add_argument("-p", "--port", help=TEXT.OPT_PORT,
action='store', nargs=1, type=str)
arg_parser.add_argument("-b", "--bauds", help=TEXT.OPT_BAUDS,
action='store', nargs=1, type=int)
arg_parser.add_argument("-l", "--log", help=TEXT.OPT_LOG,
action='store', nargs=1, type=str)
arg_parser.add_argument("-v", "--version", action='version')
args = arg_parser.parse_args()
return vars(args)
def main():
parser = argparse_ArgumentParser("Input parameters")
parser.add_argument("--main_folder", help="Folder of the results")
args = parser.parse_args()
main_folder = "./humap/results_73_neg_same_size_distmetropolis/"
#main_folder="./humap/results_73_neg_same_size_distisa/"
#main_folder="./humap/results_73_neg_same_size_distcliques/"
#main_folder="./humap/results_73_neg_same_size_distsearch_top_neigs/"
if args.main_folder:
main_folder = args.main_folder
filename = main_folder + "res_pred.out"
figname = main_folder + "res_sizewise_scores_pred.png"
sizewise_scores(filename, figname)
def build_parser():
parser = argparse_ArgumentParser(
description='Visualizing a network from sbml')
parser.add_argument('inputtarfolder',
help='Input folder with sbml files as in tar format.')
parser.add_argument('outfile', help='html file.')
parser.add_argument(
'--choice',
default="2",
help=
'What kind of input do you want ? \n 1/Single HTML file \n 2/Separated HTML files \n 3/View directly in Cytoscape \n 4/Generate a file readable in Cytoscape \n'
)
parser.add_argument(
'--selenzyme_table',
default="N",
help='Do you want to display the selenzyme information ? Y/N')
return parser
def build_parser():
return add_arguments(
argparse_ArgumentParser('Python script to pre-compute data'))
import numpy as np
import math
import cv2
import heatmap
from datetime import datetime
from keras.models import model_from_yaml
from keras.optimizers import Adam, SGD
from glob import glob
from libs.common import my_resize
from libs.pavement_common import to_patches
from argparse import ArgumentParser as argparse_ArgumentParser
ap = argparse_ArgumentParser()
ap.add_argument("-inputdir", required=False, help="Path of input images")
ap.add_argument("-outputdir", required=False, help="Path of output images")
args = vars(ap.parse_args())
image_files_path = args["inputdir"]
nrootdir = args["outputdir"]
if image_files_path is None:
image_files_path = './input_images/'
if nrootdir is None:
nrootdir = "./images_dst/"
################################################################
# change these parameters:
destination_directory = '../../Dataset/GAPs/GAPs-dataset/images/'
def main():
parser = argparse_ArgumentParser("Input parameters")
parser.add_argument("--input_file_name",
default="input_toy.yaml",
help="Input parameters file name")
parser.add_argument("--out_dir_name",
default="/results",
help="Output directory name")
parser.add_argument("--train_test_files_dir",
default="",
help="Train test file path")
parser.add_argument("--graph_files_dir",
default="",
help="Graph files' folder path")
parser.add_argument("--n_pts",
default=1,
help="number of partitions (computers)")
parser.add_argument(
"--seed_mode",
help="Seed mode - specify 'cliques' for the cliques algo")
parser.add_argument("--search_method", help="Sampling algorithm")
parser.add_argument("--model_dir", help="Directory containing model")
parser.add_argument("--ptnum", default='0', help="partition number")
parser.add_argument("--explore_prob",
default=0.01,
help="probability of exploring")
parser.add_argument("--prob_metropolis",
default=0.1,
help="metropolis probability")
parser.add_argument("--T0", default=0.88, help="isa T0")
parser.add_argument("--alpha", default=1.8, help="isa alpha")
parser.add_argument("--classi_thresh",
default=0.5,
help="Classification threshold")
parser.add_argument("--transfer2tmp",
default=True,
help="Transfer to tmp folder")
args = parser.parse_args()
with open(args.input_file_name, 'r') as f:
inputs = yaml_load(f, yaml_Loader)
if args.classi_thresh:
inputs['classi_thresh'] = float(args.classi_thresh)
if args.seed_mode:
inputs['seed_mode'] = args.seed_mode
if args.search_method:
inputs['search_method'] = args.search_method
if args.model_dir:
inputs['model_dir'] = args.model_dir
if args.explore_prob:
inputs['explore_prob'] = float(args.explore_prob)
if args.prob_metropolis:
inputs['prob_metropolis'] = float(args.prob_metropolis)
if args.T0:
inputs['T0'] = float(args.T0)
if args.alpha:
inputs['alpha'] = float(args.alpha)
# Override output directory name if same as gen
if args.out_dir_name or inputs['out_comp_nm'] == "/results/res":
if not os_path.exists(inputs['dir_nm'] + args.out_dir_name):
os_mkdir(inputs['dir_nm'] + args.out_dir_name)
inputs['out_comp_nm'] = args.out_dir_name + "/res"
inputs['train_test_files_dir'] = ''
if args.train_test_files_dir:
if not os_path.exists(inputs['dir_nm'] + args.train_test_files_dir):
os_mkdir(inputs['dir_nm'] + args.train_test_files_dir)
inputs['train_test_files_dir'] = args.train_test_files_dir
inputs['graph_files_dir'] = ''
if args.graph_files_dir:
if not os_path.exists(inputs['dir_nm'] + args.graph_files_dir):
os_mkdir(inputs['dir_nm'] + args.graph_files_dir)
inputs['graph_files_dir'] = args.graph_files_dir
with open(inputs['dir_nm'] + inputs['out_comp_nm'] + "_input_sample.yaml",
'w') as outfile:
yaml_dump(inputs, outfile, default_flow_style=False)
logging_basicConfig(filename=inputs['dir_nm'] + inputs['out_comp_nm'] +
"_logs.yaml",
level=logging_INFO)
# fin_list_graphs = control(myGraph,inputs,n=50)
out_comp_nm = inputs['dir_nm'] + inputs['out_comp_nm']
out_comp_nm_model = inputs['dir_nm'] + inputs['model_dir']
modelfname = out_comp_nm_model + "_model"
scalerfname = out_comp_nm_model + "_scaler"
max_sizeF = inputs['dir_nm'] + inputs[
'train_test_files_dir'] + "/res_max_size_search_par"
with open(max_sizeF, 'rb') as f:
max_size = pickle_load(f)
with open(scalerfname, 'rb') as f:
scaler = pickle_load(f)
myGraph = None
if inputs['seed_mode'] == "cliques":
myGraphName = inputs['dir_nm'] + inputs[
'graph_files_dir'] + "/res_myGraph"
with open(myGraphName, 'rb') as f:
myGraph = pickle_load(f)
ptns = int(args.n_pts)
if inputs['seed_mode'] == 'n_nodes':
seed_nodes_dir = out_comp_nm + "_seed_nodes"
else:
seed_nodes_dir = inputs['dir_nm'] + inputs[
'graph_files_dir'] + "/" + inputs['seed_mode'] + "_n_pts_" + str(
ptns) + "/res_seed_nodes"
seed_nodes_F = seed_nodes_dir + args.ptnum
with open(seed_nodes_F, 'rb') as f:
seed_nodes = pickle_load(f)
start_time_sample = time_time()
out_comp_nm = inputs['dir_nm'] + inputs['out_comp_nm']
num_comp = sample(inputs, myGraph, modelfname, scaler, seed_nodes,
max_size, args.transfer2tmp)
sample_time = time_time() - start_time_sample
sample_time_avg = sample_time / num_comp
folNm_out = "/tmp/" + out_comp_nm + "_orig_comps" # CHECK WHICH NODE's TMP IS BEING USED
pred_comp_list = [
pickle_load(open(folNm_out + "/" + seed_node, 'rb'))
for seed_node in seed_nodes
if os_path.exists(folNm_out + "/" + seed_node)
]
with open(out_comp_nm + "_pred_comp_list" + args.ptnum, "wb") as f:
pickle_dump(pred_comp_list, f)
tot_time = time_time() - start_time
with open(out_comp_nm + '_runtime_performance.out', "a") as fid:
print("--- Runtime performance ---", file=fid)
print("Sample time (s) = ",
sample_time,
"[",
round(100 * float(sample_time) / tot_time, 2),
"%]",
file=fid)
print("Average sample time (s) = ", sample_time_avg, file=fid)
print("Total time (s) = ", tot_time, file=fid)
def main():
parser = argparse_ArgumentParser("Input parameters")
parser.add_argument("--input_file_name",
default="input_toy.yaml",
help="Input parameters file name")
parser.add_argument("--out_dir_name",
default="/results",
help="Output directory name")
parser.add_argument("--train_test_files_dir",
default="",
help="Train test file path")
parser.add_argument("--n_pts",
default=1,
help="number of partitions (computers)")
parser.add_argument("--over_t", help="Overlap threshold")
parser.add_argument("--model_dir", help="Directory containing model")
parser.add_argument("--sample_dir", help="Sample files dir + /res")
parser.add_argument("--sample_folders_prefix",
help="Input parameters file name /results..")
parser.add_argument(
"--sample_folders_prefix_final",
help="Input file name to use final merged results Use as /results..")
parser.add_argument(
"--sample_folders_list",
nargs='+',
help="Input parameters file name /results.. separated by commas")
parser.add_argument("--graph_files_dir",
default="",
help="Graph files' folder path")
parser.add_argument("--overlap_method",
default=1,
help="Overlap method option: qi, default: jaccard")
parser.add_argument("--infer_overlap_threshold",
default='n',
help="y or n")
args = parser.parse_args()
with open(args.input_file_name, 'r') as f:
inputs = yaml_load(f, yaml_Loader)
if args.overlap_method:
inputs['overlap_method'] = args.overlap_method
if args.over_t:
inputs['over_t'] = float(args.over_t)
if args.sample_dir:
inputs['sample_dir'] = args.sample_dir
if args.model_dir:
inputs['model_dir'] = args.model_dir
if args.infer_overlap_threshold:
inputs['infer_overlap_threshold'] = args.infer_overlap_threshold
# Override output directory name if same as gen
if args.out_dir_name or inputs['out_comp_nm'] == "/results/res":
if not os_path.exists(inputs['dir_nm'] + args.out_dir_name):
os_mkdir(inputs['dir_nm'] + args.out_dir_name)
inputs['out_comp_nm'] = args.out_dir_name + "/res"
inputs['train_test_files_dir'] = ''
if args.train_test_files_dir:
if not os_path.exists(inputs['dir_nm'] + args.train_test_files_dir):
os_mkdir(inputs['dir_nm'] + args.train_test_files_dir)
inputs['train_test_files_dir'] = args.train_test_files_dir
inputs['graph_files_dir'] = ''
if args.graph_files_dir:
if not os_path.exists(inputs['dir_nm'] + args.graph_files_dir):
os_mkdir(inputs['dir_nm'] + args.graph_files_dir)
inputs['graph_files_dir'] = args.graph_files_dir
logging_basicConfig(filename=inputs['dir_nm'] + inputs['out_comp_nm'] +
"_logs.yaml",
level=logging_INFO)
# fin_list_graphs = control(myGraph,inputs,n=50)
if "sample_dir" not in inputs:
inputs['sample_dir'] = inputs['out_comp_nm']
myGraphName = inputs['dir_nm'] + inputs['graph_files_dir'] + "/res_myGraph"
with open(myGraphName, 'rb') as f:
myGraph = pickle_load(f)
if 'infer_overlap_threshold' in inputs:
if inputs['infer_overlap_threshold'] == 'y':
pp_flag = 0
if inputs['dir_nm'] == 'yeast':
pp_flag = 1
if 'overlap_method' in inputs:
if inputs['overlap_method'] == 'qi':
inputs['over_t'] = get_overlap_threshold_qi(
inputs, pp_flag, myGraph)
else:
inputs['over_t'] = get_overlap_threshold(
inputs, pp_flag, myGraph)
with open(inputs['dir_nm'] + inputs['out_comp_nm'] + "_input_pp.yaml",
'w') as outfile:
yaml_dump(inputs, outfile, default_flow_style=False)
out_comp_nm = inputs['dir_nm'] + inputs['out_comp_nm']
out_comp_nm_sample = inputs['dir_nm'] + inputs['sample_dir']
out_comp_nm_model = inputs['dir_nm'] + inputs['model_dir']
modelfname = out_comp_nm_model + "_model"
scalerfname = out_comp_nm_model + "_scaler"
with open(scalerfname, 'rb') as f:
scaler = pickle_load(f)
pred_comp_list = []
sdndap = pred_comp_list.append
if args.sample_folders_list:
for folder in args.sample_folders_list:
allfiles = './' + inputs['dir_nm'] + folder + '/res_pred_comp_list*'
for fname in glob(allfiles, recursive=True):
with open(fname, 'rb') as f:
pred_comp_tmp = pickle_load(f)
for snode in pred_comp_tmp:
sdndap(snode)
elif args.sample_folders_prefix_final:
allsubd = './' + inputs[
'dir_nm'] + args.sample_folders_prefix_final + '*/res_pred.out'
for fname in glob(allsubd, recursive=True):
with open(fname) as f:
complexes_score = [
line.rstrip().split() for line in f.readlines()
]
pred_comp_tmp = [(frozenset(comp[:-1]), float(comp[-1]))
for comp in complexes_score]
for snode in pred_comp_tmp:
sdndap(snode)
elif args.sample_folders_prefix:
allsubd = './' + inputs[
'dir_nm'] + args.sample_folders_prefix + '*/res_pred_comp_list*'
for fname in glob(allsubd, recursive=True):
with open(fname, 'rb') as f:
pred_comp_tmp = pickle_load(f)
for snode in pred_comp_tmp:
sdndap(snode)
else:
for i in range(int(args.n_pts)):
with open(out_comp_nm_sample + "_pred_comp_list" + str(i),
'rb') as f:
pred_comp_tmp = pickle_load(f)
for snode in pred_comp_tmp:
sdndap(snode)
len_pred_comp_list = 'No. of complexes before pp = ' + str(
len(pred_comp_list))
logging_info(len_pred_comp_list)
test_complex_path = inputs['dir_nm'] + inputs[
'train_test_files_dir'] + "/res_test_known_complex_nodes_list"
test_prot_list = get_prot_list(test_complex_path)
train_complex_path = inputs['dir_nm'] + inputs[
'train_test_files_dir'] + "/res_train_known_complex_nodes_list"
train_prot_list = get_prot_list(train_complex_path)
protlistfname = inputs['dir_nm'] + inputs[
'train_test_files_dir'] + "/res_protlist"
with open(protlistfname, 'rb') as f:
prot_list = pickle_load(f)
start_time_pp = time_time()
fin_list_graphs = postprocess(pred_comp_list, modelfname, scaler, inputs,
myGraph, prot_list, train_prot_list,
test_prot_list)
pp_time = time_time() - start_time_pp
tot_time = time_time() - start_time
# Write to yaml file instead
with open(out_comp_nm + '_runtime_performance.out', "a") as fid:
print("--- Runtime performance ---", file=fid)
print("Post processing complex time (s) = ",
pp_time,
"[",
round(100 * float(pp_time) / tot_time, 2),
"%]",
file=fid)
print("Total time (s) = ", tot_time, file=fid)
def main():
parser = argparse_ArgumentParser("Input parameters")
parser.add_argument("--input_file_name",
default="input_toy.yaml",
help="Input parameters file name")
parser.add_argument("--out_dir_name",
default="/results",
help="Output directory name, by default - /results")
parser.add_argument(
"--seed_mode",
help="Seed mode - specify 'cliques' for the cliques algo")
parser.add_argument("--train_test_files_dir",
default="",
help="Train test file path")
parser.add_argument("--search_method", help="Sampling algorithm")
parser.add_argument("--model_dir", help="Directory containing model")
parser.add_argument("--python_command",
default="python",
help="python / python3")
parser.add_argument(
"--read_flag",
default=0,
help="1 when you want to read from file for evaluation")
parser.add_argument(
"--complex_file_name",
default=
"humap/results_2stageclustering_comparison/humap_2stage_clustering_res.txt",
help="complexes file name")
parser.add_argument("--evaluate_additional_metrics",
default=1,
help="complexes file name")
args = parser.parse_args()
rf = args.read_flag
rf_nm = args.complex_file_name
with open(args.input_file_name, 'r') as f:
inputs = yaml_load(f, yaml_Loader)
if args.model_dir:
inputs['model_dir'] = args.model_dir
# Override output directory name if same as gen
if args.out_dir_name or inputs['out_comp_nm'] == "/results/res":
if not os_path.exists(inputs['dir_nm'] + args.out_dir_name):
os_mkdir(inputs['dir_nm'] + args.out_dir_name)
inputs['out_comp_nm'] = args.out_dir_name + "/res"
inputs['train_test_files_dir'] = ''
if args.train_test_files_dir:
if not os_path.exists(inputs['dir_nm'] + args.train_test_files_dir):
os_mkdir(inputs['dir_nm'] + args.train_test_files_dir)
inputs['train_test_files_dir'] = args.train_test_files_dir
with open(inputs['dir_nm'] + inputs['out_comp_nm'] + "_input_eval.yaml",
'w') as outfile:
yaml_dump(inputs, outfile, default_flow_style=False)
logging_basicConfig(filename=inputs['dir_nm'] + inputs['out_comp_nm'] +
"_logs.yaml",
level=logging_INFO)
# fin_list_graphs = control(myGraph,inputs,n=50)
# eval_complex(rf,rf_nm,inputs,known_complex_nodes_list,prot_list,myGraph,fin_list_graphs)
known_complex_nodes_listfname = inputs[
'dir_nm'] + "/res_known_complex_nodes_list"
protlistfname = inputs['dir_nm'] + inputs[
'train_test_files_dir'] + "/res_protlist"
with open(protlistfname, 'rb') as f:
prot_list = pickle_load(f)
with open(known_complex_nodes_listfname, 'rb') as f:
known_complex_nodes_list = pickle_load(f)
out_comp_nm = inputs['dir_nm'] + inputs['out_comp_nm']
if not rf:
with open(inputs['dir_nm'] + inputs["out_comp_nm"] + '_pred.out',
"r") as fn:
lines = fn.readlines()
fin_list_graphs = []
for line in lines:
words = line.split()
fin_list_graphs.append((set(words[:-1]), words[-1]))
N_pred_complexes = len(fin_list_graphs)
with open(out_comp_nm + '_metrics.out', "a") as fid:
print("No. of predicted complexes = ", N_pred_complexes, file=fid)
if N_pred_complexes == 0:
print("0 predicted complexes")
return
pythonCommand = args.python_command
if rf == 1:
if rf_nm == 0:
rf_nm = out_comp_nm + '_pred.out'
with open(rf_nm) as fn:
fin_list_graphs = [(set(line.rstrip('\n').split()), 1)
for line in fn] # Space separated text only
# TRAINING SET EVALUATION
with open(out_comp_nm + '_metrics.out', "a") as fid:
print("\n --- On training set ---", file=fid)
train_complex_path = inputs['dir_nm'] + inputs[
'train_test_files_dir'] + "/res_train_known_complex_nodes_list"
try:
with open(train_complex_path + "_prot_list", 'rb') as f:
train_prot_list = pickle_load(f)
except:
train_prot_list = get_prot_list(train_complex_path)
with open(train_complex_path, 'rb') as f:
train_complex_list = pickle_load(f)
eval_complex(rf, rf_nm, inputs, train_complex_list, train_prot_list,
fin_list_graphs, "_train")
if args.evaluate_additional_metrics:
try:
run_metrics(train_complex_list, fin_list_graphs, out_comp_nm,
"_train")
except:
print("Error in running additional metrics for train")
# TEST SET EVALUATION
with open(out_comp_nm + '_metrics.out', "a") as fid:
print("\n --- On test set ---", file=fid)
test_complex_path = inputs['dir_nm'] + inputs[
'train_test_files_dir'] + "/res_test_known_complex_nodes_list"
try:
with open(test_complex_path + "_prot_list", 'rb') as f:
test_prot_list = pickle_load(f)
except:
test_prot_list = get_prot_list(test_complex_path)
with open(test_complex_path, 'rb') as f:
test_complex_list = pickle_load(f)
eval_complex(rf, rf_nm, inputs, test_complex_list, test_prot_list,
fin_list_graphs, "_test")
if args.evaluate_additional_metrics:
try:
run_metrics(test_complex_list, fin_list_graphs, out_comp_nm,
"_test")
except:
print("Error in running additional metrics for test")
# ON BOTH SETS
with open(out_comp_nm + '_metrics.out', "a") as fid:
print("\n --- On both sets ---", file=fid)
eval_complex(rf, rf_nm, inputs, known_complex_nodes_list, prot_list,
fin_list_graphs, "_both")
if args.evaluate_additional_metrics:
try:
run_metrics(known_complex_nodes_list, fin_list_graphs,
out_comp_nm, "")
except:
print("Error in running additional metrics for both")
else:
start_time_eval = time_time()
# TRAINING SET EVALUATION
with open(out_comp_nm + '_metrics.out', "a") as fid:
print("\n --- On training set ---", file=fid)
train_complex_path = inputs['dir_nm'] + inputs[
'train_test_files_dir'] + "/res_train_known_complex_nodes_list"
try:
with open(train_complex_path + "_prot_list", 'rb') as f:
train_prot_list = pickle_load(f)
except:
train_prot_list = get_prot_list(train_complex_path)
with open(train_complex_path, 'rb') as f:
train_complex_list = pickle_load(f)
eval_complex(rf, rf_nm, inputs, train_complex_list, train_prot_list,
fin_list_graphs, "_train")
if args.evaluate_additional_metrics:
try:
run_metrics(train_complex_list, fin_list_graphs, out_comp_nm,
"_train")
except:
print("Error in running additional metrics for train")
# TEST SET EVALUATION
with open(out_comp_nm + '_metrics.out', "a") as fid:
print("\n --- On test set ---", file=fid)
test_complex_path = inputs['dir_nm'] + inputs[
'train_test_files_dir'] + "/res_test_known_complex_nodes_list"
try:
with open(test_complex_path + "_prot_list", 'rb') as f:
test_prot_list = pickle_load(f)
except:
test_prot_list = get_prot_list(test_complex_path)
with open(test_complex_path, 'rb') as f:
test_complex_list = pickle_load(f)
eval_complex(rf, rf_nm, inputs, test_complex_list, test_prot_list,
fin_list_graphs, "_test")
if args.evaluate_additional_metrics:
try:
run_metrics(test_complex_list, fin_list_graphs, out_comp_nm,
"_test")
except:
print("Error in running additional metrics for test")
# BOTH SETS EVALUATION
with open(out_comp_nm + '_metrics.out', "a") as fid:
print("\n --- On both sets ---", file=fid)
eval_complex(rf, rf_nm, inputs, known_complex_nodes_list, prot_list,
fin_list_graphs, "_both")
if args.evaluate_additional_metrics:
try:
run_metrics(known_complex_nodes_list, fin_list_graphs,
out_comp_nm, "")
except:
print("Error in running additional metrics for both")
if not os_path.exists(out_comp_nm + "_edge_pr_files"):
os_mkdir(out_comp_nm + "_edge_pr_files")
for pref in ["", "_train", "_test"]:
# model dir not outcompnm
out_comp_nm_model = inputs['dir_nm'] + inputs['model_dir']
results_wprob = out_comp_nm + '_tot_pred_edges_unique_max_comp_prob_inKnown' + pref + '.out'
input_pos = out_comp_nm_model + pref + '_tot_known_edges_unique.out'
outfname = out_comp_nm + "_edge_pr_files/res" + '_edge_pr_curve' + pref
os_system(pythonCommand +
" functions_py3/prcurve_overlay_noneg.py --labels All " +
"--results_wprob " + results_wprob +
" --input_positives " + input_pos + " --output_file " +
outfname)
fname = out_comp_nm + "_pred.out"
figname = out_comp_nm + "_sizewise_scores_pred.png"
sizewise_scores(fname, figname)
eval_time = time_time() - start_time_eval
tot_time = time_time() - start_time
# Write to yaml file instead
with open(out_comp_nm + '_runtime_performance.out', "a") as fid:
print("--- Runtime performance ---", file=fid)
print("Evaluate complex time (s) = ",
eval_time,
"[",
round(100 * float(eval_time) / tot_time, 2),
"%]",
file=fid)
print("Total time (s) = ", tot_time, file=fid)
def main():
parser = argparse_ArgumentParser("Input parameters")
parser.add_argument("--input_file_name", default="input_toy.yaml", help="Input parameters file name")
parser.add_argument("--out_dir_name", default="/results", help="Output directory name")
parser.add_argument("--train_test_files_dir", default="", help="Train test file path")
parser.add_argument("--graph_files_dir", default="", help="Graph files' folder path")
parser.add_argument("--seed_mode", help="Seed mode - specify 'cliques' for the cliques algo")
parser.add_argument("--max_size_thres", help="Max size threshold")
parser.add_argument("--n_pts", default=1, help="number of partitions (computers)")
args = parser.parse_args()
with open(args.input_file_name, 'r') as f:
inputs = yaml_load(f, yaml_Loader)
if args.seed_mode:
inputs['seed_mode'] = args.seed_mode
if args.max_size_thres:
inputs['max_size_thres'] = int(args.max_size_thres)
# Override output directory name if same as gen
if args.out_dir_name or inputs['out_comp_nm'] == "/results/res":
if not os_path.exists(inputs['dir_nm'] + args.out_dir_name):
os_mkdir(inputs['dir_nm'] + args.out_dir_name)
inputs['out_comp_nm'] = args.out_dir_name + "/res"
inputs['train_test_files_dir'] = ''
if args.train_test_files_dir:
if not os_path.exists(inputs['dir_nm'] + args.train_test_files_dir):
os_mkdir(inputs['dir_nm'] + args.train_test_files_dir)
inputs['train_test_files_dir'] = args.train_test_files_dir
inputs['graph_files_dir'] = ''
if args.graph_files_dir:
if not os_path.exists(inputs['dir_nm'] + args.graph_files_dir):
os_mkdir(inputs['dir_nm'] + args.graph_files_dir)
inputs['graph_files_dir'] = args.graph_files_dir
with open(inputs['dir_nm'] + inputs['out_comp_nm'] + "_input_sample_partition.yaml", 'w') as outfile:
yaml_dump(inputs, outfile, default_flow_style=False)
logging_basicConfig(filename=inputs['dir_nm'] + inputs['out_comp_nm'] + "_logs.yaml", level=logging_INFO)
neig_dicts_folder = inputs['dir_nm'] +inputs['graph_files_dir']+ "/neig_dicts"
num_comp = inputs['num_comp']
max_size_thres = inputs['max_size_thres']
max_size_trainF = inputs['dir_nm'] + inputs['train_test_files_dir']+ "/res_max_size_train"
with open(max_size_trainF, 'rb') as f:
max_size_train = pickle_load(f)
max_size = max_size_train
max_sizeF_feat = inputs['dir_nm'] + inputs['train_test_files_dir']+ "/res_max_size_search"
if os_path.exists(max_sizeF_feat):
with open(max_sizeF_feat, 'rb') as f:
max_size = pickle_load(f)
else:
with open(inputs['dir_nm'] + inputs['comf_nm']) as f:
sizes = [len(line.rstrip().split()) for line in f.readlines()]
max_size = max(sizes)
q1 = np_percentile(sizes, 25)
q3 = np_percentile(sizes, 75)
max_wo_outliers = math_ceil(q3 + 4.5*(q3-q1)) # Maximum after removing outliers
max_size = min(max_size,max_wo_outliers)
if max_size >= max_size_thres:
max_size = max_size_thres
out_comp_nm = inputs['dir_nm'] + inputs['out_comp_nm']
with open(out_comp_nm + '_metrics.out', "a") as fid:
print("Max number of steps for complex growth = ", max_size, file=fid) # NOT actual max size since you merge later
max_sizeF = inputs['dir_nm'] + inputs['train_test_files_dir']+ "/res_max_size_search_par"
with open(max_sizeF, 'wb') as f:
pickle_dump(max_size, f)
seed_mode = inputs['seed_mode']
if seed_mode == "all_nodes":
#graph_nodes = list(myGraph.nodes())
seed_nodes = rand_perm(os_listdir(neig_dicts_folder))
elif seed_mode == "n_nodes":
seed_nodes = rand_perm(os_listdir(neig_dicts_folder))[:num_comp]
elif seed_mode == "all_nodes_known_comp":
protlistfname = inputs['dir_nm']+ inputs['train_test_files_dir'] + "/res_protlist"
with open(protlistfname, 'rb') as f:
prot_list = pickle_load(f)
seed_nodes = list(prot_list)
elif seed_mode == "cliques":
myGraphName = inputs['dir_nm'] + inputs['graph_files_dir']+ "/res_myGraph"
with open(myGraphName, 'rb') as f:
myGraph = pickle_load(f)
clique_list = list(nx_find_cliques(myGraph))
to_rem = []
# Removing 2 node and big complexes
for comp in clique_list:
if len(comp) <= 2 or len(comp) >= max_size:
to_rem.append(comp)
for comp in to_rem:
clique_list.remove(comp)
seed_nodes = clique_list # Remove duplicates later.
# partition
ptns = int(args.n_pts)
nc = len(seed_nodes)
if seed_mode == 'n_nodes':
seed_nodes_F = out_comp_nm + "_seed_nodes"
each_ptn = nc // ptns
for i in range(ptns - 1):
with open(seed_nodes_F + str(i), 'wb') as f:
pickle_dump(seed_nodes[i * each_ptn:(i + 1) * each_ptn], f)
with open(seed_nodes_F + str(ptns - 1), 'wb') as f:
pickle_dump(seed_nodes[(ptns - 1) * each_ptn:], f)
else:
seed_nodes_dir = inputs['dir_nm'] + inputs['graph_files_dir']+ "/" + seed_mode + "_n_pts_" + str(ptns)
if not os_path.exists(seed_nodes_dir):
os_mkdir(seed_nodes_dir)
seed_nodes_F = seed_nodes_dir + "/res_seed_nodes"
each_ptn = nc // ptns
for i in range(ptns - 1):
with open(seed_nodes_F + str(i), 'wb') as f:
pickle_dump(seed_nodes[i * each_ptn:(i + 1) * each_ptn], f)
with open(seed_nodes_F + str(ptns - 1), 'wb') as f:
pickle_dump(seed_nodes[(ptns - 1) * each_ptn:], f)
def build_args_parser():
parser = argparse_ArgumentParser(
prog='rpfba', description='Calculate FBA to generate rpFBA collection')
parser = _add_arguments(parser)
return parser
# pdf_merging.py
from PyPDF3 import PdfFileReader, PdfFileWriter
from argparse import ArgumentParser as argparse_ArgumentParser
commands = argparse_ArgumentParser(description='merge pdf')
commands.add_argument('-a', help='first pdf')
commands.add_argument('-b', help='second pdf')
commands, unknown = commands.parse_known_args()
pdf1 = commands.a
pdf2 = commands.b
def merge_pdfs(paths, output):
pdf_writer = PdfFileWriter()
for path in paths:
pdf_reader = PdfFileReader(path)
for page in range(pdf_reader.getNumPages()):
# Add each page to the writer object
pdf_writer.addPage(pdf_reader.getPage(page))
# Write out the merged PDF
with open(output, 'wb') as out:
pdf_writer.write(out)
if __name__ == '__main__':
paths = [pdf1, pdf2]
merge_pdfs(paths, output='merged.pdf')
from glob import glob
from argparse import ArgumentParser as argparse_ArgumentParser
parser = argparse_ArgumentParser("Input parameters")
parser.add_argument("--main_folder",
default="/*",
help="Input parameters file name")
args = parser.parse_args()
def get_f1_score(file_name):
res = 0
with open(file_name) as f:
lines = f.readlines()
for line in lines[::-1]: # Reverse order
words = line.strip().split("=")
if words[0] == "Prediction F1 score ":
if float(words[1]) > 0:
res = float(words[1])
break
return res
# level1subd = './humap/*/res_metrics*'
allsubd = './humap' + args.main_folder + '*/res_metrics*'
# fname = "./humap/results_73_neg_same_size_distmetropolis/res_metrics.out"
max_f1_score = 0
max_fname = ""
all_sets = []
for fname in glob(allsubd, recursive=True):
f1score = get_f1_score(fname)
all_sets.append((fname, f1score))
def build_parser():
parser = argparse_ArgumentParser(description='SeqFind script for Selenzy')
parser = add_arguments(parser)
return parser
'', #string - FQDN or IP we get from DNS for reverse or forward lookup
'commandList':
'', #list of strings - to store command parameters to run with subprocess module
'hostIndex':
hostIndex, #indeger, reference to index in defaultCommand to replace it with target IP or name
'results': '', #string - probe run results to print on screen
'logFile':
'' #file object - file to store logs to for this particular target
}
splitChar = ',' #character used to split data in SrcFile
formatter = '' #string, used to format results output for cli printing
header = '' #string, used to contain header information for priniting to cli
#build argparser based menu:
parser = argparse_ArgumentParser(description="""
Concurrent Command to Multiple Destinations - run
commands against targets in semi-parallel fashion.
""")
parser.add_argument('-c',
action='store',
dest='PROBECOUNT',
default=100,
type=int,
help='Number of probes to run, default - 100')
parser.add_argument('-b',
action='store',
dest='barLen',
default=60,
type=int,
help='Length of probe history bar, default - 60')
parser.add_argument('-i',
action='store',