def main():
args = getArgs()
if args.seed is None:
seed = random.randrange(sys.maxsize)
args.seed = seed
print(f"generating new random seed: {seed}")
else:
print(f"setting random seed to: {args.seed}")
random.seed(args.seed)
datasetlist = args.datasets
print(f"doing experiment with {datasetlist} in that order")
k = args.kfold
results = {}
runlist = args.methods
set_keras_growth(args.gpu)
prefix = "runner"
if args.prefix is not None:
prefix = args.prefix
rootpath = prefix + datetime.now().strftime('%Y_%m_%d_%H_%M_%S')
createdir(rootpath)
min_retain_losses = list()
min_losses = list()
writejson(f"{rootpath}/settings.json", sys.argv[1:])
if args.callbacks is not None:
callbacks = args.callbacks
else:
callbacks = list()
alphalist = [0.8]
nresults = list()
for i in range(0, args.n):
nresults.append(
runalldatasets(args,
callbacks,
datasetlist,
rootpath,
runlist,
alphalist=alphalist,
n=i,
printcvresults=args.cvsummary,
printcv=args.printcv,
doevaluation=args.doevaluation,
learning_rate=args.learning_rate))
writejson(f"{rootpath}/data.json", nresults)
resdf = pd.DataFrame(nresults)
resdf.to_csv(
f"{rootpath}/results_{args.kfold}kfold_{args.epochs}epochs_{args.onehot}onehot.csv"
)
def main(mpirank, mpisize, mpicomm):
args = getArgs()
if args.seed is None:
seed = random.randrange(sys.maxsize)
args.seed = seed
print(f"generating new random seed:{seed}")
random.seed(args.seed)
datasetlist = args.datasets
k = args.kfold
results = {}
runlist = args.methods
if "," in args.gpu:
gpus = args.gpu.split(",")
mygpu = gpus[mpirank % 2]
set_keras_growth(int(mygpu))
else:
set_keras_growth(args.gpu)
dataset_results = dict()
prefix = "runner"
if args.prefix is not None:
prefix = args.prefix
rootpath = prefix + datetime.now().strftime('%Y_%m_%d_%H_%M_%S')
if mpirank == 0:
createdir(rootpath)
writejson(f"{rootpath}/settings.json", sys.argv[1:])
min_retain_losses = list()
min_losses = list()
datasetsdone = list()
if args.callbacks is not None:
callbacks = args.callbacks
else:
callbacks = list()
nresults = list()
alphalist = [
0.8
] # this code does not iterate over alpha, see mpi_deesweighting.py
for i in range(0, args.n):
dataset_results = runalldatasetsMPI(args,
callbacks,
datasetlist,
mpicomm,
mpirank,
rootpath,
runlist,
alphalist,
n=i,
printcvresults=args.cvsummary,
printcv=args.printcv,
doevaluation=args.doevaluation)
nresults.append(dataset_results)
if mpirank == 0:
writejson(f"{rootpath}/data.json", nresults)
resdf = pd.DataFrame(results)
resdf.to_csv(
f"{rootpath}/results_{args.kfold}kfold_{args.epochs}epochs_{args.onehot}onehot.csv"
)
def main():
parser = argparse.ArgumentParser(
description='Plot the validation loss per epoch during training.')
parser.add_argument(
'--resultdir',
metavar='resultdir',
type=str,
help='resultdir for loading data files including figures',
required=True)
parser.add_argument('--savedir',
metavar='savedir',
type=str,
help='Directory to write the pdf figure to',
required=True)
parser.add_argument('--filename',
metavar='filename',
type=str,
help='Filename for pdf figure',
required=True)
parser.add_argument(
'-c',
'--classes',
metavar="classes",
help='which classes should be plotted in the clustering visualization.',
type=lambda s: [item for item in s.split(',')],
dest="classes")
parser.add_argument('--addgabelresults',
metavar='addgabelresults',
type=str2bool,
help='Filename for pdf figure',
default=False)
parser.add_argument('--removeoptimizer',
metavar='removeoptimizer',
type=str2bool,
help='remove the optimizer name from the method label',
default=False)
parser.add_argument('--doeval',
metavar='doeval',
type=str2bool,
help='Do eval of the model',
default=False)
parser.add_argument('--font_scale',
metavar='font_scale',
type=float,
help='UI scale for the figure.',
required=True)
parser.add_argument(
'--split',
metavar='split',
type=int,
help=
'N split for, 5 means 20% will be used for clustering vizualisation.',
required=True)
parser.add_argument('--seed',
metavar='seed',
type=int,
help='random seed',
required=True)
parser.add_argument('--maxdatapoints',
metavar='maxdatapoints',
type=int,
help='maximum number of datapoints to plot',
required=True)
parser.add_argument(
'--hue_order',
metavar='hue_order',
type=str,
help='Ordering of the different hues in the plot '
'so that the methods gets the same hue color in each plot',
required=True)
# parser.add_argument('--modelfile', metavar='modelfile', type=str,
# help='File name for the saved model', required=True)
parser.add_argument(
'-modelfiles',
'--modelfiles',
metavar="modelfiles",
help=
'the model files of the different similiarity measurement methods.',
type=lambda s: [item for item in s.split(',')],
dest="modelfiles")
# parser.add_argument('--method', metavar='method', type=str,
# help='method to use', required=True)
args = parser.parse_args()
if not len(sys.argv) > 1:
print("not enough arguments")
parser.print_help()
sys.exit(1)
# parser = getParser()
oldargs = None
with open(f"{args.resultdir}/settings.json") as f:
oldargv = jsonlib.load(f)
oldargs = getArgs(myargs=oldargv) #parser.parse_args(args=oldargv)
#fmethods = oldargs.methods.split(",")
np.random.seed(args.seed)
oldmethods = {}
for method in oldargs.methods:
runner, oldmethods[method.split(":")[0]] = parseMethod(method)
dataset = Dataset(oldargs.datasets[0])
dsl, colmap, \
stratified_fold_generator = fromDataSetToSKLearn(dataset,
oldargs.onehot,
n_splits=args.split)
train, test = next(stratified_fold_generator)
features = dsl.getFeatures()
targets = dsl.getTargets()
resultfile = args.resultdir
save_directory = args.savedir
filename = args.filename
classes = [int(c) for c in args.classes]
c = 0
for method in oldmethods:
modelmaker = oldmethods[method]["runnerdict"]["makeModel"]
evalfunc = oldmethods[method]["runnerdict"]["eval"]
model, embeddingmodel = modelmaker(features,
targets,
oldargs.hiddenlayers,
regression=False)
modelfile = args.modelfiles[c]
c += 1
model.load_weights(modelfile)
randommodel = keras.models.clone_model(model)
shuffle_weights(randommodel)
plotROC(save_directory, model, randommodel, filename + method,
args.font_scale, features, targets, train, test)
def main(mpirank, mpisize, mpicomm):
args = getArgs()
if args.seed is not None:
random.seed(args.seed)
datasetlist = args.datasets
print(f"doing experiment with {datasetlist} in that order")
k = args.kfold
results = {}
runlist = args.methods
if "," in args.gpu:
gpus = args.gpu.split(",")
mygpu = gpus[mpirank % 2]
set_keras_growth(int(mygpu))
else:
set_keras_growth(args.gpu)
dataset_results = dict()
prefix = "runner"
if args.prefix is not None:
prefix = args.prefix
rootpath = prefix + datetime.now().strftime('%Y_%m_%d_%H_%M_%S')
if mpirank == 0:
createdir(rootpath)
writejson(f"{rootpath}/settings.json", vars(args))
min_retain_losses = list()
min_losses = list()
if args.alpharange is not None:
splits = args.alpharange.split(":")
alphastart = float(splits[0])
alphastop = float(splits[1])
alpharange = np.linspace(alphastart, alphastop, args.alphacount)
else:
alpharange = np.linspace(0.000001, 1.00001, args.alphacount)
datasetsdone = list()
if args.callbacks is not None:
callbacks = args.callbacks
else:
callbacks = list()
nresults = list()
for i in range(0, args.n):
dataset_results = runalldatasetsMPI(args,
callbacks,
datasetlist,
mpicomm,
mpirank,
rootpath,
runlist,
alpharange,
n=i,
printcvresults=args.cvsummary,
printcv=args.printcv)
nresults.append(dataset_results)
if mpirank == 0:
# plotNAlphaResults(datasetlist, nresults, rootpath)
writejson(f"{rootpath}/data.json", nresults)
resdf = pd.DataFrame(results)
resdf.to_csv(
f"{rootpath}/results_{args.kfold}kfold_{args.epochs}epochs_{args.onehot}onehot.csv"
)