def fromCmdArgs(cls, args: argparse.Namespace) -> TrainOptions:
"""Creates TrainOptions instance from cmdline arguments"""
if args.f != "":
jsonFile = Path(makePathAbsolute(args.f))
if jsonFile.exists() and jsonFile.is_file():
with jsonFile.open() as f:
content = f.read()
return jsonpickle.decode(content)
else:
raise ValueError("Could not find JSON input file")
else:
return cls(
inputFile=args.i,
outputDir=args.o,
ecWeightsFile=args.a,
type=args.t,
fpType=args.k,
fpSize=args.s,
encFPSize=args.d,
epochs=args.e,
kFolds=args.K,
testingFraction=args.l,
enableMultiLabel=args.m,
verbose=args.v,
trainAC=args.trainAC,
trainFNN=args.trainFNN,
compressFeatures=args.c,
sampleFractionOnes=args.sampleFractionOnes,
sampleDown=args.sampleDown
)
def train(opts: options.TrainOptions):
"""
Run the main training procedure
:param opts: Options defining the details of the training
"""
df = fp.importDataFile(opts.inputFile, import_function=fp.importSmilesCSV, fp_size=opts.fpSize)
# Create output dir if it doesn't exist
createDirectory(opts.outputDir)
if opts.compressFeatures: # compress features
if opts.trainAC:
# train an autoencoder on the full feature matrix
encoder = ac.train_full_ac(df, opts)
else:
# load trained model for autoencoder
(_, encoder) = ac.define_ac_model(input_size=opts.fpSize, encoding_dim=opts.encFPSize)
encoder.load_weights(makePathAbsolute(opts.ecWeightsFile))
# compress the fingerprints using the autoencoder
df = ac.compress_fingerprints(df, encoder)
if opts.trainFNN:
# train single label models
fNN.train_nn_models(df=df, opts=opts)
# train multi-label models
if opts.enableMultiLabel:
fNN.train_nn_models_multi(df=df, opts=opts)
def main():
"""
Main function that runs training/prediction defined by command line arguments
"""
parser = options.createCommandlineParser()
prog_args: Namespace = parser.parse_args()
try:
if prog_args.method == "convert":
directory = makePathAbsolute(prog_args.f)
if path.isdir(directory):
createLogger(path.join(directory, "convert.log"))
logging.info(f"Convert all data files in {directory}")
fp.convert_all(directory)
else:
raise ValueError("Input directory is not a directory")
if prog_args.method == "train":
train_opts = options.TrainOptions.fromCmdArgs(prog_args)
fixed_opts = dataclasses.replace(
train_opts,
inputFile=makePathAbsolute(train_opts.inputFile),
outputDir=makePathAbsolute(train_opts.outputDir))
createDirectory(fixed_opts.outputDir)
createLogger(path.join(fixed_opts.outputDir, "train.log"))
logging.info(
f"The following arguments are received or filled with default values:\n{fixed_opts}"
)
train(fixed_opts)
exit(0)
elif prog_args.method == "predict":
predict_opts = options.PredictOptions.fromCmdArgs(prog_args)
fixed_opts = dataclasses.replace(
predict_opts,
inputFile=makePathAbsolute(predict_opts.inputFile),
outputDir=makePathAbsolute(predict_opts.outputDir))
createDirectory(fixed_opts.outputDir)
createLogger(path.join(fixed_opts.outputDir, "predict.log"))
logging.info(
f"The following arguments are received or filled with default values:\n{prog_args}"
)
predict(fixed_opts)
exit(0)
except AttributeError as e:
print(e)
parser.print_usage()
def fromCmdArgs(cls, args: argparse.Namespace) -> PredictOptions:
"""Creates TrainOptions instance from cmdline arguments"""
if args.f != "":
jsonFile = Path(makePathAbsolute(args.f))
if jsonFile.exists() and jsonFile.is_file():
with jsonFile.open() as f:
content = f.read()
return jsonpickle.decode(content)
else:
raise ValueError("Could not find JSON input file")
else:
return cls(
inputFile=args.i,
outputDir=args.o,
ecWeightsFile=args.ECmodel,
model=args.model,
target=args.target,
fpSize=args.s,
encFPSize=args.d,
type=args.t,
fpType=args.k,
)