print('Load the target ' + str(trainIndex[refSampleInd]))
target = dh.loadDeepCyTOFData(dataPath, trainIndex[refSampleInd],
relevantMarkers, mode)
# Pre-process sample.
if choice!=5:
target = dh.preProcessSamplesCyTOFData(target)
'''
Train the de-noising auto encoder.
'''
print('Train the de-noising auto encoder.')
start = tm.time()
DAE = dae.trainDAE(target, dataPath, refSampleInd, trainIndex,
relevantMarkers, mode, keepProb, denoise,
loadModel, dataSet[choice])
denoiseTarget = dae.predictDAE(target, DAE, denoise)
'''
Train the feed-forward classifier on (de-noised) target.
'''
denoiseTarget, preprocessor = dh.standard_scale(denoiseTarget,
preprocessor = None)
if loadModel:
from keras.models import load_model
cellClassifier = load_model(os.path.join(io.DeepLearningRoot(),
'savemodels/' + dataSet[choice] +
'/cellClassifier.h5'))
else:
# for data_path in data_paths:
# data = pd.read_csv(data_path, compression='gzip', error_bad_lines=False)
# actual = pd.read_csv(data_path.replace("/x/","/y/"), compression='gzip', error_bad_lines=False)
# Pre-process sample. Don't need to, my samples are cleaned and processed
target = dh.preProcessSamplesCyTOFData(target)
'''
Train the de-noising auto encoder.
'''
print('Train the de-noising auto encoder.')
res_dir = data_dir.replace("raw/", "results/").replace(
"/x/", "/deepCyTOF_models/" + str(trainNum) + "/")
Path(res_dir).mkdir(parents=True, exist_ok=True)
DAE = dae.trainDAE(target, data_dir, refSampleInd, trainIndex,
relevantMarkers, mode, keepProb, denoise, loadModel,
res_dir)
denoiseTarget = dae.predictDAE(target, DAE, denoise)
'''
Train the feed-forward classifier on (de-noised) target.
'''
denoiseTarget, preprocessor = dh.standard_scale(denoiseTarget,
preprocessor=None)
res_dir = data_dir.replace("raw/", "results/").replace(
"/x/", "/deepCyTOF_models/" + str(trainNum) + "/")
Path(res_dir).mkdir(parents=True, exist_ok=True)
if loadModel:
from keras.models import load_model
cellClassifier = load_model(
os.path.join(io.DeepLearningRoot(),