def trainDAE(target, dataPath, refSampleInd, trainIndex, relevantMarkers, mode,
keepProb, denoise, loadModel, path):
sourceX = []
for i in np.arange(trainIndex.size-1):
sourceIndex = np.delete(trainIndex, refSampleInd)[i]
source = dh.loadDeepCyTOFData(dataPath, sourceIndex,
relevantMarkers, mode)
numZerosOK=1
toKeepS = np.sum((source.X==0), axis = 1) <= numZerosOK
if i == 0:
sourceX = source.X[toKeepS]
else:
sourceX = np.concatenate([sourceX, source.X[toKeepS]], axis = 0)
# preProcess source
sourceX = np.log(1 + np.abs(sourceX))
numZerosOK=1
toKeepT = np.sum((target.X==0), axis = 1) <= numZerosOK
inputDim = target.X.shape[1]
ae_encodingDim = 25
l2_penalty_ae = 1e-2
if denoise:
if loadModel:
from keras.models import load_model
autoencoder = load_model(os.path.join(io.DeepLearningRoot(), path + '/denoisedAE.h5'))
else:
# train de-noising auto encoder and save it.
trainTarget_ae = np.concatenate([sourceX, target.X[toKeepT]],
axis=0)
trainData_ae = trainTarget_ae * np.random.binomial(n=1, p=keepProb,
size = trainTarget_ae.shape)
input_cell = Input(shape=(inputDim,))
encoded = Dense(ae_encodingDim, activation='relu',
W_regularizer=l2(l2_penalty_ae))(input_cell)
encoded1 = Dense(ae_encodingDim, activation='relu',
W_regularizer=l2(l2_penalty_ae))(encoded)
decoded = Dense(inputDim, activation='linear',
W_regularizer=l2(l2_penalty_ae))(encoded1)
autoencoder = Model(input=input_cell, output=decoded)
autoencoder.compile(optimizer='rmsprop', loss='mse')
autoencoder.fit(trainData_ae, trainTarget_ae, nb_epoch=80,
batch_size=128, shuffle=True,
validation_split=0.1, verbose = 0,
callbacks=[mn.monitor(), cb.EarlyStopping(
monitor='val_loss', patience=25, mode='auto')])
autoencoder.save(os.path.join(io.DeepLearningRoot(), path + '/denoisedAE.h5'))
del sourceX
plt.close('all')
return autoencoder
def trainClassifier(trainSample, mode = 'None', i = 0,
hiddenLayersSizes = [12, 6, 3],
activation = 'softplus', l2_penalty = 1e-4,
path = 'None'):
# Remove unlabeled cells for training.
x_train = trainSample.X[trainSample.y != 0]
y_train = trainSample.y[trainSample.y != 0]
# Labels start from 0.
y_train = np.int_(y_train) - 1
# Special case in GvHD: label in those files are 0,1,3,4 with no 2.
if mode == 'GvHD' and (i == 5 or i == 9 or
i == 10 or i == 11):
y_train[y_train != 0] = y_train[y_train != 0] - 1
# Expand labels, to work with sparse categorical cross entropy.
y_train = np.expand_dims(y_train, -1)
# Construct a feed-forward neural network.
inputLayer = Input(shape = (x_train.shape[1],))
hidden1 = Dense(hiddenLayersSizes[0], activation = activation,
kernel_regularizer = l2(l2_penalty))(inputLayer)
hidden2 = Dense(hiddenLayersSizes[1], activation = activation,
kernel_regularizer = l2(l2_penalty))(hidden1)
hidden3 = Dense(hiddenLayersSizes[2], activation = activation,
kernel_regularizer = l2(l2_penalty))(hidden2)
# numClasses = len(np.unique(trainSample.y)) - 1 # with 0 class
numClasses = len(np.unique(trainSample.y)) # without 0 class
# numClasses = 57 # for HMIS-2
outputLayer = Dense(numClasses, activation = 'softmax')(hidden3)
encoder = Model(inputs = inputLayer, outputs = outputLayer)
net = Model(inputs = inputLayer, outputs = outputLayer)
lrate = LearningRateScheduler(step_decay)
optimizer = keras.optimizers.rmsprop(lr = 0.0)
net.compile(optimizer = optimizer,
loss = 'sparse_categorical_crossentropy')
net.fit(x_train, y_train, epochs = 80, batch_size = 128, shuffle = True,
validation_split = 0.1, verbose = 0,
callbacks=[lrate, mn.monitor(),
cb.EarlyStopping(monitor = 'val_loss',
patience = 25, mode = 'auto')])
try:
net.save(os.path.join(io.DeepLearningRoot(),
'savemodels/' + path + '/cellClassifier.h5'))
except OSError:
pass
#plt.close('all')
return net
def plotHidden(trainSample, testSample, mode = 'None', i = 0,
hiddenLayersSizes = [12, 6, 3],
activation = 'softplus', l2_penalty = 1e-4,
path = 'None'):
# Remove unlabeled cells for training.
x_train = trainSample.X[trainSample.y != 0]
y_train = trainSample.y[trainSample.y != 0]
x_test = testSample.X[testSample.y != 0]
y_test = testSample.y[testSample.y != 0]
# Labels start from 0.
y_train = np.int_(y_train) - 1
y_test = np.int_(y_test) - 1
# Special case in GvHD: label in those files are 0,1,3,4 with no 2.
if mode == 'GvHD' and (i == 5 or i == 9 or
i == 10 or i == 11):
y_train[y_train != 0] = y_train[y_train != 0] - 1
# Expand labels, to work with sparse categorical cross entropy.
y_train = np.expand_dims(y_train, -1)
y_test = np.expand_dims(y_test, -1)
# Construct a feed-forward neural network.
inputLayer = Input(shape = (x_train.shape[1],))
hidden1 = Dense(hiddenLayersSizes[0], activation = activation,
W_regularizer = l2(l2_penalty))(inputLayer)
hidden2 = Dense(hiddenLayersSizes[1], activation = activation,
W_regularizer = l2(l2_penalty))(hidden1)
hidden3 = Dense(hiddenLayersSizes[2], activation = activation,
W_regularizer = l2(l2_penalty))(hidden2)
numClasses = len(np.unique(trainSample.y)) - 1
outputLayer = Dense(numClasses, activation = 'softmax')(hidden3)
encoder = Model(input = inputLayer, output = hidden3)
# plot data in the 3rd hidden layer
h3_data = encoder.predict(x_test, verbose = 0)
#fig, (ax1) = plt1.subplots(1,1, subplot_kw={'projection':'3d'})
#ax1.scatter(h3_data[:,0], h3_data[:,1], h3_data[:,2], s = 20, c = np.squeeze(y_test))
fig = plt1.figure()
ax = fig.add_subplot(111, projection = '3d')
ax.scatter(h3_data[:,0], h3_data[:,1], h3_data[:,2], s = 20, c = np.squeeze(y_test))
#ax1.set_title('data in 3rd hidden layer')
plt1.show()
net = Model(input = inputLayer, output = outputLayer)
lrate = LearningRateScheduler(step_decay)
optimizer = keras.optimizers.rmsprop(lr = 0.0)
net.compile(optimizer = optimizer,
loss = 'sparse_categorical_crossentropy')
net.fit(x_train, y_train, nb_epoch = 80, batch_size = 128, shuffle = True,
validation_split = 0.1, verbose = 0,
callbacks=[lrate, mn.monitor(),
cb.EarlyStopping(monitor = 'val_loss',
patience = 25, mode = 'auto')])
try:
net.save(os.path.join(io.DeepLearningRoot(),
'savemodels/' + path + '/cellClassifier.h5'))
except OSError:
pass