def initialize_parameters():
# Get command-line parameters
parser = get_combo_parser()
args = parser.parse_args()
# Get parameters from configuration file
file_params = combo.read_config_file(args.config_file)
# Consolidate parameter set. Command-line parameters overwrite file configuration
params = p1_common.args_overwrite_config(args, file_params)
# print(params)
return params
def initialize_parameters():
# Get command-line parameters
parser = get_nt3_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = read_config_file(args.config_file)
#print ('Params:', fileParameters)
# Consolidate parameter set. Command-line parameters overwrite file configuration
gParameters = p1_common.args_overwrite_config(args, fileParameters)
return gParameters
def main():
# Get command-line parameters
parser = get_p1b1_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = p1b1.read_config_file(args.config_file)
#print ('Params:', fileParameters)
# Consolidate parameter set. Command-line parameters overwrite file configuration
gParameters = p1_common.args_overwrite_config(args, fileParameters)
print('Params:', gParameters)
# Construct extension to save model
ext = p1b1.extension_from_parameters(gParameters, '.pt')
logfile = args.logfile if args.logfile else args.save + ext + '.log'
p1b1.logger.info('Params: {}'.format(gParameters))
# Get default parameters for initialization and optimizer functions
kerasDefaults = p1_common.keras_default_config()
seed = gParameters['rng_seed']
# Load dataset
X_train, X_val, X_test = p1b1.load_data(gParameters, seed)
print("Shape X_train: ", X_train.shape)
print("Shape X_val: ", X_val.shape)
print("Shape X_test: ", X_test.shape)
print("Range X_train --> Min: ", np.min(X_train), ", max: ",
np.max(X_train))
print("Range X_val --> Min: ", np.min(X_val), ", max: ", np.max(X_val))
print("Range X_test --> Min: ", np.min(X_test), ", max: ", np.max(X_test))
# Set input and target to X_train
train_data = torch.from_numpy(X_train)
train_tensor = data.TensorDataset(train_data, train_data)
train_iter = data.DataLoader(train_tensor,
batch_size=gParameters['batch_size'],
shuffle=gParameters['shuffle'])
# Validation set
val_data = torch.from_numpy(X_val)
val_tensor = torch.utils.data.TensorDataset(val_data, val_data)
val_iter = torch.utils.data.DataLoader(
val_tensor,
batch_size=gParameters['batch_size'],
shuffle=gParameters['shuffle'])
# Test set
test_data = torch.from_numpy(X_test)
test_tensor = torch.utils.data.TensorDataset(test_data, test_data)
test_iter = torch.utils.data.DataLoader(
test_tensor,
batch_size=gParameters['batch_size'],
shuffle=gParameters['shuffle'])
#net = mx.sym.Variable('data')
#out = mx.sym.Variable('softmax_label')
input_dim = X_train.shape[1]
output_dim = input_dim
# Define Autoencoder architecture
layers = gParameters['dense']
activation = p1_common_pytorch.build_activation(gParameters['activation'])
loss_fn = p1_common_pytorch.get_function(gParameters['loss'])
'''
N1 = layers[0]
NE = layers[1]
net = nn.Sequential(
nn.Linear(input_dim,N1),
activation,
nn.Linear(N1,NE),
activation,
nn.Linear(NE,N1),
activation,
nn.Linear(N1,output_dim),
activation,
)
'''
# Documentation indicates this should work
net = nn.Sequential()
if layers != None:
if type(layers) != list:
layers = list(layers)
# Encoder Part
for i, l in enumerate(layers):
if i == 0:
net.add_module('in_dense', nn.Linear(input_dim, l))
net.add_module('in_act', activation)
insize = l
else:
net.add_module('en_dense%d' % i, nn.Linear(insize, l))
net.add_module('en_act%d' % i, activation)
insize = l
# Decoder Part
for i, l in reversed(list(enumerate(layers))):
if i < len(layers) - 1:
net.add_module('de_dense%d' % i, nn.Linear(insize, l))
net.add_module('de_act%d' % i, activation)
insize = l
net.add_module('out_dense', nn.Linear(insize, output_dim))
net.add_module('out_act', activation)
# Initialize weights
for m in net.modules():
if isinstance(m, nn.Linear):
p1_common_pytorch.build_initializer(m.weight,
gParameters['initialization'],
kerasDefaults)
p1_common_pytorch.build_initializer(m.bias, 'constant',
kerasDefaults, 0.0)
# Display model
print(net)
# Define context
# Define optimizer
optimizer = p1_common_pytorch.build_optimizer(net,
gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
# Seed random generator for training
torch.manual_seed(seed)
#use_gpu = torch.cuda.is_available()
use_gpu = 0
train_loss = 0
freq_log = 1
for epoch in range(gParameters['epochs']):
for batch, (in_train, _) in enumerate(train_iter):
in_train = Variable(in_train)
#print(in_train.data.shape())
if use_gpu:
in_train = in_train.cuda()
optimizer.zero_grad()
output = net(in_train)
loss = loss_fn(output, in_train)
loss.backward()
train_loss += loss.data[0]
optimizer.step()
if batch % freq_log == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch * len(in_train), len(train_iter.dataset),
100. * batch / len(train_iter),
loss.data[0])) # / len(in_train)))
print('====> Epoch: {} Average loss: {:.4f}'.format(
epoch, train_loss / len(train_iter.dataset)))
# model save
#save_filepath = "model_ae_" + ext
#ae.save(save_filepath)
# Evalute model on valdation set
for i, (in_val, _) in enumerate(val_iter):
in_val = Variable(in_val)
X_pred = net(in_val).data.numpy()
if i == 0:
in_all = in_val.data.numpy()
out_all = X_pred
else:
in_all = np.append(in_all, in_val.data.numpy(), axis=0)
out_all = np.append(out_all, X_pred, axis=0)
#print ("Shape in_all: ", in_all.shape)
#print ("Shape out_all: ", out_all.shape)
scores = p1b1.evaluate_autoencoder(in_all, out_all)
print('Evaluation on validation data:', scores)
# Evalute model on test set
for i, (in_test, _) in enumerate(test_iter):
in_test = Variable(in_test)
X_pred = net(in_test).data.numpy()
if i == 0:
in_all = in_test.data.numpy()
out_all = X_pred
else:
in_all = np.append(in_all, in_test.data.numpy(), axis=0)
out_all = np.append(out_all, X_pred, axis=0)
#print ("Shape in_all: ", in_all.shape)
#print ("Shape out_all: ", out_all.shape)
scores = p1b1.evaluate_autoencoder(in_all, out_all)
print('Evaluation on test data:', scores)
diff = in_all - out_all
plt.hist(diff.ravel(), bins='auto')
plt.title("Histogram of Errors with 'auto' bins")
plt.savefig('histogram_mx.pdf')
def main():
# Get command-line parameters
parser = get_p1b2_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = p1b2.read_config_file(args.config_file)
#print ('Params:', fileParameters)
# Consolidate parameter set. Command-line parameters overwrite file configuration
gParameters = p1_common.args_overwrite_config(args, fileParameters)
print('Params:', gParameters)
# Construct extension to save model
ext = p1b2.extension_from_parameters(gParameters, '.mx')
logfile = args.logfile if args.logfile else args.save + ext + '.log'
p1b2.logger.info('Params: {}'.format(gParameters))
# Get default parameters for initialization and optimizer functions
kerasDefaults = p1_common.keras_default_config()
seed = gParameters['rng_seed']
# Load dataset
#(X_train, y_train), (X_val, y_val), (X_test, y_test) = p1b2.load_data(gParameters, seed)
(X_train,
y_train), (X_val,
y_val), (X_test,
y_test) = p1b2.load_data_one_hot(gParameters, seed)
print("Shape X_train: ", X_train.shape)
print("Shape X_val: ", X_val.shape)
print("Shape X_test: ", X_test.shape)
print("Shape y_train: ", y_train.shape)
print("Shape y_val: ", y_val.shape)
print("Shape y_test: ", y_test.shape)
print("Range X_train --> Min: ", np.min(X_train), ", max: ",
np.max(X_train))
print("Range X_val --> Min: ", np.min(X_val), ", max: ", np.max(X_val))
print("Range X_test --> Min: ", np.min(X_test), ", max: ", np.max(X_test))
print("Range y_train --> Min: ", np.min(y_train), ", max: ",
np.max(y_train))
print("Range y_val --> Min: ", np.min(y_val), ", max: ", np.max(y_val))
print("Range y_test --> Min: ", np.min(y_test), ", max: ", np.max(y_test))
# Set input and target to X_train
train_iter = mx.io.NDArrayIter(X_train,
y_train,
gParameters['batch_size'],
shuffle=gParameters['shuffle'])
val_iter = mx.io.NDArrayIter(X_val, y_val, gParameters['batch_size'])
test_iter = mx.io.NDArrayIter(X_test, y_test, gParameters['batch_size'])
net = mx.sym.Variable('data') #X')
out = mx.sym.Variable('softmax_label') #y')
num_classes = y_train.shape[1]
# Initialize weights and learning rule
initializer_weights = p1_common_mxnet.build_initializer(
gParameters['initialization'], kerasDefaults)
initializer_bias = p1_common_mxnet.build_initializer(
'constant', kerasDefaults, 0.)
init = mx.initializer.Mixed(['bias', '.*'],
[initializer_bias, initializer_weights])
activation = gParameters['activation']
# Define MLP architecture
layers = gParameters['dense']
if layers != None:
if type(layers) != list:
layers = list(layers)
for i, l in enumerate(layers):
net = mx.sym.FullyConnected(data=net, num_hidden=l)
net = mx.sym.Activation(data=net, act_type=activation)
if gParameters['drop']:
net = mx.sym.Dropout(data=net, p=gParameters['drop'])
net = mx.sym.FullyConnected(data=net, num_hidden=num_classes) # 1)
net = mx.symbol.SoftmaxOutput(data=net, label=out)
# Display model
p1_common_mxnet.plot_network(net, 'net' + ext)
devices = mx.cpu()
if gParameters['gpus']:
devices = [mx.gpu(i) for i in gParameters['gpus']]
# Build MLP model
mlp = mx.mod.Module(symbol=net, context=devices)
# Define optimizer
optimizer = p1_common_mxnet.build_optimizer(gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
metric = p1_common_mxnet.get_function(gParameters['loss'])()
# Seed random generator for training
mx.random.seed(seed)
mlp.fit(
train_iter,
eval_data=val_iter,
# eval_metric=metric,
optimizer=optimizer,
num_epoch=gParameters['epochs'],
initializer=init)
# model save
#save_filepath = "model_mlp_" + ext
#mlp.save(save_filepath)
# Evalute model on test set
y_pred = mlp.predict(test_iter).asnumpy()
#print ("Shape y_pred: ", y_pred.shape)
scores = p1b2.evaluate_accuracy_one_hot(y_pred, y_test)
print('Evaluation on test data:', scores)
def main():
# Get command-line parameters
parser = get_p1b3_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = p1b3.read_config_file(args.config_file)
#print ('Params:', fileParameters)
# Consolidate parameter set. Command-line parameters overwrite file configuration
gParameters = p1_common.args_overwrite_config(args, fileParameters)
print('Params:', gParameters)
# Determine verbosity level
loggingLevel = logging.DEBUG if args.verbose else logging.INFO
logging.basicConfig(level=loggingLevel, format='')
# Construct extension to save model
ext = p1b3.extension_from_parameters(gParameters, '.neon')
# Get default parameters for initialization and optimizer functions
kerasDefaults = p1_common.keras_default_config()
seed = gParameters['rng_seed']
# Build dataset loader object
loader = p1b3.DataLoader(
seed=seed,
dtype=gParameters['datatype'],
val_split=gParameters['validation_split'],
test_cell_split=gParameters['test_cell_split'],
cell_features=gParameters['cell_features'],
drug_features=gParameters['drug_features'],
feature_subsample=gParameters['feature_subsample'],
scaling=gParameters['scaling'],
scramble=gParameters['scramble'],
min_logconc=gParameters['min_logconc'],
max_logconc=gParameters['max_logconc'],
subsample=gParameters['subsample'],
category_cutoffs=gParameters['category_cutoffs'])
net = mx.sym.Variable('concat_features')
out = mx.sym.Variable('growth')
# Initialize weights and learning rule
initializer_weights = p1_common_mxnet.build_initializer(
gParameters['initialization'], kerasDefaults)
initializer_bias = p1_common_mxnet.build_initializer(
'constant', kerasDefaults, 0.)
init = mx.initializer.Mixed(['bias', '.*'],
[initializer_bias, initializer_weights])
activation = gParameters['activation']
# Define model architecture
layers = []
reshape = None
if 'dense' in gParameters: # Build dense layers
for layer in gParameters['dense']:
if layer:
net = mx.sym.FullyConnected(data=net, num_hidden=layer)
net = mx.sym.Activation(data=net, act_type=activation)
if gParameters['drop']:
net = mx.sym.Dropout(data=net, p=gParameters['drop'])
else: # Build convolutional layers
net = mx.sym.Reshape(data=net,
shape=(gParameters['batch_size'], 1,
loader.input_dim, 1))
layer_list = list(range(0, len(args.convolution), 3))
for l, i in enumerate(layer_list):
nb_filter = gParameters['conv'][i]
filter_len = gParameters['conv'][i + 1]
stride = gParameters['conv'][i + 2]
if nb_filter <= 0 or filter_len <= 0 or stride <= 0:
break
net = mx.sym.Convolution(data=net,
num_filter=nb_filter,
kernel=(filter_len, 1),
stride=(stride, 1))
net = mx.sym.Activation(data=net, act_type=activation)
if gParameters['pool']:
net = mx.sym.Pooling(data=net,
pool_type="max",
kernel=(gParameters['pool'], 1),
stride=(1, 1))
net = mx.sym.Flatten(data=net)
reshape = (1, loader.input_dim, 1)
layer_list = list(range(0, len(gParameters['conv']), 3))
for l, i in enumerate(layer_list):
nb_filter = gParameters['conv'][i]
filter_len = gParameters['conv'][i + 1]
stride = gParameters['conv'][i + 2]
# print(nb_filter, filter_len, stride)
# fshape: (height, width, num_filters).
layers.append(
Conv((1, filter_len, nb_filter),
strides={
'str_h': 1,
'str_w': stride
},
init=initializer_weights,
activation=activation))
if gParameters['pool']:
layers.append(Pooling((1, gParameters['pool'])))
net = mx.sym.FullyConnected(data=net, num_hidden=1)
net = mx.symbol.LinearRegressionOutput(data=net, label=out)
# Display model
p1_common_mxnet.plot_network(net, 'net' + ext)
# Define mxnet data iterators
train_samples = int(loader.n_train)
val_samples = int(loader.n_val)
if 'train_samples' in gParameters:
train_samples = gParameters['train_samples']
if 'val_samples' in gParameters:
val_samples = gParameters['val_samples']
train_iter = ConcatDataIter(loader,
batch_size=gParameters['batch_size'],
num_data=train_samples)
val_iter = ConcatDataIter(loader,
partition='val',
batch_size=gParameters['batch_size'],
num_data=val_samples)
devices = mx.cpu()
if gParameters['gpus']:
devices = [mx.gpu(i) for i in gParameters['gpus']]
mod = mx.mod.Module(net,
data_names=('concat_features', ),
label_names=('growth', ),
context=devices)
# Define optimizer
optimizer = p1_common_mxnet.build_optimizer(gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
# Seed random generator for training
mx.random.seed(seed)
freq_log = 1
#initializer = mx.init.Xavier(factor_type="in", magnitude=2.34)
mod.fit(train_iter,
eval_data=val_iter,
eval_metric=gParameters['loss'],
optimizer=optimizer,
num_epoch=gParameters['epochs'],
initializer=init,
epoch_end_callback=mx.callback.Speedometer(
gParameters['batch_size'], 20))
def main():
# Get command-line parameters
parser = get_p1b2_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = p1b2.read_config_file(args.config_file)
#print ('Params:', fileParameters)
# Consolidate parameter set. Command-line parameters overwrite file configuration
gParameters = p1_common.args_overwrite_config(args, fileParameters)
print('Params:', gParameters)
# Construct extension to save model
ext = p1b2.extension_from_parameters(gParameters, '.keras')
logfile = args.logfile if args.logfile else args.save + ext + '.log'
p1b2.logger.info('Params: {}'.format(gParameters))
# Get default parameters for initialization and optimizer functions
kerasDefaults = p1_common.keras_default_config()
seed = gParameters['rng_seed']
# Load dataset
#(X_train, y_train), (X_test, y_test) = p1b2.load_data(gParameters, seed)
(X_train,
y_train), (X_val,
y_val), (X_test,
y_test) = p1b2.load_data_one_hot(gParameters, seed)
print("Shape X_train: ", X_train.shape)
print("Shape X_val: ", X_val.shape)
print("Shape X_test: ", X_test.shape)
print("Shape y_train: ", y_train.shape)
print("Shape y_val: ", y_val.shape)
print("Shape y_test: ", y_test.shape)
print("Range X_train --> Min: ", np.min(X_train), ", max: ",
np.max(X_train))
print("Range X_val --> Min: ", np.min(X_val), ", max: ", np.max(X_val))
print("Range X_test --> Min: ", np.min(X_test), ", max: ", np.max(X_test))
print("Range y_train --> Min: ", np.min(y_train), ", max: ",
np.max(y_train))
print("Range y_val --> Min: ", np.min(y_val), ", max: ", np.max(y_val))
print("Range y_test --> Min: ", np.min(y_test), ", max: ", np.max(y_test))
input_dim = X_train.shape[1]
input_vector = Input(shape=(input_dim, ))
output_dim = y_train.shape[1]
# Initialize weights and learning rule
initializer_weights = p1_common_keras.build_initializer(
gParameters['initialization'], kerasDefaults, seed)
initializer_bias = p1_common_keras.build_initializer(
'constant', kerasDefaults, 0.)
activation = gParameters['activation']
# Define MLP architecture
layers = gParameters['dense']
if layers != None:
if type(layers) != list:
layers = list(layers)
for i, l in enumerate(layers):
if i == 0:
x = Dense(l,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias,
kernel_regularizer=l2(gParameters['penalty']),
activity_regularizer=l2(
gParameters['penalty']))(input_vector)
else:
x = Dense(l,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias,
kernel_regularizer=l2(gParameters['penalty']),
activity_regularizer=l2(gParameters['penalty']))(x)
if gParameters['drop']:
x = Dropout(gParameters['drop'])(x)
output = Dense(output_dim,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(x)
else:
output = Dense(output_dim,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(input_vector)
# Build MLP model
mlp = Model(outputs=output, inputs=input_vector)
p1b2.logger.debug('Model: {}'.format(mlp.to_json()))
# Define optimizer
optimizer = p1_common_keras.build_optimizer(gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
# Compile and display model
mlp.compile(loss=gParameters['loss'],
optimizer=optimizer,
metrics=['accuracy'])
mlp.summary()
# Seed random generator for training
np.random.seed(seed)
mlp.fit(X_train,
y_train,
batch_size=gParameters['batch_size'],
epochs=gParameters['epochs'],
validation_data=(X_val, y_val))
# model save
#save_filepath = "model_mlp_W_" + ext
#mlp.save_weights(save_filepath)
# Evalute model on test set
y_pred = mlp.predict(X_test)
scores = p1b2.evaluate_accuracy_one_hot(y_pred, y_test)
print('Evaluation on test data:', scores)
def main():
# Get command-line parameters
parser = get_p1b1_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = p1b1.read_config_file(args.config_file)
#print ('Params:', fileParameters)
# Correct for arguments set by default by neon parser
# (i.e. instead of taking the neon parser default value fall back to the config file,
# if effectively the command-line was used, then use the command-line value)
# This applies to conflictive parameters: batch_size, epochs and rng_seed
if not any("--batch_size" in ag or "-z" in ag for ag in sys.argv):
args.batch_size = fileParameters['batch_size']
if not any("--epochs" in ag or "-e" in ag for ag in sys.argv):
args.epochs = fileParameters['epochs']
if not any("--rng_seed" in ag or "-r" in ag for ag in sys.argv):
args.rng_seed = fileParameters['rng_seed']
# Consolidate parameter set. Command-line parameters overwrite file configuration
gParameters = p1_common.args_overwrite_config(args, fileParameters)
print('Params:', gParameters)
# Determine verbosity level
loggingLevel = logging.DEBUG if args.verbose else logging.INFO
logging.basicConfig(level=loggingLevel, format='')
# Construct extension to save model
ext = p1b1.extension_from_parameters(gParameters, '.neon')
# Get default parameters for initialization and optimizer functions
kerasDefaults = p1_common.keras_default_config()
seed = gParameters['rng_seed']
# Load dataset
X_train, X_val, X_test = p1b1.load_data(gParameters, seed)
print("Shape X_train: ", X_train.shape)
print("Shape X_val: ", X_val.shape)
print("Shape X_test: ", X_test.shape)
print("Range X_train --> Min: ", np.min(X_train), ", max: ",
np.max(X_train))
print("Range X_val --> Min: ", np.min(X_val), ", max: ", np.max(X_val))
print("Range X_test --> Min: ", np.min(X_test), ", max: ", np.max(X_test))
input_dim = X_train.shape[1]
output_dim = input_dim
# Re-generate the backend after consolidating parsing and file config
gen_backend(backend=args.backend,
rng_seed=seed,
device_id=args.device_id,
batch_size=gParameters['batch_size'],
datatype=gParameters['datatype'],
max_devices=args.max_devices,
compat_mode=args.compat_mode)
# Set input and target to X_train
train = ArrayIterator(X_train)
val = ArrayIterator(X_val)
test = ArrayIterator(X_test)
# Initialize weights and learning rule
initializer_weights = p1_common_neon.build_initializer(
gParameters['initialization'], kerasDefaults)
initializer_bias = p1_common_neon.build_initializer(
'constant', kerasDefaults, 0.)
activation = p1_common_neon.get_function(gParameters['activation'])()
# Define Autoencoder architecture
layers = []
reshape = None
# Autoencoder
layers_params = gParameters['dense']
if layers_params != None:
if type(layers_params) != list:
layers_params = list(layers_params)
# Encoder Part
for i, l in enumerate(layers_params):
layers.append(
Affine(nout=l,
init=initializer_weights,
bias=initializer_bias,
activation=activation))
# Decoder Part
for i, l in reversed(list(enumerate(layers_params))):
if i < len(layers) - 1:
layers.append(
Affine(nout=l,
init=initializer_weights,
bias=initializer_bias,
activation=activation))
layers.append(
Affine(nout=output_dim,
init=initializer_weights,
bias=initializer_bias,
activation=activation))
# Build Autoencoder model
ae = Model(layers=layers)
# Define cost and optimizer
cost = GeneralizedCost(p1_common_neon.get_function(gParameters['loss'])())
optimizer = p1_common_neon.build_optimizer(gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
callbacks = Callbacks(ae, eval_set=val, eval_freq=1)
# Seed random generator for training
np.random.seed(seed)
ae.fit(train,
optimizer=optimizer,
num_epochs=gParameters['epochs'],
cost=cost,
callbacks=callbacks)
# model save
#save_fname = "model_ae_W" + ext
#ae.save_params(save_fname)
# Compute errors
X_pred = ae.get_outputs(test)
scores = p1b1.evaluate_autoencoder(X_pred, X_test)
print('Evaluation on test data:', scores)
diff = X_pred - X_test
# Plot histogram of errors comparing input and output of autoencoder
plt.hist(diff.ravel(), bins='auto')
plt.title("Histogram of Errors with 'auto' bins")
plt.savefig('histogram_neon.png')
def main():
# Get command-line parameters
parser = get_p1b2_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = p1b2.read_config_file(args.config_file)
#print ('Params:', fileParameters)
# Correct for arguments set by default by neon parser
# (i.e. instead of taking the neon parser default value fall back to the config file,
# if effectively the command-line was used, then use the command-line value)
# This applies to conflictive parameters: batch_size, epochs and rng_seed
if not any("--batch_size" in ag or "-z" in ag for ag in sys.argv):
args.batch_size = fileParameters['batch_size']
if not any("--epochs" in ag or "-e" in ag for ag in sys.argv):
args.epochs = fileParameters['epochs']
if not any("--rng_seed" in ag or "-r" in ag for ag in sys.argv):
args.rng_seed = fileParameters['rng_seed']
# Consolidate parameter set. Command-line parameters overwrite file configuration
gParameters = p1_common.args_overwrite_config(args, fileParameters)
print('Params:', gParameters)
# Determine verbosity level
loggingLevel = logging.DEBUG if args.verbose else logging.INFO
logging.basicConfig(level=loggingLevel, format='')
# Construct extension to save model
ext = p1b2.extension_from_parameters(gParameters, '.neon')
# Get default parameters for initialization and optimizer functions
kerasDefaults = p1_common.keras_default_config()
seed = gParameters['rng_seed']
# Load dataset
#(X_train, y_train), (X_test, y_test) = p1b2.load_data(gParameters, seed)
(X_train, y_train), (X_val,
y_val), (X_test,
y_test) = p1b2.load_data(gParameters, seed)
print("Shape X_train: ", X_train.shape)
print("Shape X_val: ", X_val.shape)
print("Shape X_test: ", X_test.shape)
print("Shape y_train: ", y_train.shape)
print("Shape y_val: ", y_val.shape)
print("Shape y_test: ", y_test.shape)
print("Range X_train --> Min: ", np.min(X_train), ", max: ",
np.max(X_train))
print("Range X_val --> Min: ", np.min(X_val), ", max: ", np.max(X_val))
print("Range X_test --> Min: ", np.min(X_test), ", max: ", np.max(X_test))
print("Range y_train --> Min: ", np.min(y_train), ", max: ",
np.max(y_train))
print("Range y_val --> Min: ", np.min(y_val), ", max: ", np.max(y_val))
print("Range y_test --> Min: ", np.min(y_test), ", max: ", np.max(y_test))
input_dim = X_train.shape[1]
num_classes = int(np.max(y_train)) + 1
output_dim = num_classes # The backend will represent the classes using one-hot representation (but requires an integer class as input !)
# Re-generate the backend after consolidating parsing and file config
gen_backend(backend=args.backend,
rng_seed=seed,
device_id=args.device_id,
batch_size=gParameters['batch_size'],
datatype=gParameters['data_type'],
max_devices=args.max_devices,
compat_mode=args.compat_mode)
train = ArrayIterator(X=X_train, y=y_train, nclass=num_classes)
val = ArrayIterator(X=X_val, y=y_val, nclass=num_classes)
test = ArrayIterator(X=X_test, y=y_test, nclass=num_classes)
# Initialize weights and learning rule
initializer_weights = p1_common_neon.build_initializer(
gParameters['initialization'], kerasDefaults, seed)
initializer_bias = p1_common_neon.build_initializer(
'constant', kerasDefaults, 0.)
activation = p1_common_neon.get_function(gParameters['activation'])()
# Define MLP architecture
layers = []
reshape = None
for layer in gParameters['dense']:
if layer:
layers.append(
Affine(nout=layer,
init=initializer_weights,
bias=initializer_bias,
activation=activation))
if gParameters['dropout']:
layers.append(Dropout(keep=(1 - gParameters['dropout'])))
layers.append(
Affine(nout=output_dim,
init=initializer_weights,
bias=initializer_bias,
activation=activation))
# Build MLP model
mlp = Model(layers=layers)
# Define cost and optimizer
cost = GeneralizedCost(p1_common_neon.get_function(gParameters['loss'])())
optimizer = p1_common_neon.build_optimizer(gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
callbacks = Callbacks(mlp, eval_set=val, metric=Accuracy(), eval_freq=1)
# Seed random generator for training
np.random.seed(seed)
mlp.fit(train,
optimizer=optimizer,
num_epochs=gParameters['epochs'],
cost=cost,
callbacks=callbacks)
# model save
#save_fname = "model_mlp_W_" + ext
#mlp.save_params(save_fname)
# Evalute model on test set
print('Model evaluation by neon: ', mlp.eval(test, metric=Accuracy()))
y_pred = mlp.get_outputs(test)
#print ("Shape y_pred: ", y_pred.shape)
scores = p1b2.evaluate_accuracy(p1_common.convert_to_class(y_pred), y_test)
print('Evaluation on test data:', scores)
def main():
# Get command-line parameters
parser = get_p1b1_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = p1b1.read_config_file(args.config_file)
#print ('Params:', fileParameters)
# Consolidate parameter set. Command-line parameters overwrite file configuration
gParameters = p1_common.args_overwrite_config(args, fileParameters)
print ('Params:', gParameters)
# Construct extension to save model
ext = p1b1.extension_from_parameters(gParameters, '.mx')
logfile = args.logfile if args.logfile else args.save+ext+'.log'
p1b1.logger.info('Params: {}'.format(gParameters))
# Get default parameters for initialization and optimizer functions
kerasDefaults = p1_common.keras_default_config()
seed = gParameters['rng_seed']
# Load dataset
X_train, X_val, X_test = p1b1.load_data(gParameters, seed)
print ("Shape X_train: ", X_train.shape)
print ("Shape X_val: ", X_val.shape)
print ("Shape X_test: ", X_test.shape)
print ("Range X_train --> Min: ", np.min(X_train), ", max: ", np.max(X_train))
print ("Range X_val --> Min: ", np.min(X_val), ", max: ", np.max(X_val))
print ("Range X_test --> Min: ", np.min(X_test), ", max: ", np.max(X_test))
# Set input and target to X_train
train_iter = mx.io.NDArrayIter(X_train, X_train, gParameters['batch_size'], shuffle=gParameters['shuffle'])
val_iter = mx.io.NDArrayIter(X_val, X_val, gParameters['batch_size'])
test_iter = mx.io.NDArrayIter(X_test, X_test, gParameters['batch_size'])
net = mx.sym.Variable('data')
out = mx.sym.Variable('softmax_label')
input_dim = X_train.shape[1]
output_dim = input_dim
# Initialize weights and learning rule
initializer_weights = p1_common_mxnet.build_initializer(gParameters['initialization'], kerasDefaults)
initializer_bias = p1_common_mxnet.build_initializer('constant', kerasDefaults, 0.)
init = mx.initializer.Mixed(['bias', '.*'], [initializer_bias, initializer_weights])
activation = gParameters['activation']
# Define Autoencoder architecture
layers = gParameters['dense']
if layers != None:
if type(layers) != list:
layers = list(layers)
# Encoder Part
for i,l in enumerate(layers):
net = mx.sym.FullyConnected(data=net, num_hidden=l)
net = mx.sym.Activation(data=net, act_type=activation)
# Decoder Part
for i,l in reversed( list(enumerate(layers)) ):
if i < len(layers)-1:
net = mx.sym.FullyConnected(data=net, num_hidden=l)
net = mx.sym.Activation(data=net, act_type=activation)
net = mx.sym.FullyConnected(data=net, num_hidden=output_dim)
#net = mx.sym.Activation(data=net, act_type=activation)
net = mx.symbol.LinearRegressionOutput(data=net, label=out)
# Display model
p1_common_mxnet.plot_network(net, 'net'+ext)
# Define context
devices = mx.cpu()
if gParameters['gpus']:
devices = [mx.gpu(i) for i in gParameters['gpus']]
# Build Autoencoder model
ae = mx.mod.Module(symbol=net, context=devices)
# Define optimizer
optimizer = p1_common_mxnet.build_optimizer(gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
# Seed random generator for training
mx.random.seed(seed)
freq_log = 1
ae.fit(train_iter, eval_data=val_iter,
eval_metric=gParameters['loss'],
optimizer=optimizer,
num_epoch=gParameters['epochs'])#,
#epoch_end_callback = mx.callback.Speedometer(gParameters['batch_size'], freq_log))
# model save
#save_filepath = "model_ae_" + ext
#ae.save(save_filepath)
# Evalute model on test set
X_pred = ae.predict(test_iter).asnumpy()
#print ("Shape X_pred: ", X_pred.shape)
scores = p1b1.evaluate_autoencoder(X_pred, X_test)
print('Evaluation on test data:', scores)
diff = X_pred - X_test
plt.hist(diff.ravel(), bins='auto')
plt.title("Histogram of Errors with 'auto' bins")
plt.savefig('histogram_mx.png')
def main():
# Get command-line parameters
parser = get_p1b3_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = p1b3.read_config_file(args.config_file)
#print ('Params:', fileParameters)
# Correct for arguments set by default by neon parser
# (i.e. instead of taking the neon parser default value fall back to the config file,
# if effectively the command-line was used, then use the command-line value)
# This applies to conflictive parameters: batch_size, epochs and rng_seed
if not any("--batch_size" in ag or "-z" in ag for ag in sys.argv):
args.batch_size = fileParameters['batch_size']
if not any("--epochs" in ag or "-e" in ag for ag in sys.argv):
args.epochs = fileParameters['epochs']
if not any("--rng_seed" in ag or "-r" in ag for ag in sys.argv):
args.rng_seed = fileParameters['rng_seed']
# Consolidate parameter set. Command-line parameters overwrite file configuration
gParameters = p1_common.args_overwrite_config(args, fileParameters)
print('Params:', gParameters)
# Determine verbosity level
loggingLevel = logging.DEBUG if args.verbose else logging.INFO
logging.basicConfig(level=loggingLevel, format='')
# Construct extension to save model
ext = p1b3.extension_from_parameters(gParameters, '.neon')
# Get default parameters for initialization and optimizer functions
kerasDefaults = p1_common.keras_default_config()
seed = gParameters['rng_seed']
# Build dataset loader object
loader = p1b3.DataLoader(
seed=seed,
dtype=gParameters['datatype'],
val_split=gParameters['validation_split'],
test_cell_split=gParameters['test_cell_split'],
cell_features=gParameters['cell_features'],
drug_features=gParameters['drug_features'],
feature_subsample=gParameters['feature_subsample'],
scaling=gParameters['scaling'],
scramble=gParameters['scramble'],
min_logconc=gParameters['min_logconc'],
max_logconc=gParameters['max_logconc'],
subsample=gParameters['subsample'],
category_cutoffs=gParameters['category_cutoffs'])
# Re-generate the backend after consolidating parsing and file config
gen_backend(backend=args.backend,
rng_seed=seed,
device_id=args.device_id,
batch_size=gParameters['batch_size'],
datatype=gParameters['datatype'],
max_devices=args.max_devices,
compat_mode=args.compat_mode)
# Initialize weights and learning rule
initializer_weights = p1_common_neon.build_initializer(
gParameters['initialization'], kerasDefaults, seed)
initializer_bias = p1_common_neon.build_initializer(
'constant', kerasDefaults, 0.)
activation = p1_common_neon.get_function(gParameters['activation'])()
# Define model architecture
layers = []
reshape = None
if 'dense' in gParameters: # Build dense layers
for layer in gParameters['dense']:
if layer:
layers.append(
Affine(nout=layer,
init=initializer_weights,
bias=initializer_bias,
activation=activation))
if gParameters['drop']:
layers.append(Dropout(keep=(1 - gParameters['drop'])))
else: # Build convolutional layers
reshape = (1, loader.input_dim, 1)
layer_list = list(range(0, len(gParameters['conv']), 3))
for l, i in enumerate(layer_list):
nb_filter = gParameters['conv'][i]
filter_len = gParameters['conv'][i + 1]
stride = gParameters['conv'][i + 2]
# print(nb_filter, filter_len, stride)
# fshape: (height, width, num_filters).
layers.append(
Conv((1, filter_len, nb_filter),
strides={
'str_h': 1,
'str_w': stride
},
init=initializer_weights,
activation=activation))
if gParameters['pool']:
layers.append(Pooling((1, gParameters['pool'])))
layers.append(
Affine(nout=1,
init=initializer_weights,
bias=initializer_bias,
activation=neon.transforms.Identity()))
# Build model
model = Model(layers=layers)
# Define neon data iterators
train_samples = int(loader.n_train)
val_samples = int(loader.n_val)
if 'train_samples' in gParameters:
train_samples = gParameters['train_samples']
if 'val_samples' in gParameters:
val_samples = gParameters['val_samples']
train_iter = ConcatDataIter(loader,
ndata=train_samples,
lshape=reshape,
datatype=gParameters['datatype'])
val_iter = ConcatDataIter(loader,
partition='val',
ndata=val_samples,
lshape=reshape,
datatype=gParameters['datatype'])
# Define cost and optimizer
cost = GeneralizedCost(p1_common_neon.get_function(gParameters['loss'])())
optimizer = p1_common_neon.build_optimizer(gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
callbacks = Callbacks(model, eval_set=val_iter,
eval_freq=1) #**args.callback_args)
model.fit(train_iter,
optimizer=optimizer,
num_epochs=gParameters['epochs'],
cost=cost,
callbacks=callbacks)
