def run(params):
args = candle.ArgumentStruct(**params)
seed = args.rng_seed
candle.set_seed(seed)
# Setting up random seed for reproducible and deterministic results
seed_random_state(args.rng_seed)
# check for sufficient number of epochs to start validation
if params['epochs'] < params['resp_val_start_epoch']:
raise Exception(
'Number of epochs is less than validation threshold (resp_val_start_epoch)'
)
# Construct extension to save validation results
now = datetime.datetime.now()
ext = '%02d%02d_%02d%02d_pytorch' \
% (now.month, now.day, now.hour, now.minute)
candle.verify_path(params['save_path'])
prefix = '{}{}'.format(params['save_path'], ext)
logfile = params['logfile'] if params['logfile'] else prefix + '.log'
candle.set_up_logger(logfile, unoMT.logger, params['verbose'])
unoMT.logger.info('Params: {}'.format(params))
# Computation device config (cuda or cpu)
use_cuda = not args.no_cuda and torch.cuda.is_available()
device = torch.device('cuda' if use_cuda else 'cpu')
modelUno = UnoMTModel(args, use_cuda, device)
modelUno.pre_train_config()
modelUno.train()
modelUno.print_final_stats()
def set_up_logger(logfile, logger1, logger2, verbose):
candle.verify_path(logfile)
fh = logging.FileHandler(logfile)
fh.setFormatter(
logging.Formatter("[%(asctime)s %(process)d] %(message)s",
datefmt="%Y-%m-%d %H:%M:%S"))
fh.setLevel(logging.DEBUG)
sh = logging.StreamHandler()
sh.setFormatter(logging.Formatter(''))
sh.setLevel(logging.DEBUG if verbose else logging.INFO)
for log in [logger1, logger2]:
log.setLevel(logging.DEBUG)
log.addHandler(fh)
log.addHandler(sh)
def run(gParameters):
# Construct extension to save model
ext = p1b2.extension_from_parameters(gParameters, '.keras')
candle.verify_path(gParameters['save_path'])
prefix = '{}{}'.format(gParameters['save_path'], ext)
logfile = gParameters['logfile'] if gParameters[
'logfile'] else prefix + '.log'
#candle.set_up_logger(logfile, p1b2.logger, gParameters['verbose'])
#p1b2.logger.info('Params: {}'.format(gParameters))
# Get default parameters for initialization and optimizer functions
kerasDefaults = candle.keras_default_config()
seed = gParameters['rng_seed']
# Load dataset
(X_train, y_train), (X_test, y_test) = p1b2.load_data2(gParameters, seed)
print("Shape X_test: ", X_test.shape)
print("Shape y_test: ", y_test.shape)
print("Range X_test --> Min: ", np.min(X_test), ", max: ", np.max(X_test))
print("Range y_test --> Min: ", np.min(y_test), ", max: ", np.max(y_test))
# Define optimizer
optimizer = candle.build_optimizer(gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
# load json and create model
json_file = open('p1b2.model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model_json = model_from_json(loaded_model_json)
# load weights into new model
loaded_model_json.load_weights('p1b2.model.h5')
print("Loaded model from disk")
# evaluate loaded model on test data
loaded_model_json.compile(loss=gParameters['loss'],
optimizer=optimizer,
metrics=['accuracy'])
y_pred = loaded_model_json.predict(X_test)
scores = p1b2.evaluate_accuracy_one_hot(y_pred, y_test)
print('Evaluation on test data:', scores)
def run(GP):
# set the seed
if GP['rng_seed']:
np.random.seed(GP['rng_seed'])
else:
np.random.seed(np.random.randint(10000))
# Set paths
if not os.path.isdir(GP['home_dir']):
print('Keras home directory not set')
sys.exit(0)
sys.path.append(GP['home_dir'])
# Setup loggin
args = candle.ArgumentStruct(**GP)
# set_seed(args.rng_seed)
# ext = extension_from_parameters(args)
candle.verify_path(args.save_path)
prefix = args.save_path # + ext
logfile = args.logfile if args.logfile else prefix + '.log'
candle.set_up_logger(logfile, logger, False) # args.verbose
logger.info('Params: {}'.format(GP))
import p2b1 as hf
reload(hf)
# import keras_model_utils as KEU
# reload(KEU)
# reload(p2ck)
# reload(p2ck.optimizers)
maps = hf.autoencoder_preprocess()
from keras.optimizers import SGD, RMSprop, Adam
from keras.datasets import mnist
from keras.callbacks import LearningRateScheduler, ModelCheckpoint
from keras import callbacks
from keras.layers.advanced_activations import ELU
from keras.preprocessing.image import ImageDataGenerator
# GP=hf.ReadConfig(opts.config_file)
batch_size = GP['batch_size']
learning_rate = GP['learning_rate']
kerasDefaults = candle.keras_default_config()
# #### Read Data ########
import helper
(data_files, fields) = p2b1.get_list_of_data_files(GP)
# Read from local directoy
# (data_files, fields) = helper.get_local_files('/p/gscratchr/brainusr/datasets/cancer/pilot2/3k_run16_10us.35fs-DPPC.20-DIPC.60-CHOL.20.dir/')
# (data_files, fields) = helper.get_local_files('3k_run16', '/p/lscratchf/brainusr/datasets/cancer/pilot2/')
# Define datagenerator
datagen = hf.ImageNoiseDataGenerator(corruption_level=GP['noise_factor'])
# get data dimension ##
num_samples = 0
for f in data_files:
# Seperate different arrays from the data
(X, nbrs, resnums) = helper.get_data_arrays(f)
num_samples += X.shape[0]
(X, nbrs, resnums) = helper.get_data_arrays(data_files[0])
print('\nData chunk shape: ', X.shape)
molecular_hidden_layers = GP['molecular_num_hidden']
if not molecular_hidden_layers:
X_train = hf.get_data(X, case=GP['case'])
input_dim = X_train.shape[1]
else:
# computing input dimension for outer AE
input_dim = X.shape[1] * molecular_hidden_layers[-1]
print('\nState AE input/output dimension: ', input_dim)
# get data dimension for molecular autoencoder
molecular_nbrs = np.int(GP['molecular_nbrs'])
num_molecules = X.shape[1]
num_beads = X.shape[2]
if GP['nbr_type'] == 'relative':
# relative x, y, z positions
num_loc_features = 3
loc_feat_vect = ['rel_x', 'rel_y', 'rel_z']
elif GP['nbr_type'] == 'invariant':
# relative distance and angle
num_loc_features = 2
loc_feat_vect = ['rel_dist', 'rel_angle']
else:
print('Invalid nbr_type!!')
exit()
if not GP['type_bool']:
# only consider molecular location coordinates
num_type_features = 0
type_feat_vect = []
else:
num_type_features = 5
type_feat_vect = list(fields.keys())[3:8]
num_features = num_loc_features + num_type_features + num_beads
dim = np.prod([num_beads, num_features, molecular_nbrs + 1])
bead_kernel_size = num_features
molecular_input_dim = dim
mol_kernel_size = num_beads
feature_vector = loc_feat_vect + type_feat_vect + list(fields.keys())[8:]
print('\nMolecular AE input/output dimension: ', molecular_input_dim)
print(
'\nData Format:\n[Frames (%s), Molecules (%s), Beads (%s), %s (%s)]' %
(num_samples, num_molecules, num_beads, feature_vector, num_features))
# ## Define Model, Solver and Compile ##########
print('\nDefine the model and compile')
opt = candle.build_optimizer(GP['optimizer'], learning_rate, kerasDefaults)
model_type = 'mlp'
memo = '%s_%s' % (GP['base_memo'], model_type)
# ####### Define Molecular Model, Solver and Compile #########
molecular_nonlinearity = GP['molecular_nonlinearity']
len_molecular_hidden_layers = len(molecular_hidden_layers)
conv_bool = GP['conv_bool']
full_conv_bool = GP['full_conv_bool']
if conv_bool:
molecular_model, molecular_encoder = AE_models.conv_dense_mol_auto(
bead_k_size=bead_kernel_size,
mol_k_size=mol_kernel_size,
weights_path=None,
input_shape=(1, molecular_input_dim, 1),
nonlinearity=molecular_nonlinearity,
hidden_layers=molecular_hidden_layers,
l2_reg=GP['l2_reg'],
drop=float(GP['dropout']))
elif full_conv_bool:
molecular_model, molecular_encoder = AE_models.full_conv_mol_auto(
bead_k_size=bead_kernel_size,
mol_k_size=mol_kernel_size,
weights_path=None,
input_shape=(1, molecular_input_dim, 1),
nonlinearity=molecular_nonlinearity,
hidden_layers=molecular_hidden_layers,
l2_reg=GP['l2_reg'],
drop=float(GP['dropout']))
else:
molecular_model, molecular_encoder = AE_models.dense_auto(
weights_path=None,
input_shape=(molecular_input_dim, ),
nonlinearity=molecular_nonlinearity,
hidden_layers=molecular_hidden_layers,
l2_reg=GP['l2_reg'],
drop=float(GP['dropout']))
if GP['loss'] == 'mse':
loss_func = 'mse'
elif GP['loss'] == 'custom':
loss_func = helper.combined_loss
molecular_model.compile(
optimizer=opt,
loss=loss_func,
metrics=['mean_squared_error', 'mean_absolute_error'])
print('\nModel Summary: \n')
molecular_model.summary()
# #### set up callbacks and cooling for the molecular_model ##########
drop = GP['dropout']
mb_epochs = GP['epochs']
initial_lrate = GP['learning_rate']
epochs_drop = 1 + int(np.floor(mb_epochs / 3))
def step_decay(epoch):
global initial_lrate, epochs_drop, drop
lrate = initial_lrate * np.power(drop,
np.floor((1 + epoch) / epochs_drop))
return lrate
lr_scheduler = LearningRateScheduler(step_decay)
history = callbacks.History()
# callbacks=[history,lr_scheduler]
history_logger = candle.LoggingCallback(logger.debug)
candleRemoteMonitor = candle.CandleRemoteMonitor(params=GP)
timeoutMonitor = candle.TerminateOnTimeOut(TIMEOUT)
callbacks = [history, history_logger, candleRemoteMonitor, timeoutMonitor]
loss = 0.
# ### Save the Model to disk
if GP['save_path'] is not None:
save_path = GP['save_path']
if not os.path.exists(save_path):
os.makedirs(save_path)
else:
save_path = '.'
model_json = molecular_model.to_json()
with open(save_path + '/model.json', "w") as json_file:
json_file.write(model_json)
encoder_json = molecular_encoder.to_json()
with open(save_path + '/encoder.json', "w") as json_file:
json_file.write(encoder_json)
print('Saved model to disk')
# ### Train the Model
if GP['train_bool']:
ct = hf.Candle_Molecular_Train(
molecular_model,
molecular_encoder,
data_files,
mb_epochs,
callbacks,
batch_size=batch_size,
nbr_type=GP['nbr_type'],
save_path=GP['save_path'],
len_molecular_hidden_layers=len_molecular_hidden_layers,
molecular_nbrs=molecular_nbrs,
conv_bool=conv_bool,
full_conv_bool=full_conv_bool,
type_bool=GP['type_bool'],
sampling_density=GP['sampling_density'])
frame_loss, frame_mse = ct.train_ac()
else:
frame_mse = []
frame_loss = []
return frame_loss, frame_mse
def run(params):
args = candle.ArgumentStruct(**params)
candle.set_seed(args.rng_seed)
ext = uno.extension_from_parameters(args)
candle.verify_path(args.save_path)
prefix = args.save_path + ext
logfile = args.logfile if args.logfile else prefix + '.log'
uno.set_up_logger(logfile, logger, uno.loggerUno, args.verbose)
logger.info('Params: {}'.format(params))
loader = uno_combined_data_loader.CombinedDataLoader(args.rng_seed)
loader.load(cache=args.cache,
ncols=args.feature_subsample,
agg_dose=args.agg_dose,
cell_features=args.cell_features,
drug_features=args.drug_features,
drug_median_response_min=args.drug_median_response_min,
drug_median_response_max=args.drug_median_response_max,
use_landmark_genes=args.use_landmark_genes,
use_filtered_genes=args.use_filtered_genes,
cell_feature_subset_path=args.cell_feature_subset_path
or args.feature_subset_path,
drug_feature_subset_path=args.drug_feature_subset_path
or args.feature_subset_path,
preprocess_rnaseq=args.preprocess_rnaseq,
single=args.single,
train_sources=args.train_sources,
test_sources=args.test_sources,
embed_feature_source=not args.no_feature_source,
encode_response_source=not args.no_response_source,
partition_by=args.partition_by)
target = args.agg_dose or 'Growth'
val_split = args.val_split
train_split = 1 - val_split
loader.partition_data(partition_by=args.partition_by,
cv_folds=args.cv,
train_split=train_split,
val_split=val_split,
cell_types=args.cell_types,
by_cell=args.by_cell,
by_drug=args.by_drug,
cell_subset_path=args.cell_subset_path,
drug_subset_path=args.drug_subset_path)
print('partition_by: ', args.partition_by)
if args.partition_by == 'drug_pair':
fname_drugs = args.save_path + 'infer_drug_ids'
pds = loader.get_drugs_in_val()
with open(fname_drugs, 'w') as f:
for item in pds:
f.write('%s\n' % item)
logger.info(
'Drug IDs in holdout set written in file: {}'.format(fname_drugs))
elif args.partition_by == 'cell':
fname_cells = args.save_path + 'infer_cell_ids'
pcs = loader.get_cells_in_val()
with open(fname_cells, 'w') as f:
for item in pcs:
f.write('%s\n' % item)
logger.info(
'Cell IDs in holdout set written in file: {}'.format(fname_cells))
else: #
fname_index = args.save_path + 'infer_index_ids'
pins = loader.get_index_in_val()
with open(fname_index, 'w') as f:
for item in pins:
f.write('%s\n' % item)
logger.info(
'Indices in holdout set written in file: {}'.format(fname_index))
def run(gParameters):
# Construct extension to save model
ext = p1b2.extension_from_parameters(gParameters, '.keras')
candle.verify_path(gParameters['save_path'])
prefix = '{}{}'.format(gParameters['save_path'], ext)
logfile = gParameters['logfile'] if gParameters[
'logfile'] else prefix + '.log'
candle.set_up_logger(logfile, p1b2.logger, gParameters['verbose'])
p1b2.logger.info('Params: {}'.format(gParameters))
# Get default parameters for initialization and optimizer functions
kerasDefaults = candle.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)
(X_train, y_train), (X_test, y_test) = p1b2.load_data2(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 = candle.build_initializer(
gParameters['initialization'], kerasDefaults, seed)
initializer_bias = candle.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['reg_l2']),
activity_regularizer=l2(
gParameters['reg_l2']))(input_vector)
else:
x = Dense(l,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias,
kernel_regularizer=l2(gParameters['reg_l2']),
activity_regularizer=l2(gParameters['reg_l2']))(x)
if gParameters['dropout']:
x = Dropout(gParameters['dropout'])(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 = candle.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)
history = mlp.fit(X_train,
y_train,
batch_size=gParameters['batch_size'],
epochs=gParameters['epochs'],
validation_split=gParameters['val_split']
#validation_data=(X_val, y_val)
)
best_val_loss = "{:.5f}".format(min(history.history['val_loss']))
best_val_acc = "{:.5f}".format(max(history.history['val_acc']))
print('best_val_loss =', best_val_loss, 'best_val_acc =', best_val_acc)
# model save
# save_filepath = "model_mlp_W_" + ext
# mlp.save_weights(save_filepath)
model_json = mlp.to_json()
with open(prefix + '.model.json', 'w') as f:
print(model_json, file=f)
mlp.save_weights(prefix + '.weights.h5')
# 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 run(params):
args = candle.ArgumentStruct(**params)
seed = args.rng_seed
candle.set_seed(seed)
# Construct extension to save model
ext = extension_from_parameters(params, 'keras')
candle.verify_path(params['save_path'])
prefix = '{}{}'.format(params['save_path'], ext)
logfile = params['logfile'] if params['logfile'] else prefix+'.log'
root_fname = 'Agg_attn_abs_bin'
candle.set_up_logger(logfile, attn.logger, params['verbose'])
attn.logger.info('Params: {}'.format(params))
# Get default parameters for initialization and optimizer functions
keras_defaults = candle.keras_default_config()
##
X_train, _Y_train, X_val, _Y_val, X_test, _Y_test = attn.load_data(params, seed)
# move this inside the load_data function
Y_train = _Y_train['AUC']
Y_test = _Y_test['AUC']
Y_val = _Y_val['AUC']
Y_train_neg, Y_train_pos = np.bincount(Y_train)
Y_test_neg, Y_test_pos = np.bincount(Y_test)
Y_val_neg, Y_val_pos = np.bincount(Y_val)
Y_train_total = Y_train_neg + Y_train_pos
Y_test_total = Y_test_neg + Y_test_pos
Y_val_total = Y_val_neg + Y_val_pos
total = Y_train_total + Y_test_total + Y_val_total
neg = Y_train_neg + Y_test_neg + Y_val_neg
pos = Y_train_pos + Y_test_pos + Y_val_pos
print('Examples:\n Total: {}\n Positive: {} ({:.2f}% of total)\n'.format(
total, pos, 100 * pos / total))
nb_classes = params['dense'][-1]
# Convert classes to categorical with an extra slot for the abstaining class
Y_train, Y_test, Y_val = candle.modify_labels(nb_classes+1, Y_train, Y_test, Y_val)
# Disable class weight (for initial testing of the abstention classifier)
#y_integers = np.argmax(Y_train, axis=1)
#class_weights = compute_class_weight('balanced', np.unique(y_integers), y_integers)
#d_class_weights = dict(enumerate(class_weights))
print('X_train shape:', X_train.shape)
print('X_test shape:', X_test.shape)
print('Y_train shape:', Y_train.shape)
print('Y_test shape:', Y_test.shape)
PS = X_train.shape[1]
model = build_attention_model(params, PS)
model = candle.add_model_output(model, mode='abstain', num_add=1, activation='sigmoid')
print('Model after modifying layer for abstention')
model.summary()
# Configure abstention model
mask_ = np.zeros(nb_classes+1)
mask_[-1] = 1
mu0 = 0.5 # In the long term this is not as important since mu auto tunes, however it may require a large number of epochs to converge if set far away from target
candle.abstention_variable_initialization(mu0, mask_, nb_classes)
#parallel_model = multi_gpu_model(model, gpus=4)
#parallel_model.compile(loss='mean_squared_error',
# optimizer=SGD(lr=0.0001, momentum=0.9),
# metrics=['mae',r2])
kerasDefaults = candle.keras_default_config()
if params['momentum']:
kerasDefaults['momentum_sgd'] = params['momentum']
optimizer = candle.build_optimizer(params['optimizer'], params['learning_rate'], kerasDefaults)
# compile model with abstention loss
model.compile(loss=candle.abstention_loss, optimizer=optimizer, metrics=['acc',tf_auc,candle.abs_acc,candle.acc_class1,candle.abs_acc_class1])
# set up a bunch of callbacks to do work during model training..
checkpointer = ModelCheckpoint(filepath=params['save_path'] + root_fname + '.autosave.model.h5', verbose=1, save_weights_only=False, save_best_only=True)
csv_logger = CSVLogger('{}/{}.training.log'.format(params['save_path'], root_fname))
reduce_lr = ReduceLROnPlateau(monitor='val_tf_auc', factor=0.20, patience=40, verbose=1, mode='auto', min_delta=0.0001, cooldown=3, min_lr=0.000000001)
early_stop = EarlyStopping(monitor='val_tf_auc', patience=200, verbose=1, mode='auto')
candle_monitor = candle.CandleRemoteMonitor(params=params)
candle_monitor = candle.CandleRemoteMonitor(params=params)
timeout_monitor = candle.TerminateOnTimeOut(params['timeout'])
tensorboard = TensorBoard(log_dir="tb/tb{}".format(ext))
history_logger = candle.LoggingCallback(attn.logger.debug)
abstention_cbk = candle.AbstentionAdapt_Callback(monitor='val_abs_acc_class1', scale_factor=params['abs_scale_factor'], target_acc=params['target_abs_acc'])
callbacks = [candle_monitor, timeout_monitor, csv_logger, history_logger, abstention_cbk]
if params['reduce_lr']:
callbacks.append(reduce_lr)
if params['use_cp']:
callbacks.append(checkpointer)
if params['use_tb']:
callbacks.append(tensorboard)
if params['early_stop']:
callbacks.append(early_stop)
epochs = params['epochs']
batch_size=params['batch_size']
history = model.fit(X_train, Y_train, #class_weight=d_class_weights,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(X_val, Y_val),
callbacks = callbacks)
# diagnostic plots
if 'loss' in history.history.keys():
candle.plot_history(params['save_path'] + root_fname, history, 'loss')
if 'acc' in history.history.keys():
candle.plot_history(params['save_path'] + root_fname, history, 'acc')
if 'abs_acc' in history.history.keys():
candle.plot_history(params['save_path'] + root_fname, history, 'abs_acc')
# Plot mu evolution
fname = params['save_path'] + root_fname + '.mu.png'
xlabel='Epochs'
ylabel='Abstention Weight mu'
title='mu Evolution'
attnviz.plot_array(abstention_cbk.muvalues, xlabel, ylabel, title, fname)
# Evaluate model
score = model.evaluate(X_test, Y_test, verbose=0)
Y_predict = model.predict(X_test)
evaluate_abstention(params, root_fname, nb_classes, Y_test, _Y_test, Y_predict, pos, total, score)
save_and_test_saved_model(params, model, root_fname, X_train, X_test, Y_test)
attn.logger.handlers = []
return history
def run(params):
args = candle.ArgumentStruct(**params)
candle.set_seed(args.rng_seed)
ext = uno.extension_from_parameters(args)
candle.verify_path(args.save_path)
prefix = args.save_path + 'uno' + ext
logfile = args.logfile if args.logfile else prefix+'.log'
uno.set_up_logger(logfile, logger, uno.loggerUno, args.verbose)
logger.info('Params: {}'.format(params))
# Exclude drugs / cells for UQ
if 'uq_exclude_drugs_file' in params.keys():
args.exclude_drugs = uno.read_IDs_file(args.uq_exclude_drugs_file)
logger.info('Drugs to exclude: {}'.format(args.exclude_drugs))
else:
args.exclude_drugs = []
if 'uq_exclude_cells_file' in params.keys():
args.exclude_cells = uno.read_IDs_file(args.uq_exclude_cells_file)
logger.info('Cells to exclude: {}'.format(args.exclude_cells))
else:
args.exclude_cells = []
if 'uq_exclude_indices_file' in params.keys():
exclude_indices_ = uno.read_IDs_file(args.uq_exclude_indices_file)
args.exclude_indices = [int(x) for x in exclude_indices_]
logger.info('Indices to exclude: {}'.format(args.exclude_indices))
else:
args.exclude_indices = []
if (len(args.gpus) > 0):
import tensorflow as tf
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.gpu_options.visible_device_list = ",".join(map(str, args.gpus))
K.set_session(tf.Session(config=config))
loader = uno_combined_data_loader.CombinedDataLoader(seed=args.rng_seed)
loader.load(cache=args.cache,
ncols=args.feature_subsample,
agg_dose=args.agg_dose,
cell_features=args.cell_features,
drug_features=args.drug_features,
drug_median_response_min=args.drug_median_response_min,
drug_median_response_max=args.drug_median_response_max,
use_landmark_genes=args.use_landmark_genes,
use_filtered_genes=args.use_filtered_genes,
cell_feature_subset_path=args.cell_feature_subset_path or args.feature_subset_path,
drug_feature_subset_path=args.drug_feature_subset_path or args.feature_subset_path,
preprocess_rnaseq=args.preprocess_rnaseq,
single=args.single,
train_sources=args.train_sources,
test_sources=args.test_sources,
embed_feature_source=not args.no_feature_source,
encode_response_source=not args.no_response_source,
)
target = args.agg_dose or 'Growth'
val_split = args.val_split
train_split = 1 - val_split
loader.partition_data(partition_by=args.partition_by,
cv_folds=args.cv, train_split=train_split, val_split=val_split,
cell_types=args.cell_types, by_cell=args.by_cell, by_drug=args.by_drug,
cell_subset_path=args.cell_subset_path,
drug_subset_path=args.drug_subset_path,
exclude_cells=args.exclude_cells,
exclude_drugs=args.exclude_drugs,
exclude_indices=args.exclude_indices
)
model = uno_model_utils.build_model(loader, args, logger)
logger.info('Combined model:')
model.summary(print_fn=logger.info)
# plot_model(model, to_file=prefix+'.model.png', show_shapes=True)
if args.cp:
model_json = model.to_json()
with open(prefix+'.model.json', 'w') as f:
print(model_json, file=f)
def warmup_scheduler(epoch):
lr = args.learning_rate or base_lr * args.batch_size/100
if epoch <= 5:
K.set_value(model.optimizer.lr, (base_lr * (5-epoch) + lr * epoch) / 5)
logger.debug('Epoch {}: lr={:.5g}'.format(epoch, K.get_value(model.optimizer.lr)))
return K.get_value(model.optimizer.lr)
df_pred_list = []
cv_ext = ''
cv = args.cv if args.cv > 1 else 1
for fold in range(cv):
if args.cv > 1:
logger.info('Cross validation fold {}/{}:'.format(fold+1, cv))
cv_ext = '.cv{}'.format(fold+1)
# model = uno_model_utils.build_model(loader, args, logger, silent=True)
template_model = uno_model_utils.build_model(loader, args, logger, silent=True)
if args.initial_weights:
logger.info("Loading weights from {}".format(args.initial_weights))
template_model.load_weights(args.initial_weights)
if len(args.gpus) > 1:
from keras.utils import multi_gpu_model
gpu_count = len(args.gpus)
logger.info("Multi GPU with {} gpus".format(gpu_count))
model = multi_gpu_model(template_model, cpu_merge=False, gpus=gpu_count)
else:
model = template_model
optimizer = optimizers.deserialize({'class_name': args.optimizer, 'config': {}})
base_lr = args.base_lr or K.get_value(optimizer.lr)
if args.learning_rate:
K.set_value(optimizer.lr, args.learning_rate)
if args.loss == 'heteroscedastic':
logger.info('Training heteroscedastic model:')
model.compile(loss=heteroscedastic_loss, optimizer=optimizer, metrics=[uno_model_utils.mae_heteroscedastic, uno_model_utils.r2_heteroscedastic, uno_model_utils.meanS_heteroscesdastic])
elif args.loss == 'quantile':
logger.info('Training quantile model:')
model.compile(loss=triple_quantile_loss, optimizer=optimizer, metrics=[uno_model_utils.quantile50, uno_model_utils.quantile10, uno_model_utils.quantile90])
else:
logger.info('Training homoscedastic model:')
model.compile(loss=args.loss, optimizer=optimizer, metrics=[candle.mae, candle.r2])
# calculate trainable and non-trainable params
params.update(candle.compute_trainable_params(model))
candle_monitor = candle.CandleRemoteMonitor(params=params)
timeout_monitor = candle.TerminateOnTimeOut(params['timeout'])
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=5, min_lr=0.00001)
warmup_lr = LearningRateScheduler(warmup_scheduler)
#checkpointer = ModelCheckpoint(prefix+cv_ext+'.weights.h5', save_best_only=True, save_weights_only=True)
checkpointer = candle.MultiGPUCheckpoint(prefix + cv_ext + '.model.h5', save_best_only=True)
tensorboard = TensorBoard(log_dir="tb/{}{}{}".format(args.tb_prefix, ext, cv_ext))
history_logger = candle.LoggingCallback(logger.debug)
# model_recorder = uno_model_utils.ModelRecorder()
# callbacks = [history_logger, model_recorder]
callbacks = [candle_monitor, timeout_monitor, history_logger]#, model_recorder]
if args.reduce_lr:
callbacks.append(reduce_lr)
if args.warmup_lr:
callbacks.append(warmup_lr)
if args.cp:
callbacks.append(checkpointer)
if args.tb:
callbacks.append(tensorboard)
if args.save_weights:
callbacks.append(uno_model_utils.SimpleWeightSaver(args.save_path + '/' + args.save_weights))
train_gen = uno_combined_data_generator.CombinedDataGenerator(loader, fold=fold, batch_size=args.batch_size, shuffle=args.shuffle)
val_gen = uno_combined_data_generator.CombinedDataGenerator(loader, partition='val', fold=fold, batch_size=args.batch_size, shuffle=args.shuffle)
df_val = val_gen.get_response(copy=True)
y_val = df_val[target].values
y_shuf = np.random.permutation(y_val)
uno.log_evaluation(uno.evaluate_prediction(y_val, y_shuf), logger,
description='Between random pairs in y_val:')
if args.no_gen:
x_train_list, y_train = train_gen.get_slice(size=train_gen.size, single=args.single)
x_val_list, y_val = val_gen.get_slice(size=val_gen.size, single=args.single)
history = model.fit(x_train_list, y_train,
batch_size=args.batch_size,
epochs=args.epochs,
callbacks=callbacks,
validation_data=(x_val_list, y_val))
else:
logger.info('Data points per epoch: train = %d, val = %d',train_gen.size, val_gen.size)
logger.info('Steps per epoch: train = %d, val = %d',train_gen.steps, val_gen.steps)
history = model.fit_generator(train_gen, train_gen.steps,
epochs=args.epochs,
callbacks=callbacks,
validation_data=val_gen,
validation_steps=val_gen.steps)
# if args.cp:
# model.load_weights(prefix+cv_ext+'.weights.h5')
# model = model_recorder.best_model
if args.no_gen:
y_val_pred = model.predict(x_val_list, batch_size=args.batch_size)
else:
val_gen.reset()
y_val_pred = model.predict_generator(val_gen, val_gen.steps + 1)
y_val_pred = y_val_pred[:val_gen.size]
if args.loss == 'heteroscedastic':
y_val_pred_ = y_val_pred[:,0]
s_val_pred = y_val_pred[:,1]
y_val_pred = y_val_pred_.flatten()
df_val['Predicted_'+target] = y_val_pred
df_val[target+'_Error'] = y_val_pred-y_val
df_val['Pred_S_'+target] = s_val_pred
elif args.loss == 'quantile':
y_val_pred_50q = y_val_pred[:,0]
y_val_pred_10q = y_val_pred[:,1]
y_val_pred_90q = y_val_pred[:,2]
y_val_pred = y_val_pred_50q.flatten() # 50th quantile prediction
df_val['Predicted_50q_'+target] = y_val_pred
df_val[target+'_Error_50q'] = y_val_pred-y_val
df_val['Predicted_10q_'+target] = y_val_pred_10q.flatten()
df_val['Predicted_90q_'+target] = y_val_pred_90q.flatten()
else:
y_val_pred = y_val_pred.flatten()
# df_val = df_val.assign(PredictedGrowth=y_val_pred, GrowthError=y_val_pred-y_val)
df_val['Predicted'+target] = y_val_pred
df_val[target+'Error'] = y_val_pred-y_val
scores = uno.evaluate_prediction(y_val, y_val_pred)
uno.log_evaluation(scores, logger)
df_pred_list.append(df_val)
# if args.cp:
# model_recorder.best_model.save(prefix+'.model.h5')
if hasattr(history, 'loss'):
candle.plot_history(prefix, history, 'loss')
if args.loss == 'heteroscedastic':
if hasattr(history, 'r2_heteroscedastic'):
candle.plot_history(prefix, history, 'r2_heteroscedastic')
if hasattr(history, 'meanS_heteroscedastic'):
candle.plot_history(prefix, history, 'meanS_heteroscesdastic')
elif args.loss == 'quantile':
if hasattr(history, 'quantile50'):
candle.plot_history(prefix, history, 'quantile50')
if hasattr(history, 'quantile10'):
candle.plot_history(prefix, history, 'quantile10')
if hasattr(history, 'quantile90'):
candle.plot_history(prefix, history, 'quantile90')
else:
if hasattr(history, 'r2'):
candle.plot_history(prefix, history, 'r2')
pred_fname = prefix + '.predicted.tsv'
df_pred = pd.concat(df_pred_list)
if args.agg_dose:
if args.single:
# df_pred.sort_values(['Source', 'Sample', 'Drug1', target], inplace=True)
df_pred.sort_values(['Sample', 'Drug1', target], inplace=True)
else:
df_pred.sort_values(['Source', 'Sample', 'Drug1', 'Drug2', target], inplace=True)
else:
if args.single:
# df_pred.sort_values(['Source', 'Sample', 'Drug1', 'Dose1', 'Growth'], inplace=True)
df_pred.sort_values(['Sample', 'Drug1', 'Dose1', 'Growth'], inplace=True)
else:
# df_pred.sort_values(['Source', 'Sample', 'Drug1', 'Drug2', 'Dose1', 'Dose2', 'Growth'], inplace=True)
df_pred.sort_values(['Sample', 'Drug1', 'Drug2', 'Dose1', 'Dose2', 'Growth'], inplace=True)
df_pred.to_csv(pred_fname, sep='\t', index=False, float_format='%.4g')
logger.info('Testing predictions stored in file: {}'.format(pred_fname))
if args.cp:
logger.info('Model stored in file: {}'.format(prefix+'.model.h5'))
# logger.info('Model weights stored in file: {}'.format(prefix+cv_ext+'.weights.h5'))
logger.info('Model weights stored in file: {}'.format(args.save_path + '/' + args.save_weights))
if args.cv > 1:
scores = uno.evaluate_prediction(df_pred[target], df_pred['Predicted'+target])
uno.log_evaluation(scores, logger, description='Combining cross validation folds:')
for test_source in loader.test_sep_sources:
test_gen = uno_combined_data_generator.CombinedDataGenerator(loader, partition='test', batch_size=args.batch_size, source=test_source)
df_test = test_gen.get_response(copy=True)
y_test = df_test[target].values
n_test = len(y_test)
if n_test == 0:
continue
if args.no_gen:
x_test_list, y_test = test_gen.get_slice(size=test_gen.size, single=args.single)
y_test_pred = model.predict(x_test_list, batch_size=args.batch_size)
if args.loss == 'heteroscedastic':
y_test_pred = y_test_pred[:,0]
elif args.loss == 'quantile':
y_test_pred = y_test_pred[:,0] # 50th quantile prediction
else:
y_test_pred = model.predict_generator(test_gen.flow(single=args.single), test_gen.steps)
if args.loss == 'heteroscedastic':
y_test_pred = y_test_pred[:test_gen.size,0]
elif args.loss == 'quantile':
y_test_pred = y_test_pred[:test_gen.size,0] # 50th quantile prediction
else:
y_test_pred = y_test_pred[:test_gen.size]
y_test_pred = y_test_pred.flatten()
scores = uno.evaluate_prediction(y_test, y_test_pred)
uno.log_evaluation(scores, logger, description='Testing on data from {} ({})'.format(test_source, n_test))
if K.backend() == 'tensorflow':
K.clear_session()
logger.handlers = []
return history
def run(params):
args = candle.ArgumentStruct(**params)
seed = args.rng_seed
candle.set_seed(seed)
# Construct extension to save model
ext = p1b1.extension_from_parameters(params, '.keras')
candle.verify_path(params['save_path'])
prefix = '{}{}'.format(params['save_path'], ext)
logfile = params['logfile'] if params['logfile'] else prefix+'.log'
candle.set_up_logger(logfile, p1b1.logger, params['verbose'])
p1b1.logger.info('Params: {}'.format(params))
# Get default parameters for initialization and optimizer functions
keras_defaults = candle.keras_default_config()
# Load dataset
x_train, y_train, x_val, y_val, x_test, y_test, x_labels, y_labels = p1b1.load_data(params, seed)
# cache_file = 'data_l1000_cache.h5'
# save_cache(cache_file, x_train, y_train, x_val, y_val, x_test, y_test, x_labels, y_labels)
# x_train, y_train, x_val, y_val, x_test, y_test, x_labels, y_labels = load_cache(cache_file)
p1b1.logger.info("Shape x_train: {}".format(x_train.shape))
p1b1.logger.info("Shape x_val: {}".format(x_val.shape))
p1b1.logger.info("Shape x_test: {}".format(x_test.shape))
p1b1.logger.info("Range x_train: [{:.3g}, {:.3g}]".format(np.min(x_train), np.max(x_train)))
p1b1.logger.info("Range x_val: [{:.3g}, {:.3g}]".format(np.min(x_val), np.max(x_val)))
p1b1.logger.info("Range x_test: [{:.3g}, {:.3g}]".format(np.min(x_test), np.max(x_test)))
p1b1.logger.debug('Class labels')
for i, label in enumerate(y_labels):
p1b1.logger.debug(' {}: {}'.format(i, label))
# clf = build_type_classifier(x_train, y_train, x_val, y_val)
n_classes = len(y_labels)
cond_train = y_train
cond_val = y_val
cond_test = y_test
input_dim = x_train.shape[1]
cond_dim = cond_train.shape[1]
latent_dim = params['latent_dim']
activation = params['activation']
dropout = params['dropout']
dense_layers = params['dense']
dropout_layer = AlphaDropout if params['alpha_dropout'] else Dropout
# Initialize weights and learning rule
initializer_weights = candle.build_initializer(params['initialization'], keras_defaults, seed)
initializer_bias = candle.build_initializer('constant', keras_defaults, 0.)
if dense_layers is not None:
if type(dense_layers) != list:
dense_layers = list(dense_layers)
else:
dense_layers = []
# Encoder Part
x_input = Input(shape=(input_dim,))
cond_input = Input(shape=(cond_dim,))
h = x_input
if params['model'] == 'cvae':
h = keras.layers.concatenate([x_input, cond_input])
for i, layer in enumerate(dense_layers):
if layer > 0:
x = h
h = Dense(layer, activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(h)
if params['residual']:
try:
h = keras.layers.add([h, x])
except ValueError:
pass
if params['batch_normalization']:
h = BatchNormalization()(h)
if dropout > 0:
h = dropout_layer(dropout)(h)
if params['model'] == 'ae':
encoded = Dense(latent_dim, activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(h)
else:
epsilon_std = params['epsilon_std']
z_mean = Dense(latent_dim, name='z_mean')(h)
z_log_var = Dense(latent_dim, name='z_log_var')(h)
encoded = z_mean
def vae_loss(x, x_decoded_mean):
xent_loss = binary_crossentropy(x, x_decoded_mean)
kl_loss = - 0.5 * K.sum(1 + z_log_var - K.square(z_mean) - K.exp(z_log_var), axis=-1)
return K.mean(xent_loss + kl_loss/input_dim)
def sampling(params):
z_mean_, z_log_var_ = params
batch_size = K.shape(z_mean_)[0]
epsilon = K.random_normal(shape=(batch_size, latent_dim),
mean=0., stddev=epsilon_std)
return z_mean_ + K.exp(z_log_var_ / 2) * epsilon
z = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_log_var])
if params['model'] == 'cvae':
z_cond = keras.layers.concatenate([z, cond_input])
# Decoder Part
decoder_input = Input(shape=(latent_dim,))
h = decoder_input
if params['model'] == 'cvae':
h = keras.layers.concatenate([decoder_input, cond_input])
for i, layer in reversed(list(enumerate(dense_layers))):
if layer > 0:
x = h
h = Dense(layer, activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(h)
if params['residual']:
try:
h = keras.layers.add([h, x])
except ValueError:
pass
if params['batch_normalization']:
h = BatchNormalization()(h)
if dropout > 0:
h = dropout_layer(dropout)(h)
decoded = Dense(input_dim, activation='sigmoid',
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(h)
# Build autoencoder model
if params['model'] == 'cvae':
encoder = Model([x_input, cond_input], encoded)
decoder = Model([decoder_input, cond_input], decoded)
model = Model([x_input, cond_input], decoder([z, cond_input]))
loss = vae_loss
metrics = [xent, corr, mse]
elif params['model'] == 'vae':
encoder = Model(x_input, encoded)
decoder = Model(decoder_input, decoded)
model = Model(x_input, decoder(z))
loss = vae_loss
metrics = [xent, corr, mse]
else:
encoder = Model(x_input, encoded)
decoder = Model(decoder_input, decoded)
model = Model(x_input, decoder(encoded))
loss = params['loss']
metrics = [xent, corr]
model.summary()
decoder.summary()
if params['cp']:
model_json = model.to_json()
with open(prefix+'.model.json', 'w') as f:
print(model_json, file=f)
# Define optimizer
# optimizer = candle.build_optimizer(params['optimizer'],
# params['learning_rate'],
# keras_defaults)
optimizer = optimizers.deserialize({'class_name': params['optimizer'], 'config': {}})
base_lr = params['base_lr'] or K.get_value(optimizer.lr)
if params['learning_rate']:
K.set_value(optimizer.lr, params['learning_rate'])
model.compile(loss=loss, optimizer=optimizer, metrics=metrics)
# calculate trainable and non-trainable params
params.update(candle.compute_trainable_params(model))
def warmup_scheduler(epoch):
lr = params['learning_rate'] or base_lr * params['batch_size']/100
if epoch <= 5:
K.set_value(model.optimizer.lr, (base_lr * (5-epoch) + lr * epoch) / 5)
p1b1.logger.debug('Epoch {}: lr={}'.format(epoch, K.get_value(model.optimizer.lr)))
return K.get_value(model.optimizer.lr)
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=5, min_lr=0.00001)
warmup_lr = LearningRateScheduler(warmup_scheduler)
checkpointer = ModelCheckpoint(params['save_path']+ext+'.weights.h5', save_best_only=True, save_weights_only=True)
tensorboard = TensorBoard(log_dir="tb/tb{}".format(ext))
candle_monitor = candle.CandleRemoteMonitor(params=params)
timeout_monitor = candle.TerminateOnTimeOut(params['timeout'])
history_logger = LoggingCallback(p1b1.logger.debug)
callbacks = [candle_monitor, timeout_monitor, history_logger]
if params['reduce_lr']:
callbacks.append(reduce_lr)
if params['warmup_lr']:
callbacks.append(warmup_lr)
if params['cp']:
callbacks.append(checkpointer)
if params['tb']:
callbacks.append(tensorboard)
x_val2 = np.copy(x_val)
np.random.shuffle(x_val2)
start_scores = p1b1.evaluate_autoencoder(x_val, x_val2)
p1b1.logger.info('\nBetween random pairs of validation samples: {}'.format(start_scores))
if params['model'] == 'cvae':
inputs = [x_train, cond_train]
val_inputs = [x_val, cond_val]
test_inputs = [x_test, cond_test]
else:
inputs = x_train
val_inputs = x_val
test_inputs = x_test
outputs = x_train
val_outputs = x_val
test_outputs = x_test
history = model.fit(inputs, outputs,
verbose=2,
batch_size=params['batch_size'],
epochs=params['epochs'],
callbacks=callbacks,
validation_data=(val_inputs, val_outputs))
if params['cp']:
encoder.save(prefix+'.encoder.h5')
decoder.save(prefix+'.decoder.h5')
candle.plot_history(prefix, history, 'loss')
candle.plot_history(prefix, history, 'corr', 'streaming pearson correlation')
# Evalute model on test set
x_pred = model.predict(test_inputs)
scores = p1b1.evaluate_autoencoder(x_pred, x_test)
p1b1.logger.info('\nEvaluation on test data: {}'.format(scores))
x_test_encoded = encoder.predict(test_inputs, batch_size=params['batch_size'])
y_test_classes = np.argmax(y_test, axis=1)
candle.plot_scatter(x_test_encoded, y_test_classes, prefix+'.latent')
if params['tsne']:
tsne = TSNE(n_components=2, random_state=seed)
x_test_encoded_tsne = tsne.fit_transform(x_test_encoded)
candle.plot_scatter(x_test_encoded_tsne, y_test_classes, prefix+'.latent.tsne')
# diff = x_pred - x_test
# plt.hist(diff.ravel(), bins='auto')
# plt.title("Histogram of Errors with 'auto' bins")
# plt.savefig('histogram_keras.png')
# generate synthetic data
# epsilon_std = 1.0
# for i in range(1000):
# z_sample = np.random.normal(size=(1, 2)) * epsilon_std
# x_decoded = decoder.predict(z_sample)
p1b1.logger.handlers = []
return history
def run(params):
args = candle.ArgumentStruct(**params)
seed = args.rng_seed
candle.set_seed(seed)
# Construct extension to save model
ext = attn.extension_from_parameters(params, 'keras')
candle.verify_path(params['save_path'])
prefix = '{}{}'.format(params['save_path'], ext)
logfile = params['logfile'] if params['logfile'] else prefix + '.log'
root_fname = 'Agg_attn_bin'
candle.set_up_logger(logfile, attn.logger, params['verbose'])
attn.logger.info('Params: {}'.format(params))
# Get default parameters for initialization and optimizer functions
keras_defaults = candle.keras_default_config()
##
X_train, _Y_train, X_val, _Y_val, X_test, _Y_test = attn.load_data(
params, seed)
# move this inside the load_data function
Y_train = _Y_train['AUC']
Y_test = _Y_test['AUC']
Y_val = _Y_val['AUC']
Y_train_neg, Y_train_pos = np.bincount(Y_train)
Y_test_neg, Y_test_pos = np.bincount(Y_test)
Y_val_neg, Y_val_pos = np.bincount(Y_val)
Y_train_total = Y_train_neg + Y_train_pos
Y_test_total = Y_test_neg + Y_test_pos
Y_val_total = Y_val_neg + Y_val_pos
total = Y_train_total + Y_test_total + Y_val_total
neg = Y_train_neg + Y_test_neg + Y_val_neg
pos = Y_train_pos + Y_test_pos + Y_val_pos
print('Examples:\n Total: {}\n Positive: {} ({:.2f}% of total)\n'.
format(total, pos, 100 * pos / total))
nb_classes = params['dense'][-1]
Y_train = np_utils.to_categorical(Y_train, nb_classes)
Y_test = np_utils.to_categorical(Y_test, nb_classes)
Y_val = np_utils.to_categorical(Y_val, nb_classes)
y_integers = np.argmax(Y_train, axis=1)
class_weights = compute_class_weight('balanced', np.unique(y_integers),
y_integers)
d_class_weights = dict(enumerate(class_weights))
print('X_train shape:', X_train.shape)
print('X_val shape:', X_val.shape)
print('X_test shape:', X_test.shape)
print('Y_train shape:', Y_train.shape)
print('Y_val shape:', Y_val.shape)
print('Y_test shape:', Y_test.shape)
# save the data
# data_train = {"X": X_train, "y": Y_train}
# data_val = {"X": X_val, "y": Y_val}
# data_test = {"X": X_test, "y": Y_test}
h5f = h5py.File('training_attn.h5', 'w')
h5f.create_dataset('X_train', data=X_train)
h5f.create_dataset('Y_train', data=Y_train)
h5f.create_dataset('X_val', data=X_val)
h5f.create_dataset('Y_val', data=Y_val)
h5f.create_dataset('X_test', data=X_test)
h5f.create_dataset('Y_test', data=Y_test)
h5f.close()
def run(params):
args = candle.ArgumentStruct(**params)
seed = args.rng_seed
candle.set_seed(seed)
# Construct extension to save model
ext = attn.extension_from_parameters(params, "keras")
candle.verify_path(params["save_path"])
prefix = "{}{}".format(params["save_path"], ext)
logfile = params["logfile"] if params["logfile"] else prefix + ".log"
root_fname = "Agg_attn_bin"
candle.set_up_logger(logfile, attn.logger, params["verbose"])
attn.logger.info("Params: {}".format(params))
# Get default parameters for initialization and optimizer functions
keras_defaults = candle.keras_default_config()
##
X_train, _Y_train, X_val, _Y_val, X_test, _Y_test = attn.load_data(
params, seed)
# move this inside the load_data function
Y_train = _Y_train["AUC"]
Y_test = _Y_test["AUC"]
Y_val = _Y_val["AUC"]
Y_train_neg, Y_train_pos = np.bincount(Y_train)
Y_test_neg, Y_test_pos = np.bincount(Y_test)
Y_val_neg, Y_val_pos = np.bincount(Y_val)
Y_train_total = Y_train_neg + Y_train_pos
Y_test_total = Y_test_neg + Y_test_pos
Y_val_total = Y_val_neg + Y_val_pos
total = Y_train_total + Y_test_total + Y_val_total
neg = Y_train_neg + Y_test_neg + Y_val_neg
pos = Y_train_pos + Y_test_pos + Y_val_pos
print("Examples:\n Total: {}\n Positive: {} ({:.2f}% of total)\n".
format(total, pos, 100 * pos / total))
nb_classes = params["dense"][-1]
Y_train = np_utils.to_categorical(Y_train, nb_classes)
Y_test = np_utils.to_categorical(Y_test, nb_classes)
Y_val = np_utils.to_categorical(Y_val, nb_classes)
y_integers = np.argmax(Y_train, axis=1)
class_weights = compute_class_weight("balanced", np.unique(y_integers),
y_integers)
d_class_weights = dict(enumerate(class_weights))
print("X_train shape:", X_train.shape)
print("X_test shape:", X_test.shape)
print("Y_train shape:", Y_train.shape)
print("Y_test shape:", Y_test.shape)
PS = X_train.shape[1]
model = build_attention_model(params, PS)
# parallel_model = multi_gpu_model(model, gpus=4)
# parallel_model.compile(loss='mean_squared_error',
# optimizer=SGD(lr=0.0001, momentum=0.9),
# metrics=['mae',r2])
kerasDefaults = candle.keras_default_config()
if params["momentum"]:
kerasDefaults["momentum_sgd"] = params["momentum"]
optimizer = candle.build_optimizer(params["optimizer"],
params["learning_rate"], kerasDefaults)
model.compile(
loss=params["loss"],
optimizer=optimizer,
# SGD(lr=0.00001, momentum=0.9),
# optimizer=Adam(lr=0.00001),
# optimizer=RMSprop(lr=0.0001),
# optimizer=Adadelta(),
metrics=[
"acc",
tf.keras.metrics.AUC(name="auroc", curve="ROC"),
tf.keras.metrics.AUC(name="aucpr", curve="PR"),
],
)
# set up a bunch of callbacks to do work during model training..
checkpointer = ModelCheckpoint(
filepath=params["save_path"] + root_fname + ".autosave.model.h5",
verbose=1,
save_weights_only=False,
save_best_only=True,
)
csv_logger = CSVLogger("{}/{}.training.log".format(params["save_path"],
root_fname))
reduce_lr = ReduceLROnPlateau(
monitor="val_auroc",
factor=0.20,
patience=40,
verbose=1,
mode="auto",
min_delta=0.0001,
cooldown=3,
min_lr=0.000000001,
)
early_stop = EarlyStopping(monitor="val_auroc",
patience=200,
verbose=1,
mode="auto")
candle_monitor = candle.CandleRemoteMonitor(params=params)
candle_monitor = candle.CandleRemoteMonitor(params=params)
timeout_monitor = candle.TerminateOnTimeOut(params["timeout"])
tensorboard = TensorBoard(log_dir="tb/tb{}".format(ext))
history_logger = LoggingCallback(attn.logger.debug)
callbacks = [candle_monitor, timeout_monitor, csv_logger, history_logger]
if params["reduce_lr"]:
callbacks.append(reduce_lr)
if params["use_cp"]:
callbacks.append(checkpointer)
if params["use_tb"]:
callbacks.append(tensorboard)
if params["early_stop"]:
callbacks.append(early_stop)
epochs = params["epochs"]
batch_size = params["batch_size"]
history = model.fit(
X_train,
Y_train,
class_weight=d_class_weights,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(X_val, Y_val),
callbacks=callbacks,
)
# diagnostic plots
if "loss" in history.history.keys():
candle.plot_history(params["save_path"] + root_fname, history, "loss")
if "acc" in history.history.keys():
candle.plot_history(params["save_path"] + root_fname, history, "acc")
if "auroc" in history.history.keys():
candle.plot_history(params["save_path"] + root_fname, history, "auroc")
if "auprc" in history.history.keys():
candle.plot_history(params["save_path"] + root_fname, history, "aucpr")
# Evaluate model
score = model.evaluate(X_test, Y_test, verbose=0)
Y_predict = model.predict(X_test)
evaluate_model(params, root_fname, nb_classes, Y_test, _Y_test, Y_predict,
pos, total, score)
save_and_test_saved_model(params, model, root_fname, X_train, X_test,
Y_test)
attn.logger.handlers = []
return history
def run(params):
args = candle.ArgumentStruct(**params)
candle.set_seed(args.rng_seed)
logfile_def = 'uno_infer_from_' + args.uq_infer_file + '.log'
logfile = args.logfile if args.logfile else logfile_def
uno.set_up_logger(logfile, logger, uno.loggerUno, args.verbose)
logger.info('Params: {}'.format(params))
ext = uno.extension_from_parameters(args)
candle.verify_path(args.save_path)
prefix = args.save_path + 'uno' + ext
# Load trained model
candle.register_permanent_dropout()
model = keras.models.load_model(args.model_file, compile=False)
model.load_weights(args.weights_file)
logger.info('Loaded model:')
model.summary(print_fn=logger.info)
# Determine output to infer
target = args.agg_dose or 'Growth'
if (args.uq_infer_given_drugs or args.uq_infer_given_cells or args.uq_infer_given_indices):
loader = uno_combined_data_loader.CombinedDataLoader(args.rng_seed)
loader.load(cache=args.cache,
ncols=args.feature_subsample,
agg_dose=args.agg_dose,
cell_features=args.cell_features,
drug_features=args.drug_features,
drug_median_response_min=args.drug_median_response_min,
drug_median_response_max=args.drug_median_response_max,
use_landmark_genes=args.use_landmark_genes,
use_filtered_genes=args.use_filtered_genes,
cell_feature_subset_path=args.cell_feature_subset_path or args.feature_subset_path,
drug_feature_subset_path=args.drug_feature_subset_path or args.feature_subset_path,
preprocess_rnaseq=args.preprocess_rnaseq,
single=args.single,
train_sources=args.train_sources,
test_sources=args.test_sources,
embed_feature_source=not args.no_feature_source,
encode_response_source=not args.no_response_source,
)
if args.uq_infer_given_drugs:
test_gen = given_drugs(args, loader)
elif args.uq_infer_given_cells:
test_gen = given_cells(args, loader)
else:
test_gen = given_indices(args, loader)
else:
test_gen = from_file(args, model)
df_test = test_gen.get_response(copy=True)
y_test = df_test[target].values
for i in range(args.n_pred):
if args.no_gen:
x_test_list, y_test = test_gen.get_slice(size=test_gen.size, single=args.single)
y_test_pred = model.predict(x_test_list, batch_size=args.batch_size)
else:
test_gen.reset()
y_test_pred = model.predict_generator(test_gen.flow(single=args.single), test_gen.steps)
y_test_pred = y_test_pred[:test_gen.size]
if args.loss == 'heteroscedastic':
y_test_pred_ = y_test_pred[:,0]
s_test_pred = y_test_pred[:,1]
y_test_pred = y_test_pred_.flatten()
df_test['Predicted_'+target+'_'+str(i+1)] = y_test_pred
df_test['Pred_S_'+target+'_'+str(i+1)] = s_test_pred
pred_fname = prefix + '.predicted_INFER_HET.tsv'
elif args.loss == 'quantile':
y_test_pred_50q = y_test_pred[:,0]
y_test_pred_10q = y_test_pred[:,1]
y_test_pred_90q = y_test_pred[:,2]
y_test_pred = y_test_pred_50q.flatten() # 50th quantile prediction
df_test['Predicted_50q_'+target+'_'+str(i+1)] = y_test_pred
df_test['Predicted_10q_'+target+'_'+str(i+1)] = y_test_pred_10q.flatten()
df_test['Predicted_90q_'+target+'_'+str(i+1)] = y_test_pred_90q.flatten()
pred_fname = prefix + '.predicted_INFER_QTL.tsv'
else:
y_test_pred = y_test_pred.flatten()
df_test['Predicted_'+target+'_'+str(i+1)] = y_test_pred
pred_fname = prefix + '.predicted_INFER.tsv'
if args.n_pred < 21:
scores = uno.evaluate_prediction(y_test, y_test_pred)
uno.log_evaluation(scores, logger)
df_pred = df_test
if args.agg_dose:
if args.single:
df_pred.sort_values(['Sample', 'Drug1', target], inplace=True)
else:
df_pred.sort_values(['Sample', 'Drug1', 'Drug2', target], inplace=True)
else:
if args.single:
df_pred.sort_values(['Sample', 'Drug1', 'Dose1', 'Growth'], inplace=True)
else:
df_pred.sort_values(['Sample', 'Drug1', 'Drug2', 'Dose1', 'Dose2', 'Growth'], inplace=True)
df_pred.to_csv(pred_fname, sep='\t', index=False, float_format='%.4g')
logger.info('Predictions stored in file: {}'.format(pred_fname))
if K.backend() == 'tensorflow':
K.clear_session()
logger.handlers = []
def run(params):
args = candle.ArgumentStruct(**params)
seed = args.rng_seed
candle.set_seed(seed)
# Construct extension to save model
ext = adrp.extension_from_parameters(params, ".keras")
candle.verify_path(params["save_path"])
prefix = "{}{}".format(params["save_path"], ext)
logfile = params["logfile"] if params["logfile"] else prefix + ".log"
candle.set_up_logger(logfile, adrp.logger, params["verbose"])
adrp.logger.info("Params: {}".format(params))
# Get default parameters for initialization and optimizer functions
keras_defaults = candle.keras_default_config()
##
X_train, Y_train, X_test, Y_test, PS = adrp.load_data(params, seed)
print("X_train shape:", X_train.shape)
print("X_test shape:", X_test.shape)
print("Y_train shape:", Y_train.shape)
print("Y_test shape:", Y_test.shape)
# Initialize weights and learning rule
initializer_weights = candle.build_initializer(params["initialization"],
keras_defaults, seed)
initializer_bias = candle.build_initializer("constant", keras_defaults,
0.0)
activation = params["activation"]
# TODO: set output_dim
output_dim = 1
# TODO: Use dense_layers for creating inputs/outputs
dense_layers = params["dense"]
inputs = Input(shape=(PS, ))
if dense_layers != None:
if type(dense_layers) != list:
dense_layers = list(dense_layers)
for i, l in enumerate(dense_layers):
if i == 0:
x = Dense(
l,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias,
)(inputs)
else:
x = Dense(
l,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias,
)(x)
if params["dropout"]:
x = Dropout(params["dropout"])(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,
)(inputs)
model = Model(inputs=inputs, outputs=output)
model.summary()
kerasDefaults = candle.keras_default_config()
if params["momentum"]:
kerasDefaults["momentum_sgd"] = params["momentum"]
optimizer = candle.build_optimizer(params["optimizer"],
params["learning_rate"], kerasDefaults)
model.compile(
loss=params["loss"],
optimizer=optimizer,
metrics=["mae", r2],
)
# set up a bunch of callbacks to do work during model training..
checkpointer = ModelCheckpoint(
filepath=params["save_path"] + "agg_adrp.autosave.model.h5",
verbose=1,
save_weights_only=False,
save_best_only=True,
)
csv_logger = CSVLogger(params["save_path"] + "agg_adrp.training.log")
reduce_lr = ReduceLROnPlateau(
monitor="val_loss",
factor=0.75,
patience=20,
mode="auto",
epsilon=0.0001,
cooldown=3,
min_lr=0.000000001,
)
early_stop = EarlyStopping(monitor="val_loss",
patience=100,
verbose=1,
mode="auto")
# history = parallel_model.fit(X_train, Y_train,
epochs = params["epochs"]
batch_size = params["batch_size"]
history = model.fit(
X_train,
Y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(X_test, Y_test),
callbacks=[checkpointer, csv_logger, reduce_lr, early_stop],
)
score = model.evaluate(X_test, Y_test, verbose=0)
print(score)
print(history.history.keys())
# see big fuction below, creates plots etc.
# TODO: Break post_process into multiple functions
post_process(params, X_train, X_test, Y_test, score, history, model)
adrp.logger.handlers = []
return history
