def main(args):
if len(args) < 1:
sys.stderr.write("Error - one required arguments: <data directory>\n")
sys.exit(-1)
working_dir = args[0]
print("Reading data...")
Y, label_alphabet, X_array, feature_alphabet = ctk_io.read_token_sequence_data(working_dir)
Y_array = np.array(Y)
# print("Shape of X is %s and Y is %s" % (str(X.shape), str(Y.shape)))
num_examples, dimension = X_array.shape
num_outputs = 1 if len(label_alphabet) == 2 else len(label_alphabet)
num_y_examples = len(Y)
assert num_examples == num_y_examples
Y_adj, indices = ctk_io.flatten_outputs(Y_array)
train_x, valid_x, train_y, valid_y = train_test_split(X_array, Y_array, test_size=0.2, random_state=18)
optim = RandomSearch(
lambda: get_random_config(),
lambda x, y: run_one_eval(x, y, train_x, train_y, valid_x, valid_y, len(feature_alphabet), num_outputs),
)
best_config = optim.optimize()
print("Best config: %s" % best_config)
def main(args):
if len(args) < 1:
sys.stderr.write("Error - one required arguments: <data directory>\n")
sys.exit(-1)
working_dir = args[0]
print("Reading data...")
Y, label_alphabet, X_array, feature_alphabet = ctk_io.read_token_sequence_data(
working_dir)
Y_array = np.array(Y)
#print("Shape of X is %s and Y is %s" % (str(X.shape), str(Y.shape)))
num_examples, dimension = X_array.shape
num_outputs = 1 if len(label_alphabet) == 2 else len(label_alphabet)
num_y_examples = len(Y)
assert num_examples == num_y_examples
Y_adj, indices = ctk_io.flatten_outputs(Y_array)
train_x, valid_x, train_y, valid_y = train_test_split(X_array,
Y_array,
test_size=0.2,
random_state=18)
optim = RandomSearch(
lambda: get_random_config(),
lambda x, y: run_one_eval(x, y, train_x, train_y, valid_x, valid_y,
len(feature_alphabet), num_outputs))
best_config = optim.optimize()
print("Best config: %s" % best_config)
def main(args):
if len(args) < 1:
sys.stderr.write("Error - one required arguments: <data directory>\n")
sys.exit(-1)
working_dir = args[0]
print("Reading data...")
Y, label_alphabet, X_array, feature_alphabet = ctk_io.read_token_sequence_data(working_dir)
X_segments, dimensions = split_entity_data(X_array, feature_alphabet)
Y_array = np.array(Y)
Y_adj, indices = ctk_io.flatten_outputs(Y_array)
num_outputs = 1 if len(label_alphabet) == 2 else len(label_alphabet)
num_y_examples = len(Y)
train_x0, valid_x0, train_x1, valid_x1, train_x2, valid_x2, train_y, valid_y = train_test_split(X_segments[0], X_segments[1], X_segments[2], Y_array, test_size=0.2, random_state=18)
train_x = [train_x0, train_x1, train_x2]
valid_x = [valid_x0, valid_x1, valid_x2]
optim = RandomSearch(lambda: get_random_config(), lambda x, y: run_one_eval(x, y, train_x, train_y, valid_x, valid_y, len(feature_alphabet), num_outputs ) )
best_config = optim.optimize()
print("Best config: %s" % best_config)
def main(args):
if len(args) < 1:
sys.stderr.write("Error - one required arguments: <data directory>\n")
sys.exit(-1)
working_dir = args[0]
print("Reading data...")
Y, label_alphabet, X_array, feature_alphabet = ctk_io.read_token_sequence_data(
working_dir)
X_segments, dimensions = split_entity_data(X_array, feature_alphabet)
Y_array = np.array(Y)
Y_adj, indices = ctk_io.flatten_outputs(Y_array)
num_outputs = 1 if len(label_alphabet) == 2 else len(label_alphabet)
num_y_examples = len(Y)
train_x0, valid_x0, train_x1, valid_x1, train_x2, valid_x2, train_y, valid_y = train_test_split(
X_segments[0],
X_segments[1],
X_segments[2],
Y_array,
test_size=0.2,
random_state=18)
train_x = [train_x0, train_x1, train_x2]
valid_x = [valid_x0, valid_x1, valid_x2]
optim = RandomSearch(
lambda: get_random_config(),
lambda x, y: run_one_eval(x, y, train_x, train_y, valid_x, valid_y,
len(feature_alphabet), num_outputs))
best_config = optim.optimize()
print("Best config: %s" % best_config)
def main(args):
if len(args) < 1:
sys.stderr.write("Error - one required argument: <data directory>\n")
sys.exit(-1)
working_dir = args[0]
(train_y, label_alphabet, train_x, feats_alphabet) = ctk_io.read_token_sequence_data(working_dir)
init_vectors = None #used for pre-trained embeddings
#load embeddings file
embedingFile = '/Users/chenlin/Programming/ctakesWorkspace/neural-temporal/src/main/resources/org/apache/ctakes/temporal/thyme_word2vec_timex_50.vec'
weights = ctk_io.read_embeddings(embedingFile, feats_alphabet)
# if len(args) > 1 and best_config['pretrain'] == True:
# weights = ctk_io.read_embeddings(args[1], feats_alphabet)
# elif best_config['pretrain'] and len(args) == 1:
# sys.stderr.write("Error: Pretrain specified but no weights file given!")
# sys.exit(-1)
# turn x and y into numpy array among other things
maxlen = max([len(seq) for seq in train_x])
outcomes = set(train_y)
classes = len(outcomes)
train_x = pad_sequences(train_x, maxlen=maxlen)
train_y = to_categorical(np.array(train_y), classes)
#pickle.dump(maxlen, open(os.path.join(working_dir, 'maxlen.p'),"wb"))
#pickle.dump(dataset1.alphabet, open(os.path.join(working_dir, 'alphabet.p'),"wb"))
#test_x = pad_sequences(test_x, maxlen=maxlen)
#test_y = to_categorical(np.array(test_y), classes)
print 'train_x shape:', train_x.shape
print 'train_y shape:', train_y.shape
branches = [] # models to be merged
train_xs = [] # train x for each branch
#test_xs = [] # test x for each branch
filtlens = "1,2,3,4,5"
for filter_len in filtlens.split(','):
branch = Sequential()
branch.add(Embedding(len(feats_alphabet),
weights.shape[1],
input_length=maxlen,
weights=[weights],
trainable = False))
branch.add(Convolution1D(nb_filter=200,
filter_length=int(filter_len),
border_mode='valid',
activation='relu',
subsample_length=1))
branch.add(MaxPooling1D(pool_length=2))
branch.add(Flatten())
branches.append(branch)
train_xs.append(train_x)
#test_xs.append(test_x)
branch = Sequential()
branch.add(Embedding(len(feats_alphabet),
weights.shape[1],
input_length=maxlen,
weights=[weights],
trainable = False))
branch.add(Convolution1D(nb_filter=200,
filter_length=3,
border_mode='valid',
activation='relu',
subsample_length=1))
branch.add(Convolution1D(nb_filter=200,
filter_length=3,
border_mode='same',
activation='relu',
subsample_length=1))
branch.add(MaxPooling1D(pool_length=2))
branch.add(Flatten())
branches.append(branch)
train_xs.append(train_x)
model = Sequential()
model.add(Merge(branches, mode='concat'))
model.add(Dense(250))#cfg.getint('cnn', 'hidden')))
model.add(Dropout(0.25))#cfg.getfloat('cnn', 'dropout')))
model.add(Activation('relu'))
model.add(Dropout(0.25))#cfg.getfloat('cnn', 'dropout')))
model.add(Dense(classes))
model.add(Activation('softmax'))
optimizer = RMSprop(lr=0.0001,#cfg.getfloat('cnn', 'learnrt'),
rho=0.9, epsilon=1e-08)
model.compile(loss='categorical_crossentropy',
optimizer=optimizer,
metrics=['accuracy'])
model.fit(train_xs,
train_y,
nb_epoch=20,#cfg.getint('cnn', 'epochs'),
batch_size=50,#cfg.getint('cnn', 'batches'),
verbose=1,
validation_split=0.1,
class_weight=None)
model.summary()
json_string = model.to_json()
open(os.path.join(working_dir, 'model_0.json'), 'w').write(json_string)
model.save_weights(os.path.join(working_dir, 'model_0.h5'), overwrite=True)
fn = open(os.path.join(working_dir, 'alphabets.pkl'), 'w')
pickle.dump( (feats_alphabet, label_alphabet, maxlen), fn)
fn.close()
with ZipFile(os.path.join(working_dir, 'script.model'), 'w') as myzip:
myzip.write(os.path.join(working_dir, 'model_0.json'), 'model_0.json')
myzip.write(os.path.join(working_dir, 'model_0.h5'), 'model_0.h5')
myzip.write(os.path.join(working_dir, 'alphabets.pkl'), 'alphabets.pkl')
sys.exit(0)
def main(args):
if len(args) < 1:
sys.stderr.write("Error - one required argument: <working_dir>\n")
sys.exit(-1)
working_dir = args[0]
### Extract existing model:
print("Extracting existing model")
with ZipFile(os.path.join(working_dir, 'script.model'), 'r') as myzip:
myzip.extract('model.h5', working_dir)
myzip.extract('alphabets.pkl', working_dir)
(feature_alphabet, label_alphabet) = pickle.load( open(os.path.join(working_dir, 'alphabets.pkl'), 'r' ) )
label_lookup = {val:key for (key,val) in label_alphabet.iteritems()}
model = load_model(os.path.join(working_dir, "model.h5"))
#config = model.get_config()
#model = Container.from_config(config)
## Find the model params needed by CNN method and get a cnn with one extra FC layer:
# nn_models.get_cnn_model(X_array.shape, len(feature_alphabet), num_outputs, conv_layers=convs, fc_layers=layers,
# embed_dim=embed_dim, filter_widths=width)
print("Building new model with extra layer")
convs = []
dense = []
for layer in model.layers:
if 'convolution' in layer.name:
convs.append(layer)
if 'dense' in layer.name:
dense.append(layer)
filters = [x.filter_length for x in convs]
nb_filters = (convs[0].nb_filter,)
fc_widths = [x.output_dim for x in dense]
fc_widths.append(fc_widths[-1] //2)
new_model = nn_models.get_cnn_model(model.layers[0].input_shape, model.layers[1].input_dim, model.layers[-1].output_dim,
conv_layers=nb_filters, fc_layers=fc_widths, embed_dim=model.layers[1].output_dim, filter_widths=filters )
## Just so i don't accidentally try to refer to this later
del model
## Change the name of the output layer so that we don't try to read those weights in -- we will have a different number of parameters:
#new_model.layers[-1].name = "NewOutput"
## Load as many weights as possible taking advantage of consistently named layers:
new_model.load_weights(os.path.join(working_dir, "model.h5"), by_name=True)
## Re-load data and retrain model:
print("Reading data...")
Y, label_alphabet, X_array, feature_alphabet = ctk_io.read_token_sequence_data(working_dir)
Y_array = np.array(Y)
#print("Shape of X is %s and Y is %s" % (str(X.shape), str(Y.shape)))
num_examples, dimension = X_array.shape
num_outputs = 1 if len(label_alphabet) == 2 else len(label_alphabet)
num_y_examples = len(Y)
Y_adj, indices = ctk_io.flatten_outputs(Y_array)
out_counts = Y_adj.sum(0)
stopper = nn_models.get_early_stopper()
print("Retraining model")
new_model.fit(X_array, Y_adj,
nb_epoch=nb_epoch,
batch_size=batch_size,
verbose=1,
validation_split=0.2) #,
#callbacks=[stopper]) #,
#class_weight=class_weights)
new_model.summary()
new_model.save(os.path.join(working_dir, 'new_model.h5'), overwrite=True)
with ZipFile(os.path.join(working_dir, 'extended.model'), 'w') as myzip:
myzip.write(os.path.join(working_dir, 'new_model.h5'), 'model.h5')
myzip.write(os.path.join(working_dir, 'alphabets.pkl'), 'alphabets.pkl')
def main(args):
if len(args) < 1:
sys.stderr.write("Error - one required argument: <working_dir>\n")
sys.exit(-1)
working_dir = args[0]
### Extract existing model:
print("Extracting existing model")
with ZipFile(os.path.join(working_dir, 'script.model'), 'r') as myzip:
myzip.extract('model.h5', working_dir)
myzip.extract('alphabets.pkl', working_dir)
(feature_alphabet, label_alphabet) = pickle.load(
open(os.path.join(working_dir, 'alphabets.pkl'), 'r'))
label_lookup = {val: key for (key, val) in label_alphabet.iteritems()}
model = load_model(os.path.join(working_dir, "model.h5"))
#config = model.get_config()
#model = Container.from_config(config)
## Find the model params needed by CNN method and get a cnn with one extra FC layer:
# nn_models.get_cnn_model(X_array.shape, len(feature_alphabet), num_outputs, conv_layers=convs, fc_layers=layers,
# embed_dim=embed_dim, filter_widths=width)
print("Building new model with extra layer")
convs = []
dense = []
for layer in model.layers:
if 'convolution' in layer.name:
convs.append(layer)
if 'dense' in layer.name:
dense.append(layer)
filters = [x.filter_length for x in convs]
nb_filters = (convs[0].nb_filter, )
fc_widths = [x.output_dim for x in dense]
#fc_widths.append(fc_widths[-1] //2)
fc_widths.append(fc_widths[-1])
new_model = nn_models.get_cnn_model(model.layers[0].input_shape,
model.layers[1].input_dim,
model.layers[-1].output_dim,
conv_layers=nb_filters,
fc_layers=fc_widths,
embed_dim=model.layers[1].output_dim,
filter_widths=filters)
## Just so i don't accidentally try to refer to this later
del model
## Change the name of the output layer so that we don't try to read those weights in -- we will have a different number of parameters:
#new_model.layers[-1].name = "NewOutput"
## Load as many weights as possible taking advantage of consistently named layers:
new_model.load_weights(os.path.join(working_dir, "model.h5"), by_name=True)
## Re-load data and retrain model:
print("Reading data...")
Y, label_alphabet, X_array, feature_alphabet = ctk_io.read_token_sequence_data(
working_dir)
Y_array = np.array(Y)
#print("Shape of X is %s and Y is %s" % (str(X.shape), str(Y.shape)))
num_examples, dimension = X_array.shape
num_outputs = 1 if len(label_alphabet) == 2 else len(label_alphabet)
num_y_examples = len(Y)
Y_adj, indices = ctk_io.flatten_outputs(Y_array)
out_counts = Y_adj.sum(0)
stopper = nn_models.get_early_stopper()
print("Retraining model")
new_model.fit(X_array,
Y_adj,
nb_epoch=nb_epoch,
batch_size=batch_size,
verbose=1,
validation_split=0.2) #,
#callbacks=[stopper]) #,
#class_weight=class_weights)
new_model.summary()
new_model.save(os.path.join(working_dir, 'new_model.h5'), overwrite=True)
with ZipFile(os.path.join(working_dir, 'extended.model'), 'w') as myzip:
myzip.write(os.path.join(working_dir, 'new_model.h5'), 'model.h5')
myzip.write(os.path.join(working_dir, 'alphabets.pkl'),
'alphabets.pkl')
def main(args):
if len(args) < 1:
sys.stderr.write("Error - one required argument: <data directory>\n")
sys.exit(-1)
working_dir = args[0]
(train_y, label_alphabet, train_x,
feats_alphabet) = ctk_io.read_token_sequence_data(working_dir)
init_vectors = None #used for pre-trained embeddings
# turn x and y into numpy array among other things
maxlen = max([len(seq) for seq in train_x])
outcomes = set(train_y)
classes = len(outcomes)
train_x = pad_sequences(train_x, maxlen=maxlen)
train_y = to_categorical(np.array(train_y), classes)
#pickle.dump(maxlen, open(os.path.join(working_dir, 'maxlen.p'),"wb"))
#pickle.dump(dataset1.alphabet, open(os.path.join(working_dir, 'alphabet.p'),"wb"))
#test_x = pad_sequences(test_x, maxlen=maxlen)
#test_y = to_categorical(np.array(test_y), classes)
print 'train_x shape:', train_x.shape
print 'train_y shape:', train_y.shape
#branches = [] # models to be merged
#train_xs = [] # train x for each branch
#test_xs = [] # test x for each branch
model = resnet(maxlen, feats_alphabet, classes)
optimizer = RMSprop(
lr=0.0001, #cfg.getfloat('cnn', 'learnrt'),
rho=0.9,
epsilon=1e-08)
model.compile(loss='categorical_crossentropy',
optimizer=optimizer,
metrics=['accuracy']) #{'0':'accuracy'})#
model.fit(
train_x,
train_y,
nb_epoch=10, #cfg.getint('cnn', 'epochs'),
batch_size=50, #cfg.getint('cnn', 'batches'),
verbose=1,
validation_split=0.1,
class_weight=None)
model.summary()
json_string = model.to_json()
open(os.path.join(working_dir, 'model_0.json'), 'w').write(json_string)
model.save_weights(os.path.join(working_dir, 'model_0.h5'), overwrite=True)
fn = open(os.path.join(working_dir, 'alphabets.pkl'), 'w')
pickle.dump((feats_alphabet, label_alphabet, maxlen), fn)
fn.close()
with ZipFile(os.path.join(working_dir, 'script.model'), 'w') as myzip:
myzip.write(os.path.join(working_dir, 'model_0.json'), 'model_0.json')
myzip.write(os.path.join(working_dir, 'model_0.h5'), 'model_0.h5')
myzip.write(os.path.join(working_dir, 'alphabets.pkl'),
'alphabets.pkl')
sys.exit(0)
def main(args):
if len(args) < 1:
sys.stderr.write("Error - one required argument: <data directory>\n")
sys.exit(-1)
working_dir = args[0]
(train_y, label_alphabet, train_x, feats_alphabet) = ctk_io.read_token_sequence_data(working_dir)
init_vectors = None #used for pre-trained embeddings
# turn x and y into numpy array among other things
maxlen = max([len(seq) for seq in train_x])
outcomes = set(train_y)
classes = len(outcomes)
train_x = pad_sequences(train_x, maxlen=maxlen)
train_y = to_categorical(np.array(train_y), classes)
#pickle.dump(maxlen, open(os.path.join(working_dir, 'maxlen.p'),"wb"))
#pickle.dump(dataset1.alphabet, open(os.path.join(working_dir, 'alphabet.p'),"wb"))
#test_x = pad_sequences(test_x, maxlen=maxlen)
#test_y = to_categorical(np.array(test_y), classes)
print 'train_x shape:', train_x.shape
print 'train_y shape:', train_y.shape
#branches = [] # models to be merged
#train_xs = [] # train x for each branch
#test_xs = [] # test x for each branch
model = resnet(maxlen, feats_alphabet, classes)
optimizer = RMSprop(lr=0.0001,#cfg.getfloat('cnn', 'learnrt'),
rho=0.9, epsilon=1e-08)
model.compile(loss='categorical_crossentropy',
optimizer=optimizer,
metrics= ['accuracy'])#{'0':'accuracy'})#
model.fit(train_x,
train_y,
nb_epoch=10,#cfg.getint('cnn', 'epochs'),
batch_size=50,#cfg.getint('cnn', 'batches'),
verbose=1,
validation_split=0.1,
class_weight=None)
model.summary()
json_string = model.to_json()
open(os.path.join(working_dir, 'model_0.json'), 'w').write(json_string)
model.save_weights(os.path.join(working_dir, 'model_0.h5'), overwrite=True)
fn = open(os.path.join(working_dir, 'alphabets.pkl'), 'w')
pickle.dump( (feats_alphabet, label_alphabet, maxlen), fn)
fn.close()
with ZipFile(os.path.join(working_dir, 'script.model'), 'w') as myzip:
myzip.write(os.path.join(working_dir, 'model_0.json'), 'model_0.json')
myzip.write(os.path.join(working_dir, 'model_0.h5'), 'model_0.h5')
myzip.write(os.path.join(working_dir, 'alphabets.pkl'), 'alphabets.pkl')
sys.exit(0)
