def nnet_dropout(X, Y):
"""Neural net with dropout."""
reg = 0.001 # Weight prior
noise = .5 # Likelihood st. dev.
net = (
ab.InputLayer(name="X", n_samples=n_samples) >>
ab.DenseMAP(output_dim=30, l2_reg=reg, l1_reg=0.) >>
ab.Activation(tf.tanh) >>
ab.DropOut(keep_prob=0.95) >>
ab.DenseMAP(output_dim=20, l2_reg=reg, l1_reg=0.) >>
ab.Activation(tf.tanh) >>
ab.DropOut(keep_prob=0.95) >>
ab.DenseMAP(output_dim=10, l2_reg=reg, l1_reg=0.) >>
ab.Activation(tf.tanh) >>
ab.DropOut(keep_prob=0.95) >>
ab.DenseMAP(output_dim=5, l2_reg=reg, l1_reg=0.) >>
ab.Activation(tf.tanh) >>
ab.DenseMAP(output_dim=1, l2_reg=reg, l1_reg=0.)
)
phi, reg = net(X=X)
lkhood = tf.distributions.Normal(loc=phi, scale=noise)
loss = ab.max_posterior(lkhood, Y, reg)
return phi, loss
def nnet_bayesian(X, Y):
"""Bayesian neural net."""
lambda_ = 1e-1 # Weight prior
noise = tf.Variable(0.01) # Likelihood st. dev. initialisation
net = (ab.InputLayer(name="X", n_samples=n_samples_) >>
ab.DenseVariational(output_dim=20, std=lambda_) >> ab.Activation(
tf.nn.relu) >> ab.DenseVariational(output_dim=7, std=lambda_) >>
ab.Activation(tf.nn.relu) >> ab.DenseVariational(
output_dim=5, std=lambda_) >> ab.Activation(
tf.tanh) >> ab.DenseVariational(output_dim=1, std=lambda_))
f, kl = net(X=X)
lkhood = tf.distributions.Normal(loc=f, scale=ab.pos(noise))
loss = ab.elbo(lkhood, Y, N, kl)
return f, loss
def nnet(X, Y):
"""Neural net with regularization."""
lambda_ = 1e-4 # Weight regularizer
noise = .5 # Likelihood st. dev.
net = (
ab.InputLayer(name="X", n_samples=1) >> ab.DenseMAP(
output_dim=40, l2_reg=lambda_, l1_reg=0.) >> ab.Activation(tf.tanh)
>> ab.DenseMAP(output_dim=20, l2_reg=lambda_,
l1_reg=0.) >> ab.Activation(tf.tanh) >>
ab.DenseMAP(output_dim=10, l2_reg=lambda_, l1_reg=0.) >> ab.Activation(
tf.tanh) >> ab.DenseMAP(output_dim=1, l2_reg=lambda_, l1_reg=0.))
f, reg = net(X=X)
lkhood = tf.distributions.Normal(loc=f, scale=noise)
loss = ab.max_posterior(lkhood, Y, reg)
return f, loss
def nnet_bayesian(X, Y):
"""Bayesian neural net."""
noise = 0.01
net = (
ab.InputLayer(name="X", n_samples=n_samples_) >>
ab.DenseVariational(output_dim=5) >>
ab.Activation(tf.nn.selu) >>
ab.DenseVariational(output_dim=4) >>
ab.Activation(tf.nn.selu) >>
ab.DenseVariational(output_dim=3) >>
ab.Activation(tf.nn.selu) >>
ab.DenseVariational(output_dim=1)
)
f, kl = net(X=X)
lkhood = tf.distributions.Normal(loc=f, scale=noise).log_prob(Y)
loss = ab.elbo(lkhood, kl, N)
return f, loss
def test_activation(make_data):
"""Test nonlinear activation layer."""
x, _, X = make_data
act = ab.Activation(tf.tanh)
tc = tf.test.TestCase()
with tc.test_session():
F, KL = act(X)
assert np.allclose(np.tanh(X.eval()), F.eval())
assert KL == 0
def my_model(features, labels, mode, params):
N = params["N"]
n_samples = NSAMPLES if mode == tf.estimator.ModeKeys.TRAIN \
else NPREDICTSAMPLES
X = tf.feature_column.input_layer(features, params['feature_columns'])
kernel = ab.RBF(LENSCALE, learn_lenscale=True)
net = (
ab.InputLayer(name="X", n_samples=n_samples) >>
ab.RandomFourier(n_features=NFEATURES, kernel=kernel) >>
ab.Dense(output_dim=64, init_fn="autonorm") >>
ab.Activation(tf.nn.selu) >>
ab.DenseVariational(output_dim=1, full=False, prior_std=1.0,
learn_prior=True)
)
phi, kl = net(X=X)
std = ab.pos_variable(NOISE, name="noise")
ll_f = tf.distributions.Normal(loc=phi, scale=std)
predict_mean = ab.sample_mean(phi)
# Compute predictions.
if mode == tf.estimator.ModeKeys.PREDICT:
predictions = {
'predictions': predict_mean,
'samples': phi
}
return tf.estimator.EstimatorSpec(mode, predictions=predictions)
ll = ll_f.log_prob(labels)
loss = ab.elbo(ll, kl, N)
tf.summary.scalar('loss', loss)
# Compute evaluation metrics.
mse = tf.metrics.mean_squared_error(labels=labels,
predictions=predict_mean,
name='mse_op')
r2 = r2_metric(labels, predict_mean)
metrics = {'mse': mse,
'r2': r2}
if mode == tf.estimator.ModeKeys.EVAL:
return tf.estimator.EstimatorSpec(
mode, loss=loss, eval_metric_ops=metrics)
# Create training op.
assert mode == tf.estimator.ModeKeys.TRAIN
optimizer = tf.train.AdamOptimizer()
train_op = optimizer.minimize(loss, global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op)
def nnet_dropout(X, Y):
"""Neural net with dropout."""
lambda_ = 1e-3 # Weight prior
noise = .5 # Likelihood st. dev.
net = (
ab.InputLayer(name="X", n_samples=n_samples_) >>
ab.Dense(output_dim=32, l2_reg=lambda_) >>
ab.Activation(tf.nn.selu) >>
ab.DropOut(keep_prob=0.9, independent=True) >>
ab.Dense(output_dim=16, l2_reg=lambda_) >>
ab.Activation(tf.nn.selu) >>
ab.DropOut(keep_prob=0.95, independent=True) >>
ab.Dense(output_dim=8, l2_reg=lambda_) >>
ab.Activation(tf.nn.selu) >>
ab.Dense(output_dim=1, l2_reg=lambda_)
)
f, reg = net(X=X)
lkhood = tf.distributions.Normal(loc=f, scale=noise).log_prob(Y)
loss = ab.max_posterior(lkhood, reg)
return f, loss
def nnet_ncp(X, Y):
"""Noise contrastive prior network."""
noise = ab.pos_variable(.5)
lstd = 1.
perturb_noise = 10.
net = (
ab.InputLayer(name="X", n_samples=n_samples_) >>
ab.NCPContinuousPerturb(input_noise=perturb_noise) >>
ab.Dense(output_dim=32) >>
ab.Activation(tf.nn.selu) >>
ab.Dense(output_dim=16) >>
ab.Activation(tf.nn.selu) >>
ab.Dense(output_dim=8) >>
ab.Activation(tf.nn.selu) >>
ab.DenseNCP(output_dim=1, prior_std=.1, latent_std=lstd)
)
f, kl = net(X=X)
lkhood = tf.distributions.Normal(loc=f, scale=noise).log_prob(Y)
loss = ab.elbo(lkhood, kl, N)
return f, loss
def main():
"""Run the demo."""
# Get Continuous and categorical data
df_train, df_test = fetch_data()
df = pd.concat((df_train, df_test))
X_con, X_cat, n_cats, Y = input_fn(df)
n_samples_ = tf.placeholder_with_default(T_SAMPLES, [])
# Define the continuous layers
con_layer = (
ab.InputLayer(name='con', n_samples=n_samples_) >>
ab.RandomFourier(100, kernel=ab.RBF(learn_lenscale=True)) >>
ab.Dense(output_dim=16, init_fn="autonorm")
)
# Now define the cateogrical layers, which we embed
# Note every Embed call can be different, this is just "lazy"
cat_layer_list = [ab.Embed(EMBED_DIMS, i, init_fn="autonorm")
for i in n_cats]
cat_layer = (
ab.InputLayer(name='cat', n_samples=n_samples_) >>
ab.PerFeature(*cat_layer_list) >> # Assign columns to embedding layers
ab.Activation(tf.nn.selu) >>
ab.Dense(16, init_fn="autonorm")
)
# Now we can feed the initial continuous and cateogrical layers to further
# "joint" layers after we concatenate them
net = (
ab.Concat(con_layer, cat_layer) >>
ab.Activation(tf.nn.selu) >>
ab.DenseVariational(output_dim=1)
)
# Split data into training and testing
Xt_con, Xs_con = np.split(X_con, [len(df_train)], axis=0)
Xt_cat, Xs_cat = np.split(X_cat, [len(df_train)], axis=0)
Yt, Ys = np.split(Y, [len(df_train)], axis=0)
# Graph place holders
X_con_ = tf.placeholder(tf.float32, [None, Xt_con.shape[1]])
X_cat_ = tf.placeholder(tf.int32, [None, Xt_cat.shape[1]])
Y_ = tf.placeholder(tf.float32, [None, 1])
# Feed dicts
train_dict = {X_con_: Xt_con, X_cat_: Xt_cat, Y_: Yt}
test_dict = {X_con_: Xs_con, X_cat_: Xs_cat, n_samples_: P_SAMPLES}
# Make model
N = len(Xt_con)
nn, kl = net(con=X_con_, cat=X_cat_)
likelihood = tf.distributions.Bernoulli(logits=nn)
prob = ab.sample_mean(likelihood.probs)
loss = ab.elbo(likelihood.log_prob(Y_), kl, N)
optimizer = tf.train.AdamOptimizer()
train = optimizer.minimize(loss)
init = tf.global_variables_initializer()
with tf.Session(config=CONFIG):
init.run()
# We're going to just use a feed_dict to feed in batches, which we
# generate here
batches = ab.batch(
train_dict,
batch_size=BSIZE,
n_iter=NITER)
for i, data in enumerate(batches):
train.run(feed_dict=data)
if i % 1000 == 0:
loss_val = loss.eval(feed_dict=data)
print("Iteration {}, loss = {}".format(i, loss_val))
# Predict
Ep = prob.eval(feed_dict=test_dict)
Ey = Ep > 0.5 # Max probability assignment
acc = accuracy_score(Ys.flatten(), Ey.flatten())
logloss = log_loss(Ys.flatten(), np.hstack((1 - Ep, Ep)))
print("Accuracy = {}, log loss = {}".format(acc, logloss))
# Optimization
n_epochs = 50
batch_size = 100
config = tf.ConfigProto(device_count={'GPU': 0}) # Use GPU ?
reg = 0.1
l_samples = 5
p_samples = 5
# Network architecture
net = ab.stack(
ab.InputLayer(name='X', n_samples=l_samples), # LSAMPLES,BATCH_SIZE,28*28
ab.Conv2D(filters=32, kernel_size=(5, 5),
l2_reg=reg), # LSAMPLES, BATCH_SIZE, 28, 28, 32
ab.Activation(h=tf.nn.relu),
ab.MaxPool2D(pool_size=(2, 2),
strides=(2, 2)), # LSAMPLES, BATCH_SIZE, 14, 14, 32
ab.Conv2D(filters=64, kernel_size=(5, 5),
l2_reg=reg), # LSAMPLES, BATCH_SIZE, 14, 14, 64
ab.Activation(h=tf.nn.relu),
ab.MaxPool2D(pool_size=(2, 2),
strides=(2, 2)), # LSAMPLES, BATCH_SIZE, 7, 7, 64
ab.Flatten(), # LSAMPLES, BATCH_SIZE, 7*7*64
ab.Dense(output_dim=1024, l2_reg=reg), # LSAMPLES, BATCH_SIZE, 1024
ab.Activation(h=tf.nn.relu),
ab.DropOut(0.5),
ab.Dense(output_dim=10, l2_reg=reg), # LSAMPLES, BATCH_SIZE, 10
)
def main():
"""Run the imputation demo."""
# Fetch data, one-hot targets and standardise data
data = fetch_covtype()
Xo = data.data[:, :10]
Xc = data.data[:, 10:]
Y = (data.target - 1)
Xo[:, :10] = StandardScaler().fit_transform(Xo[:, :10])
# Network construction
n_samples_ = tf.placeholder_with_default(LSAMPLES, [])
data_input = ab.InputLayer(name='Xo', n_samples=n_samples_) # Data input
# Run this with imputation
if METHOD is not None:
print("Imputation method {}.".format(METHOD))
# Fake some missing data
rnd = np.random.RandomState(RSEED)
mask = rnd.rand(*Xo.shape) < FRAC_MISSING
Xo[mask] = MISSING_VAL
# Use Aboleth to imputate
mask_input = ab.MaskInputLayer(name='M') # Missing data mask input
xm = np.ma.array(Xo, mask=mask)
if METHOD == "LearnedNormalImpute":
mean = tf.Variable(np.ma.mean(xm, axis=0).data.astype(np.float32))
std = ab.pos_variable(np.ma.std(xm, axis=0)
.data.astype(np.float32))
input_layer = ab.NormalImpute(data_input, mask_input, mean, std)
elif METHOD == "LearnedScalarImpute":
scalar = tf.Variable(tf.zeros(Xo.shape[-1]))
input_layer = ab.ScalarImpute(data_input, mask_input, scalar)
elif METHOD == "FixedNormalImpute":
mean = np.ma.mean(xm, axis=0).data.astype(np.float32)
std = np.ma.std(xm, axis=0).data.astype(np.float32)
input_layer = ab.NormalImpute(data_input, mask_input, mean, std)
elif METHOD == "FixedScalarImpute":
mean = np.ma.mean(xm, axis=0).data.astype(np.float32)
input_layer = ab.ScalarImpute(data_input, mask_input, mean)
elif METHOD == "MeanImpute":
input_layer = ab.MeanImpute(data_input, mask_input)
else:
raise ValueError("Invalid method!")
# Run this without imputation
else:
print("No missing data")
input_layer = data_input
mask = np.zeros_like(Xo)
cat_layers = (
ab.InputLayer(name='Xc', n_samples=n_samples_) >>
ab.DenseVariational(output_dim=8)
)
con_layers = (
input_layer >>
ab.DenseVariational(output_dim=8)
)
net = (
ab.Concat(cat_layers, con_layers) >>
ab.Activation(tf.nn.selu) >>
ab.DenseVariational(output_dim=NCLASSES)
)
# Split the training and testing data
Xo_tr, Xo_ts, Xc_tr, Xc_ts, Y_tr, Y_ts, M_tr, M_ts = train_test_split(
Xo.astype(np.float32),
Xc.astype(np.float32),
Y.astype(np.int32),
mask,
test_size=FRAC_TEST,
random_state=RSEED
)
N_tr, Do = Xo_tr.shape
_, Dc = Xc_tr.shape
# Data
with tf.name_scope("Input"):
Xob, Xcb, Yb, Mb = batch_training(Xo_tr, Xc_tr, Y_tr, M_tr,
n_epochs=NEPOCHS, batch_size=BSIZE)
Xo_ = tf.placeholder_with_default(Xob, shape=(None, Do))
Xc_ = tf.placeholder_with_default(Xcb, shape=(None, Dc))
# Y_ has to be this dimension for compatability with Categorical
Y_ = tf.placeholder_with_default(Yb, shape=(None,))
if METHOD is not None:
M_ = tf.placeholder_with_default(Mb, shape=(None, Do))
with tf.name_scope("Deepnet"):
if METHOD is not None:
nn, kl = net(Xo=Xo_, Xc=Xc_, M=M_)
else:
nn, kl = net(Xo=Xo_, Xc=Xc_)
lkhood = tf.distributions.Categorical(logits=nn)
loss = ab.elbo(lkhood.log_prob(Y_), kl, N_tr)
prob = ab.sample_mean(lkhood.probs)
with tf.name_scope("Train"):
optimizer = tf.train.AdamOptimizer()
global_step = tf.train.create_global_step()
train = optimizer.minimize(loss, global_step=global_step)
# Logging learning progress
log = tf.train.LoggingTensorHook(
{'step': global_step, 'loss': loss},
every_n_iter=1000
)
# This is the main training "loop"
with tf.train.MonitoredTrainingSession(
config=CONFIG,
save_summaries_steps=None,
save_checkpoint_secs=None,
hooks=[log]
) as sess:
try:
while not sess.should_stop():
sess.run(train)
except tf.errors.OutOfRangeError:
print('Input queues have been exhausted!')
pass
# Prediction
feed_dict = {Xo_: Xo_ts, Xc_: Xc_ts, Y_: [0], n_samples_: PSAMPLES}
if METHOD is not None:
feed_dict[M_] = M_ts
p = sess.run(prob, feed_dict=feed_dict)
# Get mean of samples for prediction, and max probability assignments
Ey = p.argmax(axis=1)
# Score results
acc = accuracy_score(Y_ts, Ey)
ll = log_loss(Y_ts, p)
conf = confusion_matrix(Y_ts, Ey)
print("Final scores: {}".format(METHOD))
print("\tAccuracy = {}\n\tLog loss = {}\n\tConfusion =\n{}".
format(acc, ll, conf))