def test_categorical_likelihood(make_data):
"""Test aboleth with a tf.distributions.Categorical likelihood.
Since it is a bit of an odd half-multivariate case.
"""
x, y, _, = make_data
N, K = x.shape
# Make two classes (K = 2)
Y = np.zeros(len(y), dtype=np.int32)
Y[y[:, 0] > 0] = 1
layers = ab.stack(
ab.InputLayer(name='X', n_samples=10),
lambda X: (X, 0.0) # Mock a sampling layer, with 2-class output
)
nn, reg = layers(X=x.astype(np.float32))
like = tf.distributions.Categorical(logits=nn)
ELBO = ab.elbo(like, Y, N, reg)
MAP = ab.max_posterior(like, Y, reg)
tc = tf.test.TestCase()
with tc.test_session():
tf.global_variables_initializer().run()
assert like.probs.eval().shape == (10, N, K)
assert like.prob(Y).eval().shape == (10, N)
L = ELBO.eval()
assert np.isscalar(L)
L = MAP.eval()
assert np.isscalar(L)
def test_stack_multilayer():
"""Test implementation of stack."""
f = StringMultiLayer("f", ["x", "y"], 10.0)
g = StringLayer("g", 20.0)
h = StringLayer("h", 30.0)
r = ab.stack(f, g, h)
tc = tf.test.TestCase()
with tc.test_session():
phi, loss = r(x="x", y="y")
assert phi == "h(g(f(x,y)))"
assert loss.eval() == 60.0
def make_graph():
"""Make the requirements for making a simple tf graph."""
x, Y, X = data()
layers = ab.stack(
ab.InputLayer(name='X', n_samples=10),
lambda X: (X[:, :, 0:1], 0.0) # Mock a sampling layer
)
N = len(x)
X_ = tf.placeholder(tf.float32, x.shape)
Y_ = tf.placeholder(tf.float32, Y.shape)
N_ = tf.placeholder(tf.float32)
return x, Y, N, X_, Y_, N_, layers
def test_categorical_likelihood(make_data, likelihood):
"""Test aboleth with discrete likelihoods.
Since these are kind of corner cases...
"""
x, y, _, = make_data
like, K = likelihood
N, _ = x.shape
# Make two classes (K = 2)
Y = np.zeros(len(y), dtype=np.int32)
Y[y[:, 0] > 0] = 1
if K == 1:
Y = Y[:, np.newaxis]
X_ = tf.placeholder(tf.float32, x.shape)
Y_ = tf.placeholder(tf.int32, Y.shape)
n_samples_ = tf.placeholder(tf.int32)
layers = ab.stack(
ab.InputLayer(name='X', n_samples=n_samples_),
ab.Dense(output_dim=K)
)
nn, reg = layers(X=X_)
like = like(logits=nn)
log_like = like.log_prob(Y_)
prob = like.prob(Y_)
ELBO = ab.elbo(log_like, reg, N)
MAP = ab.max_posterior(log_like, reg)
fd = {X_: x, Y_: Y, n_samples_: 10}
tc = tf.test.TestCase()
with tc.test_session():
tf.global_variables_initializer().run()
assert like.probs.eval(feed_dict=fd).shape == (10, N, K)
assert prob.eval(feed_dict=fd).shape == (10,) + Y.shape
L = ELBO.eval(feed_dict=fd)
L = MAP.eval(feed_dict=fd)
assert np.isscalar(L)
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():
# Dataset
mnist_data = tf.contrib.learn.datasets.mnist.read_data_sets('./mnist_demo',
reshape=False)
BSIZE = 10 # mini-batch size
CONFIG = tf.ConfigProto(device_count={'GPU': 0}) # Use GPU ?
LSAMPLES = 1 # We're only using 1 dropout "sample" for learning to be more
# like a MAP network
PSAMPLES = 50 # Number of samples for prediction
REG = 0.001 # weight regularizer
# Network structure
n_samples_ = tf.placeholder_with_default(LSAMPLES, [])
net = ab.stack(
ab.InputLayer(name='X', n_samples=n_samples_),
ab.DropOut(0.95, alpha=True),
ab.Dense(output_dim=128, l2_reg=REG, init_fn="autonorm"),
ab.Activation(h=tf.nn.selu),
ab.DropOut(0.9, alpha=True),
ab.Dense(output_dim=64, l2_reg=REG, init_fn="autonorm"),
ab.Activation(h=tf.nn.selu),
ab.DropOut(0.9, alpha=True),
ab.Dense(output_dim=32, l2_reg=REG, init_fn="autonorm"),
ab.Activation(h=tf.nn.selu),
ab.DropOut(0.9, alpha=True),
ab.Dense(output_dim=1, l2_reg=REG, init_fn="autonorm"),
)
def main():
"""Run the demo."""
data = load_breast_cancer()
X = data.data.astype(np.float32)
y = data.target.astype(np.int32)[:, np.newaxis]
X = StandardScaler().fit_transform(X).astype(np.float32)
N, D = X.shape
NFEATURES = 1500 # Number of random features/bases to use in the approximation
NOISE = 3.0 # Initial estimate of the observation noise
# Random Fourier Features, this is setting up an anisotropic length scale, or
# one length scale per dimension
LENSCALE = tf.Variable(5 * np.ones((21, 1), dtype=np.float32))
KERNEL = ab.RBF(ab.pos(LENSCALE))
# Variational Fourier Features -- length-scale setting here is the "prior"
# LENSCALE = 10.
# KERNEL = ab.RBFVariational(lenscale=LENSCALE, lenscale_posterior=LENSCALE)
# Build the approximate GP
net = ab.stack(
ab.InputLayer(name='X', n_samples=NSAMPLES),
ab.RandomFourier(n_features=NFEATURES, kernel=KERNEL),
ab.DenseVariational(output_dim=1, full=True)
)
# Learning and prediction settings
BATCH_SIZE = 50 # number of observations per mini batch
NEPOCHS = 100 # Number of times to iterate though the dataset
NPREDICTSAMPLES = 10 # results in NSAMPLES * NPREDICTSAMPLES samples
CONFIG = tf.ConfigProto(device_count={'GPU': 1}) # Use GPU ?
def main():
"""Run the demo."""
data = fetch_gpml_sarcos_data()
Xr = data.train.data.astype(np.float32)
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)
# Define the continuous layers
con_layer = (ab.InputLayer(name='con', n_samples=T_SAMPLES) >>
ab.DenseVariational(output_dim=5, full=True))
# Now define the cateogrical layers, which we embed
# Note every embed_var call can be different, this is just "lazy"
cat_layer_list = [ab.EmbedVariational(EMBED_DIMS, i) for i in n_cats]
cat_layer = (
ab.InputLayer(name='cat', n_samples=T_SAMPLES) >> ab.PerFeature(
*cat_layer_list) # Assign columns to an embedding layers
)
# Now we can feed the initial continuous and cateogrical layers to further
# "joint" layers after we concatenate them
net = ab.stack(ab.Concat(con_layer, cat_layer),
ab.RandomArcCosine(100, 1.),
ab.DenseVariational(output_dim=1, full=True))
# 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}
# Make model
N = len(Xt_con)
nn, kl = net(con=X_con_, cat=X_cat_)
likelihood = tf.distributions.Bernoulli(logits=nn)
loss = ab.elbo(likelihood, Y_, N, kl)
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 = ab.predict_expected(nn, test_dict, P_SAMPLES)
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))
NITER = 20000 # Training iterations per fold
BSIZE = 10 # mini-batch size
CONFIG = tf.ConfigProto(device_count={'GPU': 0}) # Use GPU ?
LSAMPLES = 1 # We're only using 1 dropout "sample" for learning to be more
# like a MAP network
PSAMPLES = 50 # Number of samples for prediction
REG = 0.001 # weight regularizer
# Network structure
n_samples_ = tf.placeholder_with_default(LSAMPLES, [])
net = ab.stack(
ab.InputLayer(name='X', n_samples=n_samples_),
ab.DropOut(0.95),
ab.DenseMAP(output_dim=64, l1_reg=0., l2_reg=REG),
ab.Activation(h=tf.nn.relu),
ab.DropOut(0.5),
ab.DenseMAP(output_dim=64, l1_reg=0., l2_reg=REG),
ab.Activation(h=tf.nn.relu),
ab.DropOut(0.5),
ab.DenseMAP(output_dim=1, l1_reg=0., l2_reg=REG),
)
def main():
"""Run the demo."""
data = load_breast_cancer()
X = data.data.astype(np.float32)
y = data.target.astype(np.int32)[:, np.newaxis]
X = StandardScaler().fit_transform(X).astype(np.float32)
N, D = X.shape