def pca(K, d, N):
#define the weights
with inf.replicate(size=K):
w = inf.models.Normal(0, 1, dim=d)
# define the generative model
with inf.replicate(size=N):
z = inf.models.Normal(0, 1, dim=K)
x = inf.models.Normal(inf.matmul(z, w), 1.0, observed=True, dim=d)
def pca_with_ard_prior(K, d, N):
#define the weights
with inf.replicate(size=K):
w = inf.models.Normal(0, 1, dim=d)
sigma = inf.models.InverseGamma(1.0, 1.0)
# define the generative model
with inf.replicate(size=N):
z = inf.models.Normal(0, 1, dim=K)
x = inf.models.Normal(inf.matmul(z, w), sigma, observed=True, dim=d)
def log_regression(K, d, N):
#define the weights
w0 = inf.models.Normal(0, 1, dim=K)
with inf.replicate(size=K):
w = inf.models.Normal(0, 1, dim=d)
# define the generative model
with inf.replicate(size=N):
x = inf.models.Normal(0, 1, observed=True, dim=d)
y = inf.models.Bernoulli(logits=w0 +
inf.matmul(x, w, transpose_b=True),
observed=True)
import edward as ed
import inferpy as inf
from inferpy.models import Normal, InverseGamma
K, d, N = 5, 10, 200
# model definition
with inf.ProbModel() as m:
#define the weights
with inf.replicate(size=K):
w = Normal(0, 1, dim=d)
sigma = InverseGamma(1.0, 1.0)
# define the generative model
with inf.replicate(size=N):
z = Normal(0, 1, dim=K)
x = Normal(inf.matmul(z, w), sigma, observed=True, dim=d)
# toy data generation
x_train = Normal(loc=0, scale=1., dim=d).sample(N)
data = {x.name: x_train}
# compile and fit the model with training data
m.compile()
m.fit(data)
#extract the hidden representation from a set of observations
hidden_encoding = m.posterior(z)
d, N = 10, 500
#number of classes
K = 3
# model definition
with inf.ProbModel() as m:
#define the weights
w0 = Normal(0, 1, dim=K)
with inf.replicate(size=K):
w = Normal(0, 1, dim=d)
# define the generative model
with inf.replicate(size=N):
x = Normal(0, 1, observed=True, dim=d)
y = Bernoulli(logits=w0 + inf.matmul(x, w, transpose_b=True),
observed=True)
# toy data generation
x_train = Normal(loc=0, scale=1, dim=d).sample(N)
y_train = Bernoulli(probs=np.random.rand(K)).sample(N)
data = {x.name: x_train, y.name: y_train}
# compile and fit the model with training data
m.compile()
m.fit(data)
print(m.posterior([w, w0]))
import edward as ed
import inferpy as inf
from inferpy.models import Normal
K, d, N = 5, 10, 200
# model definition
with inf.ProbModel() as m:
#define the weights
with inf.replicate(size=K):
w = Normal(0, 1, dim=d)
# define the generative model
with inf.replicate(size=N):
z = Normal(0, 1, dim=K)
x = Normal(inf.matmul(z, w), 1.0, observed=True, dim=d)
# toy data generation
x_train = Normal(loc=0, scale=1., dim=d).sample(N)
data = {x.name: x_train}
# compile and fit the model with training data
m.compile()
m.fit(data)
#extract the hidden representation from a set of observations
hidden_encoding = m.posterior(z)
import inferpy as inf
from inferpy.models import Normal, Bernoulli, Categorical
import numpy as np
d, N = 10, 500
# model definition
with inf.ProbModel() as m:
#define the weights
w0 = Normal(0, 1)
with inf.replicate(size=d):
w = Normal(0, 1)
# define the generative model
with inf.replicate(size=N):
x = Normal(0, 1, observed=True, dim=d)
p = w0 + inf.matmul(x, w)
y = Bernoulli(logits=p, observed=True)
# toy data generation
x_train = Normal(loc=0, scale=1, dim=d).sample(N)
y_train = Bernoulli(probs=[0.4]).sample(N)
data = {x.name: x_train, y.name: np.reshape(y_train, (N, 1))}
# compile and fit the model with training data
m.compile()
m.fit(data)
print(m.posterior([w, w0]))
scale=tf.nn.softplus(
tf.Variable(tf.random_normal([K, d]))))
inference = ed.KLqp({w: qw}, data={x: x_train})
inference.run()
# print the posterior distributions
print([qw.loc.eval()])
######## Inferpy ###########
# model definition
with inf.ProbModel() as m:
#define the weights
with inf.replicate(size=K):
w = inf.models.Normal(0, 1, dim=d)
# define the generative model
with inf.replicate(size=N):
z = inf.models.Normal(0, 1, dim=K)
x = inf.models.Normal(inf.matmul(z, w), 1.0, observed=True, dim=d)
data = {x.name: x_train}
# compile and fit the model with training data
m.compile()
m.fit(data)
#extract the hidden representation from a set of observations
hidden_encoding = m.posterior(z)
###### Inferpy ########
# model definition
with inf.ProbModel() as m:
#define the weights
w0 = inf.models.Normal(0,1, dim=K)
with inf.replicate(size=K):
w = inf.models.Normal(0, 1, dim=d)
# define the generative model
with inf.replicate(size=N):
x = inf.models.Normal(0, 1, observed=True, dim=d)
y = inf.models.Bernoulli(logits = w0 + inf.matmul(x, w, transpose_b=True), observed=True)
data = {x.name: x_train, y.name: y_train}
# compile and fit the model with training data
m.compile()
m.fit(data)
print(m.posterior([w, w0]))
import inferpy as inf
from inferpy.models import Normal
N = 200
M = 50
K = 5
# Shape [M,K]
with inf.replicate(size=K):
gamma = Normal(0, 1, dim=M)
# Shape [N,K]
with inf.replicate(size=N):
w = Normal(0, 1, dim=K)
# x_mn has shape [N,K] x [K,M] = [N,M]
with inf.replicate(size=N):
x = Normal(inf.matmul(w, gamma), 1, observed=True)
m = inf.ProbModel([w, gamma, x])
data = m.sample(size=N)
log_prob = m.log_prob(data)
m.compile(infMethod='KLqp')
m.fit(data)
print(m.posterior([w, gamma]))
d, N = 10, 200
#define the weights
w0 = Normal(0,1)
with inf.replicate(size=d):
w = Normal(0, 1)
p = Beta(1,1)
# define the generative model
with inf.replicate(size=N):
x = Normal(0, 1, observed=True, dim=d)
y0 = Normal(inf.matmul(x,w), 1.0, observed=True)
h = Categorical(probs=[p, 1-p])
y1 = Deterministic(1.)
# not working until issue #58 is solved
y = Deterministic(inf.case({h.equal(0) : y0, h.equal(1) : y1}), observed = True)
h = Categorical(probs=[0.2,0.8])
h.probs
h.sample()
d=20
#Prior for the principal components
with inf.replicate(size = K):
w = Normal(loc = 0, scale = 1, dim = d) # x.shape = [K,d]
###
# Number of observations
N = 1000
# define the generative model
with inf.replicate(size=N):
z = Normal(0, 1, dim=K) # z.shape = [N,K]
x = Normal(inf.matmul(z,w), 1.0, observed=True, dim=d) # x.shape = [N,d]
###
from inferpy import ProbModel
# Define the model
pca = ProbModel(varlist = [w,z,x])
# Compile the model
pca.compile(infMethod = 'KLqp')
###
import edward as ed
import inferpy as inf
from inferpy.models import Normal
K, d, N = 5, 10, 200
# model definition
with inf.ProbModel() as m:
#define the weights
with inf.replicate(size=K):
w = Normal(0, 1, dim=d)
# define the generative model
with inf.replicate(size=N):
z = Normal(0, 1, dim=K)
x = Normal(inf.matmul(z,w),
1.0, observed=True, dim=d)
# data generation
x_train = Normal(loc=0, scale=1., dim=d).sample(N)
data = {x.name: x_train}
# compile and fit the model with training data
m.compile()
m.fit(data)
#extract the hidden representation from a set of observations
hidden_encoding = m.posterior(z)
from inferpy.models import Normal
d, N = 10, 200
# model definition
with inf.ProbModel() as m:
#define the weights
w0 = Normal(0,1)
with inf.replicate(size=d):
w = Normal(0, 1)
# define the generative model
with inf.replicate(size=N):
x = Normal(0, 1, observed=True, dim=d)
y = Normal(w0 + inf.matmul(x,w), 1.0, observed=True)
# toy data generation
x_train = Normal(loc=0, scale=1, dim=d).sample(N)
y_train = Normal(loc=5, scale=1, dim=1).sample(N)
data = {x.name: x_train, y.name: y_train}
# compile and fit the model with training data
m.compile()
m.fit(data)
print(m.posterior([w, w0]))
