Class OneHotCategorical
Inherits From: Distribution
Defined in tensorflow/contrib/distributions/python/ops/onehot_categorical.py
.
OneHotCategorical distribution.
The categorical distribution is parameterized by the log-probabilities of a set of classes. The difference between OneHotCategorical and Categorical distributions is that OneHotCategorical is a discrete distribution over one-hot bit vectors whereas Categorical is a discrete distribution over positive integers. OneHotCategorical is equivalent to Categorical except Categorical has event_dim=() while OneHotCategorical has event_dim=K, where K is the number of classes.
This class provides methods to create indexed batches of OneHotCategorical
distributions. If the provided logits
or probs
is rank 2 or higher, for
every fixed set of leading dimensions, the last dimension represents one
single OneHotCategorical distribution. When calling distribution
functions (e.g. dist.prob(x)
), logits
and x
are broadcast to the
same shape (if possible). In all cases, the last dimension of logits,x
represents single OneHotCategorical distributions.
Examples
Creates a 3-class distribution, with the 2nd class, the most likely to be drawn from.
p = [0.1, 0.5, 0.4]
dist = OneHotCategorical(probs=p)
Creates a 3-class distribution, with the 2nd class the most likely to be drawn from, using logits.
logits = [-2, 2, 0]
dist = OneHotCategorical(logits=logits)
Creates a 3-class distribution, with the 3rd class is most likely to be drawn.
# counts is a scalar.
p = [0.1, 0.4, 0.5]
dist = OneHotCategorical(probs=p)
dist.prob([0,1,0]) # Shape []
# p will be broadcast to [[0.1, 0.4, 0.5], [0.1, 0.4, 0.5]] to match.
samples = [[0,1,0], [1,0,0]]
dist.prob(samples) # Shape [2]
__init__
__init__(
logits=None,
probs=None,
dtype=tf.dtypes.int32,
validate_args=False,
allow_nan_stats=True,
name='OneHotCategorical'
)
Initialize OneHotCategorical distributions using class log-probabilities. (deprecated)
Args:
logits
: An N-DTensor
,N >= 1
, representing the log probabilities of a set of Categorical distributions. The firstN - 1
dimensions index into a batch of independent distributions and the last dimension represents a vector of logits for each class. Only one oflogits
orprobs
should be passed in.probs
: An N-DTensor
,N >= 1
, representing the probabilities of a set of Categorical distributions. The firstN - 1
dimensions index into a batch of independent distributions and the last dimension represents a vector of probabilities for each class. Only one oflogits
orprobs
should be passed in.dtype
: The type of the event samples (default: int32).validate_args
: Pythonbool
, defaultFalse
. WhenTrue
distribution parameters are checked for validity despite possibly degrading runtime performance. WhenFalse
invalid inputs may silently render incorrect outputs.allow_nan_stats
: Pythonbool
, defaultTrue
. WhenTrue
, statistics (e.g., mean, mode, variance) use the value "NaN
" to indicate the result is undefined. WhenFalse
, an exception is raised if one or more of the statistic's batch members are undefined.name
: Pythonstr
name prefixed to Ops created by this class.
Properties
allow_nan_stats
Python bool
describing behavior when a stat is undefined.
Stats return +/- infinity when it makes sense. E.g., the variance of a Cauchy distribution is infinity. However, sometimes the statistic is undefined, e.g., if a distribution's pdf does not achieve a maximum within the support of the distribution, the mode is undefined. If the mean is undefined, then by definition the variance is undefined. E.g. the mean for Student's T for df = 1 is undefined (no clear way to say it is either + or - infinity), so the variance = E[(X - mean)**2] is also undefined.
Returns:
allow_nan_stats
: Pythonbool
.
batch_shape
Shape of a single sample from a single event index as a TensorShape
.
May be partially defined or unknown.
The batch dimensions are indexes into independent, non-identical parameterizations of this distribution.
Returns:
batch_shape
:TensorShape
, possibly unknown.
dtype
The DType
of Tensor
s handled by this Distribution
.
event_shape
Shape of a single sample from a single batch as a TensorShape
.
May be partially defined or unknown.
Returns:
event_shape
:TensorShape
, possibly unknown.
event_size
Scalar int32
tensor: the number of classes.
logits
Vector of coordinatewise logits.
name
Name prepended to all ops created by this Distribution
.
parameters
Dictionary of parameters used to instantiate this Distribution
.
probs
Vector of coordinatewise probabilities.
reparameterization_type
Describes how samples from the distribution are reparameterized.
Currently this is one of the static instances
distributions.FULLY_REPARAMETERIZED
or distributions.NOT_REPARAMETERIZED
.
Returns:
An instance of ReparameterizationType
.
validate_args
Python bool
indicating possibly expensive checks are enabled.
Methods
tf.contrib.distributions.OneHotCategorical.batch_shape_tensor
batch_shape_tensor(name='batch_shape_tensor')
Shape of a single sample from a single event index as a 1-D Tensor
.
The batch dimensions are indexes into independent, non-identical parameterizations of this distribution.
Args:
name
: name to give to the op
Returns:
batch_shape
:Tensor
.
tf.contrib.distributions.OneHotCategorical.cdf
cdf(
value,
name='cdf'
)
Cumulative distribution function.
Given random variable X
, the cumulative distribution function cdf
is:
cdf(x) := P[X <= x]
Args:
value
:float
ordouble
Tensor
.name
: Pythonstr
prepended to names of ops created by this function.
Returns:
cdf
: aTensor
of shapesample_shape(x) + self.batch_shape
with values of typeself.dtype
.
tf.contrib.distributions.OneHotCategorical.copy
copy(**override_parameters_kwargs)
Creates a deep copy of the distribution.
Args:
**override_parameters_kwargs
: String/value dictionary of initialization arguments to override with new values.
Returns:
distribution
: A new instance oftype(self)
initialized from the union of self.parameters and override_parameters_kwargs, i.e.,dict(self.parameters, **override_parameters_kwargs)
.
tf.contrib.distributions.OneHotCategorical.covariance
covariance(name='covariance')
Covariance.
Covariance is (possibly) defined only for non-scalar-event distributions.
For example, for a length-k
, vector-valued distribution, it is calculated
as,
Cov[i, j] = Covariance(X_i, X_j) = E[(X_i - E[X_i]) (X_j - E[X_j])]
where Cov
is a (batch of) k x k
matrix, 0 <= (i, j) < k
, and E
denotes expectation.
Alternatively, for non-vector, multivariate distributions (e.g.,
matrix-valued, Wishart), Covariance
shall return a (batch of) matrices
under some vectorization of the events, i.e.,
Cov[i, j] = Covariance(Vec(X)_i, Vec(X)_j) = [as above]
where Cov
is a (batch of) k' x k'
matrices,
0 <= (i, j) < k' = reduce_prod(event_shape)
, and Vec
is some function
mapping indices of this distribution's event dimensions to indices of a
length-k'
vector.
Args:
name
: Pythonstr
prepended to names of ops created by this function.
Returns:
covariance
: Floating-pointTensor
with shape[B1, ..., Bn, k', k']
where the firstn
dimensions are batch coordinates andk' = reduce_prod(self.event_shape)
.
tf.contrib.distributions.OneHotCategorical.cross_entropy
cross_entropy(
other,
name='cross_entropy'
)
Computes the (Shannon) cross entropy.
Denote this distribution (self
) by P
and the other
distribution by
Q
. Assuming P, Q
are absolutely continuous with respect to
one another and permit densities p(x) dr(x)
and q(x) dr(x)
, (Shanon)
cross entropy is defined as:
H[P, Q] = E_p[-log q(X)] = -int_F p(x) log q(x) dr(x)
where F
denotes the support of the random variable X ~ P
.
Args:
other
:tfp.distributions.Distribution
instance.name
: Pythonstr
prepended to names of ops created by this function.
Returns:
cross_entropy
:self.dtype
Tensor
with shape[B1, ..., Bn]
representingn
different calculations of (Shanon) cross entropy.
tf.contrib.distributions.OneHotCategorical.entropy
entropy(name='entropy')
Shannon entropy in nats.
tf.contrib.distributions.OneHotCategorical.event_shape_tensor
event_shape_tensor(name='event_shape_tensor')
Shape of a single sample from a single batch as a 1-D int32 Tensor
.
Args:
name
: name to give to the op
Returns:
event_shape
:Tensor
.
tf.contrib.distributions.OneHotCategorical.is_scalar_batch
is_scalar_batch(name='is_scalar_batch')
Indicates that batch_shape == []
.
Args:
name
: Pythonstr
prepended to names of ops created by this function.
Returns:
is_scalar_batch
:bool
scalarTensor
.
tf.contrib.distributions.OneHotCategorical.is_scalar_event
is_scalar_event(name='is_scalar_event')
Indicates that event_shape == []
.
Args:
name
: Pythonstr
prepended to names of ops created by this function.
Returns:
is_scalar_event
:bool
scalarTensor
.
tf.contrib.distributions.OneHotCategorical.kl_divergence
kl_divergence(
other,
name='kl_divergence'
)
Computes the Kullback--Leibler divergence.
Denote this distribution (self
) by p
and the other
distribution by
q
. Assuming p, q
are absolutely continuous with respect to reference
measure r
, the KL divergence is defined as:
KL[p, q] = E_p[log(p(X)/q(X))]
= -int_F p(x) log q(x) dr(x) + int_F p(x) log p(x) dr(x)
= H[p, q] - H[p]
where F
denotes the support of the random variable X ~ p
, H[., .]
denotes (Shanon) cross entropy, and H[.]
denotes (Shanon) entropy.
Args:
other
:tfp.distributions.Distribution
instance.name
: Pythonstr
prepended to names of ops created by this function.
Returns:
kl_divergence
:self.dtype
Tensor
with shape[B1, ..., Bn]
representingn
different calculations of the Kullback-Leibler divergence.
tf.contrib.distributions.OneHotCategorical.log_cdf
log_cdf(
value,
name='log_cdf'
)
Log cumulative distribution function.
Given random variable X
, the cumulative distribution function cdf
is:
log_cdf(x) := Log[ P[X <= x] ]
Often, a numerical approximation can be used for log_cdf(x)
that yields
a more accurate answer than simply taking the logarithm of the cdf
when
x << -1
.
Args:
value
:float
ordouble
Tensor
.name
: Pythonstr
prepended to names of ops created by this function.
Returns:
logcdf
: aTensor
of shapesample_shape(x) + self.batch_shape
with values of typeself.dtype
.
tf.contrib.distributions.OneHotCategorical.log_prob
log_prob(
value,
name='log_prob'
)
Log probability density/mass function.
Args:
value
:float
ordouble
Tensor
.name
: Pythonstr
prepended to names of ops created by this function.
Returns:
log_prob
: aTensor
of shapesample_shape(x) + self.batch_shape
with values of typeself.dtype
.
tf.contrib.distributions.OneHotCategorical.log_survival_function
log_survival_function(
value,
name='log_survival_function'
)
Log survival function.
Given random variable X
, the survival function is defined:
log_survival_function(x) = Log[ P[X > x] ]
= Log[ 1 - P[X <= x] ]
= Log[ 1 - cdf(x) ]
Typically, different numerical approximations can be used for the log
survival function, which are more accurate than 1 - cdf(x)
when x >> 1
.
Args:
value
:float
ordouble
Tensor
.name
: Pythonstr
prepended to names of ops created by this function.
Returns:
Tensor
of shape sample_shape(x) + self.batch_shape
with values of type
self.dtype
.
tf.contrib.distributions.OneHotCategorical.mean
mean(name='mean')
Mean.
tf.contrib.distributions.OneHotCategorical.mode
mode(name='mode')
Mode.
tf.contrib.distributions.OneHotCategorical.param_shapes
param_shapes(
cls,
sample_shape,
name='DistributionParamShapes'
)
Shapes of parameters given the desired shape of a call to sample()
.
This is a class method that describes what key/value arguments are required
to instantiate the given Distribution
so that a particular shape is
returned for that instance's call to sample()
.
Subclasses should override class method _param_shapes
.
Args:
sample_shape
:Tensor
or python list/tuple. Desired shape of a call tosample()
.name
: name to prepend ops with.
Returns:
dict
of parameter name to Tensor
shapes.
tf.contrib.distributions.OneHotCategorical.param_static_shapes
param_static_shapes(
cls,
sample_shape
)
param_shapes with static (i.e. TensorShape
) shapes.
This is a class method that describes what key/value arguments are required
to instantiate the given Distribution
so that a particular shape is
returned for that instance's call to sample()
. Assumes that the sample's
shape is known statically.
Subclasses should override class method _param_shapes
to return
constant-valued tensors when constant values are fed.
Args:
sample_shape
:TensorShape
or python list/tuple. Desired shape of a call tosample()
.
Returns:
dict
of parameter name to TensorShape
.
Raises:
ValueError
: ifsample_shape
is aTensorShape
and is not fully defined.
tf.contrib.distributions.OneHotCategorical.prob
prob(
value,
name='prob'
)
Probability density/mass function.
Args:
value
:float
ordouble
Tensor
.name
: Pythonstr
prepended to names of ops created by this function.
Returns:
prob
: aTensor
of shapesample_shape(x) + self.batch_shape
with values of typeself.dtype
.
tf.contrib.distributions.OneHotCategorical.quantile
quantile(
value,
name='quantile'
)
Quantile function. Aka "inverse cdf" or "percent point function".
Given random variable X
and p in [0, 1]
, the quantile
is:
quantile(p) := x such that P[X <= x] == p
Args:
value
:float
ordouble
Tensor
.name
: Pythonstr
prepended to names of ops created by this function.
Returns:
quantile
: aTensor
of shapesample_shape(x) + self.batch_shape
with values of typeself.dtype
.
tf.contrib.distributions.OneHotCategorical.sample
sample(
sample_shape=(),
seed=None,
name='sample'
)
Generate samples of the specified shape.
Note that a call to sample()
without arguments will generate a single
sample.
Args:
sample_shape
: 0D or 1Dint32
Tensor
. Shape of the generated samples.seed
: Python integer seed for RNGname
: name to give to the op.
Returns:
samples
: aTensor
with prepended dimensionssample_shape
.
tf.contrib.distributions.OneHotCategorical.stddev
stddev(name='stddev')
Standard deviation.
Standard deviation is defined as,
stddev = E[(X - E[X])**2]**0.5
where X
is the random variable associated with this distribution, E
denotes expectation, and stddev.shape = batch_shape + event_shape
.
Args:
name
: Pythonstr
prepended to names of ops created by this function.
Returns:
stddev
: Floating-pointTensor
with shape identical tobatch_shape + event_shape
, i.e., the same shape asself.mean()
.
tf.contrib.distributions.OneHotCategorical.survival_function
survival_function(
value,
name='survival_function'
)
Survival function.
Given random variable X
, the survival function is defined:
survival_function(x) = P[X > x]
= 1 - P[X <= x]
= 1 - cdf(x).
Args:
value
:float
ordouble
Tensor
.name
: Pythonstr
prepended to names of ops created by this function.
Returns:
Tensor
of shape sample_shape(x) + self.batch_shape
with values of type
self.dtype
.
tf.contrib.distributions.OneHotCategorical.variance
variance(name='variance')
Variance.
Variance is defined as,
Var = E[(X - E[X])**2]
where X
is the random variable associated with this distribution, E
denotes expectation, and Var.shape = batch_shape + event_shape
.
Args:
name
: Pythonstr
prepended to names of ops created by this function.
Returns:
variance
: Floating-pointTensor
with shape identical tobatch_shape + event_shape
, i.e., the same shape asself.mean()
.