scvi.distributions.ZeroInflatedNegativeBinomial#
- class scvi.distributions.ZeroInflatedNegativeBinomial(total_count=None, probs=None, logits=None, mu=None, theta=None, zi_logits=None, scale=None, validate_args=False)[source]#
Zero-inflated negative binomial distribution.
One of the following parameterizations must be provided:
(1), (
total_count
,probs
) wheretotal_count
is the number of failures until the experiment is stopped andprobs
the success probability. (2), (mu
,theta
) parameterization, which is the one used by scvi-tools. These parameters respectively control the mean and inverse dispersion of the distribution.In the (
mu
,theta
) parameterization, samples from the negative binomial are generated as follows:\(w \sim \textrm{Gamma}(\underbrace{\theta}_{\text{shape}}, \underbrace{\theta/\mu}_{\text{rate}})\)
\(x \sim \textrm{Poisson}(w)\)
- Parameters:
total_count (Optional[Tensor]) – Number of failures until the experiment is stopped.
zi_logits (Optional[Tensor]) – Logits scale of zero inflation probability.
scale (Optional[Tensor]) – Normalized mean expression of the distribution.
validate_args (bool) – Raise ValueError if arguments do not match constraints
Attributes table#
Returns the shape over which parameters are batched. |
|
Returns the shape of a single sample (without batching). |
|
Returns the mean of the distribution. |
|
Returns the mode of the distribution. |
|
Returns the standard deviation of the distribution. |
|
Returns the variance of the distribution. |
|
ZI logits. |
|
Methods table#
|
Returns the cumulative density/mass function evaluated at |
|
Returns entropy of distribution, batched over batch_shape. |
|
Returns tensor containing all values supported by a discrete distribution. |
|
Returns a new distribution instance (or populates an existing instance provided by a derived class) with batch dimensions expanded to |
|
Returns the inverse cumulative density/mass function evaluated at |
|
Log probability. |
Returns perplexity of distribution, batched over batch_shape. |
|
|
Generates a sample_shape shaped reparameterized sample or sample_shape shaped batch of reparameterized samples if the distribution parameters are batched. |
|
Sample from the distribution. |
|
Generates n samples or n batches of samples if the distribution parameters are batched. |
|
Sets whether validation is enabled or disabled. |
Attributes#
arg_constraints
- ZeroInflatedNegativeBinomial.arg_constraints = {'mu': GreaterThanEq(lower_bound=0), 'theta': GreaterThanEq(lower_bound=0), 'zi_logits': Real(), 'zi_probs': HalfOpenInterval(lower_bound=0.0, upper_bound=1.0)}#
batch_shape
- ZeroInflatedNegativeBinomial.batch_shape[source]#
Returns the shape over which parameters are batched.
event_shape
- ZeroInflatedNegativeBinomial.event_shape[source]#
Returns the shape of a single sample (without batching).
has_enumerate_support
- ZeroInflatedNegativeBinomial.has_enumerate_support = False#
has_rsample
- ZeroInflatedNegativeBinomial.has_rsample = False#
mean
mode
stddev
support
- ZeroInflatedNegativeBinomial.support = IntegerGreaterThan(lower_bound=0)#
variance
zi_logits
zi_probs
Methods#
cdf
- ZeroInflatedNegativeBinomial.cdf(value)[source]#
Returns the cumulative density/mass function evaluated at
value
.- Parameters:
value (Tensor) –
- Return type:
entropy
- ZeroInflatedNegativeBinomial.entropy()[source]#
Returns entropy of distribution, batched over batch_shape.
- Returns:
Tensor of shape batch_shape.
- Return type:
enumerate_support
- ZeroInflatedNegativeBinomial.enumerate_support(expand=True)[source]#
Returns tensor containing all values supported by a discrete distribution. The result will enumerate over dimension 0, so the shape of the result will be
(cardinality,) + batch_shape + event_shape
(whereevent_shape = ()
for univariate distributions).Note that this enumerates over all batched tensors in lock-step
[[0, 0], [1, 1], ...]
. Withexpand=False
, enumeration happens along dim 0, but with the remaining batch dimensions being singleton dimensions,[[0], [1], ..
.To iterate over the full Cartesian product use
itertools.product(m.enumerate_support())
.
expand
- ZeroInflatedNegativeBinomial.expand(batch_shape, _instance=None)[source]#
Returns a new distribution instance (or populates an existing instance provided by a derived class) with batch dimensions expanded to
batch_shape
. This method callsexpand
on the distribution’s parameters. As such, this does not allocate new memory for the expanded distribution instance. Additionally, this does not repeat any args checking or parameter broadcasting in__init__.py
, when an instance is first created.- Parameters:
batch_shape (torch.Size) – the desired expanded size.
_instance – new instance provided by subclasses that need to override
.expand
.
- Returns:
New distribution instance with batch dimensions expanded to
batch_size
.
icdf
- ZeroInflatedNegativeBinomial.icdf(value)[source]#
Returns the inverse cumulative density/mass function evaluated at
value
.- Parameters:
value (Tensor) –
- Return type:
log_prob
perplexity
- ZeroInflatedNegativeBinomial.perplexity()[source]#
Returns perplexity of distribution, batched over batch_shape.
- Returns:
Tensor of shape batch_shape.
- Return type:
rsample
- ZeroInflatedNegativeBinomial.rsample(sample_shape=torch.Size([]))[source]#
Generates a sample_shape shaped reparameterized sample or sample_shape shaped batch of reparameterized samples if the distribution parameters are batched.
- Parameters:
sample_shape (Size) –
- Return type:
sample
sample_n
- ZeroInflatedNegativeBinomial.sample_n(n)[source]#
Generates n samples or n batches of samples if the distribution parameters are batched.
set_default_validate_args
- static ZeroInflatedNegativeBinomial.set_default_validate_args(value)[source]#
Sets whether validation is enabled or disabled.
The default behavior mimics Python’s
assert
statement: validation is on by default, but is disabled if Python is run in optimized mode (viapython -O
). Validation may be expensive, so you may want to disable it once a model is working.- Parameters:
value (bool) – Whether to enable validation.
- Return type:
None