def __init__(
self,
draws=2000,
start=None,
model=None,
random_seed=None,
threshold=0.5,
):
"""
Parameters
----------
draws: int
The number of samples to draw from the posterior (i.e. last stage). And also the number of
independent chains. Defaults to 2000.
start: dict, or array of dict
Starting point in parameter space. It should be a list of dict with length `chains`.
When None (default) the starting point is sampled from the prior distribution.
model: Model (optional if in ``with`` context)).
random_seed: int
Value used to initialize the random number generator.
threshold: float
Determines the change of beta from stage to stage, i.e.indirectly the number of stages,
the higher the value of `threshold` the higher the number of stages. Defaults to 0.5.
It should be between 0 and 1.
"""
self.draws = draws
self.start = start
if threshold < 0 or threshold > 1:
raise ValueError(
f"Threshold value {threshold} must be between 0 and 1")
self.threshold = threshold
self.model = model
self.rng = np.random.default_rng(seed=random_seed)
self.model = modelcontext(model)
self.variables = inputvars(self.model.value_vars)
self.var_info = {}
self.tempered_posterior = None
self.prior_logp = None
self.likelihood_logp = None
self.tempered_posterior_logp = None
self.prior_logp_func = None
self.likelihood_logp_func = None
self.log_marginal_likelihood = 0
self.beta = 0
self.iteration = 0
self.resampling_indexes = None
self.weights = np.ones(self.draws) / self.draws
def __init__(self,
vars=None,
prior_cov=None,
prior_chol=None,
model=None,
**kwargs):
self.model = modelcontext(model)
chol = get_chol(prior_cov, prior_chol)
self.prior_chol = at.as_tensor_variable(chol)
if vars is None:
vars = self.model.cont_vars
else:
vars = [self.model.rvs_to_values.get(var, var) for var in vars]
vars = inputvars(vars)
super().__init__(vars, [self.model.compile_logp()], **kwargs)
def __init__(self,
vars=None,
w=1.0,
tune=True,
model=None,
iter_limit=np.inf,
**kwargs):
self.model = modelcontext(model)
self.w = w
self.tune = tune
self.n_tunes = 0.0
self.iter_limit = iter_limit
if vars is None:
vars = self.model.cont_vars
else:
vars = [self.model.rvs_to_values.get(var, var) for var in vars]
vars = inputvars(vars)
super().__init__(vars, [self.model.compile_logp()], **kwargs)
def fixed_hessian(point, vars=None, model=None):
"""
Returns a fixed Hessian for any chain location.
Parameters
----------
model: Model (optional if in `with` context)
point: dict
vars: list
Variables for which Hessian is to be calculated.
"""
model = modelcontext(model)
if vars is None:
vars = model.cont_vars
vars = inputvars(vars)
point = Point(point, model=model)
rval = np.ones(DictToArrayBijection.map(point).size) / 10
return rval
def find_MAP(start=None,
vars=None,
method="L-BFGS-B",
return_raw=False,
include_transformed=True,
progressbar=True,
maxeval=5000,
model=None,
*args,
seed: Optional[int] = None,
**kwargs):
"""Finds the local maximum a posteriori point given a model.
`find_MAP` should not be used to initialize the NUTS sampler. Simply call
``pymc.sample()`` and it will automatically initialize NUTS in a better
way.
Parameters
----------
start: `dict` of parameter values (Defaults to `model.initial_point`)
vars: list
List of variables to optimize and set to optimum (Defaults to all continuous).
method: string or callable
Optimization algorithm (Defaults to 'L-BFGS-B' unless
discrete variables are specified in `vars`, then
`Powell` which will perform better). For instructions on use of a callable,
refer to SciPy's documentation of `optimize.minimize`.
return_raw: bool
Whether to return the full output of scipy.optimize.minimize (Defaults to `False`)
include_transformed: bool, optional defaults to True
Flag for reporting automatically transformed variables in addition
to original variables.
progressbar: bool, optional defaults to True
Whether or not to display a progress bar in the command line.
maxeval: int, optional, defaults to 5000
The maximum number of times the posterior distribution is evaluated.
model: Model (optional if in `with` context)
*args, **kwargs
Extra args passed to scipy.optimize.minimize
Notes
-----
Older code examples used `find_MAP` to initialize the NUTS sampler,
but this is not an effective way of choosing starting values for sampling.
As a result, we have greatly enhanced the initialization of NUTS and
wrapped it inside ``pymc.sample()`` and you should thus avoid this method.
"""
model = modelcontext(model)
if vars is None:
vars = model.cont_vars
if not vars:
raise ValueError("Model has no unobserved continuous variables.")
vars = inputvars(vars)
disc_vars = list(typefilter(vars, discrete_types))
allinmodel(vars, model)
ipfn = make_initial_point_fn(
model=model,
jitter_rvs={},
return_transformed=True,
overrides=start,
)
if seed is None:
seed = model.rng_seeder.randint(2**30, dtype=np.int64)
start = ipfn(seed)
model.check_start_vals(start)
x0 = DictToArrayBijection.map(start)
# TODO: If the mapping is fixed, we can simply create graphs for the
# mapping and avoid all this bijection overhead
def logp_func(x):
return DictToArrayBijection.mapf(model.fastlogp_nojac)(RaveledVars(
x, x0.point_map_info))
try:
# This might be needed for calls to `dlogp_func`
# start_map_info = tuple((v.name, v.shape, v.dtype) for v in vars)
def dlogp_func(x):
return DictToArrayBijection.mapf(model.fastdlogp_nojac(vars))(
RaveledVars(x, x0.point_map_info))
compute_gradient = True
except (AttributeError, NotImplementedError, tg.NullTypeGradError):
compute_gradient = False
if disc_vars or not compute_gradient:
pm._log.warning(
"Warning: gradient not available." +
"(E.g. vars contains discrete variables). MAP " +
"estimates may not be accurate for the default " +
"parameters. Defaulting to non-gradient minimization " +
"'Powell'.")
method = "Powell"
if compute_gradient:
cost_func = CostFuncWrapper(maxeval, progressbar, logp_func,
dlogp_func)
else:
cost_func = CostFuncWrapper(maxeval, progressbar, logp_func)
try:
opt_result = minimize(cost_func,
x0.data,
method=method,
jac=compute_gradient,
*args,
**kwargs)
mx0 = opt_result["x"] # r -> opt_result
except (KeyboardInterrupt, StopIteration) as e:
mx0, opt_result = cost_func.previous_x, None
if isinstance(e, StopIteration):
pm._log.info(e)
finally:
last_v = cost_func.n_eval
if progressbar:
assert isinstance(cost_func.progress, ProgressBar)
cost_func.progress.total = last_v
cost_func.progress.update(last_v)
print(file=sys.stdout)
mx0 = RaveledVars(mx0, x0.point_map_info)
vars = get_default_varnames(model.unobserved_value_vars,
include_transformed)
mx = {
var.name: value
for var, value in zip(
vars,
model.fastfn(vars)(DictToArrayBijection.rmap(mx0)))
}
if return_raw:
return mx, opt_result
else:
return mx
def __init__(self, vars=None, num_particles=40, max_stages=100, batch="auto", model=None):
_log.warning("BART is experimental. Use with caution.")
model = modelcontext(model)
initial_values = model.recompute_initial_point()
value_bart = inputvars(vars)[0]
self.bart = model.values_to_rvs[value_bart].owner.op
self.X = self.bart.X
self.Y = self.bart.Y
self.missing_data = np.any(np.isnan(self.X))
self.m = self.bart.m
self.alpha = self.bart.alpha
self.k = self.bart.k
self.alpha_vec = self.bart.split_prior
if self.alpha_vec is None:
self.alpha_vec = np.ones(self.X.shape[1])
self.init_mean = self.Y.mean()
# if data is binary
Y_unique = np.unique(self.Y)
if Y_unique.size == 2 and np.all(Y_unique == [0, 1]):
self.mu_std = 6 / (self.k * self.m ** 0.5)
# maybe we need to check for count data
else:
self.mu_std = (2 * self.Y.std()) / (self.k * self.m ** 0.5)
self.num_observations = self.X.shape[0]
self.num_variates = self.X.shape[1]
self.available_predictors = list(range(self.num_variates))
self.sum_trees = np.full_like(self.Y, self.init_mean).astype(aesara.config.floatX)
self.a_tree = Tree.init_tree(
leaf_node_value=self.init_mean / self.m,
idx_data_points=np.arange(self.num_observations, dtype="int32"),
)
self.mean = fast_mean()
self.normal = NormalSampler()
self.prior_prob_leaf_node = compute_prior_probability(self.alpha)
self.ssv = SampleSplittingVariable(self.alpha_vec)
self.tune = True
if batch == "auto":
batch = max(1, int(self.m * 0.1))
self.batch = (batch, batch)
else:
if isinstance(batch, (tuple, list)):
self.batch = batch
else:
self.batch = (batch, batch)
self.log_num_particles = np.log(num_particles)
self.indices = list(range(2, num_particles))
self.len_indices = len(self.indices)
self.max_stages = max_stages
shared = make_shared_replacements(initial_values, vars, model)
self.likelihood_logp = logp(initial_values, [model.datalogpt], vars, shared)
self.all_particles = []
for i in range(self.m):
self.a_tree.leaf_node_value = self.init_mean / self.m
p = ParticleTree(self.a_tree)
self.all_particles.append(p)
self.all_trees = np.array([p.tree for p in self.all_particles])
super().__init__(vars, shared)