def __init__(self, data, name, learnable=False, is_observed=False):
self._current_value = coerce_to_dtype(data, is_observed)
self.name = name
self._observed = is_observed
self.parents = ()
self.learnable = learnable
if learnable:
self.link = L.Bias(axis=1, shape=self._current_value.shape[1:])
def __init__(self, data, name, learnable=False, is_observed=False):
self.name = name
self.distribution = distributions.DeterministicDistribution()
self._evaluated = False
self._observed = is_observed
self.parents = set()
self.ancestors = set()
self._type = "Deterministic"
self.learnable = learnable
self.link = None
self._value = coerce_to_dtype(data, is_observed)
if self.learnable:
if not is_discrete(data):
self._value = torch.nn.Parameter(coerce_to_dtype(data, is_observed), requires_grad=True)
self.link = ParameterModule(self._value) # add to optimizer; opt checks links
else:
self.learnable = False
warnings.warn('Currently discrete parameters are not learnable. Learnable set to False')
def observe(self, data, random_indices=()):
"""
Summary
"""
if isinstance(data, RandomVariable):
self.dataset = data
self.has_random_dataset = True
else:
self._observed_value = coerce_to_dtype(data, is_observed=True)
self.has_observed_value = True
self._observed = True
def observe(self, data):
"""
Method. It assigns an observed value to a RandomVariable.
Args:
data: torch.Tensor, numeric, or np.ndarray. Input observed data.
Returns:
None
"""
data = pandas_frame2value(data, self.name)
if isinstance(data, RandomVariable):
self.dataset = data
self.has_random_dataset = True
else:
self._observed_value = coerce_to_dtype(data, is_observed=True)
self.has_observed_value = True
self._observed = True
#
# import numpy as np
#
#
# x = np.random.normal(size=(10, 3))
# T = coerce_to_dtype(x)
# T.device
##
import numpy as np
from brancher.variables import ProbabilisticModel
from brancher.standard_variables import NormalVariable, LaplaceVariable, CauchyVariable, LogNormalVariable
from brancher import inference
from brancher.config import device
from brancher.utilities import coerce_to_dtype
print('Current device: ' + device.type)
# # Real model
# nu_real = 1.
# mu_real = -2.
# x_real = LaplaceVariable(mu_real, nu_real, "x_real")
# data = x_real._get_sample(number_samples=50)
##
import pandas as pd
x = np.random.normal(size=(10, 3))
d = pd.DataFrame(x)
t = coerce_to_dtype(d)
print(type(t))
def value(self, val):
self._current_value = coerce_to_dtype(val)
def value(self, val):
self._current_value = coerce_to_dtype(val,
is_observed=self.is_observed)
from importlib import reload
is_observed = False
##
def check_value_datatype(t):
print(t)
print(type(t))
print('Shape: ', t.shape)
print('Dtype: ', t.dtype)
##
data = 1
t = utilities.coerce_to_dtype(data, is_observed)
check_value_datatype(t)
##
data = 1.4
utilities.coerce_to_dtype(data, is_observed)
##
data = np.float64(4.3)
utilities.coerce_to_dtype(data, is_observed)
##
data = np.int8(4.3)
utilities.coerce_to_dtype(data, is_observed)
##
