def probability(self, x, cols, given=None):
""" Predictive probability of x_1, ..., x_n given y_1, ..., y_n
Parameters
----------
x : numpy.ndarray(2,)
2-D numpy array where each row is a set of observations and each
column corresponds to a feature.
cols : list
The names of each column/feature of `x`.
given : list(tuple)
List of (name, value,) conditional contraints for the probability
Returns
-------
logps : numpy.ndarray
Examples
--------
The probability that an animal is fast and agile given that it is
bulbous.
>>> engine = Engine.load('examples/zoo.bcmodels')
>>> engine.probability(np.array([[1, 1]]), ['fast', 'agile'],
... given=[('bulbous': 1]))
"""
# TODO: make sure that given goes not caontain columns rom cols
x = du.format_query_data(x)
col_idxs = [self._converters['col2idx'][col] for col in cols]
x_cnv = du.convert_data(x, cols, self._dtypes, self._converters)
if given is not None:
given = du.convert_given(given, self._dtypes, self._converters)
return mu.probability(x_cnv, self._models, col_idxs, given=given)
def probability(self, x, cols, given=None):
""" Predictive probability of x_1, ..., x_n given y_1, ..., y_n
Parameters
----------
x : numpy.ndarray(2,)
2-D numpy array where each row is a set of observations and each
column corresponds to a feature.
cols : list
The names of each column/feature of `x`.
given : list(tuple)
List of (name, value,) conditional contraints for the probability
Returns
-------
logps : numpy.ndarray
Examples
--------
The probability that an animal is fast and agile given that it is
bulbous.
>>> engine = Engine.load('examples/zoo.bcmodels')
>>> engine.probability(np.array([[1, 1]]), ['fast', 'agile'],
... given=[('bulbous': 1]))
"""
# TODO: make sure that given goes not caontain columns rom cols
x = du.format_query_data(x)
col_idxs = [self._converters['col2idx'][col] for col in cols]
x_cnv = du.convert_data(x, cols, self._dtypes, self._converters)
if given is not None:
given = du.convert_given(given, self._dtypes, self._converters)
return mu.probability(x_cnv, self._models, col_idxs, given=given)
def entropy(self, col, n_samples=500):
""" The entropy of a column.
Notes
-----
Returns differential entropy for continuous feature (obviously).
Parameters
----------
col : indexer
The name of the column
n_samples : int
The number of samples to use for the Monte Carlo approximation
(if `col` is categorical).
Returns
-------
h : float
The entropy of `col`.
"""
col_idx = self._converters['col2idx'][col]
dtype = self._dtypes[col_idx]
# Unless x is enumerable (is categorical), we approximate h(x) using
# an importance sampling extimate of h(x) using p(x) as the importance
# function.
if dtype == 'categorical':
k = self._distargs[col_idx][0]
x = np.array([[i] for i in range(k)])
logps = mu.probability(x, self._models, (col_idx, ))
assert logps.shape == (k, )
h = -np.sum(np.exp(logps) * logps)
else:
x = mu.sample(self._models, (col_idx, ), n=n_samples)
logps = mu.probability(x, self._models, (col_idx, ))
h = -np.sum(logps) / n_samples
return h
def entropy(self, col, n_samples=500):
""" The entropy of a column.
Notes
-----
Returns differential entropy for continuous feature (obviously).
Parameters
----------
col : indexer
The name of the column
n_samples : int
The number of samples to use for the Monte Carlo approximation
(if `col` is categorical).
Returns
-------
h : float
The entropy of `col`.
"""
col_idx = self._converters['col2idx'][col]
dtype = self._dtypes[col_idx]
# Unless x is enumerable (is categorical), we approximate h(x) using
# an importance sampling extimate of h(x) using p(x) as the importance
# function.
if dtype == 'categorical':
k = self._distargs[col_idx][0]
x = np.array([[i] for i in range(k)])
logps = mu.probability(x, self._models, (col_idx,))
assert logps.shape == (k,)
h = -np.sum(np.exp(logps)*logps)
else:
x = mu.sample(self._models, (col_idx,), n=n_samples)
logps = mu.probability(x, self._models, (col_idx,))
h = -np.sum(logps) / n_samples
return h
def test_double_mixed_single_view_values(model):
x = np.array([[0, 2.1]])
logp = mu.probability(x, [model], [0, 1])
assert logp == approx(-2.93134971834475)
def test_single_categorical_col_probability_values_2(model):
x = np.array([[2]], dtype=int)
logp = mu.probability(x, [model], [0])
assert logp == approx(-1.15710849534972)
def test_single_categorical_col_probability_values_1(model):
# logp of 1 in column 1
x = np.array([[0]], dtype=int)
logp = mu.probability(x, [model], [0])
assert logp == approx(-0.848561284433976)
def test_single_continuous_col_probability_values_2(model):
x = np.array([[2]], dtype=float)
logp = mu.probability(x, [model], [1])
assert logp == approx(-2.01262102403666)
def test_single_continuous_col_probability_values_1(model):
# logp of 1 in column 1
x = np.array([[1]], dtype=float)
logp = mu.probability(x, [model], [1])
assert logp == approx(-1.58025784097797)
def test_double_mixed_single_view_values(model):
x = np.array([[0, 2.1]])
logp = mu.probability(x, [model], [0, 1])
assert logp == approx(-2.93134971834475)
def test_single_categorical_col_probability_values_2(model):
x = np.array([[2]], dtype=int)
logp = mu.probability(x, [model], [0])
assert logp == approx(-1.15710849534972)
def test_single_categorical_col_probability_values_1(model):
# logp of 1 in column 1
x = np.array([[0]], dtype=int)
logp = mu.probability(x, [model], [0])
assert logp == approx(-0.848561284433976)
def test_single_continuous_col_probability_values_2(model):
x = np.array([[2]], dtype=float)
logp = mu.probability(x, [model], [1])
assert logp == approx(-2.01262102403666)
def test_single_continuous_col_probability_values_1(model):
# logp of 1 in column 1
x = np.array([[1]], dtype=float)
logp = mu.probability(x, [model], [1])
assert logp == approx(-1.58025784097797)
