def test_convert_continuous_given_should_change_cols_not_vals():
given_in = [(
'x',
1.2,
), (
'y',
3.4,
), (
'y',
2,
)]
dtypes = ['continuous'] * 2
converters = {'col2idx': {'x': 0, 'y': 1}, 'valmaps': {}}
given_out = du.convert_given(given_in, dtypes, converters)
for (k1, v1), (k2, v2) in zip(given_in, given_out):
assert k1 != k2
assert v1 == v2
assert isinstance(k1, str)
assert isinstance(k2, int)
assert given_out[0] == (
0,
1.2,
)
assert given_out[1] == (
1,
3.4,
)
assert given_out[2] == (
1,
2,
)
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 test_convert_categorical_given_should_change_cols_and_vals():
given_in = [(
'x',
'a',
), (
'y',
'bb',
), (
'y',
'cc',
)]
dtypes = ['categorical'] * 2
converters = {
'col2idx': {
'x': 0,
'y': 1
},
'valmaps': {
'x': {
'val2idx': {
'a': 0,
'b': 1,
'c': 2
}
},
'y': {
'val2idx': {
'aa': 0,
'bb': 1,
'cc': 2
}
}
}
}
given_out = du.convert_given(given_in, dtypes, converters)
assert given_out[0] == (
0,
0,
)
assert given_out[1] == (
1,
1,
)
assert given_out[2] == (
1,
2,
)
def test_convert_mixed_given_output():
given_in = [('x', 1.2,), ('y', 'bb',), ('y', 'cc',)]
dtypes = ['continuous', 'categorical']
converters = {
'col2idx':
{'x': 0, 'y': 1},
'valmaps': {
'y': {
'val2idx': {'aa': 0, 'bb': 1, 'cc': 2}}}}
given_out = du.convert_given(given_in, dtypes, converters)
assert given_out[0] == (0, 1.2,)
assert given_out[1] == (1, 1,)
assert given_out[2] == (1, 2,)
def test_convert_categorical_given_should_change_cols_and_vals():
given_in = [('x', 'a',), ('y', 'bb',), ('y', 'cc',)]
dtypes = ['categorical']*2
converters = {
'col2idx':
{'x': 0, 'y': 1},
'valmaps': {
'x': {
'val2idx': {'a': 0, 'b': 1, 'c': 2}},
'y': {
'val2idx': {'aa': 0, 'bb': 1, 'cc': 2}}}}
given_out = du.convert_given(given_in, dtypes, converters)
assert given_out[0] == (0, 0,)
assert given_out[1] == (1, 1,)
assert given_out[2] == (1, 2,)
def test_convert_continuous_given_should_change_cols_not_vals():
given_in = [('x', 1.2,), ('y', 3.4,), ('y', 2,)]
dtypes = ['continuous']*2
converters = {
'col2idx': {'x': 0, 'y': 1},
'valmaps': {}}
given_out = du.convert_given(given_in, dtypes, converters)
for (k1, v1), (k2, v2) in zip(given_in, given_out):
assert k1 != k2
assert v1 == v2
assert isinstance(k1, str)
assert isinstance(k2, int)
assert given_out[0] == (0, 1.2,)
assert given_out[1] == (1, 3.4,)
assert given_out[2] == (1, 2,)
def test_convert_mixed_given_output():
given_in = [(
'x',
1.2,
), (
'y',
'bb',
), (
'y',
'cc',
)]
dtypes = ['continuous', 'categorical']
converters = {
'col2idx': {
'x': 0,
'y': 1
},
'valmaps': {
'y': {
'val2idx': {
'aa': 0,
'bb': 1,
'cc': 2
}
}
}
}
given_out = du.convert_given(given_in, dtypes, converters)
assert given_out[0] == (
0,
1.2,
)
assert given_out[1] == (
1,
1,
)
assert given_out[2] == (
1,
2,
)
def sample(self, cols, given=None, n=1):
""" Draw samples from cols
Parameters
----------
cols : list(index)
List of columns from which to jointly draw.
given : list(tuple(int, value))
List of column-value tuples that specify conditions
n : int
The number of samples to draw
Examples
--------
Draw whether an animal is fast and agile given that it is bulbous.
>>> engine = Engine.load('examples/zoo.bcmodels')
>>> engine.sample(['fast', 'agile'], given=[('bulbous': 1]))
"""
# FIXME: make sure that given does not contain columns from cols
if given is not None:
given = du.convert_given(given, self._dtypes, self._converters)
col_idxs = [self._converters['col2idx'][col] for col in cols]
data_out = mu.sample(self._models, col_idxs, given=given, n=n)
x = du.convert_data(data_out,
cols,
self._dtypes,
self._converters,
to_val=True)
if x.shape == (
1,
1,
):
return x[0, 0]
elif x.shape[0] == 1:
return x[0, :]
else:
return x
def sample(self, cols, given=None, n=1):
""" Draw samples from cols
Parameters
----------
cols : list(index)
List of columns from which to jointly draw.
given : list(tuple(int, value))
List of column-value tuples that specify conditions
n : int
The number of samples to draw
Examples
--------
Draw whether an animal is fast and agile given that it is bulbous.
>>> engine = Engine.load('examples/zoo.bcmodels')
>>> engine.sample(['fast', 'agile'], given=[('bulbous': 1]))
"""
# FIXME: make sure that given does not contain columns from cols
if given is not None:
given = du.convert_given(given, self._dtypes, self._converters)
col_idxs = [self._converters['col2idx'][col] for col in cols]
data_out = mu.sample(self._models, col_idxs, given=given, n=n)
x = du.convert_data(data_out, cols, self._dtypes, self._converters,
to_val=True)
if x.shape == (1, 1,):
return x[0, 0]
elif x.shape[0] == 1:
return x[0, :]
else:
return x