def test_more_than_one_glm_is_ok(self):
with Model():
GLM.from_formula('y ~ x', self.data_logistic,
family=families.Binomial(link=families.logit),
name='glm1')
GLM.from_formula('y ~ x', self.data_logistic,
family=families.Binomial(link=families.logit),
name='glm2')
def test_glm(self):
with Model() as model:
GLM.from_formula('y ~ x', self.data_linear)
step = Slice(model.vars)
trace = sample(500, step, progressbar=False, random_seed=self.random_seed)
assert round(abs(np.mean(trace['Intercept'])-self.intercept), 1) == 0
assert round(abs(np.mean(trace['x'])-self.slope), 1) == 0
assert round(abs(np.mean(trace['sd'])-self.sd), 1) == 0
def test_glm_link_func(self):
with Model() as model:
GLM.from_formula('y ~ x', self.data_logistic,
family=families.Binomial(link=families.logit))
step = Slice(model.vars)
trace = sample(1000, step, progressbar=False, random_seed=self.random_seed)
assert round(abs(np.mean(trace['Intercept'])-self.intercept), 1) == 0
assert round(abs(np.mean(trace['x'])-self.slope), 1) == 0
def test_glm_offset(self):
offset = 1.
with Model() as model:
GLM.from_formula('y ~ x', self.data_linear, offset=offset)
step = Slice(model.vars)
trace = sample(500, step=step, tune=0, progressbar=False,
random_seed=self.random_seed)
assert round(abs(np.mean(trace['Intercept'])-self.intercept+offset), 1) == 0
def test_glm_link_func2(self):
with Model() as model:
GLM.from_formula('y ~ x', self.data_logistic2,
family=families.Binomial(priors={'n': self.data_logistic2['n']}))
trace = sample(1000, progressbar=False,
random_seed=self.random_seed)
assert round(abs(np.mean(trace['Intercept'])-self.intercept), 1) == 0
assert round(abs(np.mean(trace['x'])-self.slope), 1) == 0
def test_boolean_y(self):
model = GLM.from_formula('y ~ x', pd.DataFrame(
{'x': self.data_logistic['x'],
'y': self.data_logistic['y']}
)
)
model_bool = GLM.from_formula('y ~ x', pd.DataFrame(
{'x': self.data_logistic['x'],
'y': [bool(i) for i in self.data_logistic['y']]}
)
)
assert_equal(model.y.observations, model_bool.y.observations)
def test_glm_link_func2(self):
with Model() as model:
GLM.from_formula('y ~ x',
self.data_logistic2,
family=families.Binomial(
priors={'n': self.data_logistic2['n']}))
trace = sample(1000,
progressbar=False,
random_seed=self.random_seed)
assert round(abs(np.mean(trace['Intercept']) - self.intercept),
1) == 0
assert round(abs(np.mean(trace['x']) - self.slope), 1) == 0
def test_glm(self):
with Model() as model:
GLM.from_formula('y ~ x', self.data_linear)
step = Slice(model.vars)
trace = sample(500,
step,
progressbar=False,
random_seed=self.random_seed)
self.assertAlmostEqual(np.mean(trace['Intercept']), self.intercept,
1)
self.assertAlmostEqual(np.mean(trace['x']), self.slope, 1)
self.assertAlmostEqual(np.mean(trace['sd']), self.sd, 1)
def test_boolean_y(self):
model = GLM.from_formula(
'y ~ x',
pd.DataFrame({
'x': self.data_logistic['x'],
'y': self.data_logistic['y']
}))
model_bool = GLM.from_formula(
'y ~ x',
pd.DataFrame({
'x': self.data_logistic['x'],
'y': [bool(i) for i in self.data_logistic['y']]
}))
assert_equal(model.y.observations, model_bool.y.observations)
def test_glm(self):
with Model() as model:
GLM.from_formula("y ~ x", self.data_linear)
step = Slice(model.vars)
trace = sample(500,
step=step,
tune=0,
progressbar=False,
random_seed=self.random_seed)
assert round(abs(np.mean(trace["Intercept"]) - self.intercept),
1) == 0
assert round(abs(np.mean(trace["x"]) - self.slope), 1) == 0
assert round(abs(np.mean(trace["sd"]) - self.sd), 1) == 0
def test_more_than_one_glm_is_ok(self):
with Model():
GLM.from_formula(
"y ~ x",
self.data_logistic,
family=families.Binomial(link=families.logit),
name="glm1",
)
GLM.from_formula(
"y ~ x",
self.data_logistic,
family=families.Binomial(link=families.logit),
name="glm2",
)
def test_glm_offset(self):
offset = 1.0
with Model() as model:
GLM.from_formula("y ~ x", self.data_linear, offset=offset)
step = Slice(model.vars)
trace = sample(500,
step=step,
tune=0,
progressbar=False,
random_seed=self.random_seed)
assert round(
abs(np.mean(trace["Intercept"]) - self.intercept + offset),
1) == 0
def test_glm_link_func(self):
with Model() as model:
GLM.from_formula('y ~ x',
self.data_logistic,
family=families.Binomial(link=families.logit))
step = Slice(model.vars)
trace = sample(1000,
step,
progressbar=False,
random_seed=self.random_seed)
self.assertAlmostEqual(np.mean(trace['Intercept']), self.intercept,
1)
self.assertAlmostEqual(np.mean(trace['x']), self.slope, 1)
def test_boolean_y(self):
model = GLM.from_formula(
"y ~ x",
pd.DataFrame({
"x": self.data_logistic["x"],
"y": self.data_logistic["y"]
}))
model_bool = GLM.from_formula(
"y ~ x",
pd.DataFrame({
"x": self.data_logistic["x"],
"y": [bool(i) for i in self.data_logistic["y"]]
}),
)
assert_equal(model.y.observations, model_bool.y.observations)
def test_glm_link_func(self):
with Model() as model:
GLM.from_formula("y ~ x",
self.data_logistic,
family=families.Binomial(link=families.logit))
step = Slice(model.vars)
trace = sample(1000,
step=step,
tune=0,
progressbar=False,
random_seed=self.random_seed)
assert round(abs(np.mean(trace["Intercept"]) - self.intercept),
1) == 0
assert round(abs(np.mean(trace["x"]) - self.slope), 1) == 0
def test_glm_link_func2(self):
with Model() as model:
GLM.from_formula(
"y ~ x",
self.data_logistic2,
family=families.Binomial(
priors={"n": self.data_logistic2["n"]}),
)
trace = sample(1000,
progressbar=False,
init="adapt_diag",
random_seed=self.random_seed)
assert round(abs(np.mean(trace["Intercept"]) - self.intercept),
1) == 0
assert round(abs(np.mean(trace["x"]) - self.slope), 1) == 0
def test_from_xy(self):
with Model():
GLM(
self.data_logistic["x"],
self.data_logistic["y"],
family=families.Binomial(link=families.logit),
name="glm1",
)
def test_from_xy(self):
with Model():
GLM(self.data_logistic['x'],
self.data_logistic['y'],
family=families.Binomial(link=families.logit),
name='glm1')
def test_glm_formula_from_calling_scope(self):
"""Formula can extract variables from the calling scope."""
z = pd.Series([10, 20, 30])
df = pd.DataFrame({"y": [0, 1, 0], "x": [1.0, 2.0, 3.0]})
GLM.from_formula("y ~ x + z", df, family=pymc3.glm.families.Binomial())
def test_glm_formula_from_calling_scope(self):
"""Formula can extract variables from the calling scope."""
z = pd.Series([10, 20, 30])
df = pd.DataFrame({"y": [0, 1, 0], "x": [1.0, 2.0, 3.0]})
GLM.from_formula("y ~ x + z", df, family=pymc3.glm.families.Binomial())
