def test_shape_ignore_msg_in_constructor(self):
"""
Ensures that a UserWarning is raised when the 'shape_ref_pos' or
'shape_names' keyword arguments are passed to the Clog-log model
constructor. This warns people against expecting the Clog-log to use
shape parameters, and alerts them that they are using an Clog-log
model when they might have been expecting to instantiate a different
choice model.
"""
# Create a variable for the standard arguments to this function.
standard_args = [
self.fake_df, self.alt_id_col, self.obs_id_col, self.choice_col,
self.fake_specification
]
# Create a variable for the kwargs being passed to the constructor
kwarg_map_1 = {
"intercept_ref_pos": self.fake_intercept_ref_pos,
"names": self.fake_names,
"intercept_names": self.fake_intercept_names,
"shape_ref_pos": 2
}
kwarg_map_2 = {
"intercept_ref_pos": self.fake_intercept_ref_pos,
"names": self.fake_names,
"intercept_names": self.fake_intercept_names,
"shape_names": OrderedDict([("x", ["foo"])])
}
# Test to ensure that the shape ignore message is printed when using
# either of these two kwargs
with warnings.catch_warnings(record=True) as context:
# Use this filter to always trigger the UserWarnings
warnings.simplefilter('always', UserWarning)
for pos, bad_kwargs in enumerate([kwarg_map_1, kwarg_map_2]):
# Create a Clog-log model object with the irrelevant kwargs.
# This should trigger a UserWarning
clog_obj = clog.MNCL(*standard_args, **bad_kwargs)
# Check that the warning has been created.
self.assertEqual(len(context), pos + 1)
self.assertIsInstance(context[-1].category, type(UserWarning))
self.assertIn(clog._shape_ignore_msg, str(context[-1].message))
return None
def setUp(self):
# Create the betas to be used during the tests
self.fake_betas = np.array([-0.6])
# Create the fake outside intercepts to be used during the tests
self.fake_intercepts = np.array([1, 0.5])
# Create names for the intercept parameters
self.fake_intercept_names = ["ASC 1", "ASC 2"]
# Record the position of the intercept that is not being estimated
self.fake_intercept_ref_pos = 2
# Create an array of all model parameters
self.fake_all_params = np.concatenate(
(self.fake_intercepts, self.fake_betas))
# The set up being used is one where there are two choice situations,
# The first having three alternatives, and the second having only two.
# The mapping between rows and alternatives is given below.
self.fake_rows_to_alts = csr_matrix(
np.array([[1, 0, 0], [0, 1, 0], [0, 0, 1], [1, 0, 0], [0, 0, 1]]))
# Create the fake design matrix with columns denoting X
# The intercepts are not included because they are kept outside the
# index in the clog-log model.
self.fake_design = np.array([[1], [2], [3], [1.5], [3.5]])
# Create the index array for this set of choice situations
self.fake_index = self.fake_design.dot(self.fake_betas)
# Create the needed dataframe for the Clog-log constructor
self.fake_df = pd.DataFrame({
"obs_id": [1, 1, 1, 2, 2],
"alt_id": [1, 2, 3, 1, 3],
"choice": [0, 1, 0, 0, 1],
"x": self.fake_design[:, 0],
"intercept": [1 for i in range(5)]
})
# Record the various column names
self.alt_id_col = "alt_id"
self.obs_id_col = "obs_id"
self.choice_col = "choice"
# Create the index specification and name dictionaryfor the model
self.fake_specification = OrderedDict()
self.fake_names = OrderedDict()
self.fake_specification["x"] = [[1, 2, 3]]
self.fake_names["x"] = ["x (generic coefficient)"]
# Bundle the args and kwargs used to construct the Clog-log model.
self.constructor_args = [
self.fake_df, self.alt_id_col, self.obs_id_col, self.choice_col,
self.fake_specification
]
# Create a variable for the kwargs being passed to the constructor
self.constructor_kwargs = {
"intercept_ref_pos": self.fake_intercept_ref_pos,
"names": self.fake_names,
"intercept_names": self.fake_intercept_names
}
# Initialize a basic clog-log model.
# Create the clog model object whose coefficients will be estimated.
self.base_clog = clog.MNCL(*self.constructor_args,
**self.constructor_kwargs)
return None
def make_clog_and_mnl_models(self):
# The set up being used is one where there are two choice situations,
# The first having three alternatives, and the second having only two
# alternatives. There is one generic variable. Two alternative
# specific constants and all three shape parameters are used.
# Create the betas to be used during the tests
fake_betas = np.array([-0.6])
# Create the fake outside intercepts to be used during the tests
fake_intercepts = np.array([1, 0.5])
# Create names for the intercept parameters
fake_intercept_names = ["ASC 1", "ASC 2"]
# Record the position of the intercept that is not being estimated
fake_intercept_ref_pos = 2
# Create an array of all model parameters
fake_all_params = np.concatenate((fake_intercepts, fake_betas))
# Get the mappping between rows and observations
fake_rows_to_obs = csr_matrix(
np.array([[1, 0], [1, 0], [1, 0], [0, 1], [0, 1]]))
# Create the fake design matrix with columns denoting X
# The intercepts are not included because they are kept outside the
# index in the scobit model.
fake_design = np.array([[1], [2], [3], [1.5], [3.5]])
# Create the index array for this set of choice situations
fake_index = fake_design.dot(fake_betas)
# Create the needed dataframe for the model constructor
fake_df = pd.DataFrame({
"obs_id": [1, 1, 1, 2, 2],
"alt_id": [1, 2, 3, 1, 3],
"choice": [0, 1, 0, 0, 1],
"x": fake_design[:, 0],
"intercept": [1 for i in range(5)]
})
# Record the various column names
alt_id_col = "alt_id"
obs_id_col = "obs_id"
choice_col = "choice"
# Create the index specification and name dictionaryfor the model
fake_specification = OrderedDict()
fake_names = OrderedDict()
fake_specification["x"] = [[1, 2, 3]]
fake_names["x"] = ["x (generic coefficient)"]
mnl_spec = OrderedDict()
mnl_names = OrderedDict()
mnl_spec["intercept"] = [1, 2]
mnl_names["intercept"] = fake_intercept_names
mnl_spec["x"] = fake_specification["x"]
mnl_names["x"] = fake_names["x"]
# Bundle args and kwargs used to construct the Asymmetric Logit model.
clog_args = [
fake_df, alt_id_col, obs_id_col, choice_col, fake_specification
]
mnl_args = deepcopy(clog_args)
mnl_args[-1] = mnl_spec
# Create a variable for the kwargs being passed to the constructor
clog_kwargs = {
"names": fake_names,
"intercept_ref_pos": fake_intercept_ref_pos,
"intercept_names": fake_intercept_names
}
mnl_kwargs = {"names": mnl_names}
# Initialize a basic Asymmetric Logit model whose coefficients will be
# estimated.
clog_obj = clog.MNCL(*clog_args, **clog_kwargs)
mnl_obj = mnl.MNL(*mnl_args, **mnl_kwargs)
# Create the desired model attributes for the clog log model
clog_obj.coefs = pd.Series(fake_betas, index=fake_names["x"])
clog_obj.intercepts =\
pd.Series(fake_intercepts, index=fake_intercept_names)
clog_obj.shapes = None
clog_obj.nests = None
clog_obj.params =\
pd.concat([clog_obj.intercepts, clog_obj.coefs],
axis=0, ignore_index=False)
mnl_obj.params = clog_obj.params.copy()
mnl_obj.coefs = mnl_obj.params.copy()
mnl_obj.intercepts = None
mnl_obj.shapes = None
mnl_obj.nests = None
return clog_obj, mnl_obj