def test_mnl_estimation(obs, alts):
"""
Confirm that estimated params from the new interface match urbansim.urbanchoice.
Only runs if the urbansim package has been installed.
"""
try:
from urbansim.urbanchoice.mnl import mnl_estimate
except:
print("Comparison of MNL estimation results skipped because urbansim is not installed")
return
model_expression = 'obsval + altval - 1'
mct = MergedChoiceTable(obs, alts, 'choice')
# new interface
m = MultinomialLogit(mct, model_expression)
r = m.fit().get_raw_results()
# old interface
dm = dmatrix(model_expression, mct.to_frame())
chosen = np.reshape(mct.to_frame()[mct.choice_col].values, (100, 5))
log_lik, fit = mnl_estimate(np.array(dm), chosen, numalts=5)
for k,v in log_lik.items():
assert(v == pytest.approx(r['log_likelihood'][k], 0.00001))
assert_frame_equal(fit, r['fit_parameters'][['Coefficient', 'Std. Error', 'T-Score']])
def test_mnl_prediction(obs, alts):
"""
Confirm that fitted probabilities in the new codebase match urbansim.urbanchoice.
Only runs if the urbansim package has been installed.
"""
try:
from urbansim.urbanchoice.mnl import mnl_simulate
except:
print("Comparison of MNL simulation results skipped because urbansim is not installed")
return
# produce a fitted model
mct = MergedChoiceTable(obs, alts, 'choice', 5)
m = MultinomialLogit(mct, model_expression='obsval + altval - 1')
results = m.fit()
# get predicted probabilities using choicemodels
probs1 = results.probabilities(mct)
# compare to probabilities from urbansim.urbanchoice
dm = dmatrix(results.model_expression, data=mct.to_frame(), return_type='dataframe')
probs = mnl_simulate(data=dm, coeff=results.fitted_parameters,
numalts=mct.sample_size, returnprobs=True)
df = mct.to_frame()
df['prob'] = probs.flatten()
probs2 = df.prob
pd.testing.assert_series_equal(probs1, probs2)
def fit(self):
"""
Fit the model; save and report results. This uses PyLogit via ChoiceModels.
The `fit()` method can be run as many times as desired. Results will not be saved
with Orca or ModelManager until the `register()` method is run.
"""
long_df = self._to_long(self._get_data())
# Set initial coefs to 0 if none provided
pc = self._get_param_count()
if (self.initial_coefs is None) or (len(self.initial_coefs) != pc):
self.initial_coefs = np.zeros(pc).tolist()
model = MultinomialLogit(data=long_df, observation_id_col='_obs_id',
choice_col='_chosen',
model_expression=self.model_expression,
model_labels=self.model_labels,
alternative_id_col='_alt_id',
initial_coefs=self.initial_coefs)
results = model.fit()
self.name = self._generate_name()
self.summary_table = str(results.report_fit())
print(self.summary_table)
# We need the PyLogit fitted model object for prediction, so save it directly
self.model = results.get_raw_results()
def test_mnl_estimation(obs, alts):
"""
Confirm that estimated params from the new interface match urbansim.urbanchoice.
Only runs if the urbansim package has been installed.
"""
try:
from urbansim.urbanchoice.mnl import mnl_estimate
except:
print(
"Comparison of MNL estimation results skipped because urbansim is not installed"
)
return
model_expression = 'obsval + altval - 1'
mct = MergedChoiceTable(obs, alts, 'choice')
# new interface
m = MultinomialLogit(mct, model_expression)
r = m.fit().get_raw_results()
# old interface
dm = dmatrix(model_expression, mct.to_frame())
chosen = np.reshape(mct.to_frame()[mct.choice_col].values, (100, 5))
log_lik, fit = mnl_estimate(np.array(dm), chosen, numalts=5)
for k, v in log_lik.items():
assert (v == pytest.approx(r['log_likelihood'][k], 0.00001))
assert_frame_equal(
fit, r['fit_parameters'][['Coefficient', 'Std. Error', 'T-Score']])
def test_mnl(obs, alts):
"""
Confirm that MNL estimation runs, using the native estimator.
"""
model_expression = 'obsval + altval - 1'
mct = MergedChoiceTable(obs, alts, 'choice')
m = MultinomialLogit(mct, model_expression)
print(m.fit())
def test_mnl(obs, alts):
"""
Confirm that MNL estimation runs, using the native estimator.
"""
model_expression = 'obsval + altval - 1'
mct = MergedChoiceTable(obs, alts, 'choice')
m = MultinomialLogit(mct, model_expression)
print(m.fit())
def test_mnl_estimation(obs, alts):
"""
Confirm that estimated params from the new interface match urbansim.urbanchoice.
"""
model_expression = 'obsval + altval - 1'
mct = MergedChoiceTable(obs, alts, 'choice')
# new interface
m = MultinomialLogit(mct, model_expression)
r = m.fit().get_raw_results()
# old interface
dm = dmatrix(model_expression, mct.to_frame())
chosen = np.reshape(mct.to_frame()[mct.choice_col].values, (100, 5))
log_lik, fit = mnl_estimate(np.array(dm), chosen, numalts=5)
for k,v in log_lik.items():
assert(v == pytest.approx(r['log_likelihood'][k], 0.00001))
assert_frame_equal(fit, r['fit_parameters'][['Coefficient', 'Std. Error', 'T-Score']])
def test_mnl_prediction(obs, alts):
"""
Confirm that fitted probabilities in the new codebase match urbansim.urbanchoice.
Only runs if the urbansim package has been installed.
"""
try:
from urbansim.urbanchoice.mnl import mnl_simulate
except:
print(
"Comparison of MNL simulation results skipped because urbansim is not installed"
)
return
# produce a fitted model
mct = MergedChoiceTable(obs, alts, 'choice', 5)
m = MultinomialLogit(mct, model_expression='obsval + altval - 1')
results = m.fit()
# get predicted probabilities using choicemodels
probs1 = results.probabilities(mct)
# compare to probabilities from urbansim.urbanchoice
dm = dmatrix(results.model_expression,
data=mct.to_frame(),
return_type='dataframe')
probs = mnl_simulate(data=dm,
coeff=results.fitted_parameters,
numalts=mct.sample_size,
returnprobs=True)
df = mct.to_frame()
df['prob'] = probs.flatten()
probs2 = df.prob
pd.testing.assert_series_equal(probs1, probs2)
def fit(self):
"""
Fit the model; save and report results. This uses the ChoiceModels estimation
engine (originally from UrbanSim MNL).
The `fit()` method can be run as many times as desired. Results will not be saved
with Orca or ModelManager until the `register()` method is run.
"""
# TO DO - update choicemodels to accept a column name for chosen alts
observations = self._get_df(tables=self.choosers,
filters=self.chooser_filters)
chosen = observations[self.choice_column]
alternatives = self._get_df(tables=self.alternatives,
filters=self.alt_filters)
data = MergedChoiceTable(observations=observations,
alternatives=alternatives,
chosen_alternatives=chosen,
sample_size=self._get_alt_sample_size())
model = MultinomialLogit(data=data.to_frame(),
observation_id_col=data.observation_id_col,
choice_col=data.choice_col,
model_expression=self.model_expression)
results = model.fit()
self.name = self._generate_name()
self.summary_table = str(results)
print(self.summary_table)
# For now, just save the summary table and fitted parameters
coefs = results.get_raw_results()['fit_parameters']['Coefficient']
self.fitted_parameters = coefs.tolist()
def test_mnl_prediction(obs, alts):
"""
Confirm that fitted probabilities in the new codebase match urbansim.urbanchoice.
"""
# produce a fitted model
mct = MergedChoiceTable(obs, alts, 'choice', 5)
m = MultinomialLogit(mct, model_expression='obsval + altval - 1')
results = m.fit()
# get predicted probabilities using choicemodels
probs1 = results.probabilities(mct)
# compare to probabilities from urbansim.urbanchoice
dm = dmatrix(results.model_expression, data=mct.to_frame(), return_type='dataframe')
probs = mnl_simulate(data=dm, coeff=results.fitted_parameters,
numalts=mct.sample_size, returnprobs=True)
df = mct.to_frame()
df['prob'] = probs.flatten()
probs2 = df.prob
pd.testing.assert_series_equal(probs1, probs2)
def fitted_model(obs, alts):
mct = MergedChoiceTable(obs, alts, 'choice', sample_size=5)
m = MultinomialLogit(mct, model_expression='obsval + altval - 1')
return m.fit()
def fit(self, mct=None):
"""
Fit the model; save and report results. This uses the ChoiceModels estimation
engine (originally from UrbanSim MNL).
The `fit()` method can be run as many times as desired. Results will not be saved
with Orca or ModelManager until the `register()` method is run.
After sampling alternatives for each chooser, the merged choice table is saved to
the class object for diagnostic use (`mergedchoicetable` with type
choicemodels.tools.MergedChoiceTable).
Parameters
----------
mct : choicemodels.tools.MergedChoiceTable
This parameter is a temporary backdoor allowing us to pass in a more
complicated choice table than can be generated within the template, for
example including sampling weights or interaction terms.
Returns
-------
None
"""
check_choicemodels_version()
from choicemodels import MultinomialLogit
from choicemodels.tools import MergedChoiceTable
if (mct is not None):
df_from_mct = mct.to_frame()
idx_names = df_from_mct.index.names
df_from_mct = df_from_mct.reset_index()
df_from_mct = apply_filter_query(
df_from_mct, self.chooser_filters).set_index(idx_names)
mct = MergedChoiceTable.from_df(df_from_mct)
else:
observations = get_data(tables=self.choosers,
filters=self.chooser_filters,
model_expression=self.model_expression,
extra_columns=self.choice_column)
if (self.chooser_sample_size is not None):
observations = observations.sample(self.chooser_sample_size)
alternatives = get_data(tables=self.alternatives,
filters=self.alt_filters,
model_expression=self.model_expression)
mct = MergedChoiceTable(observations=observations,
alternatives=alternatives,
chosen_alternatives=self.choice_column,
sample_size=self.alt_sample_size)
model = MultinomialLogit(data=mct,
model_expression=self.model_expression)
results = model.fit()
self.name = self._generate_name()
self.summary_table = str(results)
print(self.summary_table)
coefs = results.get_raw_results()['fit_parameters']['Coefficient']
self.fitted_parameters = coefs.tolist()
self.model = results
# Save merged choice table to the class object for diagnostics
self.mergedchoicetable = mct
def fit(self, mct=None):
"""
Fit the model; save and report results. This uses the ChoiceModels estimation
engine (originally from UrbanSim MNL).
The `fit()` method can be run as many times as desired. Results will not be saved
with Orca or ModelManager until the `register()` method is run.
After sampling alternatives for each chooser, the merged choice table is saved to
the class object for diagnostic use (`mergedchoicetable` with type
choicemodels.tools.MergedChoiceTable).
Parameters
----------
mct : choicemodels.tools.MergedChoiceTable
This parameter is a temporary backdoor allowing us to pass in a more
complicated merged choice table than can be generated within the template, for
example including sampling weights or interaction terms. This will work for
model estimation, but is not yet hooked up to the prediction functionality.
Returns
-------
None
"""
if (mct is not None):
data = mct
else:
# TO DO - update choicemodels to accept a column name for chosen alts
observations = self._get_df(tables=self.choosers,
filters=self.chooser_filters)
if (self.chooser_sample_size is not None):
observations = observations.sample(self.chooser_sample_size)
chosen = observations[self.choice_column]
alternatives = self._get_df(tables=self.alternatives,
filters=self.alt_filters)
data = MergedChoiceTable(observations=observations,
alternatives=alternatives,
chosen_alternatives=chosen,
sample_size=self._get_alt_sample_size())
model = MultinomialLogit(data=data.to_frame(),
observation_id_col=data.observation_id_col,
choice_col=data.choice_col,
model_expression=self.model_expression)
results = model.fit()
self.name = self._generate_name()
self.summary_table = str(results)
print(self.summary_table)
# For now, just save the summary table and fitted parameters
coefs = results.get_raw_results()['fit_parameters']['Coefficient']
self.fitted_parameters = coefs.tolist()
# Save merged choice table to the class object for diagnostic use
self.mergedchoicetable = data
pd.set_option('display.float_format', lambda x: '%.3f' % x)
choosers = trips.loc[np.random.choice(trips.index, 500, replace=False)]
choosers = choosers.loc[choosers.trip_distance_miles.notnull()]
numalts = 10
merged = MergedChoiceTable(observations = choosers,
alternatives = tracts,
chosen_alternatives = choosers.full_tract_id,
sample_size = numalts)
model_expression = "home_density + work_density + school_density"
model = MultinomialLogit(merged.to_frame(),
merged.observation_id_col,
merged.choice_col,
model_expression)
results = model.fit()
results.report_fit()
"""
model_expression = OrderedDict([('home_density', 'all_same'),
('work_density', 'all_same'),
('school_density', 'all_same')])
model = MultinomialLogit(data = merged.to_frame(),
observation_id_col = merged.observation_id_col,
alternative_id_col = merged.alternative_id_col,
choice_col = merged.choice_col,
def fitted_model(obs, alts):
mct = MergedChoiceTable(obs, alts, 'choice', sample_size=5)
m = MultinomialLogit(mct, model_expression='obsval + altval - 1')
return m.fit()
