Estimation fix

activitysim/estimation/larch/general.py

@@ -1,18 +1,15 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
 from typing import Mapping
 
 import numpy as np
 import pandas as pd
-import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model, P, X # noqa: F401
 from larch.log import logger_name
 from larch.model.abstract_model import AbstractChoiceModel
 from larch.model.tree import NestingTree
-from larch.util import Dict
+from larch.util import Dict # noqa: F401
 
 _logger = logging.getLogger(logger_name)
 
@@ -490,13 +487,24 @@ def clean_values(
  return values
 
 
-def update_coefficients(model, data, result_dir=Path("."), output_file=None):
+def update_coefficients(
+ model, data, result_dir=Path("."), output_file=None, relabel_coef=None
+):
  if isinstance(data, pd.DataFrame):
  coefficients = data.copy()
  else:
  coefficients = data.coefficients.copy()
- est_names = [j for j in coefficients.index if j in model.pf.index]
- coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
+ if relabel_coef is not None and len(relabel_coef):
+ for j in coefficients.index:
+ if j in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j, "value"]
+ else:
+ j_ = relabel_coef.get(j, None)
+ if j_ is not None and j_ in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j_, "value"]
+ else:
+ est_names = [j for j in coefficients.index if j in model.pf.index]
+ coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
  if output_file is not None:
  os.makedirs(result_dir, exist_ok=True)
  coefficients.reset_index().to_csv(

activitysim/estimation/larch/nonmand_tour_freq.py

@@ -1,14 +1,10 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
-from typing import Mapping
 
-import numpy as np
 import pandas as pd
 import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model
 from larch.log import logger_name
 from larch.util import Dict
 
@@ -125,17 +121,34 @@ def unavail(model, x_ca):
 def nonmand_tour_freq_model(
  edb_directory="output/estimation_data_bundle/{name}/",
  return_data=False,
+ condense_parameters=False,
 ):
+ """
+ Prepare nonmandatory tour frequency models for estimation.
+
+ Parameters
+ ----------
+ edb_directory : str
+ Location of estimation data bundle for these models.
+ return_data : bool, default False
+ Whether to return the data used in preparing this function.
+ If returned, data is a dict in the second return value.
+ condense_parameters : bool, default False
+ Apply a transformation whereby all parameters in each model that
+ have the same initial value are converted to have the same name
+ (and thus to be the same parameter, used in various places).
+ """
  data = interaction_simulate_data(
  name="non_mandatory_tour_frequency",
  edb_directory=edb_directory,
  )
 
  settings = data.settings
  segment_names = [s["NAME"] for s in settings["SPEC_SEGMENTS"]]
- data.relabel_coef = link_same_value_coefficients(
- segment_names, data.coefficients, data.spec
- )
+ if condense_parameters:
+ data.relabel_coef = link_same_value_coefficients(
+ segment_names, data.coefficients, data.spec
+ )
  spec = data.spec
  coefficients = data.coefficients
  chooser_data = data.chooser_data

activitysim/estimation/test/test_larch_estimation.py

@@ -279,12 +279,24 @@ def test_tour_and_subtour_mode_choice(est_data, num_regression, dataframe_regres
 def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
 
- m = nonmand_tour_freq_model()
+ m = nonmand_tour_freq_model(condense_parameters=True)
  loglike_prior = {}
+ expected_n_params = {
+ "PTYPE_FULL": 72,
+ "PTYPE_PART": 51,
+ "PTYPE_UNIVERSITY": 70,
+ "PTYPE_NONWORK": 77,
+ "PTYPE_RETIRED": 53,
+ "PTYPE_DRIVING": 43,
+ "PTYPE_SCHOOL": 34,
+ "PTYPE_PRESCHOOL": 25,
+ }
  for segment_name in m:
  m[segment_name].load_data()
  m[segment_name].doctor(repair_ch_av="-")
  loglike_prior[segment_name] = m[segment_name].loglike()
+ assert len(m[segment_name].pf) == expected_n_params[segment_name]
+ assert len(m[segment_name].utility_ca) == 210
  r = {}
  for segment_name in m:
  r[segment_name] = m[segment_name].maximize_loglike(
@@ -297,3 +309,14 @@ def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  basename="test_nonmand_tour_freq_loglike",
  )
  _regression_check(dataframe_regression, pd.concat([x.pf for x in m.values()]))
+
+
+def test_nonmand_tour_freq_not_condensed(
+ est_data, num_regression, dataframe_regression
+):
+ from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
+
+ m = nonmand_tour_freq_model(condense_parameters=False)
+ for segment_name in m:
+ assert len(m[segment_name].pf) == 210
+ assert len(m[segment_name].utility_ca) == 210

activitysim/estimation/larch/general.py

@@ -1,18 +1,15 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
 from typing import Mapping
 
 import numpy as np
 import pandas as pd
-import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model, P, X # noqa: F401
 from larch.log import logger_name
 from larch.model.abstract_model import AbstractChoiceModel
 from larch.model.tree import NestingTree
-from larch.util import Dict
+from larch.util import Dict # noqa: F401
 
 _logger = logging.getLogger(logger_name)
 
@@ -490,13 +487,24 @@ def clean_values(
  return values
 
 
-def update_coefficients(model, data, result_dir=Path("."), output_file=None):
+def update_coefficients(
+ model, data, result_dir=Path("."), output_file=None, relabel_coef=None
+):
  if isinstance(data, pd.DataFrame):
  coefficients = data.copy()
  else:
  coefficients = data.coefficients.copy()
- est_names = [j for j in coefficients.index if j in model.pf.index]
- coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
+ if relabel_coef is not None and len(relabel_coef):
+ for j in coefficients.index:
+ if j in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j, "value"]
+ else:
+ j_ = relabel_coef.get(j, None)
+ if j_ is not None and j_ in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j_, "value"]
+ else:
+ est_names = [j for j in coefficients.index if j in model.pf.index]
+ coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
  if output_file is not None:
  os.makedirs(result_dir, exist_ok=True)
  coefficients.reset_index().to_csv(

activitysim/estimation/larch/nonmand_tour_freq.py

@@ -1,14 +1,10 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
-from typing import Mapping
 
-import numpy as np
 import pandas as pd
 import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model
 from larch.log import logger_name
 from larch.util import Dict
 
@@ -125,17 +121,34 @@ def unavail(model, x_ca):
 def nonmand_tour_freq_model(
  edb_directory="output/estimation_data_bundle/{name}/",
  return_data=False,
+ condense_parameters=False,
 ):
+ """
+ Prepare nonmandatory tour frequency models for estimation.
+
+ Parameters
+ ----------
+ edb_directory : str
+ Location of estimation data bundle for these models.
+ return_data : bool, default False
+ Whether to return the data used in preparing this function.
+ If returned, data is a dict in the second return value.
+ condense_parameters : bool, default False
+ Apply a transformation whereby all parameters in each model that
+ have the same initial value are converted to have the same name
+ (and thus to be the same parameter, used in various places).
+ """
  data = interaction_simulate_data(
  name="non_mandatory_tour_frequency",
  edb_directory=edb_directory,
  )
 
  settings = data.settings
  segment_names = [s["NAME"] for s in settings["SPEC_SEGMENTS"]]
- data.relabel_coef = link_same_value_coefficients(
- segment_names, data.coefficients, data.spec
- )
+ if condense_parameters:
+ data.relabel_coef = link_same_value_coefficients(
+ segment_names, data.coefficients, data.spec
+ )
  spec = data.spec
  coefficients = data.coefficients
  chooser_data = data.chooser_data

activitysim/estimation/test/test_larch_estimation.py

@@ -279,12 +279,24 @@ def test_tour_and_subtour_mode_choice(est_data, num_regression, dataframe_regres
 def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
 
- m = nonmand_tour_freq_model()
+ m = nonmand_tour_freq_model(condense_parameters=True)
  loglike_prior = {}
+ expected_n_params = {
+ "PTYPE_FULL": 72,
+ "PTYPE_PART": 51,
+ "PTYPE_UNIVERSITY": 70,
+ "PTYPE_NONWORK": 77,
+ "PTYPE_RETIRED": 53,
+ "PTYPE_DRIVING": 43,
+ "PTYPE_SCHOOL": 34,
+ "PTYPE_PRESCHOOL": 25,
+ }
  for segment_name in m:
  m[segment_name].load_data()
  m[segment_name].doctor(repair_ch_av="-")
  loglike_prior[segment_name] = m[segment_name].loglike()
+ assert len(m[segment_name].pf) == expected_n_params[segment_name]
+ assert len(m[segment_name].utility_ca) == 210
  r = {}
  for segment_name in m:
  r[segment_name] = m[segment_name].maximize_loglike(
@@ -297,3 +309,14 @@ def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  basename="test_nonmand_tour_freq_loglike",
  )
  _regression_check(dataframe_regression, pd.concat([x.pf for x in m.values()]))
+
+
+def test_nonmand_tour_freq_not_condensed(
+ est_data, num_regression, dataframe_regression
+):
+ from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
+
+ m = nonmand_tour_freq_model(condense_parameters=False)
+ for segment_name in m:
+ assert len(m[segment_name].pf) == 210
+ assert len(m[segment_name].utility_ca) == 210

activitysim/estimation/larch/general.py

@@ -1,18 +1,15 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
 from typing import Mapping
 
 import numpy as np
 import pandas as pd
-import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model, P, X # noqa: F401
 from larch.log import logger_name
 from larch.model.abstract_model import AbstractChoiceModel
 from larch.model.tree import NestingTree
-from larch.util import Dict
+from larch.util import Dict # noqa: F401
 
 _logger = logging.getLogger(logger_name)
 
@@ -490,13 +487,24 @@ def clean_values(
  return values
 
 
-def update_coefficients(model, data, result_dir=Path("."), output_file=None):
+def update_coefficients(
+ model, data, result_dir=Path("."), output_file=None, relabel_coef=None
+):
  if isinstance(data, pd.DataFrame):
  coefficients = data.copy()
  else:
  coefficients = data.coefficients.copy()
- est_names = [j for j in coefficients.index if j in model.pf.index]
- coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
+ if relabel_coef is not None and len(relabel_coef):
+ for j in coefficients.index:
+ if j in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j, "value"]
+ else:
+ j_ = relabel_coef.get(j, None)
+ if j_ is not None and j_ in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j_, "value"]
+ else:
+ est_names = [j for j in coefficients.index if j in model.pf.index]
+ coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
  if output_file is not None:
  os.makedirs(result_dir, exist_ok=True)
  coefficients.reset_index().to_csv(

activitysim/estimation/larch/nonmand_tour_freq.py

@@ -1,14 +1,10 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
-from typing import Mapping
 
-import numpy as np
 import pandas as pd
 import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model
 from larch.log import logger_name
 from larch.util import Dict
 
@@ -125,17 +121,34 @@ def unavail(model, x_ca):
 def nonmand_tour_freq_model(
  edb_directory="output/estimation_data_bundle/{name}/",
  return_data=False,
+ condense_parameters=False,
 ):
+ """
+ Prepare nonmandatory tour frequency models for estimation.
+
+ Parameters
+ ----------
+ edb_directory : str
+ Location of estimation data bundle for these models.
+ return_data : bool, default False
+ Whether to return the data used in preparing this function.
+ If returned, data is a dict in the second return value.
+ condense_parameters : bool, default False
+ Apply a transformation whereby all parameters in each model that
+ have the same initial value are converted to have the same name
+ (and thus to be the same parameter, used in various places).
+ """
  data = interaction_simulate_data(
  name="non_mandatory_tour_frequency",
  edb_directory=edb_directory,
  )
 
  settings = data.settings
  segment_names = [s["NAME"] for s in settings["SPEC_SEGMENTS"]]
- data.relabel_coef = link_same_value_coefficients(
- segment_names, data.coefficients, data.spec
- )
+ if condense_parameters:
+ data.relabel_coef = link_same_value_coefficients(
+ segment_names, data.coefficients, data.spec
+ )
  spec = data.spec
  coefficients = data.coefficients
  chooser_data = data.chooser_data

activitysim/estimation/test/test_larch_estimation.py

@@ -279,12 +279,24 @@ def test_tour_and_subtour_mode_choice(est_data, num_regression, dataframe_regres
 def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
 
- m = nonmand_tour_freq_model()
+ m = nonmand_tour_freq_model(condense_parameters=True)
  loglike_prior = {}
+ expected_n_params = {
+ "PTYPE_FULL": 72,
+ "PTYPE_PART": 51,
+ "PTYPE_UNIVERSITY": 70,
+ "PTYPE_NONWORK": 77,
+ "PTYPE_RETIRED": 53,
+ "PTYPE_DRIVING": 43,
+ "PTYPE_SCHOOL": 34,
+ "PTYPE_PRESCHOOL": 25,
+ }
  for segment_name in m:
  m[segment_name].load_data()
  m[segment_name].doctor(repair_ch_av="-")
  loglike_prior[segment_name] = m[segment_name].loglike()
+ assert len(m[segment_name].pf) == expected_n_params[segment_name]
+ assert len(m[segment_name].utility_ca) == 210
  r = {}
  for segment_name in m:
  r[segment_name] = m[segment_name].maximize_loglike(
@@ -297,3 +309,14 @@ def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  basename="test_nonmand_tour_freq_loglike",
  )
  _regression_check(dataframe_regression, pd.concat([x.pf for x in m.values()]))
+
+
+def test_nonmand_tour_freq_not_condensed(
+ est_data, num_regression, dataframe_regression
+):
+ from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
+
+ m = nonmand_tour_freq_model(condense_parameters=False)
+ for segment_name in m:
+ assert len(m[segment_name].pf) == 210
+ assert len(m[segment_name].utility_ca) == 210

activitysim/estimation/larch/general.py

@@ -1,18 +1,15 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
 from typing import Mapping
 
 import numpy as np
 import pandas as pd
-import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model, P, X # noqa: F401
 from larch.log import logger_name
 from larch.model.abstract_model import AbstractChoiceModel
 from larch.model.tree import NestingTree
-from larch.util import Dict
+from larch.util import Dict # noqa: F401
 
 _logger = logging.getLogger(logger_name)
 
@@ -490,13 +487,24 @@ def clean_values(
  return values
 
 
-def update_coefficients(model, data, result_dir=Path("."), output_file=None):
+def update_coefficients(
+ model, data, result_dir=Path("."), output_file=None, relabel_coef=None
+):
  if isinstance(data, pd.DataFrame):
  coefficients = data.copy()
  else:
  coefficients = data.coefficients.copy()
- est_names = [j for j in coefficients.index if j in model.pf.index]
- coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
+ if relabel_coef is not None and len(relabel_coef):
+ for j in coefficients.index:
+ if j in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j, "value"]
+ else:
+ j_ = relabel_coef.get(j, None)
+ if j_ is not None and j_ in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j_, "value"]
+ else:
+ est_names = [j for j in coefficients.index if j in model.pf.index]
+ coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
  if output_file is not None:
  os.makedirs(result_dir, exist_ok=True)
  coefficients.reset_index().to_csv(

activitysim/estimation/larch/nonmand_tour_freq.py

@@ -1,14 +1,10 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
-from typing import Mapping
 
-import numpy as np
 import pandas as pd
 import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model
 from larch.log import logger_name
 from larch.util import Dict
 
@@ -125,17 +121,34 @@ def unavail(model, x_ca):
 def nonmand_tour_freq_model(
  edb_directory="output/estimation_data_bundle/{name}/",
  return_data=False,
+ condense_parameters=False,
 ):
+ """
+ Prepare nonmandatory tour frequency models for estimation.
+
+ Parameters
+ ----------
+ edb_directory : str
+ Location of estimation data bundle for these models.
+ return_data : bool, default False
+ Whether to return the data used in preparing this function.
+ If returned, data is a dict in the second return value.
+ condense_parameters : bool, default False
+ Apply a transformation whereby all parameters in each model that
+ have the same initial value are converted to have the same name
+ (and thus to be the same parameter, used in various places).
+ """
  data = interaction_simulate_data(
  name="non_mandatory_tour_frequency",
  edb_directory=edb_directory,
  )
 
  settings = data.settings
  segment_names = [s["NAME"] for s in settings["SPEC_SEGMENTS"]]
- data.relabel_coef = link_same_value_coefficients(
- segment_names, data.coefficients, data.spec
- )
+ if condense_parameters:
+ data.relabel_coef = link_same_value_coefficients(
+ segment_names, data.coefficients, data.spec
+ )
  spec = data.spec
  coefficients = data.coefficients
  chooser_data = data.chooser_data

activitysim/estimation/test/test_larch_estimation.py

@@ -279,12 +279,24 @@ def test_tour_and_subtour_mode_choice(est_data, num_regression, dataframe_regres
 def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
 
- m = nonmand_tour_freq_model()
+ m = nonmand_tour_freq_model(condense_parameters=True)
  loglike_prior = {}
+ expected_n_params = {
+ "PTYPE_FULL": 72,
+ "PTYPE_PART": 51,
+ "PTYPE_UNIVERSITY": 70,
+ "PTYPE_NONWORK": 77,
+ "PTYPE_RETIRED": 53,
+ "PTYPE_DRIVING": 43,
+ "PTYPE_SCHOOL": 34,
+ "PTYPE_PRESCHOOL": 25,
+ }
  for segment_name in m:
  m[segment_name].load_data()
  m[segment_name].doctor(repair_ch_av="-")
  loglike_prior[segment_name] = m[segment_name].loglike()
+ assert len(m[segment_name].pf) == expected_n_params[segment_name]
+ assert len(m[segment_name].utility_ca) == 210
  r = {}
  for segment_name in m:
  r[segment_name] = m[segment_name].maximize_loglike(
@@ -297,3 +309,14 @@ def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  basename="test_nonmand_tour_freq_loglike",
  )
  _regression_check(dataframe_regression, pd.concat([x.pf for x in m.values()]))
+
+
+def test_nonmand_tour_freq_not_condensed(
+ est_data, num_regression, dataframe_regression
+):
+ from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
+
+ m = nonmand_tour_freq_model(condense_parameters=False)
+ for segment_name in m:
+ assert len(m[segment_name].pf) == 210
+ assert len(m[segment_name].utility_ca) == 210

activitysim/estimation/larch/general.py

@@ -1,18 +1,15 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
 from typing import Mapping
 
 import numpy as np
 import pandas as pd
-import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model, P, X # noqa: F401
 from larch.log import logger_name
 from larch.model.abstract_model import AbstractChoiceModel
 from larch.model.tree import NestingTree
-from larch.util import Dict
+from larch.util import Dict # noqa: F401
 
 _logger = logging.getLogger(logger_name)
 
@@ -490,13 +487,24 @@ def clean_values(
  return values
 
 
-def update_coefficients(model, data, result_dir=Path("."), output_file=None):
+def update_coefficients(
+ model, data, result_dir=Path("."), output_file=None, relabel_coef=None
+):
  if isinstance(data, pd.DataFrame):
  coefficients = data.copy()
  else:
  coefficients = data.coefficients.copy()
- est_names = [j for j in coefficients.index if j in model.pf.index]
- coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
+ if relabel_coef is not None and len(relabel_coef):
+ for j in coefficients.index:
+ if j in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j, "value"]
+ else:
+ j_ = relabel_coef.get(j, None)
+ if j_ is not None and j_ in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j_, "value"]
+ else:
+ est_names = [j for j in coefficients.index if j in model.pf.index]
+ coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
  if output_file is not None:
  os.makedirs(result_dir, exist_ok=True)
  coefficients.reset_index().to_csv(

activitysim/estimation/larch/nonmand_tour_freq.py

@@ -1,14 +1,10 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
-from typing import Mapping
 
-import numpy as np
 import pandas as pd
 import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model
 from larch.log import logger_name
 from larch.util import Dict
 
@@ -125,17 +121,34 @@ def unavail(model, x_ca):
 def nonmand_tour_freq_model(
  edb_directory="output/estimation_data_bundle/{name}/",
  return_data=False,
+ condense_parameters=False,
 ):
+ """
+ Prepare nonmandatory tour frequency models for estimation.
+
+ Parameters
+ ----------
+ edb_directory : str
+ Location of estimation data bundle for these models.
+ return_data : bool, default False
+ Whether to return the data used in preparing this function.
+ If returned, data is a dict in the second return value.
+ condense_parameters : bool, default False
+ Apply a transformation whereby all parameters in each model that
+ have the same initial value are converted to have the same name
+ (and thus to be the same parameter, used in various places).
+ """
  data = interaction_simulate_data(
  name="non_mandatory_tour_frequency",
  edb_directory=edb_directory,
  )
 
  settings = data.settings
  segment_names = [s["NAME"] for s in settings["SPEC_SEGMENTS"]]
- data.relabel_coef = link_same_value_coefficients(
- segment_names, data.coefficients, data.spec
- )
+ if condense_parameters:
+ data.relabel_coef = link_same_value_coefficients(
+ segment_names, data.coefficients, data.spec
+ )
  spec = data.spec
  coefficients = data.coefficients
  chooser_data = data.chooser_data

activitysim/estimation/test/test_larch_estimation.py

@@ -279,12 +279,24 @@ def test_tour_and_subtour_mode_choice(est_data, num_regression, dataframe_regres
 def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
 
- m = nonmand_tour_freq_model()
+ m = nonmand_tour_freq_model(condense_parameters=True)
  loglike_prior = {}
+ expected_n_params = {
+ "PTYPE_FULL": 72,
+ "PTYPE_PART": 51,
+ "PTYPE_UNIVERSITY": 70,
+ "PTYPE_NONWORK": 77,
+ "PTYPE_RETIRED": 53,
+ "PTYPE_DRIVING": 43,
+ "PTYPE_SCHOOL": 34,
+ "PTYPE_PRESCHOOL": 25,
+ }
  for segment_name in m:
  m[segment_name].load_data()
  m[segment_name].doctor(repair_ch_av="-")
  loglike_prior[segment_name] = m[segment_name].loglike()
+ assert len(m[segment_name].pf) == expected_n_params[segment_name]
+ assert len(m[segment_name].utility_ca) == 210
  r = {}
  for segment_name in m:
  r[segment_name] = m[segment_name].maximize_loglike(
@@ -297,3 +309,14 @@ def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  basename="test_nonmand_tour_freq_loglike",
  )
  _regression_check(dataframe_regression, pd.concat([x.pf for x in m.values()]))
+
+
+def test_nonmand_tour_freq_not_condensed(
+ est_data, num_regression, dataframe_regression
+):
+ from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
+
+ m = nonmand_tour_freq_model(condense_parameters=False)
+ for segment_name in m:
+ assert len(m[segment_name].pf) == 210
+ assert len(m[segment_name].utility_ca) == 210

activitysim/estimation/larch/general.py

@@ -1,18 +1,15 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
 from typing import Mapping
 
 import numpy as np
 import pandas as pd
-import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model, P, X # noqa: F401
 from larch.log import logger_name
 from larch.model.abstract_model import AbstractChoiceModel
 from larch.model.tree import NestingTree
-from larch.util import Dict
+from larch.util import Dict # noqa: F401
 
 _logger = logging.getLogger(logger_name)
 
@@ -490,13 +487,24 @@ def clean_values(
  return values
 
 
-def update_coefficients(model, data, result_dir=Path("."), output_file=None):
+def update_coefficients(
+ model, data, result_dir=Path("."), output_file=None, relabel_coef=None
+):
  if isinstance(data, pd.DataFrame):
  coefficients = data.copy()
  else:
  coefficients = data.coefficients.copy()
- est_names = [j for j in coefficients.index if j in model.pf.index]
- coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
+ if relabel_coef is not None and len(relabel_coef):
+ for j in coefficients.index:
+ if j in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j, "value"]
+ else:
+ j_ = relabel_coef.get(j, None)
+ if j_ is not None and j_ in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j_, "value"]
+ else:
+ est_names = [j for j in coefficients.index if j in model.pf.index]
+ coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
  if output_file is not None:
  os.makedirs(result_dir, exist_ok=True)
  coefficients.reset_index().to_csv(

activitysim/estimation/larch/nonmand_tour_freq.py

@@ -1,14 +1,10 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
-from typing import Mapping
 
-import numpy as np
 import pandas as pd
 import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model
 from larch.log import logger_name
 from larch.util import Dict
 
@@ -125,17 +121,34 @@ def unavail(model, x_ca):
 def nonmand_tour_freq_model(
  edb_directory="output/estimation_data_bundle/{name}/",
  return_data=False,
+ condense_parameters=False,
 ):
+ """
+ Prepare nonmandatory tour frequency models for estimation.
+
+ Parameters
+ ----------
+ edb_directory : str
+ Location of estimation data bundle for these models.
+ return_data : bool, default False
+ Whether to return the data used in preparing this function.
+ If returned, data is a dict in the second return value.
+ condense_parameters : bool, default False
+ Apply a transformation whereby all parameters in each model that
+ have the same initial value are converted to have the same name
+ (and thus to be the same parameter, used in various places).
+ """
  data = interaction_simulate_data(
  name="non_mandatory_tour_frequency",
  edb_directory=edb_directory,
  )
 
  settings = data.settings
  segment_names = [s["NAME"] for s in settings["SPEC_SEGMENTS"]]
- data.relabel_coef = link_same_value_coefficients(
- segment_names, data.coefficients, data.spec
- )
+ if condense_parameters:
+ data.relabel_coef = link_same_value_coefficients(
+ segment_names, data.coefficients, data.spec
+ )
  spec = data.spec
  coefficients = data.coefficients
  chooser_data = data.chooser_data

activitysim/estimation/test/test_larch_estimation.py

@@ -279,12 +279,24 @@ def test_tour_and_subtour_mode_choice(est_data, num_regression, dataframe_regres
 def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
 
- m = nonmand_tour_freq_model()
+ m = nonmand_tour_freq_model(condense_parameters=True)
  loglike_prior = {}
+ expected_n_params = {
+ "PTYPE_FULL": 72,
+ "PTYPE_PART": 51,
+ "PTYPE_UNIVERSITY": 70,
+ "PTYPE_NONWORK": 77,
+ "PTYPE_RETIRED": 53,
+ "PTYPE_DRIVING": 43,
+ "PTYPE_SCHOOL": 34,
+ "PTYPE_PRESCHOOL": 25,
+ }
  for segment_name in m:
  m[segment_name].load_data()
  m[segment_name].doctor(repair_ch_av="-")
  loglike_prior[segment_name] = m[segment_name].loglike()
+ assert len(m[segment_name].pf) == expected_n_params[segment_name]
+ assert len(m[segment_name].utility_ca) == 210
  r = {}
  for segment_name in m:
  r[segment_name] = m[segment_name].maximize_loglike(
@@ -297,3 +309,14 @@ def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  basename="test_nonmand_tour_freq_loglike",
  )
  _regression_check(dataframe_regression, pd.concat([x.pf for x in m.values()]))
+
+
+def test_nonmand_tour_freq_not_condensed(
+ est_data, num_regression, dataframe_regression
+):
+ from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
+
+ m = nonmand_tour_freq_model(condense_parameters=False)
+ for segment_name in m:
+ assert len(m[segment_name].pf) == 210
+ assert len(m[segment_name].utility_ca) == 210

activitysim/estimation/larch/general.py

@@ -1,18 +1,15 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
 from typing import Mapping
 
 import numpy as np
 import pandas as pd
-import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model, P, X # noqa: F401
 from larch.log import logger_name
 from larch.model.abstract_model import AbstractChoiceModel
 from larch.model.tree import NestingTree
-from larch.util import Dict
+from larch.util import Dict # noqa: F401
 
 _logger = logging.getLogger(logger_name)
 
@@ -490,13 +487,24 @@ def clean_values(
  return values
 
 
-def update_coefficients(model, data, result_dir=Path("."), output_file=None):
+def update_coefficients(
+ model, data, result_dir=Path("."), output_file=None, relabel_coef=None
+):
  if isinstance(data, pd.DataFrame):
  coefficients = data.copy()
  else:
  coefficients = data.coefficients.copy()
- est_names = [j for j in coefficients.index if j in model.pf.index]
- coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
+ if relabel_coef is not None and len(relabel_coef):
+ for j in coefficients.index:
+ if j in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j, "value"]
+ else:
+ j_ = relabel_coef.get(j, None)
+ if j_ is not None and j_ in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j_, "value"]
+ else:
+ est_names = [j for j in coefficients.index if j in model.pf.index]
+ coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
  if output_file is not None:
  os.makedirs(result_dir, exist_ok=True)
  coefficients.reset_index().to_csv(

activitysim/estimation/larch/nonmand_tour_freq.py

@@ -1,14 +1,10 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
-from typing import Mapping
 
-import numpy as np
 import pandas as pd
 import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model
 from larch.log import logger_name
 from larch.util import Dict
 
@@ -125,17 +121,34 @@ def unavail(model, x_ca):
 def nonmand_tour_freq_model(
  edb_directory="output/estimation_data_bundle/{name}/",
  return_data=False,
+ condense_parameters=False,
 ):
+ """
+ Prepare nonmandatory tour frequency models for estimation.
+
+ Parameters
+ ----------
+ edb_directory : str
+ Location of estimation data bundle for these models.
+ return_data : bool, default False
+ Whether to return the data used in preparing this function.
+ If returned, data is a dict in the second return value.
+ condense_parameters : bool, default False
+ Apply a transformation whereby all parameters in each model that
+ have the same initial value are converted to have the same name
+ (and thus to be the same parameter, used in various places).
+ """
  data = interaction_simulate_data(
  name="non_mandatory_tour_frequency",
  edb_directory=edb_directory,
  )
 
  settings = data.settings
  segment_names = [s["NAME"] for s in settings["SPEC_SEGMENTS"]]
- data.relabel_coef = link_same_value_coefficients(
- segment_names, data.coefficients, data.spec
- )
+ if condense_parameters:
+ data.relabel_coef = link_same_value_coefficients(
+ segment_names, data.coefficients, data.spec
+ )
  spec = data.spec
  coefficients = data.coefficients
  chooser_data = data.chooser_data

activitysim/estimation/test/test_larch_estimation.py

@@ -279,12 +279,24 @@ def test_tour_and_subtour_mode_choice(est_data, num_regression, dataframe_regres
 def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
 
- m = nonmand_tour_freq_model()
+ m = nonmand_tour_freq_model(condense_parameters=True)
  loglike_prior = {}
+ expected_n_params = {
+ "PTYPE_FULL": 72,
+ "PTYPE_PART": 51,
+ "PTYPE_UNIVERSITY": 70,
+ "PTYPE_NONWORK": 77,
+ "PTYPE_RETIRED": 53,
+ "PTYPE_DRIVING": 43,
+ "PTYPE_SCHOOL": 34,
+ "PTYPE_PRESCHOOL": 25,
+ }
  for segment_name in m:
  m[segment_name].load_data()
  m[segment_name].doctor(repair_ch_av="-")
  loglike_prior[segment_name] = m[segment_name].loglike()
+ assert len(m[segment_name].pf) == expected_n_params[segment_name]
+ assert len(m[segment_name].utility_ca) == 210
  r = {}
  for segment_name in m:
  r[segment_name] = m[segment_name].maximize_loglike(
@@ -297,3 +309,14 @@ def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  basename="test_nonmand_tour_freq_loglike",
  )
  _regression_check(dataframe_regression, pd.concat([x.pf for x in m.values()]))
+
+
+def test_nonmand_tour_freq_not_condensed(
+ est_data, num_regression, dataframe_regression
+):
+ from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
+
+ m = nonmand_tour_freq_model(condense_parameters=False)
+ for segment_name in m:
+ assert len(m[segment_name].pf) == 210
+ assert len(m[segment_name].utility_ca) == 210

activitysim/estimation/larch/general.py

@@ -1,18 +1,15 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
 from typing import Mapping
 
 import numpy as np
 import pandas as pd
-import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model, P, X # noqa: F401
 from larch.log import logger_name
 from larch.model.abstract_model import AbstractChoiceModel
 from larch.model.tree import NestingTree
-from larch.util import Dict
+from larch.util import Dict # noqa: F401
 
 _logger = logging.getLogger(logger_name)
 
@@ -490,13 +487,24 @@ def clean_values(
  return values
 
 
-def update_coefficients(model, data, result_dir=Path("."), output_file=None):
+def update_coefficients(
+ model, data, result_dir=Path("."), output_file=None, relabel_coef=None
+):
  if isinstance(data, pd.DataFrame):
  coefficients = data.copy()
  else:
  coefficients = data.coefficients.copy()
- est_names = [j for j in coefficients.index if j in model.pf.index]
- coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
+ if relabel_coef is not None and len(relabel_coef):
+ for j in coefficients.index:
+ if j in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j, "value"]
+ else:
+ j_ = relabel_coef.get(j, None)
+ if j_ is not None and j_ in model.pf.index:
+ coefficients.loc[j, "value"] = model.pf.loc[j_, "value"]
+ else:
+ est_names = [j for j in coefficients.index if j in model.pf.index]
+ coefficients.loc[est_names, "value"] = model.pf.loc[est_names, "value"]
  if output_file is not None:
  os.makedirs(result_dir, exist_ok=True)
  coefficients.reset_index().to_csv(

activitysim/estimation/larch/nonmand_tour_freq.py

@@ -1,14 +1,10 @@
-import itertools
 import logging
 import os
-import re
 from pathlib import Path
-from typing import Mapping
 
-import numpy as np
 import pandas as pd
 import yaml
-from larch import DataFrames, Model, P, X
+from larch import DataFrames, Model
 from larch.log import logger_name
 from larch.util import Dict
 
@@ -125,17 +121,34 @@ def unavail(model, x_ca):
 def nonmand_tour_freq_model(
  edb_directory="output/estimation_data_bundle/{name}/",
  return_data=False,
+ condense_parameters=False,
 ):
+ """
+ Prepare nonmandatory tour frequency models for estimation.
+
+ Parameters
+ ----------
+ edb_directory : str
+ Location of estimation data bundle for these models.
+ return_data : bool, default False
+ Whether to return the data used in preparing this function.
+ If returned, data is a dict in the second return value.
+ condense_parameters : bool, default False
+ Apply a transformation whereby all parameters in each model that
+ have the same initial value are converted to have the same name
+ (and thus to be the same parameter, used in various places).
+ """
  data = interaction_simulate_data(
  name="non_mandatory_tour_frequency",
  edb_directory=edb_directory,
  )
 
  settings = data.settings
  segment_names = [s["NAME"] for s in settings["SPEC_SEGMENTS"]]
- data.relabel_coef = link_same_value_coefficients(
- segment_names, data.coefficients, data.spec
- )
+ if condense_parameters:
+ data.relabel_coef = link_same_value_coefficients(
+ segment_names, data.coefficients, data.spec
+ )
  spec = data.spec
  coefficients = data.coefficients
  chooser_data = data.chooser_data

activitysim/estimation/test/test_larch_estimation.py

@@ -279,12 +279,24 @@ def test_tour_and_subtour_mode_choice(est_data, num_regression, dataframe_regres
 def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
 
- m = nonmand_tour_freq_model()
+ m = nonmand_tour_freq_model(condense_parameters=True)
  loglike_prior = {}
+ expected_n_params = {
+ "PTYPE_FULL": 72,
+ "PTYPE_PART": 51,
+ "PTYPE_UNIVERSITY": 70,
+ "PTYPE_NONWORK": 77,
+ "PTYPE_RETIRED": 53,
+ "PTYPE_DRIVING": 43,
+ "PTYPE_SCHOOL": 34,
+ "PTYPE_PRESCHOOL": 25,
+ }
  for segment_name in m:
  m[segment_name].load_data()
  m[segment_name].doctor(repair_ch_av="-")
  loglike_prior[segment_name] = m[segment_name].loglike()
+ assert len(m[segment_name].pf) == expected_n_params[segment_name]
+ assert len(m[segment_name].utility_ca) == 210
  r = {}
  for segment_name in m:
  r[segment_name] = m[segment_name].maximize_loglike(
@@ -297,3 +309,14 @@ def test_nonmand_tour_freq(est_data, num_regression, dataframe_regression):
  basename="test_nonmand_tour_freq_loglike",
  )
  _regression_check(dataframe_regression, pd.concat([x.pf for x in m.values()]))
+
+
+def test_nonmand_tour_freq_not_condensed(
+ est_data, num_regression, dataframe_regression
+):
+ from activitysim.estimation.larch.nonmand_tour_freq import nonmand_tour_freq_model
+
+ m = nonmand_tour_freq_model(condense_parameters=False)
+ for segment_name in m:
+ assert len(m[segment_name].pf) == 210
+ assert len(m[segment_name].utility_ca) == 210