def prepare_for_estimate(self, agents_for_estimation_storage, agents_for_estimation_table, agent_set, **kwargs):
estimation_set = Dataset(in_storage = agents_for_estimation_storage,
in_table_name=agents_for_estimation_table,
id_name=agent_set.get_id_name(), dataset_name=agent_set.get_dataset_name())
hhs_est = HouseholdDataset(in_storage=agents_for_estimation_storage, in_table_name='households_for_estimation')
self.dataset_pool.replace_dataset('household', hhs_est)
self.dataset_pool.replace_dataset(estimation_set.get_dataset_name(), estimation_set)
spec, index = ChoiceModel.prepare_for_estimate(self, estimation_set, **kwargs)
return (spec, index, estimation_set)
def prepare_for_estimate(self, estimation_storage, agents_for_estimation_table, agent_set,
households_for_estimation_table=None, **kwargs):
estimation_set = Dataset(in_storage = estimation_storage,
in_table_name=agents_for_estimation_table,
id_name=agent_set.get_id_name(), dataset_name=agent_set.get_dataset_name())
if households_for_estimation_table is not None:
hhs = HouseholdDataset(in_storage=estimation_storage, in_table_name='households_for_estimation')
self.dataset_pool.replace_dataset('household', hhs)
self.dataset_pool.replace_dataset(estimation_set.get_dataset_name(), estimation_set)
spec, index = HierarchicalChoiceModel.prepare_for_estimate(self, estimation_set, **kwargs)
return (spec, index, estimation_set)
def prepare_for_estimate_hh(self, estimation_storage, agents_for_estimation_table, agent_set,
persons_for_estimation_table=None, **kwargs):
estimation_set = Dataset(in_storage = estimation_storage,
in_table_name=agents_for_estimation_table,
id_name=agent_set.get_id_name(), dataset_name=agent_set.get_dataset_name())
if persons_for_estimation_table is not None:
pers = PersonDataset(in_storage=estimation_storage, in_table_name=persons_for_estimation_table)
self.dataset_pool.replace_dataset('person', pers)
self.dataset_pool.replace_dataset(estimation_set.get_dataset_name(), estimation_set)
spec, index = ChoiceModel.prepare_for_estimate(self, estimation_set, **kwargs)
return (spec, index, estimation_set)
def prepare_for_run(self, dataset=None, control_totals=None, weight_attribute=None, excel_path=None, excel_sheet_number=1, excel_data_info={}, esri_storage_location=None,
dataset_name=None, current_year=0, datasets_and_weights_in_years=None, dataset_pool=None):
"""
If dataset is not given, it is loaded from the esri storage. In such a case, dataset_name should be the name of the shape file (without postfix).
If control_totals is not given, it is loaded from an excel table.
datasets_and_weights_in_years is a dictionary with years as keys and tuples of dataset_name and weight attribute as values.
If its given and it has a value for the current year, its value overwrites the arguments 'dataset_name' and 'weight_attribute'.
The method returns a tuple wit three elements: dataset (Dataset object), control_totals (Dataset object), weight_attribute (string)
Those are going to be used in the run method.
"""
if control_totals is None:
logger.log_status("Getting data from Excel for AllocationModel")
excel_doc = ExcelDocument()
excel_doc.open(excel_path)
excel_doc.set_sheet(excel_sheet_number)
control_total_data = excel_doc.get_dict_table_from_column_names_and_ranges(excel_data_info)
excel_doc.close()
excel_doc.quit()
del excel_doc
dict_storage = StorageFactory().get_storage('dict_storage')
dict_storage.write_table(table_name = 'control_totals', table_data = control_total_data)
control_totals = Dataset(in_storage = dict_storage, in_table_name = 'control_totals', id_name='year')
if datasets_and_weights_in_years is not None and current_year in datasets_and_weights_in_years.keys():
dataset_name, weight_attribute = datasets_and_weights_in_years[current_year]
dataset = None
if dataset is None:
logger.log_status("Getting data from esri_storage for AllocationModel")
esri_storage = StorageFactory().get_storage('esri_storage', storage_location=esri_storage_location)
#Was: dataset = Dataset(in_storage=esri_storage, in_table_name=dataset_name, id_name=dataset_name+'_id', dataset_name=dataset_name)
dataset = DatasetFactory().search_for_dataset(dataset_name, dataset_pool.get_package_order(), arguments={'in_storage': esri_storage, 'id_name':dataset_name+'_id'} )
dataset_pool.add_datasets_if_not_included({dataset_name:dataset, control_totals.get_dataset_name():control_totals})
return (dataset, control_totals, weight_attribute)
#households.plot_histogram("income", bins = 10)
#households.r_histogram("income")
#households.r_scatter("persons", "income")
households.correlation_coefficient("persons", "income")
households.correlation_matrix(["persons", "income"])
households.summary()
households.add_primary_attribute(data=[4,6,9,2,4,8,2,1,3,2], name="location")
households.get_attribute_names()
households.modify_attribute(name="location", data=[0,0], index=[0,1])
households.get_attribute("location")
households.get_data_element_by_id(5).location
#households.write_dataset(out_storage=storage, out_table_name="households_output")
households.get_dataset_name()
# Working with models
from opus_core.choice_model import ChoiceModel
choicemodel = ChoiceModel(choice_set=[1,2,3],
utilities = "opus_core.linear_utilities",
probabilities = "opus_core.mnl_probabilities",
choices = "opus_core.random_choices")
from numpy import array
from opus_core.equation_specification import EquationSpecification
specification = EquationSpecification(
coefficients = array([
"beta01", "beta12", "beta03", "beta13"
]),
variables = array([
"constant","household.persons", "constant", "household.persons"
def prepare_for_run(self,
dataset=None,
control_totals=None,
weight_attribute=None,
excel_path=None,
excel_sheet_number=1,
excel_data_info={},
esri_storage_location=None,
dataset_name=None,
current_year=0,
datasets_and_weights_in_years=None,
dataset_pool=None):
"""
If dataset is not given, it is loaded from the esri storage. In such a case, dataset_name should be the name of the shape file (without postfix).
If control_totals is not given, it is loaded from an excel table.
datasets_and_weights_in_years is a dictionary with years as keys and tuples of dataset_name and weight attribute as values.
If its given and it has a value for the current year, its value overwrites the arguments 'dataset_name' and 'weight_attribute'.
The method returns a tuple wit three elements: dataset (Dataset object), control_totals (Dataset object), weight_attribute (string)
Those are going to be used in the run method.
"""
if control_totals is None:
logger.log_status("Getting data from Excel for AllocationModel")
excel_doc = ExcelDocument()
excel_doc.open(excel_path)
excel_doc.set_sheet(excel_sheet_number)
control_total_data = excel_doc.get_dict_table_from_column_names_and_ranges(
excel_data_info)
excel_doc.close()
excel_doc.quit()
del excel_doc
dict_storage = StorageFactory().get_storage('dict_storage')
dict_storage.write_table(table_name='control_totals',
table_data=control_total_data)
control_totals = Dataset(in_storage=dict_storage,
in_table_name='control_totals',
id_name='year')
if datasets_and_weights_in_years is not None and current_year in datasets_and_weights_in_years.keys(
):
dataset_name, weight_attribute = datasets_and_weights_in_years[
current_year]
dataset = None
if dataset is None:
logger.log_status(
"Getting data from esri_storage for AllocationModel")
esri_storage = StorageFactory().get_storage(
'esri_storage', storage_location=esri_storage_location)
#Was: dataset = Dataset(in_storage=esri_storage, in_table_name=dataset_name, id_name=dataset_name+'_id', dataset_name=dataset_name)
dataset = DatasetFactory().search_for_dataset(
dataset_name,
dataset_pool.get_package_order(),
arguments={
'in_storage': esri_storage,
'id_name': dataset_name + '_id'
})
dataset_pool.add_datasets_if_not_included({
dataset_name:
dataset,
control_totals.get_dataset_name():
control_totals
})
return (dataset, control_totals, weight_attribute)
#households.plot_histogram("income", bins = 10)
#households.r_histogram("income")
#households.r_scatter("persons", "income")
households.correlation_coefficient("persons", "income")
households.correlation_matrix(["persons", "income"])
households.summary()
households.add_primary_attribute(data=[4,6,9,2,4,8,2,1,3,2], name="location")
households.get_attribute_names()
households.modify_attribute(name="location", data=[0,0], index=[0,1])
households.get_attribute("location")
households.get_data_element_by_id(5).location
#households.write_dataset(out_storage=storage, out_table_name="households_output")
households.get_dataset_name()
# Working with models
from opus_core.choice_model import ChoiceModel
choicemodel = ChoiceModel(choice_set=[1,2,3],
utilities = "opus_core.linear_utilities",
probabilities = "opus_core.mnl_probabilities",
choices = "opus_core.random_choices")
from numpy import array
from opus_core.equation_specification import EquationSpecification
specification = EquationSpecification(
coefficients = array([
"beta01", "beta12", "beta03", "beta13"
]),
variables = array([
"constant","household.persons", "constant", "household.persons"
