def test_my_inputs(self):
storage = StorageFactory().get_storage('dict_storage')
job_building_types_table_name = 'job_building_types'
storage.write_table(
table_name=job_building_types_table_name,
table_data={
'id':array([1,2,3,4]),
'home_based': array([1, 0, 1, 0])
}
)
jobs_table_name = 'jobs'
storage.write_table(
table_name=jobs_table_name,
table_data={
'job_id':arange(10)+1,
'building_type': array([3,3,2,2,4,2,1,3,4,1])
}
)
job_building_types = JobBuildingTypeDataset(in_storage=storage, in_table_name=job_building_types_table_name)
jobs = JobDataset(in_storage=storage, in_table_name=jobs_table_name)
jobs.compute_variables(self.variable_name, resources=Resources({'job_building_type': job_building_types}))
values = jobs.get_attribute(self.variable_name)
should_be = array([0,0,1,1,1,1,0,0,1,0])
self.assert_(ma.allequal(values, should_be),
'Error in ' + self.variable_name)
def test_my_inputs(self):
storage = StorageFactory().get_storage('dict_storage')
job_building_types_table_name = 'job_building_types'
storage.write_table(table_name=job_building_types_table_name,
table_data={
'id': array([1, 2, 3, 4]),
'home_based': array([1, 0, 1, 0])
})
jobs_table_name = 'jobs'
storage.write_table(table_name=jobs_table_name,
table_data={
'job_id':
arange(10) + 1,
'building_type':
array([3, 3, 2, 2, 4, 2, 1, 3, 4, 1])
})
job_building_types = JobBuildingTypeDataset(
in_storage=storage, in_table_name=job_building_types_table_name)
jobs = JobDataset(in_storage=storage, in_table_name=jobs_table_name)
jobs.compute_variables(self.variable_name,
resources=Resources(
{'job_building_type': job_building_types}))
values = jobs.get_attribute(self.variable_name)
should_be = array([0, 0, 1, 1, 1, 1, 0, 0, 1, 0])
self.assert_(ma.allequal(values, should_be),
'Error in ' + self.variable_name)
def test_my_inputs(self):
storage = StorageFactory().get_storage("dict_storage")
job_building_types_table_name = "job_building_types"
storage.write_table(
table_name=job_building_types_table_name,
table_data={"id": array([1, 2, 3, 4]), "home_based": array([0, 1, 0, 1])},
)
jobs_table_name = "jobs"
storage.write_table(
table_name=jobs_table_name,
table_data={"job_id": arange(10) + 1, "building_type": array([3, 3, 2, 2, 4, 2, 1, 3, 4, 1])},
)
job_building_types = JobBuildingTypeDataset(in_storage=storage, in_table_name=job_building_types_table_name)
jobs = JobDataset(in_storage=storage, in_table_name=jobs_table_name)
jobs.compute_variables(self.variable_name, resources=Resources({"job_building_type": job_building_types}))
values = jobs.get_attribute(self.variable_name)
should_be = array([0, 0, 1, 1, 1, 1, 0, 0, 1, 0], dtype="bool8")
self.assert_(ma.allequal(values, should_be), "Error in " + self.variable_name)
def test_run_model_with_known_buildings(self):
storage = self.storage
storage.write_table(
table_name = 'buildings',
table_data = {
'building_id': array([1,2,3,4,5,6,7]),
'parcel_id': array([1,1,2,2,2,3,3]),
'is_residential': array([0,0,0,1,1,0,0])
}
)
storage.write_table(
table_name = 'employment_events',
table_data = {
'parcel_id': array([2, 2, -1, -1, 1]),
'building_id': array([-1, -1, 6, 7, -1]),
'scheduled_year': array([2006, 2006, 2006, 2006, 2006]),
'number_of_non_home_based_jobs': array([3500, 500, -100, 0, 100]),
'number_of_home_based_jobs': array([0, 20, 0, 10, 0]),
'sector_id': array([1, 2, 15, 2, 1]),
'replace_non_home_based_jobs': array([0, 0, 0, 1, 0])
}
)
# change in 2006
############
# parcel/sector 1 2 3
# 1 +100nhb +3500nhb --
# 2 =0nhb +500nhb/+20hb +10hb
# 15 -- -- -100nhb
dataset_pool = DatasetPool(storage=storage, package_order=['urbansim_parcel', 'urbansim'])
job_set = JobDataset(in_storage=storage)
job_set.modify_attribute('building_id', array(6000*[1] + 4000*[3] + 3000*[6]))
dataset_pool.add_datasets_if_not_included({'job':job_set})
model = EmploymentEventsModel(dataset_pool=dataset_pool)
model.run(dataset_pool.get_dataset('employment_event'), job_set, current_year=2006)
buildings = dataset_pool.get_dataset('building')
jobs_in_sec_1 = buildings.compute_variables(['urbansim_parcel.building.number_of_jobs_of_sector_1'],
dataset_pool=dataset_pool)
jobs_in_sec_2 = buildings.compute_variables(['urbansim_parcel.building.number_of_jobs_of_sector_2'],
dataset_pool=dataset_pool)
jobs_in_sec_15 = buildings.compute_variables(['urbansim_parcel.building.number_of_jobs_of_sector_15'],
dataset_pool=dataset_pool)
self.assertEqual(jobs_in_sec_1[0:2].sum()==4100, True) # parcel 1
self.assertEqual(jobs_in_sec_1[2] == 5500, True) # parcel 2 non-residential
self.assertEqual(jobs_in_sec_1[5:7].sum()==1000, True) # parcel 3
self.assertEqual(jobs_in_sec_2[0:2].sum()==1000, True) # parcel 1
self.assertEqual(jobs_in_sec_2[2] == 1500, True) # parcel 2 non-residential
self.assertEqual(jobs_in_sec_2[3:5].sum() == 20, True) # parcel 2 residential
self.assertEqual(jobs_in_sec_2[5]==100, True) # parcel 3, building 6
self.assertEqual(jobs_in_sec_2[6]==10, True) # parcel 3, building 7
self.assertEqual(jobs_in_sec_15[0:2].sum()==1000, True) # parcel 2 non-residential
self.assertEqual(jobs_in_sec_15[2] == 1000, True) # parcel 2 residential
self.assertEqual(jobs_in_sec_15[5]==900, True) # parcel 3, building 6
def test_same_distribution_after_job_addition(self):
"""Add 1,750 new jobs of sector 1 without specifying a distribution across gridcells (so it is assumed equal)
Test that the total number of jobs in each sector after the addition matches the totals specified
in annual_employment_control_totals.
Ensure that the number of unplaced jobs after the addition is exactly 1,750 because this model
is not responsible for placing jobs, only for creating them.
NOTE: unplaced jobs are indicated by grid_id <= 0
"""
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name=jobs_set_table_name,
table_data=self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage,
in_table_name=jobs_set_table_name)
annual_employment_control_totals_data = self.annual_employment_control_totals_data
annual_employment_control_totals_data[
"total_non_home_based_employment"] = array(
[5750, 1400, 4000, 1600])
ect_set_table_name = 'ect_set'
storage.write_table(
table_name=ect_set_table_name,
table_data=annual_employment_control_totals_data,
)
ect_set = ControlTotalDataset(in_storage=storage,
in_table_name=ect_set_table_name,
what="employment")
# run model
model = RegionalEmploymentTransitionModel()
model.run(year=2000,
job_set=jobs_set,
control_totals=ect_set,
job_building_types=self.job_building_types)
#check that there are indeed 14750 total jobs after running the model
areas = jobs_set.get_attribute("large_area_id")
results = array([0, 0])
for iarea in [0, 1]:
results[iarea] = where(areas == [1, 2][iarea])[0].size
should_be = [8150, 7600]
self.assertEqual(
ma.allequal(should_be, results), True,
"Error, should_be: %s, but result: %s" % (should_be, results))
#check that total #jobs within each sector are close to what was set in the control_totals
results = self.get_count_all_sectors_and_areas(jobs_set)
should_be = [5750, 1400, 1000, 4000, 1600, 2000]
self.assertEqual(
ma.allclose(results, should_be, rtol=0.00001), True,
"Error, should_be: %s, but result: %s" % (should_be, results))
def test_distribute_unplaced_jobs_model(self):
# Places 1750 jobs of sector 15
# gridcell has expected about
# 1 4000 sector 15 jobs 5000 sector 15 jobs
# 1000 sector 1 jobs 1000 sector 1 jobs
# 2 2000 sector 15 jobs 2500 sector 15 jobs
# 1000 sector 1 jobs 1000 sector 1 jobs
# 3 1000 sector 15 jobs 1250 sector 15 jobs
# 1000 sector 1 jobs 1000 sector 1 jobs
# unplaced 1750 sector 15 jobs 0
# create jobs
storage = StorageFactory().get_storage("dict_storage")
job_data = {
"job_id": arange(11750) + 1,
"sector_id": array(7000 * [15] + 3000 * [1] + 1750 * [15]),
"grid_id": array(4000 * [1] + 2000 * [2] + 1000 * [3] + 1000 * [1] + 1000 * [2] + 1000 * [3] + 1750 * [-1]),
}
jobs_table_name = "jobs"
storage.write_table(table_name=jobs_table_name, table_data=job_data)
jobs = JobDataset(in_storage=storage, in_table_name=jobs_table_name)
storage = StorageFactory().get_storage("dict_storage")
building_types_table_name = "building_types"
storage.write_table(table_name=building_types_table_name, table_data={"grid_id": arange(3) + 1})
gridcells = GridcellDataset(in_storage=storage, in_table_name=building_types_table_name)
# run model
model = DistributeUnplacedJobsModel(debuglevel=4)
model.run(gridcells, jobs)
# get results
# no jobs are unplaced
result1 = where(jobs.get_attribute("grid_id") < 0)[0]
self.assertEqual(result1.size, 0)
# the first 10000jobs kept their locations
result2 = jobs.get_attribute_by_index("grid_id", arange(10000))
# logger.log_status(result2)
self.assertEqual(ma.allclose(result2, job_data["grid_id"][0:10000], rtol=0), True)
# run model with filter
# unplace first 500 jobs of sector 15
jobs.modify_attribute(name="grid_id", data=zeros(500), index=arange(500))
# unplace first 500 jobs of sector 1
jobs.modify_attribute(name="grid_id", data=zeros(500), index=arange(7000, 7501))
# place only unplaced jobs of sector 1
model.run(gridcells, jobs, agents_filter="job.sector_id == 1")
# 500 jobs of sector 15 should be unplaced
result3 = where(jobs.get_attribute("grid_id") <= 0)[0]
self.assertEqual(result3.size, 500)
# jobs of sector 1 are placed
result4 = jobs.get_attribute_by_index("grid_id", arange(7000, 7501))
self.assertEqual((result4 <= 0).sum(), 0)
def test_unplaced_jobs_after_job_addition(self):
"""The initial jobs table is now adjusted to include 2000 unplaced jobs.
Add 1,750 new jobs and ensure that the number of unplaced jobs after the addition
is exactly 3,750 because this model is not responsible for placing jobs, only for creating them.
"""
# create and populate jobs table for model input
add_jobs_data = {
"job_id": arange(13001, 15001),
"grid_id": array(2000*[0]),
"sector_id": array(2000*[1]),
"building_type": array(2000*[Constants._industrial_code])
}
annual_employment_control_totals_data = self.annual_employment_control_totals_data
annual_employment_control_totals_data["total_non_home_based_employment"] = array([10750, 3000])
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name=jobs_set_table_name,
table_data=self.jobs_data
)
jobs_set = JobDataset(in_storage=storage, in_table_name=jobs_set_table_name)
ect_set_table_name = 'ect_set'
storage.write_table(
table_name=ect_set_table_name,
table_data=annual_employment_control_totals_data,
)
ect_set = ControlTotalDataset(in_storage=storage, in_table_name=ect_set_table_name, what="employment")
jobs_set.add_elements(add_jobs_data)
# run model with input databases
model = EmploymentTransitionModel()
model.run(year=2000, job_set=jobs_set, control_totals=ect_set, job_building_types=self.job_building_types)
#check that there are indeed 16750 total jobs after running the model
results = jobs_set.size()
should_be = [16750]
self.assertEqual(ma.allequal(should_be, results), True, "Error")
#check that the number of unplaced jobs is the number of new jobs created + number of unplaced jobs before running model
results = where(jobs_set.get_attribute("grid_id")<=0)[0].size
should_be = [3750.0]
self.assertEqual(ma.allclose(results, should_be, rtol=0.00001), True)
def run_model2():
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name=jobs_set_table_name,
table_data=self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage,
in_table_name=jobs_set_table_name)
model = RegionalEmploymentTransitionModel()
model.run(year=2000,
job_set=jobs_set,
control_totals=ect_set,
job_building_types=self.job_building_types)
# check that the distribution of building type is the same before and after subtracting jobs
jobs_set.compute_variables([
"urbansim.job.is_in_employment_sector_1_industrial",
"urbansim.job.is_in_employment_sector_2_industrial",
"urbansim.job.is_in_employment_sector_1_commercial",
"urbansim.job.is_in_employment_sector_2_commercial",
"urbansim.job.is_in_employment_sector_1_governmental",
"urbansim.job.is_in_employment_sector_2_governmental"
],
resources=Resources({
"job_building_type":
self.job_building_types
}))
result = array([
jobs_set.get_attribute(
"is_in_employment_sector_1_industrial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_2_industrial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_1_commercial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_2_commercial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_1_governmental").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_2_governmental").sum()
])
return result
def test_same_distribution_after_job_addition(self):
"""Add 1,750 new jobs of sector 1 without specifying a distribution across gridcells (so it is assumed equal)
Test that the total number of jobs in each sector after the addition matches the totals specified
in annual_employment_control_totals.
Ensure that the number of unplaced jobs after the addition is exactly 1,750 because this model
is not responsible for placing jobs, only for creating them.
NOTE: unplaced jobs are indicated by grid_id <= 0
"""
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name = jobs_set_table_name,
table_data = self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage, in_table_name=jobs_set_table_name)
annual_employment_control_totals_data = self.annual_employment_control_totals_data
annual_employment_control_totals_data["total_non_home_based_employment"] = array([5750, 1400, 4000, 1600])
ect_set_table_name = 'ect_set'
storage.write_table(
table_name = ect_set_table_name,
table_data = annual_employment_control_totals_data,
)
ect_set = ControlTotalDataset(in_storage=storage, in_table_name=ect_set_table_name, what="employment")
# run model
model = RegionalEmploymentTransitionModel()
model.run(year=2000, job_set=jobs_set, control_totals=ect_set, job_building_types=self.job_building_types)
#check that there are indeed 14750 total jobs after running the model
areas = jobs_set.get_attribute("large_area_id")
results = array([0,0])
for iarea in [0,1]:
results[iarea] = where(areas == [1,2][iarea])[0].size
should_be = [8150, 7600]
self.assertEqual(ma.allequal(should_be, results), True, "Error, should_be: %s, but result: %s" % (should_be, results))
#check that total #jobs within each sector are close to what was set in the control_totals
results = self.get_count_all_sectors_and_areas(jobs_set)
should_be = [5750, 1400, 1000, 4000, 1600, 2000]
self.assertEqual(ma.allclose(results, should_be, rtol=0.00001), True,
"Error, should_be: %s, but result: %s" % (should_be, results))
def run_model2():
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name = jobs_set_table_name,
table_data = self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage, in_table_name=jobs_set_table_name)
model = RegionalEmploymentTransitionModel()
model.run(year=2000, job_set=jobs_set, control_totals=ect_set, job_building_types=self.job_building_types)
# check that the distribution of building type is the same before and after subtracting jobs
jobs_set.compute_variables(["urbansim.job.is_in_employment_sector_1_industrial",
"urbansim.job.is_in_employment_sector_2_industrial",
"urbansim.job.is_in_employment_sector_1_commercial",
"urbansim.job.is_in_employment_sector_2_commercial",
"urbansim.job.is_in_employment_sector_1_governmental",
"urbansim.job.is_in_employment_sector_2_governmental"],
resources = Resources({"job_building_type":self.job_building_types}))
result = array([jobs_set.get_attribute("is_in_employment_sector_1_industrial").sum(),
jobs_set.get_attribute("is_in_employment_sector_2_industrial").sum(),
jobs_set.get_attribute("is_in_employment_sector_1_commercial").sum(),
jobs_set.get_attribute("is_in_employment_sector_2_commercial").sum(),
jobs_set.get_attribute("is_in_employment_sector_1_governmental").sum(),
jobs_set.get_attribute("is_in_employment_sector_2_governmental").sum()
])
return result
def test_scaling_jobs_model(self):
# Places 1750 jobs of sector 15
# gridcell has expected about
# 1 4000 sector 15 jobs 5000 sector 15 jobs
# 1000 sector 1 jobs 1000 sector 1 jobs
# 2 2000 sector 15 jobs 2500 sector 15 jobs
# 1000 sector 1 jobs 1000 sector 1 jobs
# 3 1000 sector 15 jobs 1250 sector 15 jobs
# 1000 sector 1 jobs 1000 sector 1 jobs
# unplaced 1750 sector 15 jobs 0
storage = StorageFactory().get_storage('dict_storage')
jobs_table_name = 'building_types'
storage.write_table(
table_name=jobs_table_name,
table_data={
"job_id":
arange(11750) + 1,
"sector_id":
array(7000 * [15] + 3000 * [1] + 1750 * [15]),
"grid_id":
array(4000 * [1] + 2000 * [2] + 1000 * [3] + 1000 * [1] +
1000 * [2] + 1000 * [3] + 1750 * [-1])
})
jobs = JobDataset(in_storage=storage, in_table_name=jobs_table_name)
gridcells_table_name = 'gridcells'
storage.write_table(table_name=gridcells_table_name,
table_data={"grid_id": arange(3) + 1})
gridcells = GridcellDataset(in_storage=storage,
in_table_name=gridcells_table_name)
# run model
model = ScalingJobsModel(debuglevel=4)
model.run(gridcells, jobs, agents_index=arange(10001, 11750))
# get results
gridcells.compute_variables([
"urbansim.gridcell.number_of_jobs_of_sector_15",
"urbansim.gridcell.number_of_jobs_of_sector_1"
],
resources=Resources({"job": jobs}))
# sector 1 jobs should be exactly the same
result1 = gridcells.get_attribute("number_of_jobs_of_sector_1")
self.assertEqual(
ma.allclose(result1, array([1000, 1000, 1000]), rtol=0), True)
# the distribution of sector 15 jobs should be the same with higher means
result2 = gridcells.get_attribute("number_of_jobs_of_sector_15")
# logger.log_status(result2)
self.assertEqual(
ma.allclose(result2, array([5000, 2500, 1250]), rtol=0.05), True)
def __init__(self):
in_storage = StorageFactory().get_storage(
'sql_storage',
hostname=settings.get_db_host_name(),
username=settings.get_db_user_name(),
password=settings.get_db_password(),
database_name=settings.db)
jobs = JobDataset(in_storage=in_storage, nchunks=5)
print "Read and Write JobDataset."
out_storage = StorageFactory().build_storage_for_dataset(
type='flt_storage', storage_location=settings.dir)
ReadWriteADataset(jobs,
out_storage=out_storage,
out_table_name=settings.jobsubdir)
def test_unplaced_jobs_after_job_addition(self):
"""The initial jobs table is now adjusted to include 2000 unplaced jobs.
Add 1,750 new jobs and ensure that the number of unplaced jobs after the addition
is exactly 3,750 because this model is not responsible for placing jobs, only for creating them.
"""
# create and populate jobs table for model input
add_jobs_data = {
"job_id": arange(13001, 15001),
"grid_id": array(2000 * [0]),
"sector_id": array(2000 * [1]),
"building_type": array(2000 * [Constants._industrial_code])
}
annual_employment_control_totals_data = self.annual_employment_control_totals_data
annual_employment_control_totals_data[
"total_non_home_based_employment"] = array([10750, 3000])
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(table_name=jobs_set_table_name,
table_data=self.jobs_data)
jobs_set = JobDataset(in_storage=storage,
in_table_name=jobs_set_table_name)
ect_set_table_name = 'ect_set'
storage.write_table(
table_name=ect_set_table_name,
table_data=annual_employment_control_totals_data,
)
ect_set = ControlTotalDataset(in_storage=storage,
in_table_name=ect_set_table_name,
what="employment")
jobs_set.add_elements(add_jobs_data)
# run model with input databases
model = EmploymentTransitionModel()
model.run(year=2000,
job_set=jobs_set,
control_totals=ect_set,
job_building_types=self.job_building_types)
#check that there are indeed 16750 total jobs after running the model
results = jobs_set.size()
should_be = [16750]
self.assertEqual(ma.allequal(should_be, results), True, "Error")
#check that the number of unplaced jobs is the number of new jobs created + number of unplaced jobs before running model
results = where(jobs_set.get_attribute("grid_id") <= 0)[0].size
should_be = [3750.0]
self.assertEqual(ma.allclose(results, should_be, rtol=0.00001), True)
def run_model():
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name=jobs_set_table_name,
table_data=self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage,
in_table_name=jobs_set_table_name)
model = RegionalEmploymentTransitionModel()
model.run(year=2000,
job_set=jobs_set,
control_totals=ect_set,
job_building_types=self.job_building_types)
# check that the distribution of jobs is the same before and after subtracting jobs
results = self.get_count_all_sectors_and_areas(jobs_set)
return results
def run(self, nbs, jobs, data_objects, dbcon, variables=(), coefficients=(), submodels=(), \
debuglevel=0):
t1 = time()
l = len(variables)
print variables, coefficients, submodels
specification = EquationSpecification(variables=variables,
coefficients=coefficients,
submodels=submodels)
# storage = StorageFactory().get_storage(type='mysql_storage', storage_location=dbcon)
# specification = EquationSpecification(storage=storage)
# specification.load(place="employment_non_home_based_location_choice_model_specification")
# coefficients = Coefficients(storage=storage)
# coefficients.load(place="employment_commercial_location_choice_model_coefficients")
elcm = EmploymentLocationChoiceModelCreator().get_model(
location_set=nbs, sample_size_locations=10
) # choice set size (includes current location)
##save estimation results
con = OpusDatabase(hostname=DB_settings.db_host_name,
username=DB_settings.db_user_name,
password=DB_settings.db_password,
database_name=This_Settings.outputdb)
estimation_set = JobDataset(in_storage=StorageFactory().get_storage(
'sql_storage', storage_location=dbcon),
in_place="jobs_for_estimation")
result = elcm.estimate(specification,
agent_set=estimation_set,
data_objects=data_objects,
debuglevel=debuglevel)
#save estimation results
# save_object(specification, 'employment_location_choice_model_specification', type='mysql_storage', base=con)
# save_object(result[0], 'employment_location_choice_model_coefficients', type='mysql_storage', base=con)
print "Simulation done. " + str(time() - t1) + " s"
def __init__(self,
variables=(),
coefficients=(),
submodels=(),
debuglevel=0):
# neighborhoods, jobs and households are loaded from disk ('flt_storage'), other objects from mysql. Change it as you need.
self.nbs = NeighborhoodDataset(in_storage=StorageFactory().get_storage('flt_storage', storage_location=This_Settings.dir),
in_place=This_Settings.nbsubdir, \
out_storage=StorageFactory().get_storage('flt_storage', storage_location = This_Settings.outputdir),
debuglevel=debuglevel)
self.jobs = JobDataset(in_base=This_Settings.dir,
in_storage=StorageFactory().get_storage(
'flt_storage',
storage_location=This_Settings.dir),
out_storage=StorageFactory().get_storage(
'flt_storage',
storage_location=This_Settings.outputdir),
in_place=This_Settings.jobsubdir,
debuglevel=debuglevel)
Con = OpusDatabase(hostname=DB_settings.db_host_name,
username=DB_settings.db_user_name,
password=DB_settings.db_password,
database_name=This_Settings.db)
self.hhs = HouseholdDataset(
in_base=This_Settings.dir,
in_storage=StorageFactory().get_storage(
'flt_storage', storage_location=This_Settings.dir),
out_storage=StorageFactory().get_storage(
'flt_storage', storage_location=This_Settings.outputdir),
in_place=This_Settings.hhsubdir,
debuglevel=debuglevel)
self.resources = Resources({"household": self.hhs, "job": self.jobs})
#simulate
Paris_simulation().run(nbs=self.nbs, jobs=self.jobs, \
data_objects=self.resources,\
dbcon=Con, variables=variables, coefficients=coefficients, submodels=submodels, debuglevel=debuglevel)
Con.close_connection()
def test_same_distribution_after_job_subtraction(self):
"""Removes 1,750 sector_1 jobs, without specifying the distribution across gridcells (so it is assumed equal)
Test that the distribution (in %) of sector 1 jobs across gridcells before and after the subtraction are
relatively equal.
"""
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(table_name = jobs_set_table_name, table_data = self.jobs_data)
jobs_set = JobDataset(in_storage=storage, in_table_name=jobs_set_table_name)
ect_set_table_name = 'ect_set'
storage.write_table(table_name = ect_set_table_name, table_data = self.annual_employment_control_totals_data)
ect_set = ControlTotalDataset(in_storage=storage, in_table_name=ect_set_table_name, what="employment")
model = RegionalEmploymentTransitionModel()
model.run(year=2000, job_set=jobs_set, control_totals=ect_set, job_building_types=self.job_building_types)
# check the totals in regions
areas = jobs_set.get_attribute("large_area_id")
results = array([0,0])
for iarea in [0,1]:
results[iarea] = where(areas == [1,2][iarea])[0].size
should_be = [4250, 7000]
self.assertEqual(ma.allequal(should_be, results), True, "Error, should_be: %s, but result: %s" % (should_be, results))
def run_model():
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name = jobs_set_table_name,
table_data = self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage, in_table_name=jobs_set_table_name)
model = RegionalEmploymentTransitionModel()
model.run(year=2000, job_set=jobs_set, control_totals=ect_set, job_building_types=self.job_building_types)
# check that the distribution of jobs is the same before and after subtracting jobs
results = self.get_count_all_sectors_and_areas(jobs_set)
return results
expected_results = array([2250.0, 1000, 1000, 3000, 2000.0, 2000])
self.run_stochastic_test(__file__, run_model, expected_results, 10)
def run_model2():
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name = jobs_set_table_name,
table_data = self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage, in_table_name=jobs_set_table_name)
model = RegionalEmploymentTransitionModel()
model.run(year=2000, job_set=jobs_set, control_totals=ect_set, job_building_types=self.job_building_types)
# check that the distribution of building type is the same before and after subtracting jobs
jobs_set.compute_variables(["urbansim.job.is_in_employment_sector_1_industrial",
"urbansim.job.is_in_employment_sector_2_industrial",
"urbansim.job.is_in_employment_sector_1_commercial",
"urbansim.job.is_in_employment_sector_2_commercial",
"urbansim.job.is_in_employment_sector_1_governmental",
"urbansim.job.is_in_employment_sector_2_governmental"],
resources = Resources({"job_building_type":self.job_building_types}))
result = array([jobs_set.get_attribute("is_in_employment_sector_1_industrial").sum(),
jobs_set.get_attribute("is_in_employment_sector_2_industrial").sum(),
jobs_set.get_attribute("is_in_employment_sector_1_commercial").sum(),
jobs_set.get_attribute("is_in_employment_sector_2_commercial").sum(),
jobs_set.get_attribute("is_in_employment_sector_1_governmental").sum(),
jobs_set.get_attribute("is_in_employment_sector_2_governmental").sum()
])
return result
expected_results = array([3500.0/7000.0*5250.0, 900, 3500.0/7000.0*5250.0, 1800, 0, 300])
self.run_stochastic_test(__file__, run_model2, expected_results, 20)
def test_same_distribution_after_job_subtraction(self):
"""Removes 1,750 sector_1 jobs, without specifying the distribution across gridcells (so it is assumed equal)
Test that the distribution (in %) of sector 1 jobs across gridcells before and after the subtraction are
relatively equal.
"""
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(table_name=jobs_set_table_name,
table_data=self.jobs_data)
jobs_set = JobDataset(in_storage=storage,
in_table_name=jobs_set_table_name)
ect_set_table_name = 'ect_set'
storage.write_table(
table_name=ect_set_table_name,
table_data=self.annual_employment_control_totals_data)
ect_set = ControlTotalDataset(in_storage=storage,
in_table_name=ect_set_table_name,
what="employment")
# unplace some jobs
jobs_set.modify_attribute(name="grid_id",
data=zeros(int(jobs_set.size() / 2)),
index=arange(int(jobs_set.size() / 2)))
#run model with input Datasets
model = EmploymentTransitionModel()
model.run(year=2000,
job_set=jobs_set,
control_totals=ect_set,
job_building_types=self.job_building_types)
results = jobs_set.size()
should_be = [11250]
self.assertEqual(ma.allequal(should_be, results), True, "Error")
def run_model():
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name=jobs_set_table_name,
table_data=self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage,
in_table_name=jobs_set_table_name)
model = EmploymentTransitionModel()
model.run(year=2000,
job_set=jobs_set,
control_totals=ect_set,
job_building_types=self.job_building_types)
# check that the distribution of jobs is the same before and after subtracting jobs
results = self.get_count_all_sectors_and_gridcells(jobs_set)
return results
expected_results = array([
4000.0 / 7000.0 * 5250.0, 1000, 1000, 2000.0 / 7000.0 * 5250.0,
1000, 1000, 1000.0 / 7000.0 * 5250.0, 1000, 1000
])
self.run_stochastic_test(__file__, run_model, expected_results, 10)
def run_model2():
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name=jobs_set_table_name,
table_data=self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage,
in_table_name=jobs_set_table_name)
model = EmploymentTransitionModel()
model.run(year=2000,
job_set=jobs_set,
control_totals=ect_set,
job_building_types=self.job_building_types)
# check that the distribution of building type is the same before and after subtracting jobs
jobs_set.compute_variables([
"urbansim.job.is_in_employment_sector_1_industrial",
"urbansim.job.is_in_employment_sector_2_industrial",
"urbansim.job.is_in_employment_sector_1_commercial",
"urbansim.job.is_in_employment_sector_2_commercial",
"urbansim.job.is_in_employment_sector_1_governmental",
"urbansim.job.is_in_employment_sector_2_governmental"
],
resources=Resources({
"job_building_type":
self.job_building_types
}))
result = array([
jobs_set.get_attribute(
"is_in_employment_sector_1_industrial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_2_industrial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_1_commercial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_2_commercial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_1_governmental").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_2_governmental").sum()
])
return result
expected_results = array([
3500.0 / 7000.0 * 5250.0, 900, 3500.0 / 7000.0 * 5250.0, 1800, 0,
300
])
self.run_stochastic_test(__file__, run_model2, expected_results, 20)
def test_same_distribution_after_job_addition(self):
"""Add 1,750 new jobs of sector 1 without specifying a distribution across gridcells (so it is assumed equal)
Test that the total number of jobs in each sector after the addition matches the totals specified
in annual_employment_control_totals.
Ensure that the number of unplaced jobs after the addition is exactly 1,750 because this model
is not responsible for placing jobs, only for creating them.
NOTE: unplaced jobs are indicated by grid_id <= 0
"""
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name=jobs_set_table_name,
table_data=self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage,
in_table_name=jobs_set_table_name)
annual_employment_control_totals_data = self.annual_employment_control_totals_data
annual_employment_control_totals_data[
"total_non_home_based_employment"] = array([8750, 3000])
ect_set_table_name = 'ect_set'
storage.write_table(
table_name=ect_set_table_name,
table_data=annual_employment_control_totals_data,
)
ect_set = ControlTotalDataset(in_storage=storage,
in_table_name=ect_set_table_name,
what="employment")
# run model
model = EmploymentTransitionModel()
model.run(year=2000,
job_set=jobs_set,
control_totals=ect_set,
job_building_types=self.job_building_types)
#check that there are indeed 14750 total jobs after running the model
results = jobs_set.size()
should_be = [14750]
self.assertEqual(ma.allequal(should_be, results), True, "Error")
#check that total #jobs within each sector are close to what was set in the control_totals
results = self.get_count_all_sectors(jobs_set)
should_be = [8750.0, 3000, 3000]
self.assertEqual(ma.allclose(results, should_be, rtol=0.00001), True)
#check that the number of unplaced jobs is the number of new jobs created (1750)
results = where(jobs_set.get_attribute("grid_id") <= 0)[0].size
should_be = [1750.0]
self.assertEqual(ma.allclose(results, should_be, rtol=0.00001), True)
# test distribution of building type
def run_model():
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(table_name=jobs_set_table_name,
table_data=self.jobs_data)
jobs_set = JobDataset(in_storage=storage,
in_table_name=jobs_set_table_name)
model = EmploymentTransitionModel()
model.run(year=2000,
job_set=jobs_set,
control_totals=ect_set,
job_building_types=self.job_building_types)
# check that the distribution of building type is the same before and after subtracting jobs
jobs_set.compute_variables([
"urbansim.job.is_in_employment_sector_1_industrial",
"urbansim.job.is_in_employment_sector_2_industrial",
"urbansim.job.is_in_employment_sector_1_commercial",
"urbansim.job.is_in_employment_sector_2_commercial",
"urbansim.job.is_in_employment_sector_1_governmental",
"urbansim.job.is_in_employment_sector_2_governmental"
],
resources=Resources({
"job_building_type":
self.job_building_types
}))
result = array([
jobs_set.get_attribute(
"is_in_employment_sector_1_industrial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_2_industrial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_1_commercial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_2_commercial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_1_governmental").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_2_governmental").sum()
])
return result
expected_results = array([
3500.0 / 7000.0 * 8750.0, 900, 3500.0 / 7000.0 * 8750.0, 1800, 0,
300
])
#print expected_results
self.run_stochastic_test(__file__, run_model, expected_results, 10)
# check data types
self.assertEqual(
jobs_set.get_attribute("sector_id").dtype, int32,
"Error in data type of the new job set. Should be: int32, is: %s" %
str(jobs_set.get_attribute("sector_id").dtype))
self.assertEqual(
jobs_set.get_attribute("building_type").dtype, int8,
"Error in data type of the new job set. Should be: int8, is: %s" %
str(jobs_set.get_attribute("building_type").dtype))
def test_distribute_unplaced_jobs_model(self):
# Places 1750 jobs of sector 15
# gridcell has expected about
# 1 4000 sector 15 jobs 5000 sector 15 jobs
# 1000 sector 1 jobs 1000 sector 1 jobs
# 2 2000 sector 15 jobs 2500 sector 15 jobs
# 1000 sector 1 jobs 1000 sector 1 jobs
# 3 1000 sector 15 jobs 1250 sector 15 jobs
# 1000 sector 1 jobs 1000 sector 1 jobs
# unplaced 1750 sector 15 jobs 0
# create jobs
storage = StorageFactory().get_storage('dict_storage')
job_data = {
"job_id": arange(11750)+1,
"sector_id": array(7000*[15]+3000*[1]+1750*[15]),
"grid_id":array(4000*[1]+2000*[2]+1000*[3]+1000*[1]+1000*[2]+1000*[3]+1750*[-1])
}
jobs_table_name = 'jobs'
storage.write_table(table_name=jobs_table_name, table_data=job_data)
jobs = JobDataset(in_storage=storage, in_table_name=jobs_table_name)
storage = StorageFactory().get_storage('dict_storage')
building_types_table_name = 'building_types'
storage.write_table(
table_name=building_types_table_name,
table_data={
"grid_id":arange(3)+1
}
)
gridcells = GridcellDataset(in_storage=storage, in_table_name=building_types_table_name)
# run model
model = DistributeUnplacedJobsModel(debuglevel=4)
model.run(gridcells, jobs)
# get results
# no jobs are unplaced
result1 = where(jobs.get_attribute("grid_id")<0)[0]
self.assertEqual(result1.size, 0)
# the first 10000jobs kept their locations
result2 = jobs.get_attribute_by_index("grid_id", arange(10000))
# logger.log_status(result2)
self.assertEqual(ma.allclose(result2, job_data["grid_id"][0:10000], rtol=0), True)
# run model with filter
# unplace first 500 jobs of sector 15
jobs.modify_attribute(name='grid_id', data=zeros(500), index=arange(500))
# unplace first 500 jobs of sector 1
jobs.modify_attribute(name='grid_id', data=zeros(500), index=arange(7000, 7501))
# place only unplaced jobs of sector 1
model.run(gridcells, jobs, agents_filter='job.sector_id == 1')
# 500 jobs of sector 15 should be unplaced
result3 = where(jobs.get_attribute("grid_id")<=0)[0]
self.assertEqual(result3.size, 500)
# jobs of sector 1 are placed
result4 = jobs.get_attribute_by_index("grid_id", arange(7000, 7501))
self.assertEqual((result4 <= 0).sum(), 0)
def test_agents_placed_in_appropriate_types(self):
"""Create 1000 unplaced industrial jobs and 1 commercial job. Allocate 50 commercial
gridcells with enough space for 10 commercial jobs per gridcell. After running the
EmploymentLocationChoiceModel, the 1 commercial job should be placed,
but the 100 industrial jobs should remain unplaced
"""
storage = StorageFactory().get_storage('dict_storage')
storage.write_table(table_name='job_building_types',
table_data = {
'id':array([2,1]),
'name': array(['commercial', 'industrial'])
}
)
job_building_types = JobBuildingTypeDataset(in_storage=storage, in_table_name='job_building_types')
storage.write_table(table_name='jobs',
table_data = {
'job_id': arange(1001)+1,
'grid_id': array([0]*1001),
'building_type': array([1]*1000 + [2])
}
)
jobs = JobDataset(in_storage=storage, in_table_name='jobs')
storage.write_table(table_name='gridcells',
table_data = {
'grid_id': arange(50)+1,
'commercial_sqft': array([1000]*50),
'commercial_sqft_per_job': array([100]*50)
}
)
gridcells = GridcellDataset(in_storage=storage, in_table_name='gridcells')
coefficients = Coefficients(names=("dummy",), values=(0.1,))
specification = EquationSpecification(variables=("gridcell.commercial_sqft",), coefficients=("dummy",))
compute_resources = Resources({"job":jobs, "job_building_type": job_building_types})
agents_index = where(jobs.get_attribute("grid_id") == 0)
unplace_jobs = DatasetSubset(jobs, agents_index)
agents_index = where(unplace_jobs.get_attribute("building_type") == 2)[0]
gridcells.compute_variables(["urbansim.gridcell.number_of_commercial_jobs"],
resources=compute_resources)
commercial_jobs = gridcells.get_attribute("number_of_commercial_jobs")
gridcells.compute_variables(["urbansim.gridcell.number_of_industrial_jobs"],
resources=compute_resources)
industrial_jobs = gridcells.get_attribute("number_of_industrial_jobs")
model_group = ModelGroup(job_building_types, "name")
elcm = EmploymentLocationChoiceModel(ModelGroupMember(model_group,"commercial"), location_set=gridcells,
agents_grouping_attribute = "job.building_type",
choices = "opus_core.random_choices_from_index", sample_size_locations = 30)
elcm.run(specification, coefficients, agent_set = jobs, agents_index=agents_index, debuglevel=1)
gridcells.compute_variables(["urbansim.gridcell.number_of_commercial_jobs"],
resources=compute_resources)
commercial_jobs = gridcells.get_attribute("number_of_commercial_jobs")
gridcells.compute_variables(["urbansim.gridcell.number_of_industrial_jobs"],
resources=compute_resources)
industrial_jobs = gridcells.get_attribute("number_of_industrial_jobs")
self.assertEqual(commercial_jobs.sum() == 1,
True, "Error, there should only be a total of 1 commercial job")
self.assertEqual(industrial_jobs.sum() == 0,
True, "Error, there should be no industrial jobs because there's no space for them")
location_set=zones_psrc,
sampler="opus_core.samplers.weighted_sampler",
sample_size_locations=10,
choices="opus_core.random_choices_from_index",
compute_capacity_flag=False,
estimate_config=Resources({"weights_for_estimation_string": None}))
specification = EquationSpecification(
variables=("urbansim.zone.number_of_jobs", "urbansim.household.income"),
coefficients=("NOJ", "INC"))
agents_psrc.compute_variables(["urbansim.household.zone_id"],
resources=Resources({"gridcell":
locations_psrc}))
jobs_psrc = JobDataset(in_storage=StorageFactory().get_storage(
'flt_storage', storage_location="/home/hana/urbansim/data/GPSRC"),
in_table_name="jobs")
coef, result = hlcm_psrc_zones.estimate(specification,
agents_psrc,
agents_index=idx,
estimate_config=Resources(
{"estimation_size_agents": 0.01}),
data_objects={
"job": jobs_psrc,
"gridcell": locations_psrc
},
debuglevel=4)
result = hlcm_psrc_zones.run(specification,
coef,
agents_psrc,
def test_same_distribution_after_job_addition(self):
"""Add 1,750 new jobs of sector 1 without specifying a distribution across gridcells (so it is assumed equal)
Test that the total number of jobs in each sector after the addition matches the totals specified
in annual_employment_control_totals.
Ensure that the number of unplaced jobs after the addition is exactly 1,750 because this model
is not responsible for placing jobs, only for creating them.
NOTE: unplaced jobs are indicated by grid_id <= 0
"""
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name=jobs_set_table_name,
table_data=self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage, in_table_name=jobs_set_table_name)
annual_employment_control_totals_data = self.annual_employment_control_totals_data
annual_employment_control_totals_data["total_non_home_based_employment"] = array([8750, 3000])
ect_set_table_name = 'ect_set'
storage.write_table(
table_name=ect_set_table_name,
table_data=annual_employment_control_totals_data,
)
ect_set = ControlTotalDataset(in_storage=storage, in_table_name=ect_set_table_name, what="employment")
# run model
model = EmploymentTransitionModel()
model.run(year=2000, job_set=jobs_set, control_totals=ect_set, job_building_types=self.job_building_types)
#check that there are indeed 14750 total jobs after running the model
results = jobs_set.size()
should_be = [14750]
self.assertEqual(ma.allequal(should_be, results), True, "Error")
#check that total #jobs within each sector are close to what was set in the control_totals
results = self.get_count_all_sectors(jobs_set)
should_be = [8750.0, 3000, 3000]
self.assertEqual(ma.allclose(results, should_be, rtol=0.00001), True)
#check that the number of unplaced jobs is the number of new jobs created (1750)
results = where(jobs_set.get_attribute("grid_id")<=0)[0].size
should_be = [1750.0]
self.assertEqual(ma.allclose(results, should_be, rtol=0.00001), True)
# test distribution of building type
def run_model():
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name=jobs_set_table_name,
table_data=self.jobs_data
)
jobs_set = JobDataset(in_storage=storage, in_table_name=jobs_set_table_name)
model = EmploymentTransitionModel()
model.run(year=2000, job_set=jobs_set, control_totals=ect_set, job_building_types=self.job_building_types)
# check that the distribution of building type is the same before and after subtracting jobs
jobs_set.compute_variables(["urbansim.job.is_in_employment_sector_1_industrial",
"urbansim.job.is_in_employment_sector_2_industrial",
"urbansim.job.is_in_employment_sector_1_commercial",
"urbansim.job.is_in_employment_sector_2_commercial",
"urbansim.job.is_in_employment_sector_1_governmental",
"urbansim.job.is_in_employment_sector_2_governmental"],
resources = Resources({"job_building_type":self.job_building_types}))
result = array([jobs_set.get_attribute("is_in_employment_sector_1_industrial").sum(),
jobs_set.get_attribute("is_in_employment_sector_2_industrial").sum(),
jobs_set.get_attribute("is_in_employment_sector_1_commercial").sum(),
jobs_set.get_attribute("is_in_employment_sector_2_commercial").sum(),
jobs_set.get_attribute("is_in_employment_sector_1_governmental").sum(),
jobs_set.get_attribute("is_in_employment_sector_2_governmental").sum()
])
return result
expected_results = array([3500.0/7000.0*8750.0, 900, 3500.0/7000.0*8750.0, 1800, 0, 300])
#print expected_results
self.run_stochastic_test(__file__, run_model, expected_results, 10)
# check data types
self.assertEqual(jobs_set.get_attribute("sector_id").dtype, int32,
"Error in data type of the new job set. Should be: int32, is: %s" % str(jobs_set.get_attribute("sector_id").dtype))
self.assertEqual(jobs_set.get_attribute("building_type").dtype, int8,
"Error in data type of the new job set. Should be: int8, is: %s" % str(jobs_set.get_attribute("building_type").dtype))
def test_same_distribution_after_job_subtraction(self):
"""Removes 1,750 sector_1 jobs, without specifying the distribution across gridcells (so it is assumed equal)
Test that the distribution (in %) of sector 1 jobs across gridcells before and after the subtraction are
relatively equal.
"""
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(table_name=jobs_set_table_name, table_data=self.jobs_data)
jobs_set = JobDataset(in_storage=storage, in_table_name=jobs_set_table_name)
ect_set_table_name = 'ect_set'
storage.write_table(table_name=ect_set_table_name, table_data=self.annual_employment_control_totals_data)
ect_set = ControlTotalDataset(in_storage=storage, in_table_name=ect_set_table_name, what="employment")
# unplace some jobs
jobs_set.modify_attribute(name="grid_id", data=zeros(int(jobs_set.size()/2)), index=arange(int(jobs_set.size()/2)))
#run model with input Datasets
model = EmploymentTransitionModel()
model.run(year=2000, job_set=jobs_set, control_totals=ect_set, job_building_types=self.job_building_types)
results = jobs_set.size()
should_be = [11250]
self.assertEqual(ma.allequal(should_be, results), True, "Error")
def run_model():
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name=jobs_set_table_name,
table_data=self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage, in_table_name=jobs_set_table_name)
model = EmploymentTransitionModel()
model.run(year=2000, job_set=jobs_set, control_totals=ect_set, job_building_types=self.job_building_types)
# check that the distribution of jobs is the same before and after subtracting jobs
results = self.get_count_all_sectors_and_gridcells(jobs_set)
return results
expected_results = array([4000.0/7000.0*5250.0, 1000, 1000, 2000.0/7000.0*5250.0, 1000,
1000, 1000.0/7000.0*5250.0, 1000, 1000])
self.run_stochastic_test(__file__, run_model, expected_results, 10)
def run_model2():
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name=jobs_set_table_name,
table_data=self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage, in_table_name=jobs_set_table_name)
model = EmploymentTransitionModel()
model.run(year=2000, job_set=jobs_set, control_totals=ect_set, job_building_types=self.job_building_types)
# check that the distribution of building type is the same before and after subtracting jobs
jobs_set.compute_variables(["urbansim.job.is_in_employment_sector_1_industrial",
"urbansim.job.is_in_employment_sector_2_industrial",
"urbansim.job.is_in_employment_sector_1_commercial",
"urbansim.job.is_in_employment_sector_2_commercial",
"urbansim.job.is_in_employment_sector_1_governmental",
"urbansim.job.is_in_employment_sector_2_governmental"],
resources = Resources({"job_building_type":self.job_building_types}))
result = array([jobs_set.get_attribute("is_in_employment_sector_1_industrial").sum(),
jobs_set.get_attribute("is_in_employment_sector_2_industrial").sum(),
jobs_set.get_attribute("is_in_employment_sector_1_commercial").sum(),
jobs_set.get_attribute("is_in_employment_sector_2_commercial").sum(),
jobs_set.get_attribute("is_in_employment_sector_1_governmental").sum(),
jobs_set.get_attribute("is_in_employment_sector_2_governmental").sum()
])
return result
expected_results = array([3500.0/7000.0*5250.0, 900, 3500.0/7000.0*5250.0, 1800, 0, 300])
self.run_stochastic_test(__file__, run_model2, expected_results, 20)
def test_erm_correct_distribution_of_jobs_relocate(self):
# In addition to unplaced jobs choose 50% of jobs of sector 2 to relocate and
# no job of sector 1.
# gridcell has expected
# 1 100 sector 1 jobs 100 sector 1 jobs
# 400 sector 2 jobs about 200 sector 2 jobs
# 2 100 sector 1 jobs 100 sector 1 jobs
# 200 sector 2 jobs about 100 sector 2 jobs
# 3 100 sector 1 jobs 100 sector 1 jobs
# 100 sector 2 jobs about 50 sector 2 jobs
# unplaced 10 sector 1 jobs
# 10 sector 2 jobs
storage = StorageFactory().get_storage("dict_storage")
# create jobs
job_grid_ids = array(100 * [1] + 100 * [2] + 100 * [3] + 400 * [1] + 200 * [2] + 100 * [3] + 20 * [-1])
storage.write_table(
table_name="jobs",
table_data={
"job_id": arange(1020) + 1,
"sector_id": array(300 * [1] + 700 * [2] + 10 * [1] + 10 * [2]),
"grid_id": job_grid_ids,
},
)
jobs = JobDataset(in_storage=storage, in_table_name="jobs")
# create gridcells
storage.write_table(table_name="gridcells", table_data={"grid_id": arange(3) + 1})
gridcells = GridcellDataset(in_storage=storage, in_table_name="gridcells")
# create rate set with rate 0 for jobs of sector 1 and 0.5 for jobs of sector 2
storage.write_table(
table_name="rates", table_data={"sector_id": array([1, 2]), "job_relocation_probability": array([0, 0.5])}
)
rates = JobRelocationRateDataset(in_storage=storage, in_table_name="rates")
# run model
model = EmploymentRelocationModelCreator().get_model(debuglevel=0)
hrm_resources = Resources({"annual_job_relocation_rate": rates})
# get results from one run
movers_indices = model.run(jobs, resources=hrm_resources)
jobs.compute_variables(["urbansim.job.is_in_employment_sector_1"])
# unplace chosen jobs
compute_resources = Resources({"job": jobs, "urbansim_constant": {"industrial_code": 1, "commercial_code": 2}})
jobs.set_values_of_one_attribute(attribute="grid_id", values=-1, index=movers_indices)
gridcells.compute_variables(
["urbansim.gridcell.number_of_jobs_of_sector_1", "urbansim.gridcell.number_of_jobs_of_sector_2"],
resources=compute_resources,
)
# only 100 jobs of sector 1 (unplaced jobs) should be selected
result1 = jobs.get_attribute_by_index("is_in_employment_sector_1", movers_indices).astype(int8).sum()
self.assertEqual(result1 == 10, True)
# number of sector 1 jobs should not change
result2 = gridcells.get_attribute("number_of_jobs_of_sector_1")
self.assertEqual(ma.allclose(result2, array([100, 100, 100]), rtol=0), True)
def run_model():
jobs.modify_attribute(name="grid_id", data=job_grid_ids)
indices = model.run(jobs, resources=hrm_resources)
jobs.modify_attribute(name="grid_id", data=-1, index=indices)
gridcells.compute_variables(["urbansim.gridcell.number_of_jobs_of_sector_2"], resources=compute_resources)
return gridcells.get_attribute("number_of_jobs_of_sector_2")
# distribution of sector 2 jobs should be the same, the mean are halfs of the original values
should_be = array([200, 100, 50])
self.run_stochastic_test(__file__, run_model, should_be, 10)
def setUp( self ):
"""here, we simulate 50 residential units
and 5000 commercial, industrial, and governmental sqft added to each of the gridcells in previous years.
"""
### TODO: do not redefine these constants.
self.comc = 1
self.indc = 3
self.govc = 2
self.sfhc = 4
self.mfhc = 5
storage = StorageFactory().get_storage('dict_storage')
gridcells_table_name = 'gridcells'
# create 100 gridcells, each with 200 residential units and space for 100 commercial jobs,
# 100 industrial jobs, and residential, industrial, and commercial value at $500,000 each
storage.write_table(
table_name=gridcells_table_name,
table_data={
"grid_id": arange( 1, 100+1 ),
"commercial_sqft_per_job":array( 100*[100] ),
"industrial_sqft_per_job":array( 100*[100] ),
"single_family_improvement_value":array( 100*[500000] ),
"commercial_improvement_value":array( 100*[500000] ),
"industrial_improvement_value":array( 100*[500000] )
}
)
self.gridcells = GridcellDataset(in_storage=storage, in_table_name=gridcells_table_name)
buildings_table_name = 'buildings'
# 2000 buildings (1000 with 20 residential units each, 500 with 20 commercial job and 500 with 20 industrial job each)
storage.write_table(
table_name=buildings_table_name,
table_data={
"building_id":arange( 1, 2000+1 ), # 2000 buildings
"grid_id":array( 20*range( 1, 100+1 ), dtype=int32 ), # spread evenly across 100 gridcells
"building_type_id":array(1000*[self.sfhc] +
500*[self.comc] +
500*[self.indc], dtype=int8),
"sqft": array(1000*[0] +
500*[2000] +
500*[2000], dtype=int32),
"residential_units": array(1000*[20] +
500* [0] +
500* [0], dtype=int32),
"improvement_value": array(1000*[50] +
500* [50] +
500* [50], dtype=float32),
"year_built": array(1000*[1940] +
500* [1940] +
500* [1940], dtype=int32)
}
)
self.buildings = BuildingDataset(in_storage=storage, in_table_name=buildings_table_name)
households_table_name = 'households'
# create 10000 households, 100 in each of the 100 gridcells.
# there will initially be 100 vacant residential units in each gridcell then.
storage.write_table(
table_name=households_table_name,
table_data={
"household_id":arange( 1, 10000+1 ),
"grid_id":array( 100*range( 1, 100+1 ), dtype=int32 )
}
)
self.households = HouseholdDataset(in_storage=storage, in_table_name=households_table_name)
building_types_table_name = 'building_types'
storage.write_table(
table_name=building_types_table_name,
table_data={
"building_type_id":array([self.govc,self.comc,self.indc, self.sfhc, self.mfhc], dtype=int8),
"name": array(["governmental", "commercial", "industrial", "single_family","multiple_family"]),
"units": array(["governmental_sqft", "commercial_sqft", "industrial_sqft", "residential_units", "residential_units"]),
"is_residential": array([0,0,0,1,1], dtype='?')
}
)
self.building_types = BuildingTypeDataset(in_storage=storage, in_table_name=building_types_table_name)
job_building_types_table_name = 'job_building_types'
storage.write_table(
table_name=job_building_types_table_name,
table_data={
"id":array([self.govc,self.comc,self.indc, self.sfhc, self.mfhc], dtype=int8),
"name": array(["governmental", "commercial", "industrial", "single_family","multiple_family"])
}
)
self.job_building_types = JobBuildingTypeDataset(in_storage=storage, in_table_name=job_building_types_table_name)
jobs_table_name = 'jobs'
# create 2500 commercial jobs and distribute them equally across the 100 gridcells,
# 25 commercial buildings/gridcell
storage.write_table(
table_name=jobs_table_name,
table_data={
"job_id":arange( 1, 2500+1 ),
"grid_id":array( 25*range( 1, 100+1 ), dtype=int32 ),
"sector_id":array( 2500*[1], dtype=int32 ),
"building_type":array(2500*[self.comc], dtype=int8)
}
)
self.jobs = JobDataset(in_storage=storage, in_table_name=jobs_table_name)
self.dataset_pool = DatasetPool()
self.dataset_pool.add_datasets_if_not_included({
"household":self.households,
"job":self.jobs,
"building":self.buildings,
"building_type": self.building_types,
"job_building_type": self.job_building_types})
self.building_categories = {'commercial': array([1000,5000]),
'industrial': array([500,800,1000])}
def run(self, in_storage, out_storage, business_table="business", jobs_table="jobs", control_totals_table=None):
logger.log_status("Unrolling %s table." % business_table)
# get attributes from the establisments table
business_dataset = BusinessDataset(in_storage=in_storage, in_table_name=business_table)
business_sizes = business_dataset.get_attribute(self.number_of_jobs_attr).astype("int32")
sectors = business_dataset.get_attribute("sector_id")
tazes = business_dataset.get_attribute(self.geography_id_attr).astype("int32")
building_ids = array([], dtype='int32')
if "building_id" in business_dataset.get_primary_attribute_names():
building_ids = business_dataset.get_attribute("building_id")
parcel_ids = array([], dtype='int32')
if "parcel_id" in business_dataset.get_primary_attribute_names():
parcel_ids = business_dataset.get_attribute("parcel_id")
home_based = array([], dtype='int16')
if "home_based" in business_dataset.get_primary_attribute_names():
home_based = business_dataset.get_attribute("home_based")
building_sqft = business_dataset.get_attribute(self.sqft_attr)
building_sqft[building_sqft <= 0] = 0
join_flags = None
if "join_flag" in business_dataset.get_primary_attribute_names():
join_flags = business_dataset.get_attribute("join_flag")
impute_sqft_flag = None
if "impute_building_sqft_flag" in business_dataset.get_primary_attribute_names():
impute_sqft_flag = business_dataset.get_attribute("impute_building_sqft_flag")
# inititalize jobs attributes
total_size = business_sizes.sum()
jobs_data = {}
jobs_data["sector_id"] = resize(array([-1], dtype=sectors.dtype), total_size)
jobs_data["building_id"] = resize(array([-1], dtype=building_ids.dtype), total_size)
jobs_data["parcel_id"] = resize(array([-1], dtype=parcel_ids.dtype), total_size)
jobs_data[self.geography_id_attr] = resize(array([-1], dtype=tazes.dtype), total_size)
jobs_data["building_type"] = resize(array([-1], dtype=home_based.dtype), total_size)
jobs_data["sqft"] = resize(array([], dtype=building_sqft.dtype), total_size)
if join_flags is not None:
jobs_data["join_flag"] = resize(array([], dtype=join_flags.dtype), total_size)
if impute_sqft_flag is not None:
jobs_data["impute_building_sqft_flag"] = resize(array([], dtype=impute_sqft_flag.dtype), total_size)
indices = cumsum(business_sizes)
# iterate over establishments. For each business create the corresponding number of jobs by filling the corresponding part
# of the arrays
start_index=0
for i in range(business_dataset.size()):
end_index = indices[i]
jobs_data["sector_id"][start_index:end_index] = sectors[i]
if building_ids.size > 0:
jobs_data["building_id"][start_index:end_index] = building_ids[i]
if parcel_ids.size > 0:
jobs_data["parcel_id"][start_index:end_index] = parcel_ids[i]
jobs_data[self.geography_id_attr][start_index:end_index] = tazes[i]
if home_based.size > 0:
jobs_data["building_type"][start_index:end_index] = home_based[i]
if self.compute_sqft_per_job:
jobs_data["sqft"][start_index:end_index] = round((building_sqft[i]-building_sqft[i]/10.0)/float(business_sizes[i])) # sqft per employee
else:
jobs_data["sqft"][start_index:end_index] = building_sqft[i]
if join_flags is not None:
jobs_data["join_flag"][start_index:end_index] = join_flags[i]
if impute_sqft_flag is not None:
jobs_data["impute_building_sqft_flag"][start_index:end_index] = impute_sqft_flag[i]
start_index = end_index
jobs_data["job_id"] = arange(total_size)+1
if self.compute_sqft_per_job:
jobs_data["sqft"] = clip(jobs_data["sqft"], 0, self.maximum_sqft)
jobs_data["sqft"][logical_and(jobs_data["sqft"]>0, jobs_data["sqft"]<self.minimum_sqft)] = self.minimum_sqft
# correct missing job_building_types
wmissing_bt = where(jobs_data["building_type"]<=0)[0]
if wmissing_bt.size > 0:
jobs_data["building_type"][wmissing_bt] = 2 # assign non-homebased type for now. It can be re-classified in the assign_bldgs_to_jobs... script
# create jobs table and write it out
storage = StorageFactory().get_storage('dict_storage')
storage.write_table(
table_name="jobs",
table_data=jobs_data
)
job_dataset = JobDataset(in_storage=storage)
if self.unplace_jobs_with_non_existing_buildings:
self.do_unplace_jobs_with_non_existing_buildings(job_dataset, out_storage)
# Match to control totals (only eliminate jobs if control totals are smaller than the actual number of jobs).
if control_totals_table is not None:
logger.log_status("Matching to control totals.")
control_totals = ControlTotalDataset(what='employment', id_name=['zone_id', 'sector_id'],
in_table_name=control_totals_table, in_storage=in_storage)
control_totals.load_dataset(attributes=['zone_id', 'sector_id', 'jobs'])
zones_sectors = control_totals.get_id_attribute()
njobs = control_totals.get_attribute('jobs')
remove = array([], dtype='int32')
for i in range(zones_sectors.shape[0]):
zone, sector = zones_sectors[i,:]
in_sector = job_dataset.get_attribute("sector_id") == sector
in_zone_in_sector = logical_and(in_sector, job_dataset.get_attribute("zone_id") == zone)
if in_zone_in_sector.sum() <= njobs[i]:
continue
to_be_removed = in_zone_in_sector.sum() - njobs[i]
this_removal = 0
not_considered = ones(job_dataset.size(), dtype='bool8')
for unit in ['parcel_id', 'building_id', None]: # first consider jobs without parcel id, then without building_id, then all
if unit is not None:
wnunit = job_dataset.get_attribute(unit) <= 0
eligible = logical_and(not_considered, logical_and(in_zone_in_sector, wnunit))
not_considered[where(wnunit)] = False
else:
eligible = logical_and(not_considered, in_zone_in_sector)
eligible_sum = eligible.sum()
if eligible_sum > 0:
where_eligible = where(eligible)[0]
if eligible_sum <= to_be_removed-this_removal:
draw = arange(eligible_sum)
else:
draw = sample_noreplace(where_eligible, to_be_removed-this_removal, eligible_sum)
remove = concatenate((remove, where_eligible[draw]))
this_removal += draw.size
if this_removal >= to_be_removed:
break
job_dataset.remove_elements(remove)
logger.log_status("%s jobs removed." % remove.size)
logger.log_status("Write jobs table.")
job_dataset.write_dataset(out_table_name=jobs_table, out_storage=out_storage)
logger.log_status("Created %s jobs." % job_dataset.size())
def get_resources(self, data_dictionary, dataset):
"""Create resources for computing a variable. """
resources = Resources()
for key in data_dictionary.keys():
if key in self.datasets:
data = data_dictionary[key]
storage = StorageFactory().get_storage('dict_storage')
if self.id_names[key] not in data_dictionary[key].keys(
) and not isinstance(self.id_names[key], list):
data[self.id_names[key]] = arange(
1,
len(data_dictionary[key][data_dictionary[key].keys()
[0]]) + 1) # add id array
id_name = self.id_names[key]
storage.write_table(table_name='data', table_data=data)
if key == "gridcell":
gc = GridcellDataset(in_storage=storage,
in_table_name='data')
# add relative_x and relative_y
gc.get_id_attribute()
n = int(ceil(sqrt(gc.size())))
if "relative_x" not in data.keys():
x = (indices((n, n)) + 1)[1].ravel()
gc.add_attribute(x[0:gc.size()],
"relative_x",
metadata=1)
if "relative_y" not in data.keys():
y = (indices((n, n)) + 1)[0].ravel()
gc.add_attribute(y[0:gc.size()],
"relative_y",
metadata=1)
resources.merge({key: gc})
elif key == "household":
resources.merge({
key:
HouseholdDataset(in_storage=storage,
in_table_name='data')
})
elif key == "development_project":
resources.merge({
key:
DevelopmentProjectDataset(in_storage=storage,
in_table_name='data')
})
elif key == "development_event":
resources.merge({
key:
DevelopmentEventDataset(in_storage=storage,
in_table_name='data')
})
elif key == "neighborhood":
resources.merge({
key:
NeighborhoodDataset(in_storage=storage,
in_table_name='data')
})
elif key == "job":
resources.merge({
key:
JobDataset(in_storage=storage, in_table_name='data')
})
elif key == "zone":
resources.merge({
key:
ZoneDataset(in_storage=storage, in_table_name='data')
})
elif key == "travel_data":
resources.merge({
key:
TravelDataDataset(in_storage=storage,
in_table_name='data')
})
elif key == "faz":
resources.merge({
key:
FazDataset(in_storage=storage, in_table_name='data')
})
elif key == "fazdistrict":
resources.merge({
key:
FazdistrictDataset(in_storage=storage,
in_table_name='data')
})
elif key == "race":
resources.merge({
key:
RaceDataset(in_storage=storage, in_table_name='data')
})
elif key == "county":
resources.merge({
key:
CountyDataset(in_storage=storage, in_table_name='data')
})
elif key == "large_area":
resources.merge({
key:
LargeAreaDataset(in_storage=storage,
in_table_name='data')
})
elif key == "development_group":
resources.merge({
key:
DevelopmentGroupDataset(in_storage=storage,
in_table_name='data')
})
elif key == "employment_sector_group":
resources.merge({
key:
EmploymentSectorGroupDataset(in_storage=storage,
in_table_name='data')
})
elif key == "plan_type_group":
resources.merge({
key:
PlanTypeGroupDataset(in_storage=storage,
in_table_name='data')
})
elif key == "building":
resources.merge({
key:
BuildingDataset(in_storage=storage,
in_table_name='data')
})
else:
resources.merge({key: data_dictionary[key]})
if dataset in self.interactions:
if dataset == "household_x_gridcell":
resources.merge({
"dataset":
HouseholdXGridcellDataset(dataset1=resources["household"],
dataset2=resources["gridcell"])
})
if dataset == "job_x_gridcell":
resources.merge({
"dataset":
JobXGridcellDataset(dataset1=resources["job"],
dataset2=resources["gridcell"])
})
if dataset == "household_x_zone":
resources.merge({
"dataset":
HouseholdXZoneDataset(dataset1=resources["household"],
dataset2=resources["zone"])
})
if dataset == "household_x_neighborhood":
resources.merge({
"dataset":
HouseholdXNeighborhoodDataset(
dataset1=resources["household"],
dataset2=resources["neighborhood"])
})
if dataset == "development_project_x_gridcell":
resources.merge({
"dataset":
DevelopmentProjectXGridcellDataset(
dataset1=resources["development_project"],
dataset2=resources["gridcell"])
})
else:
resources.merge({"dataset": resources[dataset]})
resources.merge({"check_variables": '*', "debug": 4})
return resources
def test_controlling_sector(self):
""" Controls for one marginal characteristics, namely age_of_head.
"""
annual_employment_control_totals_data = {
"year": array([2000, 2000, 2000, 2001, 2001, 2001, 2002, 2002, 2002]),
"sector_id": array([ 1,2,3, 1,2,3, 1,2,3]),
"number_of_jobs": array([25013, 21513, 18227, # 2000
10055, 15003, 17999, # 2001
15678, 14001, 20432]) # 2002
}
jobs_data = {
"job_id":arange(15000)+1,
"grid_id": array(15000*[1]),
"sector_id": array(1000*[1] + 1000*[1] + 2000*[1] + 1000*[1] +
2000*[2] + 1000*[2] + 1000*[2]+ 1000*[2] +
1000*[3] + 1000*[3] + 2000*[3] + 1000*[3])
}
storage = StorageFactory().get_storage('dict_storage')
storage.write_table(table_name='job_set', table_data=jobs_data)
job_set = JobDataset(in_storage=storage, in_table_name='job_set')
storage.write_table(table_name='ect_set', table_data=annual_employment_control_totals_data)
ect_set = ControlTotalDataset(in_storage=storage, in_table_name='ect_set', what='',
id_name=[])
model = TransitionModel(job_set, control_total_dataset=ect_set)
model.run(year=2000, target_attribute_name="number_of_jobs", reset_dataset_attribute_value={'grid_id':-1})
results = job_set.size()
should_be = [(ect_set.get_attribute("number_of_jobs")[0:3]).sum()]
self.assertEqual(ma.allclose(should_be, results, rtol=1e-1),
True, "Error, should_be: %s, but result: %s" % (should_be, results))
cats = 3
results = zeros(cats, dtype=int32)
for i in range(0, cats):
results[i] = (job_set.get_attribute('sector_id') == ect_set.get_attribute("sector_id")[i]).sum()
should_be = ect_set.get_attribute("number_of_jobs")[0:3]
self.assertEqual(ma.allclose(results, should_be, rtol=1e-6),
True, "Error, should_be: %s, but result: %s" % (should_be, results))
# this run should remove households in all four categories
#model.run(year=2001, household_set=hh_set, control_totals=hct_set, characteristics=hc_set)
model.run(year=2001, target_attribute_name="number_of_jobs", reset_dataset_attribute_value={'grid_id':-1})
results = job_set.size()
should_be = [(ect_set.get_attribute("number_of_jobs")[3:6]).sum()]
self.assertEqual(ma.allclose(should_be, results, rtol=1e-1),
True, "Error, should_be: %s, but result: %s" % (should_be, results))
cats = 3
results = zeros(cats, dtype=int32)
for i in range(0, cats):
results[i] = (job_set.get_attribute('sector_id') == ect_set.get_attribute("sector_id")[i+3]).sum()
should_be = ect_set.get_attribute("number_of_jobs")[3:6]
self.assertEqual(ma.allclose(results, should_be, rtol=1e-6),
True, "Error, should_be: %s, but result: %s" % (should_be, results))
# this run should add and remove households
#model.run(year=2002, household_set=hh_set, control_totals=hct_set, characteristics=hc_set)
model.run(year=2002, target_attribute_name="number_of_jobs", reset_dataset_attribute_value={'grid_id':-1})
results = job_set.size()
should_be = [(ect_set.get_attribute("number_of_jobs")[6:9]).sum()]
self.assertEqual(ma.allclose(should_be, results, rtol=1e-1),
True, "Error, should_be: %s, but result: %s" % (should_be, results))
cats = 3
results = zeros(cats, dtype=int32)
for i in range(0, cats):
results[i] = (job_set.get_attribute('sector_id') == ect_set.get_attribute("sector_id")[i+6]).sum()
should_be = ect_set.get_attribute("number_of_jobs")[6:9]
self.assertEqual(ma.allclose(results, should_be, rtol=1e-6),
True, "Error, should_be: %s, but result: %s" % (should_be, results))
def test_agents_placed_in_appropriate_types(self):
"""Create 1000 unplaced industrial jobs and 1 commercial job. Allocate 50 commercial
gridcells with enough space for 10 commercial jobs per gridcell. After running the
EmploymentLocationChoiceModel, the 1 commercial job should be placed,
but the 100 industrial jobs should remain unplaced
"""
storage = StorageFactory().get_storage('dict_storage')
storage.write_table(table_name='job_building_types',
table_data={
'id': array([2, 1]),
'name': array(['commercial', 'industrial'])
})
job_building_types = JobBuildingTypeDataset(
in_storage=storage, in_table_name='job_building_types')
storage.write_table(table_name='jobs',
table_data={
'job_id': arange(1001) + 1,
'grid_id': array([0] * 1001),
'building_type': array([1] * 1000 + [2])
})
jobs = JobDataset(in_storage=storage, in_table_name='jobs')
storage.write_table(table_name='gridcells',
table_data={
'grid_id': arange(50) + 1,
'commercial_sqft': array([1000] * 50),
'commercial_sqft_per_job': array([100] * 50)
})
gridcells = GridcellDataset(in_storage=storage,
in_table_name='gridcells')
coefficients = Coefficients(names=("dummy", ), values=(0.1, ))
specification = EquationSpecification(
variables=("gridcell.commercial_sqft", ), coefficients=("dummy", ))
compute_resources = Resources({
"job": jobs,
"job_building_type": job_building_types
})
agents_index = where(jobs.get_attribute("grid_id") == 0)
unplace_jobs = DatasetSubset(jobs, agents_index)
agents_index = where(
unplace_jobs.get_attribute("building_type") == 2)[0]
gridcells.compute_variables(
["urbansim.gridcell.number_of_commercial_jobs"],
resources=compute_resources)
commercial_jobs = gridcells.get_attribute("number_of_commercial_jobs")
gridcells.compute_variables(
["urbansim.gridcell.number_of_industrial_jobs"],
resources=compute_resources)
industrial_jobs = gridcells.get_attribute("number_of_industrial_jobs")
model_group = ModelGroup(job_building_types, "name")
elcm = EmploymentLocationChoiceModel(
ModelGroupMember(model_group, "commercial"),
location_set=gridcells,
agents_grouping_attribute="job.building_type",
choices="opus_core.random_choices_from_index",
sample_size_locations=30)
elcm.run(specification,
coefficients,
agent_set=jobs,
agents_index=agents_index,
debuglevel=1)
gridcells.compute_variables(
["urbansim.gridcell.number_of_commercial_jobs"],
resources=compute_resources)
commercial_jobs = gridcells.get_attribute("number_of_commercial_jobs")
gridcells.compute_variables(
["urbansim.gridcell.number_of_industrial_jobs"],
resources=compute_resources)
industrial_jobs = gridcells.get_attribute("number_of_industrial_jobs")
self.assertEqual(
commercial_jobs.sum() == 1, True,
"Error, there should only be a total of 1 commercial job")
self.assertEqual(
industrial_jobs.sum() == 0, True,
"Error, there should be no industrial jobs because there's no space for them"
)
def run(self,
in_storage,
out_storage,
business_table="business",
jobs_table="jobs",
control_totals_table=None):
logger.log_status("Unrolling %s table." % business_table)
# get attributes from the establisments table
business_dataset = BusinessDataset(in_storage=in_storage,
in_table_name=business_table)
business_sizes = business_dataset.get_attribute(
self.number_of_jobs_attr).astype("int32")
sectors = business_dataset.get_attribute("sector_id")
tazes = business_dataset.get_attribute(
self.geography_id_attr).astype("int32")
building_ids = array([], dtype='int32')
if "building_id" in business_dataset.get_primary_attribute_names():
building_ids = business_dataset.get_attribute("building_id")
parcel_ids = array([], dtype='int32')
if "parcel_id" in business_dataset.get_primary_attribute_names():
parcel_ids = business_dataset.get_attribute("parcel_id")
home_based = array([], dtype='int16')
if "home_based" in business_dataset.get_primary_attribute_names():
home_based = business_dataset.get_attribute("home_based")
building_sqft = business_dataset.get_attribute(self.sqft_attr)
building_sqft[building_sqft <= 0] = 0
join_flags = None
if "join_flag" in business_dataset.get_primary_attribute_names():
join_flags = business_dataset.get_attribute("join_flag")
impute_sqft_flag = None
if "impute_building_sqft_flag" in business_dataset.get_primary_attribute_names(
):
impute_sqft_flag = business_dataset.get_attribute(
"impute_building_sqft_flag")
# inititalize jobs attributes
total_size = business_sizes.sum()
jobs_data = {}
jobs_data["sector_id"] = resize(array([-1], dtype=sectors.dtype),
total_size)
jobs_data["building_id"] = resize(
array([-1], dtype=building_ids.dtype), total_size)
jobs_data["parcel_id"] = resize(array([-1], dtype=parcel_ids.dtype),
total_size)
jobs_data[self.geography_id_attr] = resize(
array([-1], dtype=tazes.dtype), total_size)
jobs_data["building_type"] = resize(
array([-1], dtype=home_based.dtype), total_size)
jobs_data["sqft"] = resize(array([], dtype=building_sqft.dtype),
total_size)
if join_flags is not None:
jobs_data["join_flag"] = resize(array([], dtype=join_flags.dtype),
total_size)
if impute_sqft_flag is not None:
jobs_data["impute_building_sqft_flag"] = resize(
array([], dtype=impute_sqft_flag.dtype), total_size)
indices = cumsum(business_sizes)
# iterate over establishments. For each business create the corresponding number of jobs by filling the corresponding part
# of the arrays
start_index = 0
for i in range(business_dataset.size()):
end_index = indices[i]
jobs_data["sector_id"][start_index:end_index] = sectors[i]
if building_ids.size > 0:
jobs_data["building_id"][start_index:end_index] = building_ids[
i]
if parcel_ids.size > 0:
jobs_data["parcel_id"][start_index:end_index] = parcel_ids[i]
jobs_data[self.geography_id_attr][start_index:end_index] = tazes[i]
if home_based.size > 0:
jobs_data["building_type"][start_index:end_index] = home_based[
i]
if self.compute_sqft_per_job:
jobs_data["sqft"][start_index:end_index] = round(
(building_sqft[i] - building_sqft[i] / 10.0) /
float(business_sizes[i])) # sqft per employee
else:
jobs_data["sqft"][start_index:end_index] = building_sqft[i]
if join_flags is not None:
jobs_data["join_flag"][start_index:end_index] = join_flags[i]
if impute_sqft_flag is not None:
jobs_data["impute_building_sqft_flag"][
start_index:end_index] = impute_sqft_flag[i]
start_index = end_index
jobs_data["job_id"] = arange(total_size) + 1
if self.compute_sqft_per_job:
jobs_data["sqft"] = clip(jobs_data["sqft"], 0, self.maximum_sqft)
jobs_data["sqft"][logical_and(
jobs_data["sqft"] > 0,
jobs_data["sqft"] < self.minimum_sqft)] = self.minimum_sqft
# correct missing job_building_types
wmissing_bt = where(jobs_data["building_type"] <= 0)[0]
if wmissing_bt.size > 0:
jobs_data["building_type"][
wmissing_bt] = 2 # assign non-homebased type for now. It can be re-classified in the assign_bldgs_to_jobs... script
# create jobs table and write it out
storage = StorageFactory().get_storage('dict_storage')
storage.write_table(table_name="jobs", table_data=jobs_data)
job_dataset = JobDataset(in_storage=storage)
if self.unplace_jobs_with_non_existing_buildings:
self.do_unplace_jobs_with_non_existing_buildings(
job_dataset, out_storage)
# Match to control totals (only eliminate jobs if control totals are smaller than the actual number of jobs).
if control_totals_table is not None:
logger.log_status("Matching to control totals.")
control_totals = ControlTotalDataset(
what='employment',
id_name=['zone_id', 'sector_id'],
in_table_name=control_totals_table,
in_storage=in_storage)
control_totals.load_dataset(
attributes=['zone_id', 'sector_id', 'jobs'])
zones_sectors = control_totals.get_id_attribute()
njobs = control_totals.get_attribute('jobs')
remove = array([], dtype='int32')
for i in range(zones_sectors.shape[0]):
zone, sector = zones_sectors[i, :]
in_sector = job_dataset.get_attribute("sector_id") == sector
in_zone_in_sector = logical_and(
in_sector,
job_dataset.get_attribute("zone_id") == zone)
if in_zone_in_sector.sum() <= njobs[i]:
continue
to_be_removed = in_zone_in_sector.sum() - njobs[i]
this_removal = 0
not_considered = ones(job_dataset.size(), dtype='bool8')
for unit in [
'parcel_id', 'building_id', None
]: # first consider jobs without parcel id, then without building_id, then all
if unit is not None:
wnunit = job_dataset.get_attribute(unit) <= 0
eligible = logical_and(
not_considered,
logical_and(in_zone_in_sector, wnunit))
not_considered[where(wnunit)] = False
else:
eligible = logical_and(not_considered,
in_zone_in_sector)
eligible_sum = eligible.sum()
if eligible_sum > 0:
where_eligible = where(eligible)[0]
if eligible_sum <= to_be_removed - this_removal:
draw = arange(eligible_sum)
else:
draw = sample_noreplace(
where_eligible, to_be_removed - this_removal,
eligible_sum)
remove = concatenate((remove, where_eligible[draw]))
this_removal += draw.size
if this_removal >= to_be_removed:
break
job_dataset.remove_elements(remove)
logger.log_status("%s jobs removed." % remove.size)
logger.log_status("Write jobs table.")
job_dataset.write_dataset(out_table_name=jobs_table,
out_storage=out_storage)
logger.log_status("Created %s jobs." % job_dataset.size())
class RunAssignBldgsToJobs(Model):
model_name = 'Assigning Buildings To Jobs'
def run(self, job_dataset, dataset_pool):
AssignBuildingsToJobs().run(job_dataset, dataset_pool)
ds = CreateBuildingSqftPerJobDataset()._do_run(dataset_pool)
dataset_pool.replace_dataset('building_sqft_per_job', ds)
if __name__ == '__main__':
# Uncomment the right instorage and outstorage.
# input/output_database_name is used only if MysqlStorage is uncommented.
# input/output_cache is used only if FltStorage is uncommented.
input_database_name = "psrc_2005_parcel_baseyear_change_20070613"
output_database_name = "psrc_2005_data_workspace_hana"
input_cache = "/Users/hana/urbansim_cache/psrc/data_preparation/cache/2000"
output_cache = "/Users/hana/urbansim_cache/psrc/data_preparation/stepIV"
input_cache = "/workspace/work/psrc/unroll_jobs/unroll_jobs_from_establishments_cache"
output_cache = "/workspace/work/psrc/unroll_jobs/output"
#instorage = MysqlStorage().get(input_database_name)
#outstorage = MysqlStorage().get(output_database_name)
instorage = FltStorage().get(input_cache)
outstorage = FltStorage().get(output_cache)
pool_storage = instorage
job_dataset = JobDataset(in_storage=instorage, in_table_name = "jobs")
dataset_pool = DatasetPool(package_order=['urbansim_parcel', 'urbansim'],
storage=pool_storage)
seed(1)
AssignBuildingsToJobs().run(job_dataset, dataset_pool, out_storage=outstorage)
CreateBuildingSqftPerJobDataset().run(in_storage=outstorage, out_storage=outstorage)
def test_same_distribution_after_job_subtraction(self):
"""Removes 1,750 sector_1 jobs, without specifying the distribution across gridcells (so it is assumed equal)
Test that the distribution (in %) of sector 1 jobs across gridcells before and after the subtraction are
relatively equal.
"""
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(table_name=jobs_set_table_name,
table_data=self.jobs_data)
jobs_set = JobDataset(in_storage=storage,
in_table_name=jobs_set_table_name)
ect_set_table_name = 'ect_set'
storage.write_table(
table_name=ect_set_table_name,
table_data=self.annual_employment_control_totals_data)
ect_set = ControlTotalDataset(in_storage=storage,
in_table_name=ect_set_table_name,
what="employment")
model = RegionalEmploymentTransitionModel()
model.run(year=2000,
job_set=jobs_set,
control_totals=ect_set,
job_building_types=self.job_building_types)
# check the totals in regions
areas = jobs_set.get_attribute("large_area_id")
results = array([0, 0])
for iarea in [0, 1]:
results[iarea] = where(areas == [1, 2][iarea])[0].size
should_be = [4250, 7000]
self.assertEqual(
ma.allequal(should_be, results), True,
"Error, should_be: %s, but result: %s" % (should_be, results))
def run_model():
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name=jobs_set_table_name,
table_data=self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage,
in_table_name=jobs_set_table_name)
model = RegionalEmploymentTransitionModel()
model.run(year=2000,
job_set=jobs_set,
control_totals=ect_set,
job_building_types=self.job_building_types)
# check that the distribution of jobs is the same before and after subtracting jobs
results = self.get_count_all_sectors_and_areas(jobs_set)
return results
expected_results = array([2250.0, 1000, 1000, 3000, 2000.0, 2000])
self.run_stochastic_test(__file__, run_model, expected_results, 10)
def run_model2():
storage = StorageFactory().get_storage('dict_storage')
jobs_set_table_name = 'jobs_set'
storage.write_table(
table_name=jobs_set_table_name,
table_data=self.jobs_data,
)
jobs_set = JobDataset(in_storage=storage,
in_table_name=jobs_set_table_name)
model = RegionalEmploymentTransitionModel()
model.run(year=2000,
job_set=jobs_set,
control_totals=ect_set,
job_building_types=self.job_building_types)
# check that the distribution of building type is the same before and after subtracting jobs
jobs_set.compute_variables([
"urbansim.job.is_in_employment_sector_1_industrial",
"urbansim.job.is_in_employment_sector_2_industrial",
"urbansim.job.is_in_employment_sector_1_commercial",
"urbansim.job.is_in_employment_sector_2_commercial",
"urbansim.job.is_in_employment_sector_1_governmental",
"urbansim.job.is_in_employment_sector_2_governmental"
],
resources=Resources({
"job_building_type":
self.job_building_types
}))
result = array([
jobs_set.get_attribute(
"is_in_employment_sector_1_industrial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_2_industrial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_1_commercial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_2_commercial").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_1_governmental").sum(),
jobs_set.get_attribute(
"is_in_employment_sector_2_governmental").sum()
])
return result
expected_results = array([
3500.0 / 7000.0 * 5250.0, 900, 3500.0 / 7000.0 * 5250.0, 1800, 0,
300
])
self.run_stochastic_test(__file__, run_model2, expected_results, 20)
def test_run_model_with_known_buildings(self):
storage = self.storage
storage.write_table(table_name='buildings',
table_data={
'building_id': array([1, 2, 3, 4, 5, 6, 7]),
'parcel_id': array([1, 1, 2, 2, 2, 3, 3]),
'is_residential': array([0, 0, 0, 1, 1, 0, 0])
})
storage.write_table(table_name='employment_events',
table_data={
'parcel_id':
array([2, 2, -1, -1, 1]),
'building_id':
array([-1, -1, 6, 7, -1]),
'scheduled_year':
array([2006, 2006, 2006, 2006, 2006]),
'number_of_non_home_based_jobs':
array([3500, 500, -100, 0, 100]),
'number_of_home_based_jobs':
array([0, 20, 0, 10, 0]),
'sector_id':
array([1, 2, 15, 2, 1]),
'replace_non_home_based_jobs':
array([0, 0, 0, 1, 0])
})
# change in 2006
############
# parcel/sector 1 2 3
# 1 +100nhb +3500nhb --
# 2 =0nhb +500nhb/+20hb +10hb
# 15 -- -- -100nhb
dataset_pool = DatasetPool(
storage=storage, package_order=['urbansim_parcel', 'urbansim'])
job_set = JobDataset(in_storage=storage)
job_set.modify_attribute('building_id',
array(6000 * [1] + 4000 * [3] + 3000 * [6]))
dataset_pool.add_datasets_if_not_included({'job': job_set})
model = EmploymentEventsModel(dataset_pool=dataset_pool)
model.run(dataset_pool.get_dataset('employment_event'),
job_set,
current_year=2006)
buildings = dataset_pool.get_dataset('building')
jobs_in_sec_1 = buildings.compute_variables(
['urbansim_parcel.building.number_of_jobs_of_sector_1'],
dataset_pool=dataset_pool)
jobs_in_sec_2 = buildings.compute_variables(
['urbansim_parcel.building.number_of_jobs_of_sector_2'],
dataset_pool=dataset_pool)
jobs_in_sec_15 = buildings.compute_variables(
['urbansim_parcel.building.number_of_jobs_of_sector_15'],
dataset_pool=dataset_pool)
self.assertEqual(jobs_in_sec_1[0:2].sum() == 4100, True) # parcel 1
self.assertEqual(jobs_in_sec_1[2] == 5500,
True) # parcel 2 non-residential
self.assertEqual(jobs_in_sec_1[5:7].sum() == 1000, True) # parcel 3
self.assertEqual(jobs_in_sec_2[0:2].sum() == 1000, True) # parcel 1
self.assertEqual(jobs_in_sec_2[2] == 1500,
True) # parcel 2 non-residential
self.assertEqual(jobs_in_sec_2[3:5].sum() == 20,
True) # parcel 2 residential
self.assertEqual(jobs_in_sec_2[5] == 100, True) # parcel 3, building 6
self.assertEqual(jobs_in_sec_2[6] == 10, True) # parcel 3, building 7
self.assertEqual(jobs_in_sec_15[0:2].sum() == 1000,
True) # parcel 2 non-residential
self.assertEqual(jobs_in_sec_15[2] == 1000,
True) # parcel 2 residential
self.assertEqual(jobs_in_sec_15[5] == 900,
True) # parcel 3, building 6