def __init__(self,
gbd_round_id: int,
location_set_version_id: Optional[int] = None):
"""
Grabs and stores demographic information needed for shared functions.
Will also make a location hierarchy dag.
Parameters
----------
gbd_round_id
The GBD round
location_set_version_id
The location set version to use (right now EpiViz-AT is passing
dismod location set versions, but this will eventually switch
to the cause of death hierarchy that is more extensive).
"""
demographics = db_queries.get_demographics(gbd_team='epi',
gbd_round_id=gbd_round_id)
self.age_group_id = demographics['age_group_id']
self.sex_id = demographics['sex_id'] + [3]
cod_demographics = db_queries.get_demographics(
gbd_team='cod', gbd_round_id=gbd_round_id)
self.year_id = cod_demographics['year_id']
if location_set_version_id:
location_dag = LocationDAG(
location_set_version_id=location_set_version_id,
gbd_round_id=gbd_round_id)
self.location_id = list(location_dag.dag.nodes)
self.drill_locations = list(location_dag.dag.nodes)
else:
self.location_id = []
self.drill_locations = []
def test_location_drill_start_end(ihme):
these_settings = deepcopy(BASE_CASE)
model_settings = these_settings["model"]
tree = LocationDAG(these_settings['location_set_version_id'],
these_settings['gbd_round_id'])
region_ids = tree.parent_children(1)
parent_test_loc = choice(region_ids)
test_children = list(tree.parent_children(parent_test_loc))
num_test_children = randint(2, len(test_children))
children_test_locs = sample(test_children, num_test_children)
num_descendants = 0
for child in children_test_locs:
num_descendants += len(tree.descendants(child))
model_settings['drill_location_end'] = children_test_locs
model_settings['drill_location_start'] = parent_test_loc
these_settings['model'] = model_settings
s = load_settings(these_settings)
mi = MeasurementInputsFromSettings(settings=s)
# demographics.location_id shoul be set to all descendants of each
# location in drill_location_end, plus drill_location_end locations
# themselves, plus the drill_location_start location
assert len(mi.demographics.location_id) == (num_descendants +
len(children_test_locs) + 1)
assert len(mi.demographics.drill_locations) == (len(children_test_locs) +
1)
def test_no_drill(ihme):
these_settings = deepcopy(BASE_CASE)
model_settings = these_settings["model"]
tree = LocationDAG(these_settings['location_set_version_id'],
these_settings['gbd_round_id'])
num_descendants = len(tree.descendants(1))
model_settings.pop('drill_location_end')
model_settings.pop('drill_location_start')
these_settings['model'] = model_settings
s = load_settings(these_settings)
mi = MeasurementInputsFromSettings(settings=s)
# since we haven't set either drill_location_start or
# drill_location_end, demographics.location_id should be set
# to the entire hierarchy
assert len(mi.demographics.location_id) == num_descendants + 1
assert len(mi.demographics.drill_locations) == num_descendants + 1
def test_location_drill_start_only(ihme):
these_settings = deepcopy(BASE_CASE)
model_settings = these_settings["model"]
tree = LocationDAG(these_settings['location_set_version_id'],
these_settings['gbd_round_id'])
region_ids = tree.parent_children(1)
test_loc = choice(region_ids)
num_descendants = len(tree.descendants(test_loc))
num_mr_locs = len(tree.parent_children(test_loc))
model_settings.pop("drill_location_end")
model_settings['drill_location_start'] = test_loc
these_settings["model"] = model_settings
s = load_settings(these_settings)
mi = MeasurementInputsFromSettings(settings=s)
# with drill_location_end unset, demographics.location_id should
# be set to all descendants of the test loc, plus the test loc itself
assert len(mi.demographics.location_id) == num_descendants + 1
assert len(mi.demographics.drill_locations) == num_mr_locs
def __init__(self,
gbd_round_id: int,
location_set_version_id: Optional[int] = None):
"""
Demographic groups needed for shared functions.
"""
demographics = db_queries.get_demographics(gbd_team='epi',
gbd_round_id=gbd_round_id)
self.age_group_id = demographics['age_group_id']
self.sex_id = demographics['sex_id'] + [3]
cod_demographics = db_queries.get_demographics(
gbd_team='cod', gbd_round_id=gbd_round_id)
self.year_id = cod_demographics['year_id']
if location_set_version_id:
location_dag = LocationDAG(
location_set_version_id=location_set_version_id,
gbd_round_id=gbd_round_id)
self.location_id = list(location_dag.dag.nodes)
self.mortality_rate_location_id = list(location_dag.dag.nodes)
else:
self.location_id = []
self.mortality_rate_location_id = []
def __init__(self, model_version_id: int,
gbd_round_id: int, decomp_step_id: int,
conn_def: str,
country_covariate_id: List[int],
csmr_cause_id: int, crosswalk_version_id: int,
csmr_process_version_id: Optional[int] = None,
location_set_version_id: Optional[int] = None,
drill_location_start: Optional[int] = None,
drill_location_end: Optional[List[int]] = None):
"""
The class that constructs all of the measurement inputs. Pulls ASDR,
CSMR, crosswalk versions, and country covariates, and puts them into
one data frame that then formats itself for the dismod database.
Performs covariate value interpolation if age and year ranges
don't match up with GBD age and year ranges.
Parameters
----------
model_version_id
the model version ID
gbd_round_id
the GBD round ID
decomp_step_id
the decomp step ID
csmr_process_version_id
process version ID for CSMR
csmr_cause_id: (int) cause to pull CSMR from
crosswalk_version_id
crosswalk version to use
country_covariate_id
list of covariate IDs
conn_def
connection definition from .odbc file (e.g. 'epi') to connect to the IHME databases
location_set_version_id
can be None, if it's none, get the best location_set_version_id for estimation hierarchy of this GBD round
drill_location_start
which location ID to drill from as the parent
drill_location_end
which immediate children of the drill_location_start parent to include in the drill
Attributes
----------
self.decomp_step : str
the decomp step in string form
self.demographics : cascade_at.inputs.demographics.Demographics
a demographics object that specifies the age group, sex,
location, and year IDs to grab
self.integrand_map : Dict[int, int]
dictionary mapping from GBD measure IDs to DisMod IDs
self.asdr : cascade_at.inputs.asdr.ASDR
all-cause mortality input object
self.csmr : cascade_at.inputs.csmr.CSMR
cause-specific mortality input object from cause csmr_cause_id
self.data : cascade_at.inputs.data.CrosswalkVersion
crosswalk version data from IHME database
self.covariate_data : List[cascade_at.inputs.covariate_data.CovariateData]
list of covariate data objects that contains the raw covariate data mapped to IDs
self.location_dag : cascade_at.inputs.locations.LocationDAG
DAG of locations to be used
self.population: (cascade_at.inputs.population.Population)
population object that is used for covariate weighting
self.data_eta: (Dict[str, float]): dictionary of eta value to be
applied to each measure
self.density: (Dict[str, str]): dictionary of density to be
applied to each measure
self.nu: (Dict[str, float]): dictionary of nu value to be applied
to each measure
self.dismod_data: (pd.DataFrame) resulting dismod data formatted
to be used in the dismod database
Examples
--------
>>> from cascade_at.settings.base_case import BASE_CASE
>>> from cascade_at.settings.settings import load_settings
>>>
>>> settings = load_settings(BASE_CASE)
>>> covariate_id = [i.country_covariate_id for i in settings.country_covariate]
>>>
>>> i = MeasurementInputs(
>>> model_version_id=settings.model.model_version_id,
>>> gbd_round_id=settings.gbd_round_id,
>>> decomp_step_id=settings.model.decomp_step_id,
>>> csmr_process_version_id=None,
>>> csmr_cause_id = settings.model.add_csmr_cause,
>>> crosswalk_version_id=settings.model.crosswalk_version_id,
>>> country_covariate_id=covariate_id,
>>> conn_def='epi',
>>> location_set_version_id=settings.location_set_version_id
>>> )
>>> i.get_raw_inputs()
>>> i.configure_inputs_for_dismod(settings)
"""
LOG.info(f"Initializing input object for model version ID {model_version_id}.")
LOG.info(f"GBD Round ID {gbd_round_id}.")
LOG.info(f"Pulling from connection {conn_def}.")
self.model_version_id = model_version_id
self.gbd_round_id = gbd_round_id
self.decomp_step_id = decomp_step_id
self.csmr_process_version_id = csmr_process_version_id
self.csmr_cause_id = csmr_cause_id
self.crosswalk_version_id = crosswalk_version_id
self.country_covariate_id = country_covariate_id
self.conn_def = conn_def
self.drill_location_start = drill_location_start
self.drill_location_end = drill_location_end
self.decomp_step = ds.decomp_step_from_decomp_step_id(self.decomp_step_id)
if location_set_version_id is None:
self.location_set_version_id = get_location_set_version_id(gbd_round_id=self.gbd_round_id)
else:
self.location_set_version_id = location_set_version_id
self.demographics = Demographics(
gbd_round_id=self.gbd_round_id,
location_set_version_id=self.location_set_version_id)
self.location_dag = LocationDAG(
location_set_version_id=self.location_set_version_id,
gbd_round_id=self.gbd_round_id
)
# Need to subset the locations to only those needed for
# the drill. drill_locations_all is the set of locations
# to pull data for, including all descendents. drill_locations
# is the set of locations just parent-children in the drill.
drill_locations_all, drill_locations = locations_by_drill(
drill_location_start=self.drill_location_start,
drill_location_end=self.drill_location_end,
dag=self.location_dag
)
if drill_locations_all:
self.demographics.location_id = drill_locations_all
self.demographics.drill_locations = drill_locations
self.exclude_outliers = True
self.asdr = None
self.csmr = None
self.population = None
self.data = None
self.covariates = None
self.age_groups = None
self.data_eta = None
self.density = None
self.nu = None
self.measures_to_exclude = None
self.dismod_data = None
self.covariate_data = None
self.country_covariate_data = None
self.covariate_specs = None
self.omega = None
def dag(ihme):
d = LocationDAG(location_set_version_id=544, gbd_round_id=6)
return d
def dag(df):
return LocationDAG(df=df)
def run(model_version_id: int,
jobmon: bool = True,
make: bool = True,
n_sim: int = 10,
addl_workflow_args: Optional[str] = None,
skip_configure: bool = False) -> None:
"""
Runs the whole cascade or drill for a model version (which one is specified
in the model version settings).
Parameters
----------
model_version_id
The model version to run
jobmon
Whether or not to use Jobmon. If not using Jobmon, executes
the commands in sequence in this session.
make
Whether or not to make the directory structure for the databases, inputs, and outputs.
n_sim
Number of simulations to do going down the cascade
addl_workflow_args
skip_configure
"""
LOG.info(f"Starting model for {model_version_id}.")
context = Context(model_version_id=model_version_id,
make=make,
configure_application=True)
context.update_status(status='Submitted')
settings = settings_from_model_version_id(
model_version_id=model_version_id, conn_def=context.model_connection)
dag = LocationDAG(location_set_version_id=settings.location_set_version_id,
gbd_round_id=settings.gbd_round_id)
if settings.model.drill == 'drill':
cascade_command = Drill(
model_version_id=model_version_id,
drill_parent_location_id=settings.model.drill_location_start,
drill_sex=settings.model.drill_sex)
elif settings.model.drill == 'cascade':
location_start = None
sex = None
if isinstance(settings.model.drill_location_start, int):
location_start = settings.model.drill_location_start
if isinstance(settings.model.drill_sex, int):
sex = settings.model.drill_sex
cascade_command = TraditionalCascade(
model_version_id=model_version_id,
split_sex=settings.model.split_sex == 'most_detailed',
dag=dag,
n_sim=n_sim,
location_start=settings.model.drill_location_start,
sex=sex,
skip_configure=skip_configure)
else:
raise NotImplementedError(
f"The drill/cascade setting {settings.model.drill} is not implemented."
)
if jobmon:
LOG.info("Configuring jobmon.")
wf = jobmon_workflow_from_cascade_command(
cc=cascade_command,
context=context,
addl_workflow_args=addl_workflow_args)
error = wf.run()
if error:
context.update_status(status='Failed')
raise RuntimeError("Jobmon workflow failed.")
else:
LOG.info("Running without jobmon.")
for c in cascade_command.get_commands():
LOG.info(f"Running {c}.")
process = subprocess.run(c,
shell=True,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
if process.returncode:
context.update_status(status='Failed')
raise RuntimeError(f"Command {c} failed with error"
f"{process.stderr.decode()}")
context.update_status(status='Complete')
def __init__(self,
model_version_id,
gbd_round_id,
decomp_step_id,
csmr_process_version_id,
csmr_cause_id,
crosswalk_version_id,
country_covariate_id,
conn_def,
location_set_version_id=None,
drill=None):
"""
The class that constructs all of the measurement inputs. Pulls ASDR, CSMR, crosswalk versions,
and country covariates, and puts them into one data frame that then formats itself
for the dismod database. Performs covariate value interpolation if age and year ranges
don't match up with GBD age and year ranges.
Parameters:
model_version_id: (int) the model version ID
gbd_round_id: (int) the GBD round ID
decomp_step_id: (int) the decomp step ID
csmr_process_version_id: (int) process version ID for CSMR
csmr_cause_id: (int) cause to pull CSMR from
crosswalk_version_id: (int) crosswalk version to use
country_covariate_id: (list of int) list of covariate IDs
conn_def: (str) connection definition from .odbc file (e.g. 'epi')
location_set_version_id: (int) can be None, if it's none, get the
best location_set_version_id for estimation hierarchy of this GBD round.
drill: (int) optional, which location ID to drill from as the parent
Attributes:
self.decomp_step: (str) the decomp step in string form
self.demographics: (cascade_at.inputs.demographics.Demographics) a demographics object
that specifies the age group, sex, location, and year IDs to grab
self.integrand_map: (dict) dictionary mapping from GBD measure IDs to DisMod IDs
self.asdr: (cascade_at.inputs.asdr.ASDR) all-cause mortality input object
self.csmr: (cascade_at.inputs.csmr.CSMR) cause-specific mortality input object from cause
csmr_cause_id
self.data: (cascade_at.inputs.data.CrosswalkVersion) crosswalk version data from IHME database
self.covariate_data: (List[cascade_at.inputs.covariate_data.CovariateData]) list of covariate
data objects that contains the raw covariate data mapped to IDs
self.location_dag: (cascade_at.inputs.locations.LocationDAG) DAG of locations to be used
self.population: (cascade_at.inputs.population.Population) population object that is used
for covariate weighting
self.data_eta: (Dict[str, float]): dictionary of eta value to be applied to each measure
self.density: (Dict[str, str]): dictionary of density to be applied to each measure
self.nu: (Dict[str, float]): dictionary of nu value to be applied to each measure
self.dismod_data: (pd.DataFrame) resulting dismod data formatted to be used in the dismod database
Usage:
>>> from cascade_at.settings.base_case import BASE_CASE
>>> from cascade_at.settings.settings import load_settings
>>> settings = load_settings(BASE_CASE)
>>> covariate_ids = [i.country_covariate_id for i in settings.country_covariate]
>>> i = MeasurementInputs(model_version_id=settings.model.model_version_id,
>>> gbd_round_id=settings.gbd_round_id,
>>> decomp_step_id=settings.model.decomp_step_id,
>>> csmr_process_version_id=None,
>>> csmr_cause_id = settings.model.add_csmr_cause,
>>> crosswalk_version_id=settings.model.crosswalk_version_id,
>>> country_covariate_id=covariate_ids,
>>> conn_def='epi',
>>> location_set_version_id=settings.location_set_version_id)
>>> i.get_raw_inputs()
>>> i.configure_inputs_for_dismod()
"""
LOG.info(
f"Initializing input object for model version ID {model_version_id}."
)
LOG.info(f"GBD Round ID {gbd_round_id}.")
LOG.info(f"Pulling from connection {conn_def}.")
self.model_version_id = model_version_id
self.gbd_round_id = gbd_round_id
self.decomp_step_id = decomp_step_id
self.csmr_process_version_id = csmr_process_version_id
self.csmr_cause_id = csmr_cause_id
self.crosswalk_version_id = crosswalk_version_id
self.country_covariate_id = country_covariate_id
self.conn_def = conn_def
self.decomp_step = ds.decomp_step_from_decomp_step_id(
self.decomp_step_id)
self.demographics = Demographics(gbd_round_id=self.gbd_round_id)
if location_set_version_id is None:
self.location_set_version_id = get_location_set_version_id(
gbd_round_id=self.gbd_round_id)
else:
self.location_set_version_id = location_set_version_id
self.location_dag = LocationDAG(
location_set_version_id=self.location_set_version_id,
gbd_round_id=self.gbd_round_id)
if drill:
LOG.info(
f"This is a DRILL model, so only going to pull data associated with "
f"drill location start {drill} and its descendants.")
drill_descendants = list(
self.location_dag.descendants(location_id=drill))
self.demographics.location_id = [drill] + drill_descendants
self.exclude_outliers = True
self.asdr = None
self.csmr = None
self.population = None
self.data = None
self.covariates = None
self.age_groups = None
self.data_eta = None
self.density = None
self.nu = None
self.measures_to_exclude = None
self.dismod_data = None
self.covariate_data = None
self.country_covariate_data = None
self.covariate_specs = None
self.omega = None
def l_dag(df):
return LocationDAG(df=df, root=1)
def test_dag_no_root(df):
with pytest.raises(LocationDAGError):
LocationDAG(df=df)
def test_dag_error_missing_args():
with pytest.raises(LocationDAGError):
LocationDAG(location_set_version_id=0)
def test_dag_error_noargs():
with pytest.raises(LocationDAGError):
LocationDAG()
def test_dag_from_df(df):
dag = LocationDAG(df=df, root=1)
assert set(dag.dag.successors(1)) == {2, 3}
assert set(dag.dag.successors(2)) == {4, 5}
assert set(dag.descendants(1)) == {2, 3, 4, 5}
def run(model_version_id: int,
jobmon: bool = True,
make: bool = True,
n_sim: int = 10,
n_pool: int = 10,
addl_workflow_args: Optional[str] = None,
skip_configure: bool = False,
json_file: Optional[str] = None,
test_dir: Optional[str] = None,
execute_dag: bool = True) -> None:
"""
Runs the whole cascade or drill for a model version (whichever one is specified
in the model version settings).
Creates a cascade command and a bunch of cascade operations based
on the model version settings. More information on this structure
is in :ref:`executor`.
Parameters
----------
model_version_id
The model version to run
jobmon
Whether or not to use Jobmon. If not using Jobmon, executes
the commands in sequence in this session.
make
Whether or not to make the directory structure for the databases, inputs, and outputs.
n_sim
Number of simulations to do going down the cascade
addl_workflow_args
Additional workflow args to add to the jobmon workflow name
so that it is unique if you're testing
skip_configure
Skip configuring the inputs because
"""
LOG.info(f"Starting model for {model_version_id}.")
context = Context(model_version_id=model_version_id,
make=make,
configure_application=not skip_configure,
root_directory=test_dir)
context.update_status(status='Submitted')
if json_file:
with open(json_file) as fn:
LOG.info(f"Reading settings from {json_file}")
parameter_json = json.loads(fn.read())
settings = load_settings(parameter_json)
# Save the json file as it is used throughout the cascade
LOG.info(f"Replacing {context.settings_file}")
context.write_inputs(settings=parameter_json)
else:
settings = settings_from_model_version_id(
model_version_id=model_version_id,
conn_def=context.model_connection)
dag = LocationDAG(location_set_version_id=settings.location_set_version_id,
gbd_round_id=settings.gbd_round_id)
if settings.model.drill == 'drill':
cascade_command = Drill(
model_version_id=model_version_id,
drill_parent_location_id=settings.model.drill_location_start,
drill_sex=settings.model.drill_sex,
n_sim=n_sim,
n_pool=n_pool,
skip_configure=skip_configure,
)
elif settings.model.drill == 'cascade':
location_start = None
sex = None
if isinstance(settings.model.drill_location_start, int):
location_start = settings.model.drill_location_start
if isinstance(settings.model.drill_sex, int):
sex = settings.model.drill_sex
cascade_command = TraditionalCascade(
model_version_id=model_version_id,
split_sex=settings.model.split_sex == 'most_detailed',
dag=dag,
n_sim=n_sim,
n_pool=n_pool,
location_start=settings.model.drill_location_start,
sex=sex,
skip_configure=skip_configure,
)
else:
raise NotImplementedError(
f"The drill/cascade setting {settings.model.drill} is not implemented."
)
dag_cmds_path = (context.inputs_dir / 'dag_commands.txt')
LOG.info(f"Writing cascade dag commands to {dag_cmds_path}.")
dag_cmds_path.write_text('\n'.join(cascade_command.get_commands()))
if not execute_dag: return
if jobmon:
LOG.info("Configuring jobmon.")
wf = jobmon_workflow_from_cascade_command(
cc=cascade_command,
context=context,
addl_workflow_args=addl_workflow_args)
wf_run = wf.run(seconds_until_timeout=60 * 60 * 24 * 3, resume=True)
if wf_run.status != 'D':
context.update_status(status='Failed')
raise RuntimeError("Jobmon workflow failed.")
else:
LOG.info("Running without jobmon.")
for c in cascade_command.get_commands():
LOG.info(f"Running {c}")
process = subprocess.run(c,
shell=True,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
if process.returncode:
context.update_status(status='Failed')
raise RuntimeError(f"Command {c} failed with error"
f"{process.stderr.decode()}")
if process.stderr:
print(process.stderr.decode())
if process.stdout:
print(process.stdout.decode())
context.update_status(status='Complete')