df = get_all_cause_vr(location_set_version_id)
print_log_message("Aggregating under 1 and all ages")
df = aggregate_age_groups(df)
print_log_message("Aggregating sub national locations")
df = aggregate_to_country_level(df, location_set_version_id)
# append together
# df = pd.concat([df1, df2])
print_log_message("Got a dataframe with {} rows".format(len(df)))
# add names and important metadata
df = add_metadata(df)
return df
if __name__ == "__main__":
# can pass a dictionary of source: [source_list], nid: [nid_list], etc.
# otherwise, will get ALL VR with cause of death data
# vr_filter = {}
location_set_version_id = CONF.get_id('location_set_version')
write = True
df = prepare_allcause_vr(location_set_version_id)
if write:
# write to archive and active directories
write_vr_file(df)
)
squarer = Squarer(cause_meta_df, age_meta_df)
model_df = squarer.get_computed_dataframe(model_df)
elif "HH_SURVEYS" in model_group:
model_df = square_dhs_data(model_df, cause_meta_df,
age_meta_df, location_hierarchy)
print_log_message(log_statistic(model_df))
print_log_message("Restricting model data to only existing cause_ids")
model_df = restrict_to_cause_ids(code_system_cause_dict, model_df)
print_log_message("Adding NR location info")
model_df = format_for_nr(model_df, location_hierarchy)
if model_group_is_run_by_cause(model_group):
run_phase_by_cause(model_df, model_group, launch_set_id)
else:
run_phase_by_model_group(model_df, model_group, launch_set_id)
print_log_message("Job complete. Exiting...")
if __name__ == "__main__":
model_group = str(sys.argv[1])
launch_set_id = int(sys.argv[2])
location_set_version_id = CONF.get_id('location_set_version')
cause_set_version_id = CONF.get_id('cause_set_version')
main(model_group, location_set_version_id, cause_set_version_id,
launch_set_id)
