def deploy_dod_projections(disable_validation, input_state_dir, input_county_dir, output): """Generates and runs dod data projections from model outputs. Used for manual trigger # triggering persistance to s3 AWS_PROFILE=covidactnow BUCKET_NAME=covidactnow-deleteme python run.py deploy-dod-projections # deploy to the data bucket AWS_PROFILE=covidactnow BUCKET_NAME=data.covidactnow.org python run.py deploy-dod-projections # triggering persistance to local python run.py deploy-dod-projections """ for intervention in list(Intervention): # TODO(issues/#259): Split up the dod pipeline to process states/counties since states support inference # TODO(issues/#258): remove check once counties support inferrence if intervention in Intervention.county_supported_interventions(): logger.info(f"Starting to generate files for {intervention.name}.") state_result, county_result = dod_pipeline.run_projections( input_state_dir, input_county_dir, intervention, run_validation=not disable_validation ) dod_pipeline.deploy_results(state_result, output) dod_pipeline.deploy_results(county_result, output) logger.info('finished dod job')
def deploy_counties_api(disable_validation, input_dir, output, summary_output): """The entry function for invocation""" for intervention in list(Intervention): # TODO(issues/#258): remove check once counties support inferrence if intervention in Intervention.county_supported_interventions(): county_result = api_pipeline.run_projections( input_dir, AggregationLevel.COUNTY, intervention, run_validation=not disable_validation, ) county_summaries, county_timeseries = api_pipeline.generate_api( county_result, input_dir ) api_pipeline.deploy_results([*county_summaries, *county_timeseries], output) counties_summary = api_pipeline.build_counties_summary(county_summaries, intervention) counties_timeseries = api_pipeline.build_counties_timeseries(county_timeseries, intervention) summarized_timeseries = api_pipeline.build_prediction_header_timeseries_data(counties_timeseries) api_pipeline.deploy_prediction_timeseries_csvs(summarized_timeseries, summary_output) api_pipeline.deploy_results([counties_summary], summary_output, write_csv=True) api_pipeline.deploy_results([counties_timeseries], summary_output) logger.info("finished top counties job")
def _get_intervention_type(intervention_type, state, state_interventions_df): if intervention_type == Intervention.SELECTED_MITIGATION.value: state_intervention_results = state_interventions_df.loc[ state_interventions_df["state"] == state]["intervention"] if not state_intervention_results.empty: intervention_string = state_intervention_results.values[0] return Intervention.from_str(intervention_string).value return intervention_type
def __init__(self, data): data = data.reset_index(drop=True) self.fips = data[schema.FIPS].iloc[0] self.data = data self.intervention = Intervention(data[schema.INTERVENTION].iloc[0]) self.data["short_fall"] = _calculate_shortfall( self.data[schema.ALL_HOSPITALIZED], self.data[schema.BEDS])
def get_intervention_for_state(state) -> Intervention: return Intervention.from_str(get_interventions()[state])
def write_region(self, regional_input: RegionalInput) -> None: """Generates the CAN UI output format for a given region. Args: regional_input: the region and its data """ # Get the latest observed values to use in calculating shims observed_latest_dict = regional_input.latest state = observed_latest_dict[CommonFields.STATE] log.info("Mapping output to WebUI.", state=state, fips=regional_input.fips) shim_log = structlog.getLogger(fips=regional_input.fips) pyseir_outputs = regional_input.ensemble_results() try: fit_results = regional_input.inference_result() t0_simulation = datetime.fromisoformat(fit_results["t0_date"]) except (KeyError, ValueError): log.error("Fit result not found for fips. Skipping...", fips=regional_input.fips) return population = regional_input.population # We will shim all suppression policies by the same amount (since historical tracking error # for all policies is the same). baseline_policy = "suppression_policy__inferred" # This could be any valid policy # We need the index in the model's temporal frame. idx_offset = int(fit_results["t_today"] - fit_results["t0"]) observed_death_latest = observed_latest_dict[CommonFields.DEATHS] observed_total_hosps_latest = observed_latest_dict[ CommonFields.CURRENT_HOSPITALIZED] observed_icu_latest = observed_latest_dict[CommonFields.CURRENT_ICU] # For Deaths model_death_latest = pyseir_outputs[baseline_policy]["total_deaths"][ "ci_50"][idx_offset] model_acute_latest = pyseir_outputs[baseline_policy]["HGen"]["ci_50"][ idx_offset] model_icu_latest = pyseir_outputs[baseline_policy]["HICU"]["ci_50"][ idx_offset] model_total_hosps_latest = model_acute_latest + model_icu_latest death_shim = shim.calculate_strict_shim( model=model_death_latest, observed=observed_death_latest, log=shim_log.bind(type=CommonFields.DEATHS), ) total_hosp_shim = shim.calculate_strict_shim( model=model_total_hosps_latest, observed=observed_total_hosps_latest, log=shim_log.bind(type=CommonFields.CURRENT_HOSPITALIZED), ) # For ICU This one is a little more interesting since we often don't have ICU. In this case # we use information from the same aggregation level (intralevel) to keep the ratios # between general hospitalization and icu hospitalization icu_shim = shim.calculate_intralevel_icu_shim( model_acute=model_acute_latest, model_icu=model_icu_latest, observed_icu=observed_icu_latest, observed_total_hosps=observed_total_hosps_latest, log=shim_log.bind(type=CommonFields.CURRENT_ICU), ) # Iterate through each suppression policy. # Model output is interpolated to the dates desired for the API. suppression_policies = [ key for key in pyseir_outputs.keys() if key.startswith("suppression_policy") ] for suppression_policy in suppression_policies: output_for_policy = pyseir_outputs[suppression_policy] output_model = pd.DataFrame() t_list = output_for_policy["t_list"] t_list_downsampled = range(0, int(max(t_list)), self.output_interval_days) output_model[schema.DAY_NUM] = t_list_downsampled output_model[schema.DATE] = [ (t0_simulation + timedelta(days=t)).date().strftime("%Y-%m-%d") for t in t_list_downsampled ] output_model[schema.TOTAL] = population output_model[schema.TOTAL_SUSCEPTIBLE] = np.interp( t_list_downsampled, t_list, output_for_policy["S"]["ci_50"]) output_model[schema.EXPOSED] = np.interp( t_list_downsampled, t_list, output_for_policy["E"]["ci_50"]) output_model[schema.INFECTED] = np.interp( t_list_downsampled, t_list, np.add(output_for_policy["I"]["ci_50"], output_for_policy["A"]["ci_50"]), ) # Infected + Asympt. output_model[schema.INFECTED_A] = output_model[schema.INFECTED] interpolated_model_acute_values = np.interp( t_list_downsampled, t_list, output_for_policy["HGen"]["ci_50"]) output_model[schema.INFECTED_B] = interpolated_model_acute_values raw_model_icu_values = output_for_policy["HICU"]["ci_50"] interpolated_model_icu_values = np.interp(t_list_downsampled, t_list, raw_model_icu_values) # 21 August 2020: The line assigning schema.INFECTED_C in the output_model is # commented out while the Linear Regression estimator is patched through this pipeline # to be consumed downstream by the ICU utilization calculations. It is left here as a # marker for the future if the ICU utilization calculations is dis-entangled from the # PySEIR model outputs. output_model[schema.INFECTED_C] = ( icu_shim + interpolated_model_icu_values).clip(min=0) # General + ICU beds. don't include vent here because they are also counted in ICU output_model[schema.ALL_HOSPITALIZED] = ( interpolated_model_acute_values + interpolated_model_icu_values + total_hosp_shim).clip(min=0) output_model[schema.ALL_INFECTED] = output_model[schema.INFECTED] # Shim Deaths to Match Observed raw_model_deaths_values = output_for_policy["total_deaths"][ "ci_50"] interp_model_deaths_values = np.interp(t_list_downsampled, t_list, raw_model_deaths_values) output_model[schema.DEAD] = (interp_model_deaths_values + death_shim).clip(min=0) # Continue mapping final_beds = np.mean(output_for_policy["HGen"]["capacity"]) output_model[schema.BEDS] = final_beds output_model[schema.CUMULATIVE_INFECTED] = np.interp( t_list_downsampled, t_list, np.cumsum(output_for_policy["total_new_infections"]["ci_50"]), ) if fit_results: output_model[schema.Rt] = np.interp( t_list_downsampled, t_list, fit_results["eps2"] * fit_results["R0"] * np.ones(len(t_list)), ) output_model[schema.Rt_ci90] = np.interp( t_list_downsampled, t_list, 2 * fit_results["eps2_error"] * fit_results["R0"] * np.ones(len(t_list)), ) else: output_model[schema.Rt] = 0 output_model[schema.Rt_ci90] = 0 output_model[schema.CURRENT_VENTILATED] = ( icu_shim + np.interp(t_list_downsampled, t_list, output_for_policy["HVent"]["ci_50"])).clip(min=0) output_model[schema.POPULATION] = population # Average capacity. output_model[schema.ICU_BED_CAPACITY] = np.mean( output_for_policy["HICU"]["capacity"]) output_model[schema.VENTILATOR_CAPACITY] = np.mean( output_for_policy["HVent"]["capacity"]) # Truncate date range of output. output_dates = pd.to_datetime(output_model["date"]) output_model = output_model[ (output_dates >= datetime(month=3, day=3, year=2020)) & (output_dates < datetime.today() + timedelta(days=90))] # Fill in results for the Rt indicator. rt_results = regional_input.inferred_infection_rate() if rt_results is None or rt_results.empty: log.warning( "No Rt Results found, clearing Rt in output.", fips=regional_input.fips, suppression_policy=suppression_policy, ) output_model[schema.RT_INDICATOR] = "NaN" output_model[schema.RT_INDICATOR_CI90] = "NaN" else: rt_results.index = rt_results["date"].dt.strftime("%Y-%m-%d") merged = output_model.merge( rt_results[["Rt_MAP_composite", "Rt_ci95_composite"]], right_index=True, left_on="date", how="left", ) output_model[schema.RT_INDICATOR] = merged["Rt_MAP_composite"] # With 90% probability the value is between rt_indicator - ci90 # to rt_indicator + ci90 output_model[schema.RT_INDICATOR_CI90] = ( merged["Rt_ci95_composite"] - merged["Rt_MAP_composite"]) output_model[[schema.RT_INDICATOR, schema.RT_INDICATOR_CI90]] = output_model[[ schema.RT_INDICATOR, schema.RT_INDICATOR_CI90 ]].fillna("NaN") int_columns = [ col for col in output_model.columns if col not in ( schema.DATE, schema.Rt, schema.Rt_ci90, schema.RT_INDICATOR, schema.RT_INDICATOR_CI90, schema.FIPS, ) ] # Casing floats to ints and then replacing filled in zeros with NaN values instead of # propagating zeros. na_int_columns = output_model.loc[:, int_columns].isna() output_model.loc[:, int_columns] = output_model[int_columns].fillna( 0).astype(int) output_model[na_int_columns] = np.nan output_model.loc[:, [ schema.Rt, schema.Rt_ci90, schema.RT_INDICATOR, schema. RT_INDICATOR_CI90 ]] = output_model[[ schema.Rt, schema.Rt_ci90, schema.RT_INDICATOR, schema.RT_INDICATOR_CI90 ]] output_model[schema.FIPS] = regional_input.fips intervention = Intervention.from_webui_data_adaptor( suppression_policy) output_model[schema.INTERVENTION] = intervention.value output_path = get_run_artifact_path(regional_input.region, RunArtifact.WEB_UI_RESULT, output_dir=self.output_dir) output_path = output_path.replace("__INTERVENTION_IDX__", str(intervention.value)) output_model.to_json(output_path, orient=OUTPUT_JSON_ORIENT)
def map_fips(self, fips): """ For a given county fips code, generate the CAN UI output format. Parameters ---------- fips: str County FIPS code to map. """ logging.info(f"Mapping output to WebUI for {self.state}, {fips}") pyseir_outputs = load_data.load_ensemble_results(fips) if len(fips) == 5 and fips not in self.df_whitelist.fips.values: logging.info(f"Excluding {fips} due to white list...") return try: fit_results = load_inference_result(fips) t0_simulation = datetime.fromisoformat(fit_results["t0_date"]) except (KeyError, ValueError): logging.error(f"Fit result not found for {fips}. Skipping...") return # --------------------------------------------------------------------- # Rescale hosps based on the population ratio... Could swap this to # infection ratio later? # --------------------------------------------------------------------- hosp_times, current_hosp, _ = load_data.load_hospitalization_data_by_state( state=self.state_abbreviation, t0=t0_simulation, convert_cumulative_to_current=True, category="hospitalized", ) _, current_icu, _ = load_data.load_hospitalization_data_by_state( state=self.state_abbreviation, t0=t0_simulation, convert_cumulative_to_current=True, category="icu", ) if len(fips) == 5: population = self.population_data.get_record_for_fips(fips)[CommonFields.POPULATION] else: population = self.population_data.get_record_for_state(self.state_abbreviation)[ CommonFields.POPULATION ] # logging.info(f'Mapping output to WebUI for {self.state}, {fips}') # pyseir_outputs = load_data.load_ensemble_results(fips) # if pyseir_outputs is None: # logging.warning(f'Fit result not found for {fips}: Skipping county') # return None policies = [key for key in pyseir_outputs.keys() if key.startswith("suppression_policy")] if current_hosp is not None: t_latest_hosp_data, current_hosp = hosp_times[-1], current_hosp[-1] t_latest_hosp_data_date = t0_simulation + timedelta(days=int(t_latest_hosp_data)) state_hosp_gen = load_data.get_compartment_value_on_date( fips=fips[:2], compartment="HGen", date=t_latest_hosp_data_date ) state_hosp_icu = load_data.get_compartment_value_on_date( fips=fips[:2], compartment="HICU", date=t_latest_hosp_data_date ) if len(fips) == 5: # Rescale the county level hospitalizations by the expected # ratio of county / state hospitalizations from simulations. # We use ICU data if available too. county_hosp = load_data.get_compartment_value_on_date( fips=fips, compartment="HGen", date=t_latest_hosp_data_date, ensemble_results=pyseir_outputs, ) county_icu = load_data.get_compartment_value_on_date( fips=fips, compartment="HICU", date=t_latest_hosp_data_date, ensemble_results=pyseir_outputs, ) current_hosp *= (county_hosp + county_icu) / (state_hosp_gen + state_hosp_icu) hosp_rescaling_factor = current_hosp / (state_hosp_gen + state_hosp_icu) # Some states have covidtracking issues. We shouldn't ground ICU cases # to zero since so far these have all been bad reporting. if current_icu is not None and current_icu[-1] > 0: icu_rescaling_factor = current_icu[-1] / state_hosp_icu else: icu_rescaling_factor = current_hosp / (state_hosp_gen + state_hosp_icu) else: hosp_rescaling_factor = 1.0 icu_rescaling_factor = 1.0 # Iterate through each suppression policy. # Model output is interpolated to the dates desired for the API. for i_policy, suppression_policy in enumerate( [key for key in pyseir_outputs.keys() if key.startswith("suppression_policy")] ): output_for_policy = pyseir_outputs[suppression_policy] output_model = pd.DataFrame() t_list = output_for_policy["t_list"] t_list_downsampled = range(0, int(max(t_list)), self.output_interval_days) output_model[schema.DAY_NUM] = t_list_downsampled output_model[schema.DATE] = [ (t0_simulation + timedelta(days=t)).date().strftime("%m/%d/%y") for t in t_list_downsampled ] output_model[schema.TOTAL] = population output_model[schema.TOTAL_SUSCEPTIBLE] = np.interp( t_list_downsampled, t_list, output_for_policy["S"]["ci_50"] ) output_model[schema.EXPOSED] = np.interp( t_list_downsampled, t_list, output_for_policy["E"]["ci_50"] ) output_model[schema.INFECTED] = np.interp( t_list_downsampled, t_list, np.add(output_for_policy["I"]["ci_50"], output_for_policy["A"]["ci_50"]), ) # Infected + Asympt. output_model[schema.INFECTED_A] = output_model[schema.INFECTED] output_model[schema.INFECTED_B] = hosp_rescaling_factor * np.interp( t_list_downsampled, t_list, output_for_policy["HGen"]["ci_50"] ) # Hosp General output_model[schema.INFECTED_C] = icu_rescaling_factor * np.interp( t_list_downsampled, t_list, output_for_policy["HICU"]["ci_50"] ) # Hosp ICU # General + ICU beds. don't include vent here because they are also counted in ICU output_model[schema.ALL_HOSPITALIZED] = np.add( output_model[schema.INFECTED_B], output_model[schema.INFECTED_C] ) output_model[schema.ALL_INFECTED] = output_model[schema.INFECTED] output_model[schema.DEAD] = np.interp( t_list_downsampled, t_list, output_for_policy["total_deaths"]["ci_50"] ) final_beds = np.mean(output_for_policy["HGen"]["capacity"]) output_model[schema.BEDS] = final_beds output_model[schema.CUMULATIVE_INFECTED] = np.interp( t_list_downsampled, t_list, np.cumsum(output_for_policy["total_new_infections"]["ci_50"]), ) if fit_results: output_model[schema.Rt] = np.interp( t_list_downsampled, t_list, fit_results["eps"] * fit_results["R0"] * np.ones(len(t_list)), ) output_model[schema.Rt_ci90] = np.interp( t_list_downsampled, t_list, 2 * fit_results["eps_error"] * fit_results["R0"] * np.ones(len(t_list)), ) else: output_model[schema.Rt] = 0 output_model[schema.Rt_ci90] = 0 output_model[schema.CURRENT_VENTILATED] = icu_rescaling_factor * np.interp( t_list_downsampled, t_list, output_for_policy["HVent"]["ci_50"] ) output_model[schema.POPULATION] = population # Average capacity. output_model[schema.ICU_BED_CAPACITY] = np.mean(output_for_policy["HICU"]["capacity"]) output_model[schema.VENTILATOR_CAPACITY] = np.mean( output_for_policy["HVent"]["capacity"] ) # Truncate date range of output. output_dates = pd.to_datetime(output_model["date"]) output_model = output_model[ (output_dates >= datetime(month=3, day=3, year=2020)) & (output_dates < datetime.today() + timedelta(days=90)) ] output_model = output_model.fillna(0) # Fill in results for the Rt indicator. try: rt_results = load_Rt_result(fips) rt_results.index = rt_results["Rt_MAP_composite"].index.strftime("%m/%d/%y") merged = output_model.merge( rt_results[["Rt_MAP_composite", "Rt_ci95_composite"]], right_index=True, left_on="date", how="left", ) output_model[schema.RT_INDICATOR] = merged["Rt_MAP_composite"] # With 90% probability the value is between rt_indicator - ci90 to rt_indicator + ci90 output_model[schema.RT_INDICATOR_CI90] = ( merged["Rt_ci95_composite"] - merged["Rt_MAP_composite"] ) except (ValueError, KeyError) as e: output_model[schema.RT_INDICATOR] = "NaN" output_model[schema.RT_INDICATOR_CI90] = "NaN" output_model[[schema.RT_INDICATOR, schema.RT_INDICATOR_CI90]] = output_model[ [schema.RT_INDICATOR, schema.RT_INDICATOR_CI90] ].fillna("NaN") # Truncate floats and cast as strings to match data model. int_columns = [ col for col in output_model.columns if col not in ( schema.DATE, schema.Rt, schema.Rt_ci90, schema.RT_INDICATOR, schema.RT_INDICATOR_CI90, ) ] output_model.loc[:, int_columns] = ( output_model[int_columns].fillna(0).astype(int).astype(str) ) output_model.loc[ :, [schema.Rt, schema.Rt_ci90, schema.RT_INDICATOR, schema.RT_INDICATOR_CI90] ] = ( output_model[ [schema.Rt, schema.Rt_ci90, schema.RT_INDICATOR, schema.RT_INDICATOR_CI90] ] .fillna(0) .round(decimals=4) .astype(str) ) # Convert the records format to just list(list(values)) output_model = [ [val for val in timestep.values()] for timestep in output_model.to_dict(orient="records") ] output_path = get_run_artifact_path( fips, RunArtifact.WEB_UI_RESULT, output_dir=self.output_dir ) policy_enum = Intervention.from_webui_data_adaptor(suppression_policy) output_path = output_path.replace("__INTERVENTION_IDX__", str(policy_enum.value)) with open(output_path, "w") as f: json.dump(output_model, f)
def map_fips(self, fips): """ For a given county fips code, generate the CAN UI output format. Parameters ---------- fips: str County FIPS code to map. """ if len(fips) == 5: population = self.population_data.get_county_level( 'USA', state=self.state_abbreviation, fips=fips) else: population = self.population_data.get_state_level( 'USA', state=self.state_abbreviation) logging.info(f'Mapping output to WebUI for {self.state}, {fips}') pyseir_outputs = load_data.load_ensemble_results(fips) policies = [ key for key in pyseir_outputs.keys() if key.startswith('suppression_policy') ] all_hospitalized_today = None try: fit_results = load_inference_result(fips) except ValueError: fit_results = None logging.error( f'Fit result not found for {fips}: Skipping inference elements' ) for i_policy, suppression_policy in enumerate(policies): if suppression_policy == 'suppression_policy__full_containment': # No longer shipping this. continue output_for_policy = pyseir_outputs[suppression_policy] output_model = pd.DataFrame() if suppression_policy == 'suppression_policy__inferred' and fit_results: if len(fips) == 5 and fips not in self.df_whitelist.fips: continue t0 = datetime.fromisoformat(fit_results['t0_date']) # Hospitalizations need to be rescaled by the inferred factor to match observations for display. now_idx = int( (datetime.today() - datetime.fromisoformat(fit_results['t0_date'])).days) total_hosps = output_for_policy['HGen']['ci_50'][ now_idx] + output_for_policy['HICU']['ci_50'][now_idx] hosp_fraction = all_hospitalized_today / total_hosps else: t0 = datetime.today() hosp_fraction = 1. t_list = output_for_policy['t_list'] t_list_downsampled = range(0, int(max(t_list)), self.output_interval_days) # Col 0 output_model['days'] = t_list_downsampled # Col 1 output_model['date'] = [ (t0 + timedelta(days=t)).date().strftime('%m/%d/%y') for t in t_list_downsampled ] # Col 2 output_model['t'] = population # Col 3 output_model['b'] = np.interp(t_list_downsampled, t_list, output_for_policy['S']['ci_50']) # Col 4 output_model['c'] = np.interp(t_list_downsampled, t_list, output_for_policy['E']['ci_50']) # Col 5 output_model['d'] = np.interp( t_list_downsampled, t_list, np.add(output_for_policy['I']['ci_50'], output_for_policy['A']['ci_50'])) # Infected + Asympt. # Col 6 output_model['e'] = output_model['d'] # Col 7 output_model['f'] = np.interp( t_list_downsampled, t_list, output_for_policy['HGen']['ci_50']) # Hosp General # Col 8 output_model['g'] = np.interp( t_list_downsampled, t_list, output_for_policy['HICU']['ci_50']) # Hosp ICU # Col 9 output_model['all_hospitalized'] = hosp_fraction * np.add( output_model['f'], output_model['g']) # Col 10 output_model['all_infected'] = output_model['d'] # Col 11 output_model['dead'] = np.interp( t_list_downsampled, t_list, output_for_policy['total_deaths']['ci_50']) # Col 12 final_beds = np.mean( output_for_policy['HGen']['capacity']) + np.mean( output_for_policy['HICU']['capacity']) output_model['beds'] = final_beds output_model['cumulative_infected'] = np.interp( t_list_downsampled, t_list, np.cumsum(output_for_policy['total_new_infections']['ci_50'])) if fit_results: output_model['R_t'] = np.interp( t_list_downsampled, t_list, fit_results['eps'] * fit_results['R0'] * np.ones(len(t_list))) output_model['R_t_stdev'] = np.interp( t_list_downsampled, t_list, fit_results['eps_error'] * fit_results['R0'] * np.ones(len(t_list))) else: output_model['R_t'] = 0 output_model['R_t_stdev'] = 0 # Record the current number of hospitalizations in order to rescale the inference results. all_hospitalized_today = output_model['all_hospitalized'][0] # Don't backfill inferences if suppression_policy != 'suppression_policy__inferred': backfill = self.backfill_output_model_fips( fips, t0, final_beds, output_model) output_model = pd.concat([ backfill, output_model ])[output_model.columns].reset_index(drop=True) # Truncate date range of output. output_dates = pd.to_datetime(output_model['date']) output_model = output_model[ (output_dates > datetime(month=3, day=3, year=2020)) & (output_dates < datetime.today() + timedelta(days=90))] output_model = output_model.fillna(0) for col in ['l']: output_model[col] = 0 output_model['population'] = population for col in ['m', 'n']: output_model[col] = 0 # Truncate floats and cast as strings to match data model. int_columns = [ col for col in output_model.columns if col not in ('date', 'R_t', 'R_t_stdev') ] output_model.loc[:, int_columns] = output_model[int_columns].fillna( 0).astype(int).astype(str) output_model.loc[:, ['R_t', 'R_t_stdev']] = output_model[[ 'R_t', 'R_t_stdev' ]].fillna(0).round(decimals=4).astype(str) # Convert the records format to just list(list(values)) output_model = [[ val for val in timestep.values() ] for timestep in output_model.to_dict(orient='records')] output_path = get_run_artifact_path(fips, RunArtifact.WEB_UI_RESULT, output_dir=self.output_dir) policy_enum = Intervention.from_webui_data_adaptor( suppression_policy) output_path = output_path.replace('__INTERVENTION_IDX__', str(policy_enum.value)) with open(output_path, 'w') as f: json.dump(output_model, f)
def map_fips(self, fips: str) -> None: """ For a given fips code, for either a county or state, generate the CAN UI output format. Parameters ---------- fips: str FIPS code to map. """ log.info("Mapping output to WebUI.", state=self.state, fips=fips) pyseir_outputs = load_data.load_ensemble_results(fips) try: fit_results = load_inference_result(fips) t0_simulation = datetime.fromisoformat(fit_results["t0_date"]) except (KeyError, ValueError): log.error("Fit result not found for fips. Skipping...", fips=fips) return population = self._get_population(fips) # Get multiplicative conversion factors to scale model output to fit dataset current values hosp_rescaling_factor, icu_rescaling_factor = self._get_model_to_dataset_conversion_factors( t0_simulation=t0_simulation, fips=fips, pyseir_outputs=pyseir_outputs, ) # Iterate through each suppression policy. # Model output is interpolated to the dates desired for the API. suppression_policies = [ key for key in pyseir_outputs.keys() if key.startswith("suppression_policy") ] for suppression_policy in suppression_policies: output_for_policy = pyseir_outputs[suppression_policy] output_model = pd.DataFrame() t_list = output_for_policy["t_list"] t_list_downsampled = range(0, int(max(t_list)), self.output_interval_days) output_model[schema.DAY_NUM] = t_list_downsampled output_model[schema.DATE] = [ (t0_simulation + timedelta(days=t)).date().strftime("%m/%d/%y") for t in t_list_downsampled ] output_model[schema.TOTAL] = population output_model[schema.TOTAL_SUSCEPTIBLE] = np.interp( t_list_downsampled, t_list, output_for_policy["S"]["ci_50"]) output_model[schema.EXPOSED] = np.interp( t_list_downsampled, t_list, output_for_policy["E"]["ci_50"]) output_model[schema.INFECTED] = np.interp( t_list_downsampled, t_list, np.add(output_for_policy["I"]["ci_50"], output_for_policy["A"]["ci_50"]), ) # Infected + Asympt. output_model[schema.INFECTED_A] = output_model[schema.INFECTED] output_model[ schema.INFECTED_B] = hosp_rescaling_factor * np.interp( t_list_downsampled, t_list, output_for_policy["HGen"]["ci_50"]) # Hosp General raw_model_icu_values = output_for_policy["HICU"]["ci_50"] interpolated_model_icu_values = np.interp(t_list_downsampled, t_list, raw_model_icu_values) final_derived_model_value = icu_rescaling_factor * interpolated_model_icu_values output_model[schema.INFECTED_C] = final_derived_model_value # General + ICU beds. don't include vent here because they are also counted in ICU output_model[schema.ALL_HOSPITALIZED] = np.add( output_model[schema.INFECTED_B], output_model[schema.INFECTED_C]) output_model[schema.ALL_INFECTED] = output_model[schema.INFECTED] output_model[schema.DEAD] = np.interp( t_list_downsampled, t_list, output_for_policy["total_deaths"]["ci_50"]) final_beds = np.mean(output_for_policy["HGen"]["capacity"]) output_model[schema.BEDS] = final_beds output_model[schema.CUMULATIVE_INFECTED] = np.interp( t_list_downsampled, t_list, np.cumsum(output_for_policy["total_new_infections"]["ci_50"]), ) if fit_results: output_model[schema.Rt] = np.interp( t_list_downsampled, t_list, fit_results["eps"] * fit_results["R0"] * np.ones(len(t_list)), ) output_model[schema.Rt_ci90] = np.interp( t_list_downsampled, t_list, 2 * fit_results["eps_error"] * fit_results["R0"] * np.ones(len(t_list)), ) else: output_model[schema.Rt] = 0 output_model[schema.Rt_ci90] = 0 output_model[ schema.CURRENT_VENTILATED] = icu_rescaling_factor * np.interp( t_list_downsampled, t_list, output_for_policy["HVent"]["ci_50"]) output_model[schema.POPULATION] = population # Average capacity. output_model[schema.ICU_BED_CAPACITY] = np.mean( output_for_policy["HICU"]["capacity"]) output_model[schema.VENTILATOR_CAPACITY] = np.mean( output_for_policy["HVent"]["capacity"]) # Truncate date range of output. output_dates = pd.to_datetime(output_model["date"]) output_model = output_model[ (output_dates >= datetime(month=3, day=3, year=2020)) & (output_dates < datetime.today() + timedelta(days=90))] output_model = output_model.fillna(0) # Fill in results for the Rt indicator. try: rt_results = load_Rt_result(fips) rt_results.index = rt_results[ "Rt_MAP_composite"].index.strftime("%m/%d/%y") merged = output_model.merge( rt_results[["Rt_MAP_composite", "Rt_ci95_composite"]], right_index=True, left_on="date", how="left", ) output_model[schema.RT_INDICATOR] = merged["Rt_MAP_composite"] # With 90% probability the value is between rt_indicator - ci90 # to rt_indicator + ci90 output_model[schema.RT_INDICATOR_CI90] = ( merged["Rt_ci95_composite"] - merged["Rt_MAP_composite"]) except (ValueError, KeyError) as e: log.warning("Clearing Rt in output for fips.", fips=fips, exc_info=e) output_model[schema.RT_INDICATOR] = "NaN" output_model[schema.RT_INDICATOR_CI90] = "NaN" output_model[[schema.RT_INDICATOR, schema.RT_INDICATOR_CI90]] = output_model[[ schema.RT_INDICATOR, schema.RT_INDICATOR_CI90 ]].fillna("NaN") # Truncate floats and cast as strings to match data model. int_columns = [ col for col in output_model.columns if col not in ( schema.DATE, schema.Rt, schema.Rt_ci90, schema.RT_INDICATOR, schema.RT_INDICATOR_CI90, ) ] output_model.loc[:, int_columns] = ( output_model[int_columns].fillna(0).astype(int).astype(str)) output_model.loc[:, [ schema.Rt, schema.Rt_ci90, schema.RT_INDICATOR, schema. RT_INDICATOR_CI90 ]] = (output_model[[ schema.Rt, schema.Rt_ci90, schema.RT_INDICATOR, schema.RT_INDICATOR_CI90 ]].fillna(0).round(decimals=4).astype(str)) # Convert the records format to just list(list(values)) output_model = [[ val for val in timestep.values() ] for timestep in output_model.to_dict(orient="records")] output_path = get_run_artifact_path(fips, RunArtifact.WEB_UI_RESULT, output_dir=self.output_dir) policy_enum = Intervention.from_webui_data_adaptor( suppression_policy) output_path = output_path.replace("__INTERVENTION_IDX__", str(policy_enum.value)) with open(output_path, "w") as f: json.dump(output_model, f)
def get_intervention_for_state(state): # TODO: read this from a dataset class interventions_url = "https://raw.githubusercontent.com/covid-projections/covid-projections/master/src/assets/data/interventions.json" interventions = requests.get(interventions_url).json() return Intervention.from_str(interventions[state])