[Bug] remove subtype times file (#87)

* feat: Remove subtype_times_file

Reason for change:
When using subtype files with pregenerate _leaks, as site are
regenerated, the subtypes times are not carried over.

Resolution:
As site survey times can currently be set in the infrastructure file
on a per site basis AND it is desired to move this functionality over
to the subtype file, the subtype_times_file has been removed and the
functionality will be  reintroduced to the subtype file at a later date.

Effect(s) of change:
subtype_times_file removed

* fix: Removed references to subtype_times_file

Reason for change:
With the removal of the subtype times file, references to this removed
functionality must also be removed.

Resolution:
Removed all references in
end-to-end testing suite and the sample subtype_times_file in the
inputs.

Effect(s) of change:
All references to the Subtype times file are now removed.

* fix: Edit E2E expected output parameters

Reason for change:
E2E tests were failing because they had not been updated for
the latest parameter additions: n_init_days and n_init_leaks.

Resolution:
Adjusted the parameters in expected outputs to include n_init_days and
n_init_leaks.

Effect(s) of change:
E2E test can pass again now

LDAR_Sim/src/default_parameters/p_default.yml

@@ -7,7 +7,6 @@ weather_file: "weather_alberta.nc"
 weather_is_hourly: True # True/False
 infrastructure_file: "facilities_alberta.csv"
 site_samples: 500
-subtype_times_file: "_placeholder_str_"
 subtype_file: "_placeholder_str_"
 consider_weather: False # True/False
 repair_delay:

LDAR_Sim/src/initialization/sites.py

@@ -128,16 +128,6 @@ def generate_sites(program, in_dir, pregen_leaks):
     # even if n_samples is None, the sample function is still used to shuffle
     sites = random.sample(sites, n_samples)
 
-    # Get subtype Times
-    if program['subtype_times_file'] is not None:
-        subtypes_times_f = pd.read_csv(
-            in_dir / program['subtype_times_file'],
-            index_col='subtype_code')
-        subtypes_times = subtypes_times_f.to_dict('index')
-        for site in sites:
-            subtype_time = subtypes_times[site['subtype_code']]
-            site.update(subtype_time)
-
     # Get leaks from file
     if program['emissions']['leak_file'] is not None:
         program['emissions']['empirical_leaks'] = np.array(

LDAR_Sim/src/ldar_sim.py

@@ -80,14 +80,7 @@ def __init__(self, global_params, state, params, timeseries):
                 state['sites'] = random.sample(
                     state['sites'],
                     params['site_samples'])
-            if params['subtype_times_file'] is not None:
-                subtype_times_file = pd.read_csv(
-                    params['input_directory'] / params['subtype_times_file'])
-                cols_to_add = subtype_times_file.columns[1:].tolist()
-                for col in cols_to_add:
-                    for site in state['sites']:
-                        site[col] = subtype_times_file.loc[subtype_times_file['subtype_code'] ==
-                                                           int(site['subtype_code']), col].iloc[0]
+
             # Shuffle all the entries to randomize order for identical 't_Since_last_LDAR' values
             random.shuffle(state['sites'])
 

LDAR_Sim/testing/end_to_end_testing/test_suite/Site_level_venting/expected_outputs/_metadata.txt

@@ -1,2 +1,2 @@
-{'P_air': {'version': '2.0', 'parameter_level': 'program', 'methods': {'airH': {'consider_daylight': False, 'cost': {'per_day': 0, 'per_hour': 0, 'per_site': 100, 'upfront': 0}, 'coverage': {'spatial': 1.0, 'temporal': 1.0}, 'deployment_type': 'mobile', 'follow_up': {'preferred_method': None, 'delay': 0, 'instant_threshold': None, 'instant_threshold_type': 'absolute', 'interaction_priority': 'threshold', 'min_followups': [], 'min_followup_type': 'annual', 'min_followup_days_to_end': 0, 'proportion': 1.0, 'redundancy_filter': 'recent', 'threshold': 0.0, 'threshold_type': 'absolute'}, 'is_follow_up': False, 'label': 'airH', 'max_workday': 8, 'measurement_scale': 'site', 'n_crews': None, 'parameter_level': 'method', 'reporting_delay': 2, 'scheduling': {'deployment_months': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], 'deployment_years': [], 'LDAR_crew_init_location': [-114.062, 51.044], 'home_bases_files': 'Airport_AB_Coordinates.csv', 'route_planning': False, 'travel_speeds': [], 'min_time_bt_surveys': None}, 'sensor': {'type': 'default', 'QE': 0.0, 'MDL': [5.55], 'mod_loc': None}, 't_bw_sites': {'file': None, 'vals': [5]}, 'weather_envs': {'precip': [0.0, 0.5], 'temp': [-40.0, 40.0], 'wind': [0.0, 10.0]}, 'version': '2.0', 'RS': 4, 'time': 5}, 'OGI_FU': {'consider_daylight': False, 'cost': {'per_day': 0, 'per_hour': 0, 'per_site': 500, 'upfront': 0}, 'coverage': {'spatial': 1.0, 'temporal': 1.0}, 'deployment_type': 'mobile', 'follow_up': {'preferred_method': None, 'delay': 0, 'instant_threshold': None, 'instant_threshold_type': 'absolute', 'interaction_priority': 'threshold', 'min_followups': [], 'min_followup_type': 'annual', 'min_followup_days_to_end': 0, 'proportion': 1.0, 'redundancy_filter': 'recent', 'threshold': 0.0, 'threshold_type': 'absolute'}, 'is_follow_up': True, 'label': 'OGI_FU', 'max_workday': 8, 'measurement_scale': 'component', 'n_crews': None, 'parameter_level': 'method', 'reporting_delay': 2, 'scheduling': {'deployment_months': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], 'deployment_years': [], 'LDAR_crew_init_location': [-114.062, 51.044], 'home_bases_files': 'Airport_AB_Coordinates.csv', 'route_planning': False, 'travel_speeds': [], 'min_time_bt_surveys': None}, 'sensor': {'type': 'OGI_camera_zim', 'QE': 0.0, 'MDL': [0.24, 0.39], 'mod_loc': None}, 't_bw_sites': {'file': None, 'vals': [30]}, 'weather_envs': {'precip': [0.0, 0.5], 'temp': [-40.0, 40.0], 'wind': [0.0, 10.0]}, 'version': '2.0', 'RS': None, 'time': 120}}, 'method_labels': ['airH', 'OGI_FU'], 'program_name': 'P_air', 'weather_file': 'ERA5_2017_2019_Perm.nc', 'weather_is_hourly': True, 'infrastructure_file': 'facilities_Perm.csv', 'site_samples': 50, 'subtype_times_file': None, 'subtype_file': None, 'consider_weather': False, 'repair_delay': {'type': 'default', 'val': [14.0]}, 'emissions': {'consider_venting': True, 'leak_dist_params': [-1.79, 2.17], 'leak_dist_type': 'lognorm', 'leak_file': None, 'leak_file_use': 'sample', 'LPR': 0.0065, 'max_leak_rate': 100000, 'subtype_leak_dist_file': None, 'units': ['kilogram', 'hour']}, 'NRd': 365, 'economics': {'carbon_price_tonnesCO2e': 40.0, 'cost_CCUS': 20.0, 'GWP_CH4': 28.0, 'sale_price_natgas': 3.0, 'repair_costs': {'vals': [200], 'file': None}, 'verification_cost': 0}, 'start_date': [2017, 1, 1], 'end_date': [2021, 12, 31]}, 'P_none': {'version': '2.0', 'parameter_level': 'program', 'methods': {}, 'method_labels': [], 'program_name': 'P_none', 'weather_file': 'ERA5_2017_2019_Perm.nc', 'weather_is_hourly': True, 'infrastructure_file': 'facilities_Perm.csv', 'site_samples': 50, 'subtype_times_file': None, 'subtype_file': None, 'consider_weather': False, 'repair_delay': {'type': 'default', 'val': [14.0]}, 'emissions': {'consider_venting': True, 'leak_dist_params': [-1.79, 2.17], 'leak_dist_type': 'lognorm', 'leak_file': None, 'leak_file_use': 'sample', 'LPR': 0.0065, 'max_leak_rate': 100000, 'subtype_leak_dist_file': None, 'units': ['kilogram', 'hour']}, 'NRd': 365, 'economics': {'carbon_price_tonnesCO2e': 40.0, 'cost_CCUS': 20.0, 'GWP_CH4': 28.0, 'sale_price_natgas': 3.0, 'repair_costs': {'vals': [200], 'file': None}, 'verification_cost': 0}, 'start_date': [2017, 1, 1], 'end_date': [2021, 12, 31], 'subtypes': {0: {'dist_type': 'lognorm', 'dist_scale': 0.1669601696670407, 'dist_shape': [2.17], 'leak_rate_units': ['kilogram', 'hour'], 'leak_rate_dist': <scipy.stats._distn_infrastructure.rv_continuous_frozen object at 0x0000020CCE025990>}}}, 'P_OGI': {'version': '2.0', 'parameter_level': 'program', 'methods': {'OGI': {'consider_daylight': False, 'cost': {'per_day': 0, 'per_hour': 0, 'per_site': 500, 'upfront': 0}, 'coverage': {'spatial': 1.0, 'temporal': 1.0}, 'deployment_type': 'mobile', 'follow_up': {'preferred_method': None, 'delay': 0, 'instant_threshold': None, 'instant_threshold_type': 'absolute', 'interaction_priority': 'threshold', 'min_followups': [], 'min_followup_type': 'annual', 'min_followup_days_to_end': 0, 'proportion': 1.0, 'redundancy_filter': 'recent', 'threshold': 0.0, 'threshold_type': 'absolute'}, 'is_follow_up': False, 'label': 'OGI', 'max_workday': 8, 'measurement_scale': 'component', 'n_crews': None, 'parameter_level': 'method', 'reporting_delay': 2, 'scheduling': {'deployment_months': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], 'deployment_years': [], 'LDAR_crew_init_location': [-114.062, 51.044], 'home_bases_files': 'Airport_AB_Coordinates.csv', 'route_planning': False, 'travel_speeds': [], 'min_time_bt_surveys': None}, 'sensor': {'type': 'OGI_camera_zim', 'QE': 0.0, 'MDL': [0.24, 0.39], 'mod_loc': None}, 't_bw_sites': {'file': None, 'vals': [30]}, 'weather_envs': {'precip': [0.0, 0.5], 'temp': [-40.0, 40.0], 'wind': [0.0, 10.0]}, 'version': '2.0', 'RS': 4, 'time': 120}}, 'method_labels': ['OGI'], 'program_name': 'P_OGI', 'weather_file': 'ERA5_2017_2019_Perm.nc', 'weather_is_hourly': True, 'infrastructure_file': 'facilities_Perm.csv', 'site_samples': 50, 'subtype_times_file': None, 'subtype_file': None, 'consider_weather': False, 'repair_delay': {'type': 'default', 'val': [14.0]}, 'emissions': {'consider_venting': True, 'leak_dist_params': [-1.79, 2.17], 'leak_dist_type': 'lognorm', 'leak_file': None, 'leak_file_use': 'sample', 'LPR': 0.0065, 'max_leak_rate': 100000, 'subtype_leak_dist_file': None, 'units': ['kilogram', 'hour']}, 'NRd': 365, 'economics': {'carbon_price_tonnesCO2e': 40.0, 'cost_CCUS': 20.0, 'GWP_CH4': 28.0, 'sale_price_natgas': 3.0, 'repair_costs': {'vals': [200], 'file': None}, 'verification_cost': 0}, 'start_date': [2017, 1, 1], 'end_date': [2021, 12, 31]}}
+{'P_air': {'version': '2.0', 'parameter_level': 'program', 'methods': {'airH': {'consider_daylight': False, 'cost': {'per_day': 0, 'per_hour': 0, 'per_site': 100, 'upfront': 0}, 'coverage': {'spatial': 1.0, 'temporal': 1.0}, 'deployment_type': 'mobile', 'follow_up': {'preferred_method': None, 'delay': 0, 'instant_threshold': None, 'instant_threshold_type': 'absolute', 'interaction_priority': 'threshold', 'min_followups': [], 'min_followup_type': 'annual', 'min_followup_days_to_end': 0, 'proportion': 1.0, 'redundancy_filter': 'recent', 'threshold': 0.0, 'threshold_type': 'absolute'}, 'is_follow_up': False, 'label': 'airH', 'max_workday': 8, 'measurement_scale': 'site', 'n_crews': None, 'parameter_level': 'method', 'reporting_delay': 2, 'scheduling': {'deployment_months': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], 'deployment_years': [], 'LDAR_crew_init_location': [-114.062, 51.044], 'home_bases_files': 'Airport_AB_Coordinates.csv', 'route_planning': False, 'travel_speeds': [], 'min_time_bt_surveys': None}, 'sensor': {'type': 'default', 'QE': 0.0, 'MDL': [5.55], 'mod_loc': None}, 't_bw_sites': {'file': None, 'vals': [5]}, 'weather_envs': {'precip': [0.0, 0.5], 'temp': [-40.0, 40.0], 'wind': [0.0, 10.0]}, 'version': '2.0', 'RS': 4, 'time': 5}, 'OGI_FU': {'consider_daylight': False, 'cost': {'per_day': 0, 'per_hour': 0, 'per_site': 500, 'upfront': 0}, 'coverage': {'spatial': 1.0, 'temporal': 1.0}, 'deployment_type': 'mobile', 'follow_up': {'preferred_method': None, 'delay': 0, 'instant_threshold': None, 'instant_threshold_type': 'absolute', 'interaction_priority': 'threshold', 'min_followups': [], 'min_followup_type': 'annual', 'min_followup_days_to_end': 0, 'proportion': 1.0, 'redundancy_filter': 'recent', 'threshold': 0.0, 'threshold_type': 'absolute'}, 'is_follow_up': True, 'label': 'OGI_FU', 'max_workday': 8, 'measurement_scale': 'component', 'n_crews': None, 'parameter_level': 'method', 'reporting_delay': 2, 'scheduling': {'deployment_months': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], 'deployment_years': [], 'LDAR_crew_init_location': [-114.062, 51.044], 'home_bases_files': 'Airport_AB_Coordinates.csv', 'route_planning': False, 'travel_speeds': [], 'min_time_bt_surveys': None}, 'sensor': {'type': 'OGI_camera_zim', 'QE': 0.0, 'MDL': [0.24, 0.39], 'mod_loc': None}, 't_bw_sites': {'file': None, 'vals': [30]}, 'weather_envs': {'precip': [0.0, 0.5], 'temp': [-40.0, 40.0], 'wind': [0.0, 10.0]}, 'version': '2.0', 'RS': None, 'time': 120}}, 'method_labels': ['airH', 'OGI_FU'], 'program_name': 'P_air', 'weather_file': 'ERA5_2017_2019_Perm.nc', 'weather_is_hourly': True, 'infrastructure_file': 'facilities_Perm.csv', 'site_samples': 50, 'subtype_file': None, 'consider_weather': False, 'repair_delay': {'type': 'default', 'val': [14.0]}, 'emissions': {'consider_venting': True, 'leak_dist_params': [-1.79, 2.17], 'leak_dist_type': 'lognorm', 'leak_file': None, 'leak_file_use': 'sample', 'LPR': 0.0065, 'max_leak_rate': 100000, 'subtype_leak_dist_file': None, 'units': ['kilogram', 'hour']}, 'NRd': 365, 'economics': {'carbon_price_tonnesCO2e': 40.0, 'cost_CCUS': 20.0, 'GWP_CH4': 28.0, 'sale_price_natgas': 3.0, 'repair_costs': {'vals': [200], 'file': None}, 'verification_cost': 0}, 'start_date': [2017, 1, 1], 'end_date': [2021, 12, 31]}, 'P_none': {'version': '2.0', 'parameter_level': 'program', 'methods': {}, 'method_labels': [], 'program_name': 'P_none', 'weather_file': 'ERA5_2017_2019_Perm.nc', 'weather_is_hourly': True, 'infrastructure_file': 'facilities_Perm.csv', 'site_samples': 50, 'subtype_file': None, 'consider_weather': False, 'repair_delay': {'type': 'default', 'val': [14.0]}, 'emissions': {'consider_venting': True, 'leak_dist_params': [-1.79, 2.17], 'leak_dist_type': 'lognorm', 'leak_file': None, 'leak_file_use': 'sample', 'LPR': 0.0065, 'max_leak_rate': 100000, 'subtype_leak_dist_file': None, 'units': ['kilogram', 'hour']}, 'NRd': 365, 'economics': {'carbon_price_tonnesCO2e': 40.0, 'cost_CCUS': 20.0, 'GWP_CH4': 28.0, 'sale_price_natgas': 3.0, 'repair_costs': {'vals': [200], 'file': None}, 'verification_cost': 0}, 'start_date': [2017, 1, 1], 'end_date': [2021, 12, 31], 'subtypes': {0: {'dist_type': 'lognorm', 'dist_scale': 0.1669601696670407, 'dist_shape': [2.17], 'leak_rate_units': ['kilogram', 'hour'], 'leak_rate_dist': <scipy.stats._distn_infrastructure.rv_continuous_frozen object at 0x0000020CCE025990>}}}, 'P_OGI': {'version': '2.0', 'parameter_level': 'program', 'methods': {'OGI': {'consider_daylight': False, 'cost': {'per_day': 0, 'per_hour': 0, 'per_site': 500, 'upfront': 0}, 'coverage': {'spatial': 1.0, 'temporal': 1.0}, 'deployment_type': 'mobile', 'follow_up': {'preferred_method': None, 'delay': 0, 'instant_threshold': None, 'instant_threshold_type': 'absolute', 'interaction_priority': 'threshold', 'min_followups': [], 'min_followup_type': 'annual', 'min_followup_days_to_end': 0, 'proportion': 1.0, 'redundancy_filter': 'recent', 'threshold': 0.0, 'threshold_type': 'absolute'}, 'is_follow_up': False, 'label': 'OGI', 'max_workday': 8, 'measurement_scale': 'component', 'n_crews': None, 'parameter_level': 'method', 'reporting_delay': 2, 'scheduling': {'deployment_months': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], 'deployment_years': [], 'LDAR_crew_init_location': [-114.062, 51.044], 'home_bases_files': 'Airport_AB_Coordinates.csv', 'route_planning': False, 'travel_speeds': [], 'min_time_bt_surveys': None}, 'sensor': {'type': 'OGI_camera_zim', 'QE': 0.0, 'MDL': [0.24, 0.39], 'mod_loc': None}, 't_bw_sites': {'file': None, 'vals': [30]}, 'weather_envs': {'precip': [0.0, 0.5], 'temp': [-40.0, 40.0], 'wind': [0.0, 10.0]}, 'version': '2.0', 'RS': 4, 'time': 120}}, 'method_labels': ['OGI'], 'program_name': 'P_OGI', 'weather_file': 'ERA5_2017_2019_Perm.nc', 'weather_is_hourly': True, 'infrastructure_file': 'facilities_Perm.csv', 'site_samples': 50, 'subtype_file': None, 'consider_weather': False, 'repair_delay': {'type': 'default', 'val': [14.0]}, 'emissions': {'consider_venting': True, 'leak_dist_params': [-1.79, 2.17], 'leak_dist_type': 'lognorm', 'leak_file': None, 'leak_file_use': 'sample', 'LPR': 0.0065, 'max_leak_rate': 100000, 'subtype_leak_dist_file': None, 'units': ['kilogram', 'hour']}, 'NRd': 365, 'economics': {'carbon_price_tonnesCO2e': 40.0, 'cost_CCUS': 20.0, 'GWP_CH4': 28.0, 'sale_price_natgas': 3.0, 'repair_costs': {'vals': [200], 'file': None}, 'verification_cost': 0}, 'start_date': [2017, 1, 1], 'end_date': [2021, 12, 31]}}
 2023-06-05 12:36:07.100267