def get_generation_process_df(source='egrid', regions='all'):
"""Create a dataframe of inputs and outputs to electricity generation processes."""
from electricitylci.egrid_filter import electricity_for_selected_egrid_facilities, emissions_and_waste_for_selected_egrid_facilities
from electricitylci.generation import create_generation_process_df
generation_process_df = create_generation_process_df(
electricity_for_selected_egrid_facilities,
emissions_and_waste_for_selected_egrid_facilities,
subregion=regions)
return generation_process_df
def get_gen_plus_netl():
"""
This will combine the netl life cycle data for solar, solar thermal,
geothermal, wind, and hydro and will include impacts from construction, etc.
that would be omitted from the regular sources of emissions.
It then generates power plant emissions. The two different dataframes are
combined to provide a single dataframe representing annual emissions or
life cycle emissions apportioned over the appropriate number of years for
all reporting power plants.
Returns
-------
dataframe
"""
import electricitylci.generation as gen
from electricitylci.combinator import (
concat_map_upstream_databases,
concat_clean_upstream_and_plant,
)
import electricitylci.geothermal as geo
import electricitylci.solar_upstream as solar
import electricitylci.wind_upstream as wind
import electricitylci.hydro_upstream as hydro
import electricitylci.solar_thermal_upstream as solartherm
eia_gen_year = config.model_specs.eia_gen_year
print(
"Generating inventories for geothermal, solar, wind, hydro, and solar thermal..."
)
geo_df = geo.generate_upstream_geo(eia_gen_year)
solar_df = solar.generate_upstream_solar(eia_gen_year)
wind_df = wind.generate_upstream_wind(eia_gen_year)
hydro_df = hydro.generate_hydro_emissions()
solartherm_df = solartherm.generate_upstream_solarthermal(eia_gen_year)
netl_gen = concat_map_upstream_databases(
eia_gen_year,
geo_df,
solar_df,
wind_df,
solartherm_df,
)
netl_gen["DataCollection"] = 5
netl_gen["GeographicalCorrelation"] = 1
netl_gen["TechnologicalCorrelation"] = 1
netl_gen["ReliabilityScore"] = 1
netl_gen = pd.concat([netl_gen, hydro_df[netl_gen.columns]],
ignore_index=True,
sort=False)
print("Getting reported emissions for generators...")
gen_df = gen.create_generation_process_df()
combined_gen = concat_clean_upstream_and_plant(gen_df, netl_gen)
return combined_gen
def get_generation_process_df(regions=None, **kwargs):
"""
Create a dataframe of emissions from power generation by fuel type in each
region. kwargs would include the upstream emissions dataframe (upstream_df) if
upstream emissions are being included.
Parameters
----------
regions : str, optional
Regions to include in the analysis (the default is None, which uses the value
read from a settings YAML file). Other options include "eGRID", "NERC", "BA",
"US", "FERC", and "EIA"
Returns
-------
DataFrame
Each row represents information about a single emission from a fuel category
in a single region. Columns are:
'Subregion', 'FuelCategory', 'FlowName', 'FlowUUID', 'Compartment',
'Year', 'Source', 'Unit', 'ElementaryFlowPrimeContext',
'TechnologicalCorrelation', 'TemporalCorrelation', 'DataCollection',
'Emission_factor', 'Reliability_Score', 'GeographicalCorrelation',
'GeomMean', 'GeomSD', 'Maximum', 'Minimum'
"""
from electricitylci.generation import create_generation_process_df
from electricitylci.combinator import concat_clean_upstream_and_plant
if config.model_specs.include_renewable_generation is True:
generation_process_df = get_gen_plus_netl()
else:
generation_process_df = create_generation_process_df()
if config.model_specs.include_netl_water is True:
import electricitylci.plant_water_use as water
water_df = water.generate_plant_water_use(
config.model_specs.eia_gen_year)
generation_process_df = concat_clean_upstream_and_plant(
generation_process_df, water_df)
if config.model_specs.include_upstream_processes is True:
try:
upstream_df = kwargs['upstream_df']
upstream_dict = kwargs['upstream_dict']
except KeyError:
print(
"A kwarg named 'upstream_dict' must be included if include_upstream_processes"
"is True")
# upstream_dict = write_upstream_process_database_to_dict(
# upstream_df
# )
# upstream_dict = write_upstream_dicts_to_jsonld(upstream_dict)
combined_df, canadian_gen = combine_upstream_and_gen_df(
generation_process_df, upstream_df)
gen_plus_fuels = add_fuels_to_gen(generation_process_df, upstream_df,
canadian_gen, upstream_dict)
else:
import electricitylci.import_impacts as import_impacts
canadian_gen_df = import_impacts.generate_canadian_mixes(
generation_process_df)
generation_process_df = pd.concat(
[generation_process_df, canadian_gen_df], ignore_index=True)
gen_plus_fuels = generation_process_df
#This change has been made to accomodate the new method of generating
#consumption mixes for FERC regions. They now pull BAs to provide
#a more accurate inventory. The tradeoff here is that it's no longer possible
#to make a FERC region generation mix and also provide the consumption mix.
#Or it could be possible but would requir running through aggregate twice.
# generation_process_df = aggregate_gen(
# gen_plus_fuels, subregion=regions
# )
if regions is None:
regions = config.model_specs.regional_aggregation
if regions in ["BA", "FERC", "US"]:
generation_process_df = aggregate_gen(gen_plus_fuels, subregion="BA")
else:
generation_process_df = aggregate_gen(gen_plus_fuels,
subregion=regions)
return generation_process_df
def get_generation_process_df(use_alt_gen_process=None,
regions=None,
**kwargs):
"""
Create a dataframe of emissions from power generation by fuel type in each
region. kwargs would include the upstream emissions dataframe (upstream_df) if
upstream emissions are being included.
Parameters
----------
use_alt_gen_process : bool, optional
If the NETL alternate generation process method should be used (the default is
None, which uses the value is read from a settings YAML file).
regions : str, optional
Regions to include in the analysis (the default is None, which uses the value
read from a settings YAML file). Other options include "eGRID", "NERC", "BA",
"US", "FERC", and "EIA"
Returns
-------
If
DataFrame
Each row represents information about a single emission from a fuel category
in a single region. Columns are:
'Subregion', 'FuelCategory', 'FlowName', 'FlowUUID', 'Compartment',
'Year', 'Source', 'Unit', 'ElementaryFlowPrimeContext',
'TechnologicalCorrelation', 'TemporalCorrelation', 'DataCollection',
'Emission_factor', 'Reliability_Score', 'GeographicalCorrelation',
'GeomMean', 'GeomSD', 'Maximum', 'Minimum'
"""
if use_alt_gen_process is None:
use_alt_gen_process = model_specs['use_alt_gen_process']
if regions is None:
regions = model_specs['regional_aggregation']
if use_alt_gen_process is True:
try:
upstream_df = kwargs['upstream_df']
except KeyError:
print(
"A kwarg named 'upstream_dict' must be included if use_alt_gen_process "
"is True")
# upstream_df = get_upstream_process_df()
if model_specs['include_upstream_processes'] is True:
upstream_dict = write_upstream_process_database_to_dict(
upstream_df)
upstream_dict = write_upstream_dicts_to_jsonld(upstream_dict)
gen_df = get_alternate_gen_plus_netl()
combined_df, canadian_gen = combine_upstream_and_gen_df(
gen_df, upstream_df)
gen_plus_fuels = add_fuels_to_gen(gen_df, upstream_df,
canadian_gen, upstream_dict)
else:
gen_df = get_alternate_gen_plus_netl()
upstream_df = pd.DataFrame(columns=gen_df.columns)
upstream_dict = {}
gen_plus_fuels = gen_df
#This change has been made to accomodate the new method of generating
#consumption mixes for FERC regions. They now pull BAs to provide
#a more accurate inventory. The tradeoff here is that it's no longer possible
#to make a FERC region generation mix and also provide the consumption mix.
#Or it could be possible but would requir running through aggregate twice.
# generation_process_df = aggregate_gen(
# gen_plus_fuels, subregion=regions
# )
generation_process_df = aggregate_gen(gen_plus_fuels, subregion="BA")
return generation_process_df
else:
from electricitylci.egrid_filter import (
electricity_for_selected_egrid_facilities,
egrid_facilities_to_include,
emissions_and_waste_for_selected_egrid_facilities,
)
from electricitylci.eia923_generation import build_generation_data
from electricitylci.generation import create_generation_process_df
from electricitylci.model_config import replace_egrid
if replace_egrid is True:
# This is a dummy function that doesn't exist yet
# updated_emissions = build_new_emissions(year)
generation_data = build_generation_data()
generation_process_df = create_generation_process_df(
generation_data,
emissions_and_waste_for_selected_egrid_facilities,
subregion=regions,
)
else:
electricity_for_selected_egrid_facilities["Year"] = model_specs[
"egrid_year"]
generation_process_df = create_generation_process_df(
electricity_for_selected_egrid_facilities,
emissions_and_waste_for_selected_egrid_facilities,
subregion=regions,
)
return generation_process_df
if __name__ == "__main__":
import electricitylci.coal_upstream as coal
import electricitylci.natural_gas_upstream as ng
import electricitylci.petroleum_upstream as petro
import electricitylci.geothermal as geo
import electricitylci.solar_upstream as solar
import electricitylci.wind_upstream as wind
import electricitylci.nuclear_upstream as nuke
# coal_df = coal.generate_upstream_coal(2016)
# ng_df = ng.generate_upstream_ng(2016)
petro_df = petro.generate_petroleum_upstream(2016)
geo_df = geo.generate_upstream_geo(2016)
solar_df = solar.generate_upstream_solar(2016)
wind_df = wind.generate_upstream_wind(2016)
nuke_df = nuke.generate_upstream_nuc(2016)
upstream_df = concat_map_upstream_databases(petro_df, geo_df, solar_df,
wind_df, nuke_df)
plant_df = gen.create_generation_process_df()
plant_df["stage_code"] = "Power plant"
print(plant_df.columns)
print(upstream_df.columns)
combined_df = concat_clean_upstream_and_plant(plant_df, upstream_df)
canadian_inventory = import_impacts.generate_canadian_mixes(combined_df)
combined_df = pd.concat([combined_df, canadian_inventory])
combined_df.sort_values(
by=["eGRID_ID", "Compartment", "FlowName", "stage_code"], inplace=True)
combined_df.to_csv(f"{output_dir}/combined_df.csv")