def _process_table_creation_gen(process_name, exchanges_list, fuel_type):
fuel_category_dict = {
"COAL":
"21: Mining, Quarrying, and Oil and Gas Extraction/2121: Coal Mining",
"GAS": "22: Utilities/2212: Natural Gas Distribution",
"OIL":
"31-33: Manufacturing/3241: Petroleum and Coal Products Manufacturing",
"NUCLEAR": "31-33: Manufacturing/3251: Basic Chemical Manufacturing",
# "GEOTHERMAL": "22: Utilities/2211: Electric Power Generation Transmission and Distribuion",
# "WIND": "22: Utilities/2211: Electric Power Generation Transmission and Distribuion",
# "SOLAR": "22: Utilities/2211: Electric Power Generation Transmission and Distribuion",
"CONSTRUCTION": "23: Construction/2371: Utility System Construction",
}
ar = dict()
ar["@type"] = "Process"
ar["allocationFactors"] = ""
ar["defaultAllocationMethod"] = ""
ar["exchanges"] = exchanges_list
ar["location"] = "" # location(region)
ar["parameters"] = ""
module_logger.info(
f"passing {fuel_type.lower()}_upstream to process_doc_creation")
ar['processDocumentation'] = process_doc_creation(
process_type=f"{fuel_type.lower()}_upstream")
ar["processType"] = "LCI_RESULT"
ar["name"] = process_name
if fuel_type is "coal_transport":
ar["category"] = fuel_category_dict["COAL"]
else:
ar["category"] = fuel_category_dict[fuel_type]
ar["description"] = process_description_creation(
f"{fuel_type.lower()}_upstream")
ar["version"] = make_valid_version_num(elci_version)
return ar
def process_table_creation_distribution(region, exchanges_list):
"""Add docstring."""
ar = dict()
ar["@type"] = "Process"
ar["allocationFactors"] = ""
ar["defaultAllocationMethod"] = ""
ar["exchanges"] = exchanges_list
ar["location"] = location(region)
ar["parameters"] = ""
ar["processDocumentation"] = process_doc_creation()
ar["processType"] = "UNIT_PROCESS"
ar["name"] = distribution_to_end_user_name + " - " + region
ar[
"category"
] = "22: Utilities/2211: Electric Power Generation, Transmission and Distribution"
ar["description"] = (
"Electricity distribution to end user in the "
+ str(region)
+ " region."
)
ar["description"]=(ar["description"]
+ " This process was created with ElectricityLCI "
+ "(https://github.com/USEPA/ElectricityLCI) version " + elci_version
+ " using the " + model_specs.model_name + " configuration."
)
ar["version"] = make_valid_version_num(elci_version)
return ar
def process_table_creation_gen(fuelname, exchanges_list, region):
"""Add docstring."""
ar = dict()
ar["@type"] = "Process"
ar["allocationFactors"] = ""
ar["defaultAllocationMethod"] = ""
ar["exchanges"] = exchanges_list
ar["location"] = location(region)
ar["parameters"] = ""
ar["processDocumentation"] = process_doc_creation()
ar["processType"] = "UNIT_PROCESS"
ar["name"] = (generation_name_parts["Base name"] + "; from " +
str(fuelname) + "; " +
generation_name_parts["Location type"])
ar["category"] = (
"22: Utilities/2211: Electric Power Generation, Transmission and Distribution/"
+ fuelname)
ar["description"] = ("Electricity from " + str(fuelname) +
" produced at generating facilities in the " +
str(region) + " region")
try:
# Use the software version number as the process version
ar["version"] = make_valid_version_num(elci_version)
except:
#Set to 1 by default
ar["version"] = 1
return ar
def olcaschema_genprocess(database, upstream_dict={}, subregion="BA"):
"""Turns the give database containing generator facility emissions
into dictionaries that contain the required data for insertion into
an openLCA-compatible json-ld. Additionally, default providers
for fuel inputs are mapped, using the information contained in the dictionary
containing openLCA-formatted data for the fuels.
Parameters
----------
database : dataframe
Dataframe containing aggregated emissions to be turned into openLCA
unit processes
upstream_dict : dictionary, optional
Dictionary as created by upstream_dict.py, containing the openLCA
formatted data for all of the fuel inputs. This function will use the
names and UUIDs from the entries to assign them as default providers.
subregion : str, optional
The subregion level of the aggregated data, by default "BA". See
aggregation_selector.py for available subregions.
Returns
-------
dictionary: dictionary contaning openLCA-formatted data
"""
from electricitylci.process_dictionary_writer import (
unit,
flow_table_creation,
ref_exchange_creator,
uncertainty_table_creation,
process_doc_creation,
)
from electricitylci.aggregation_selector import subregion_col
region_agg = subregion_col(subregion)
fuel_agg = ["FuelCategory"]
if region_agg:
base_cols = region_agg + fuel_agg
else:
base_cols = fuel_agg
non_agg_cols = [
"stage_code",
"FlowName",
"FlowUUID",
"Compartment",
"Unit",
"Year",
"source_string",
"TemporalCorrelation",
"TechnologicalCorrelation",
"GeographicalCorrelation",
"DataCollection",
"ReliabilityScore",
"uncertaintyMin",
"uncertaintyMax",
"uncertaintyLognormParams",
"Emission_factor",
"GeomMean",
"GeomSD",
]
def turn_data_to_dict(data, upstream_dict):
module_logger.debug(
f"Turning flows from {data.name} into dictionaries")
cols_for_exchange_dict = [
"internalId",
"@type",
"avoidedProduct",
"flow",
"flowProperty",
"input",
"quantitativeReference",
"baseUncertainty",
"provider",
"amount",
"amountFormula",
"unit",
"pedigreeUncertainty",
"dqEntry",
"uncertainty",
"comment",
]
year = ",".join(data["Year"].astype(str).unique())
datasources = ",".join(data["source_string"].astype(str).unique())
data["Maximum"] = data["uncertaintyMax"]
data["Minimum"] = data["uncertaintyMin"]
data["uncertainty"] = ""
data["internalId"] = ""
data["@type"] = "Exchange"
data["avoidedProduct"] = False
data["flowProperty"] = ""
data["input"] = False
input_filter = (
(data["Compartment"].str.lower().str.contains("input"))
| (data["Compartment"].str.lower().str.contains("resource"))
| (data["Compartment"].str.lower().str.contains("technosphere")))
data.loc[input_filter, "input"] = True
data["baseUncertainty"] = ""
data["provider"] = ""
data["unit"] = data["Unit"]
# data["ElementaryFlowPrimeContext"] = data["Compartment"]
# default_unit = unit("kg")
# data["unit"] = [default_unit] * len(data)
data["FlowType"] = "ELEMENTARY_FLOW"
product_filter = (
(data["Compartment"].str.lower().str.contains("technosphere"))
| (data["Compartment"].str.lower().str.contains("valuable")))
data.loc[product_filter, "FlowType"] = "PRODUCT_FLOW"
waste_filter = ((
data["Compartment"].str.lower().str.contains("technosphere")))
data.loc[waste_filter, "FlowType"] = "WASTE_FLOW"
data["flow"] = ""
provider_filter = data["stage_code"].isin(upstream_dict.keys())
for index, row in data.loc[provider_filter, :].iterrows():
provider_dict = {
"name":
upstream_dict[getattr(row, "stage_code")]["name"],
"categoryPath":
upstream_dict[getattr(row, "stage_code")]["category"],
"processType":
"UNIT_PROCESS",
"@id":
upstream_dict[getattr(row, "stage_code")]["uuid"],
}
data.at[index, "provider"] = provider_dict
data.at[index, "unit"] = unit(upstream_dict[getattr(
row, "stage_code")]["q_reference_unit"])
data.at[index, "FlowType"] = "PRODUCT_FLOW"
for index, row in data.iterrows():
data.at[index, "uncertainty"] = uncertainty_table_creation(
data.loc[index:index, :])
data.at[index,
"flow"] = flow_table_creation(data.loc[index:index, :])
data["amount"] = data["Emission_factor"]
data["amountFormula"] = ""
data["quantitativeReference"] = False
data["dqEntry"] = (
"(" + str(round(data["ReliabilityScore"].iloc[0], 1)) + ";" +
str(round(data["TemporalCorrelation"].iloc[0], 1)) + ";" +
str(round(data["GeographicalCorrelation"].iloc[0], 1)) + ";" +
str(round(data["TechnologicalCorrelation"].iloc[0], 1)) + ";" +
str(round(data["DataCollection"].iloc[0], 1)) + ")")
data["pedigreeUncertainty"] = ""
data["comment"] = f"{datasources} - {year}"
data_for_dict = data[cols_for_exchange_dict]
data_for_dict = data_for_dict.append(ref_exchange_creator(),
ignore_index=True)
data_dict = data_for_dict.to_dict("records")
return data_dict
database_groupby = database.groupby(by=base_cols)
process_df = pd.DataFrame(database_groupby[non_agg_cols].apply(
turn_data_to_dict, (upstream_dict)))
process_df.columns = ["exchanges"]
process_df.reset_index(inplace=True)
process_df["@type"] = "Process"
process_df["allocationFactors"] = ""
process_df["defaultAllocationMethod"] = ""
process_df["location"] = ""
process_df["parameters"] = ""
# process_doc_dict = process_doc_creation(process_type)
# process_df["processDocumentation"] = [process_doc_dict]*len(process_df)
process_df["processType"] = "UNIT_PROCESS"
process_df["category"] = (
"22: Utilities/2211: Electric Power Generation, Transmission and Distribution/"
+ process_df[fuel_agg].values)
if region_agg is None:
process_df["description"] = (
"Electricity from " + process_df[fuel_agg].values +
" produced at generating facilities in the US.")
process_df["name"] = ("Electricity - " + process_df[fuel_agg].values +
" - US")
else:
process_df["description"] = (
"Electricity from " + process_df[fuel_agg].values +
" produced at generating facilities in the " +
process_df[region_agg].values + " region.")
process_df["name"] = ("Electricity - " + process_df[fuel_agg].values +
" - " + process_df[region_agg].values)
process_df["description"] = (
process_df["description"] +
" This process was created with ElectricityLCI " +
"(https://github.com/USEPA/ElectricityLCI) version " + elci_version +
" using the " + model_specs.model_name + " configuration.")
process_df["version"] = make_valid_version_num(elci_version)
process_df["processDocumentation"] = [
process_doc_creation(x)
for x in list(process_df["FuelCategory"].str.lower())
]
process_cols = [
"@type",
"allocationFactors",
"defaultAllocationMethod",
"exchanges",
"location",
"parameters",
"processDocumentation",
"processType",
"name",
"version",
"category",
"description",
]
result = process_df[process_cols].to_dict("index")
return result