Loading .gitignore +1 −0 Original line number Diff line number Diff line Loading @@ -4,3 +4,4 @@ .Ruserdata hydro-cf-trends.Rproj data output R/EIA_xl_readers.R +382 −1 Original line number Diff line number Diff line ## Functions for reading EIA spreadsheets get_EIA_annual_gen <- function(xl_dir){ get_EIA_annual_gen <- function(gnr_dir, plt_dir){ # Identify full list of conventional HY plants to target for analysis... # ... using 2021 generator data (most recent complete EIA set). We look... # ... for plants generating in 2021, then filter out the smallest < 5MW... # ... to make the study manageable while still capturing almost all capacity. suppressWarnings( read_xlsx(paste0(gnr_dir, "f923_2021/", "EIA923_Schedules_2_3_4_5_M_12_2021_Final_Revision.xlsx"), skip = 5, progress = FALSE) |> filter(`AER\r\nFuel Type Code` == "HYC") |> select(EIA_ID = `Plant Id`) |> unique() |> mutate(EIA_ID = as.integer(EIA_ID)) -> HYC_with_gen_2021 ) suppressWarnings( read_xlsx(paste0(plt_dir, "/eia8602021/", "3_1_Generator_Y2021.xlsx"), skip = 1) |> select(EIA_ID = `Plant Code`, nameplate = `Nameplate Capacity (MW)`, `Prime Mover`) |> filter(`Prime Mover` == "HY") |> mutate(EIA_ID = as.integer(EIA_ID)) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) |> filter(EIA_ID %in% HYC_with_gen_2021[["EIA_ID"]]) -> HYC_cap_2021 ) # Return simple table showing impact of removing plants < 5MW HYC_cap_2021 |> mutate(sub_5MW = if_else(nameplate < 5, TRUE, FALSE)) |> summarise(n_plants = n(), total_cap = sum(nameplate), .by = sub_5MW) |> write_csv("./output/misc/impact_of_excluding_sub5MW_plants.csv") # get target plant list HYC_cap_2021 |> filter(nameplate >= 5) |> pull(EIA_ID) -> target_plants 2001:2021L |> map_dfr(function(yr){ if(yr %in% 2001:2003){ read.dbf(paste0( plt_dir, "/eia860", yr, "/GENY", substr(yr,3,4), ".dbf" )) |> as_tibble() |> filter(PRIMEMOVER == "HY") |> select(EIA_ID = PLNTCODE, nameplate = NAMEPLATE) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all } if(yr %in% 2004:2008){ suppressWarnings( read_xls(paste0( plt_dir, "/eia860", yr, "/GenY", substr(yr, 3, 4), ".xls" )) |> as_tibble() |> filter(PRIMEMOVER == "HY") |> select(EIA_ID = PLNTCODE, nameplate = NAMEPLATE) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all ) } if(yr %in% 2009){ suppressWarnings( read_xls(paste0( plt_dir, "/eia860", yr, "/GeneratorY", substr(yr, 3, 4), ".xls" )) |> as_tibble() |> filter(PRIME_MOVER == "HY") |> select(EIA_ID = PLANT_CODE , nameplate = NAMEPLATE) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all ) } if(yr %in% 2010){ suppressWarnings( read_xls(paste0( plt_dir, "/eia860", yr, "/GeneratorsY", yr, ".xls" )) |> as_tibble() |> filter(PRIME_MOVER == "HY") |> select(EIA_ID = PLANT_CODE , nameplate = NAMEPLATE) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all ) } if(yr %in% 2011){ suppressWarnings( read_xlsx(paste0( plt_dir, "/eia860", yr, "/GeneratorY", yr, ".xlsx" ), skip = 1) |> as_tibble() |> filter(PRIME_MOVER == "HY") |> select(EIA_ID = PLANT_CODE, nameplate = NAMEPLATE) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all ) } if(yr %in% 2012){ suppressWarnings( read_xlsx(paste0( plt_dir, "/eia860", yr, "/GeneratorY", yr, ".xlsx" ), skip = 1) |> as_tibble() |> filter(`Prime Mover` == "HY") |> select(EIA_ID = `Plant Code`, nameplate = `Nameplate Capacity (MW)`) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all ) } if(yr %in% 2013:2021){ suppressWarnings( read_xlsx(paste0( plt_dir, "/eia860", yr, "/3_1_Generator_Y", yr, ".xlsx" ), skip = 1) |> as_tibble() |> filter(`Prime Mover` == "HY") |> select(EIA_ID = `Plant Code`, nameplate = `Nameplate Capacity (MW)`) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all ) } tibble(EIA_ID = target_plants) |> left_join(nameplate_all, by = join_by(EIA_ID)) |> mutate(year = !!yr) } ) -> plant_nameplate_MW_2001_2021 # reported plant capacity pre-2001 is available only via generation data files... 1970:2000L |> map_dfr(function(yr){ suppressWarnings( read_xls(paste0(gnr_dir, "f759", yr, "u.xls")) |> mutate(PCODE = as.integer(PCODE)) |> filter(PCODE %in% target_plants) |> summarise(nameplate = 1e-3 * sum(CAPACITY), .by = PCODE) |> # ^^ unit correction to MW rename(EIA_ID = PCODE) -> plant_nameplate ) return( tibble(EIA_ID = target_plants) |> left_join(plant_nameplate, by = join_by(EIA_ID)) |> mutate(year = !!yr) ) }) -> plant_nameplate_MW_1970_2000 bind_rows( plant_nameplate_MW_1970_2000, plant_nameplate_MW_2001_2021 ) -> plant_nameplant_MW # interpolate gap in capacity data with zero values plant_nameplant_MW |> split(~EIA_ID) |> map_dfr(function(x){ x |> mutate( nameplate = if_else(year %in% 1987:2000 & nameplate == 0, NA_real_, nameplate), nameplate = na.approx(nameplate, na.rm = F)) }) -> plant_nameplate_MW_interpolated # Read generation 1970:2000L |> map_dfr(function(yr){ if(yr %in% 1970:1995){ suppressWarnings( read_xls(paste0(gnr_dir, "f759", yr, "u.xls")) |> mutate(PCODE = as.integer(PCODE)) |> select(EIA_ID = PCODE, starts_with("GEN")) |> pivot_longer(!EIA_ID) |> summarise(gen_MWh = sum(value), .by = EIA_ID) -> plant_gen ) } if(yr %in% 1996:2000){ suppressWarnings( read_xls(paste0(gnr_dir, "f759", yr, "u.xls")) |> mutate(PCODE = as.integer(PCODE)) |> select(EIA_ID = PCODE, NETGENERAT) |> summarise(gen_MWh = sum(NETGENERAT), .by = EIA_ID) -> plant_gen ) } tibble(EIA_ID = target_plants) |> left_join(plant_gen, by = join_by(EIA_ID)) |> mutate(year = !!yr) |> mutate(gen_MWh = if_else(year %in% 1970:1989, gen_MWh * 1e-3, gen_MWh)) }) -> gen_1970_2000 2001:2021 %>% map_dfr(function(yr){ if(yr %in% 2001:2002){ file_name <- paste0(gnr_dir, "f906920_", yr, "/f906920_", yr, ".xls") # read EIA file suppressWarnings( read_xls(file_name, skip = 7, .name_repair = "unique_quiet") |> rename(eia_id = `Plant ID`) |> mutate(eia_id = as.integer(eia_id)) -> EIA_data ) # filter EIA file for hydro EIA_data %>% filter(eia_id %in% target_plants) %>% select(EIA_ID = eia_id, MWh = `NET GENERATION (megawatthours)`) |> summarise(MWh = sum(MWh), .by = EIA_ID) -> EIA_hydro # make netgen numeric and add frequency of reporting "true_monthly?" return( tibble(EIA_ID = target_plants) |> left_join(EIA_hydro, by = "EIA_ID") |> mutate_if(is.character, as.numeric) |> mutate(year = !!yr) ) } if(yr %in% 2003:2007){ file_name <- paste0(gnr_dir, "f906920_", yr, "/f906920_", yr, ".xls") # read EIA file suppressWarnings( read_xls(file_name, skip = 7, .name_repair = "unique_quiet") |> rename(EIA_ID = `Plant ID`) -> EIA_data ) # filter EIA file for hydro EIA_data |> select(EIA_ID, MWh = `NET GENERATION (megawatthours)`) |> filter(EIA_ID %in% target_plants) |> summarise(MWh = sum(MWh, na.rm = T), .by = EIA_ID) -> EIA_hydro return( tibble(EIA_ID = target_plants) |> left_join(EIA_hydro, by = "EIA_ID") |> mutate(year = !!yr) ) } if(yr %in% 2008:2021){ if(yr %in% 2008:2010){ file_name <- paste0(gnr_dir, "f923_", yr, "/EIA923 SCHEDULES ", yr, ".xls") suppressWarnings( read_xls(file_name, skip = 7, .name_repair = "unique_quiet") |> rename(EIA_ID = `Plant ID`) -> EIA_data ) } if(yr %in% 2011:2020){ file_name <- paste0(gnr_dir, "f923_", yr, "/EIA923 SCHEDULES ", yr, ".xlsx") suppressWarnings( read_xlsx(file_name, skip = 5, .name_repair = "unique_quiet") %>% rename(EIA_ID = `Plant Id`) -> EIA_data ) } if(yr == 2021){ file_name <- paste0(gnr_dir, "f923_", yr, "/EIA923_Schedules_2_3_4_5_M_12_2021_Final_Revision.xlsx") suppressWarnings( read_xlsx(file_name, skip = 5, .name_repair = "unique_quiet") |> rename(EIA_ID = `Plant Id`) -> EIA_data ) } # filter EIA file for hydro suppressWarnings( EIA_data |> select(EIA_ID, any_of(c("NET GENERATION (megawatthours)", "Net Generation (Megawatthours)", "Net Generation\r\n(Megawatthours)"))) -> EIA_data_ ) names(EIA_data_) <- c("EIA_ID", "MWh") EIA_data_ |> filter(EIA_ID %in% target_plants) |> summarise(MWh = sum(MWh, na.rm = T), .by = EIA_ID) -> EIA_hydro return( tibble(EIA_ID = target_plants) |> left_join(EIA_hydro, by = "EIA_ID") |> mutate(year = !!yr) ) } }) -> EIA_hydro_netgen_2001_2021 # generate table of hrs per year for computation of maximum output tibble( date = seq.Date(from = ymd("1970-01-01"), to = ymd("2021-12-31"), by = 1) ) |> mutate(year = year(date)) |> summarise(n_hrs = n() * 24, .by = year) -> hrs_per_year # combine nameplate and generation to get CF bind_rows( gen_1970_2000, EIA_hydro_netgen_2001_2021 |> rename(gen_MWh = MWh) ) |> left_join(plant_nameplate_MW_interpolated, by = join_by(EIA_ID, year)) |> left_join(hrs_per_year, join_by(year)) |> mutate(cap_MWh = nameplate * n_hrs, CF = gen_MWh / cap_MWh) -> gen_cap_CF_1970_2021 return(gen_cap_CF_1970_2021) } _targets.R +12 −3 Original line number Diff line number Diff line Loading @@ -13,7 +13,9 @@ tar_option_set( "purrr", "furrr", "future", "sf") "sf", "foreign", "zoo") ) #options(clustermq.scheduler = "multisession") Loading @@ -30,7 +32,14 @@ list( format = "file" ), tar_target( EIA_annual_gen, get_EIA_annual_gen(xl_dir = EIA_529_906_920_923) EIA_860, "./data/EIA/Plant/", format = "file" ), tar_target( EIA_annual_gen_cap_CF_1970_2021, get_EIA_annual_gen(gnr_dir = EIA_529_906_920_923, plt_dir = EIA_860), format = "parquet" ) ) _targets/meta/meta +5 −2 Original line number Diff line number Diff line name|type|data|command|depend|seed|path|time|size|bytes|format|repository|iteration|parent|children|seconds|warnings|error .Random.seed|object|1ce8be4dd88ddeeb||||||||||||||| EIA_529_906_920_923|stem|429fb55d18257b0e|7e8ad8e942ac6d8d|ef46db3751d8e999|-1754950433|./data/EIA/Generation/|t19552.6038571127s|db7d75b1b9e45804|24576|file|local|vector|||0.82|| EIA_annual_gen|stem|d131862dc333587a|058b1fa983426efc|7647f84d89c236d8|-1955140278||t19552.6216109002s|44e327d1ee1978d7|43|rds|local|vector|||0|| get_EIA_annual_gen|function|6f020b783a1d9451||||||||||||||| EIA_860|stem|db95ac5d1da1bd03|fd2da67a7010fb85|ef46db3751d8e999|-1646985544|./data/EIA/Plant/|t19552.6038846689s|c8fc69c6c41e109f|12288|file|local|vector|||2.19|| EIA_annual_gen|stem|8df8ad9ee42d49d6|922aefb19c709325|b0d9bfb57fa52bff|-1955140278||t19555.5959348734s|c08769dc4ce04be3|812175|parquet|local|vector|||69.36|| EIA_annual_gen_cap_CF_1970_2021|stem|8df8ad9ee42d49d6|922aefb19c709325|b0d9bfb57fa52bff|-623511298||t19555.6015050991s|c08769dc4ce04be3|812175|parquet|local|vector|||68.46|| get_EIA_annual_gen|function|1f87eeb76f308b73||||||||||||||| Loading
.gitignore +1 −0 Original line number Diff line number Diff line Loading @@ -4,3 +4,4 @@ .Ruserdata hydro-cf-trends.Rproj data output
R/EIA_xl_readers.R +382 −1 Original line number Diff line number Diff line ## Functions for reading EIA spreadsheets get_EIA_annual_gen <- function(xl_dir){ get_EIA_annual_gen <- function(gnr_dir, plt_dir){ # Identify full list of conventional HY plants to target for analysis... # ... using 2021 generator data (most recent complete EIA set). We look... # ... for plants generating in 2021, then filter out the smallest < 5MW... # ... to make the study manageable while still capturing almost all capacity. suppressWarnings( read_xlsx(paste0(gnr_dir, "f923_2021/", "EIA923_Schedules_2_3_4_5_M_12_2021_Final_Revision.xlsx"), skip = 5, progress = FALSE) |> filter(`AER\r\nFuel Type Code` == "HYC") |> select(EIA_ID = `Plant Id`) |> unique() |> mutate(EIA_ID = as.integer(EIA_ID)) -> HYC_with_gen_2021 ) suppressWarnings( read_xlsx(paste0(plt_dir, "/eia8602021/", "3_1_Generator_Y2021.xlsx"), skip = 1) |> select(EIA_ID = `Plant Code`, nameplate = `Nameplate Capacity (MW)`, `Prime Mover`) |> filter(`Prime Mover` == "HY") |> mutate(EIA_ID = as.integer(EIA_ID)) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) |> filter(EIA_ID %in% HYC_with_gen_2021[["EIA_ID"]]) -> HYC_cap_2021 ) # Return simple table showing impact of removing plants < 5MW HYC_cap_2021 |> mutate(sub_5MW = if_else(nameplate < 5, TRUE, FALSE)) |> summarise(n_plants = n(), total_cap = sum(nameplate), .by = sub_5MW) |> write_csv("./output/misc/impact_of_excluding_sub5MW_plants.csv") # get target plant list HYC_cap_2021 |> filter(nameplate >= 5) |> pull(EIA_ID) -> target_plants 2001:2021L |> map_dfr(function(yr){ if(yr %in% 2001:2003){ read.dbf(paste0( plt_dir, "/eia860", yr, "/GENY", substr(yr,3,4), ".dbf" )) |> as_tibble() |> filter(PRIMEMOVER == "HY") |> select(EIA_ID = PLNTCODE, nameplate = NAMEPLATE) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all } if(yr %in% 2004:2008){ suppressWarnings( read_xls(paste0( plt_dir, "/eia860", yr, "/GenY", substr(yr, 3, 4), ".xls" )) |> as_tibble() |> filter(PRIMEMOVER == "HY") |> select(EIA_ID = PLNTCODE, nameplate = NAMEPLATE) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all ) } if(yr %in% 2009){ suppressWarnings( read_xls(paste0( plt_dir, "/eia860", yr, "/GeneratorY", substr(yr, 3, 4), ".xls" )) |> as_tibble() |> filter(PRIME_MOVER == "HY") |> select(EIA_ID = PLANT_CODE , nameplate = NAMEPLATE) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all ) } if(yr %in% 2010){ suppressWarnings( read_xls(paste0( plt_dir, "/eia860", yr, "/GeneratorsY", yr, ".xls" )) |> as_tibble() |> filter(PRIME_MOVER == "HY") |> select(EIA_ID = PLANT_CODE , nameplate = NAMEPLATE) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all ) } if(yr %in% 2011){ suppressWarnings( read_xlsx(paste0( plt_dir, "/eia860", yr, "/GeneratorY", yr, ".xlsx" ), skip = 1) |> as_tibble() |> filter(PRIME_MOVER == "HY") |> select(EIA_ID = PLANT_CODE, nameplate = NAMEPLATE) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all ) } if(yr %in% 2012){ suppressWarnings( read_xlsx(paste0( plt_dir, "/eia860", yr, "/GeneratorY", yr, ".xlsx" ), skip = 1) |> as_tibble() |> filter(`Prime Mover` == "HY") |> select(EIA_ID = `Plant Code`, nameplate = `Nameplate Capacity (MW)`) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all ) } if(yr %in% 2013:2021){ suppressWarnings( read_xlsx(paste0( plt_dir, "/eia860", yr, "/3_1_Generator_Y", yr, ".xlsx" ), skip = 1) |> as_tibble() |> filter(`Prime Mover` == "HY") |> select(EIA_ID = `Plant Code`, nameplate = `Nameplate Capacity (MW)`) |> summarise(nameplate = sum(nameplate), .by = EIA_ID) -> nameplate_all ) } tibble(EIA_ID = target_plants) |> left_join(nameplate_all, by = join_by(EIA_ID)) |> mutate(year = !!yr) } ) -> plant_nameplate_MW_2001_2021 # reported plant capacity pre-2001 is available only via generation data files... 1970:2000L |> map_dfr(function(yr){ suppressWarnings( read_xls(paste0(gnr_dir, "f759", yr, "u.xls")) |> mutate(PCODE = as.integer(PCODE)) |> filter(PCODE %in% target_plants) |> summarise(nameplate = 1e-3 * sum(CAPACITY), .by = PCODE) |> # ^^ unit correction to MW rename(EIA_ID = PCODE) -> plant_nameplate ) return( tibble(EIA_ID = target_plants) |> left_join(plant_nameplate, by = join_by(EIA_ID)) |> mutate(year = !!yr) ) }) -> plant_nameplate_MW_1970_2000 bind_rows( plant_nameplate_MW_1970_2000, plant_nameplate_MW_2001_2021 ) -> plant_nameplant_MW # interpolate gap in capacity data with zero values plant_nameplant_MW |> split(~EIA_ID) |> map_dfr(function(x){ x |> mutate( nameplate = if_else(year %in% 1987:2000 & nameplate == 0, NA_real_, nameplate), nameplate = na.approx(nameplate, na.rm = F)) }) -> plant_nameplate_MW_interpolated # Read generation 1970:2000L |> map_dfr(function(yr){ if(yr %in% 1970:1995){ suppressWarnings( read_xls(paste0(gnr_dir, "f759", yr, "u.xls")) |> mutate(PCODE = as.integer(PCODE)) |> select(EIA_ID = PCODE, starts_with("GEN")) |> pivot_longer(!EIA_ID) |> summarise(gen_MWh = sum(value), .by = EIA_ID) -> plant_gen ) } if(yr %in% 1996:2000){ suppressWarnings( read_xls(paste0(gnr_dir, "f759", yr, "u.xls")) |> mutate(PCODE = as.integer(PCODE)) |> select(EIA_ID = PCODE, NETGENERAT) |> summarise(gen_MWh = sum(NETGENERAT), .by = EIA_ID) -> plant_gen ) } tibble(EIA_ID = target_plants) |> left_join(plant_gen, by = join_by(EIA_ID)) |> mutate(year = !!yr) |> mutate(gen_MWh = if_else(year %in% 1970:1989, gen_MWh * 1e-3, gen_MWh)) }) -> gen_1970_2000 2001:2021 %>% map_dfr(function(yr){ if(yr %in% 2001:2002){ file_name <- paste0(gnr_dir, "f906920_", yr, "/f906920_", yr, ".xls") # read EIA file suppressWarnings( read_xls(file_name, skip = 7, .name_repair = "unique_quiet") |> rename(eia_id = `Plant ID`) |> mutate(eia_id = as.integer(eia_id)) -> EIA_data ) # filter EIA file for hydro EIA_data %>% filter(eia_id %in% target_plants) %>% select(EIA_ID = eia_id, MWh = `NET GENERATION (megawatthours)`) |> summarise(MWh = sum(MWh), .by = EIA_ID) -> EIA_hydro # make netgen numeric and add frequency of reporting "true_monthly?" return( tibble(EIA_ID = target_plants) |> left_join(EIA_hydro, by = "EIA_ID") |> mutate_if(is.character, as.numeric) |> mutate(year = !!yr) ) } if(yr %in% 2003:2007){ file_name <- paste0(gnr_dir, "f906920_", yr, "/f906920_", yr, ".xls") # read EIA file suppressWarnings( read_xls(file_name, skip = 7, .name_repair = "unique_quiet") |> rename(EIA_ID = `Plant ID`) -> EIA_data ) # filter EIA file for hydro EIA_data |> select(EIA_ID, MWh = `NET GENERATION (megawatthours)`) |> filter(EIA_ID %in% target_plants) |> summarise(MWh = sum(MWh, na.rm = T), .by = EIA_ID) -> EIA_hydro return( tibble(EIA_ID = target_plants) |> left_join(EIA_hydro, by = "EIA_ID") |> mutate(year = !!yr) ) } if(yr %in% 2008:2021){ if(yr %in% 2008:2010){ file_name <- paste0(gnr_dir, "f923_", yr, "/EIA923 SCHEDULES ", yr, ".xls") suppressWarnings( read_xls(file_name, skip = 7, .name_repair = "unique_quiet") |> rename(EIA_ID = `Plant ID`) -> EIA_data ) } if(yr %in% 2011:2020){ file_name <- paste0(gnr_dir, "f923_", yr, "/EIA923 SCHEDULES ", yr, ".xlsx") suppressWarnings( read_xlsx(file_name, skip = 5, .name_repair = "unique_quiet") %>% rename(EIA_ID = `Plant Id`) -> EIA_data ) } if(yr == 2021){ file_name <- paste0(gnr_dir, "f923_", yr, "/EIA923_Schedules_2_3_4_5_M_12_2021_Final_Revision.xlsx") suppressWarnings( read_xlsx(file_name, skip = 5, .name_repair = "unique_quiet") |> rename(EIA_ID = `Plant Id`) -> EIA_data ) } # filter EIA file for hydro suppressWarnings( EIA_data |> select(EIA_ID, any_of(c("NET GENERATION (megawatthours)", "Net Generation (Megawatthours)", "Net Generation\r\n(Megawatthours)"))) -> EIA_data_ ) names(EIA_data_) <- c("EIA_ID", "MWh") EIA_data_ |> filter(EIA_ID %in% target_plants) |> summarise(MWh = sum(MWh, na.rm = T), .by = EIA_ID) -> EIA_hydro return( tibble(EIA_ID = target_plants) |> left_join(EIA_hydro, by = "EIA_ID") |> mutate(year = !!yr) ) } }) -> EIA_hydro_netgen_2001_2021 # generate table of hrs per year for computation of maximum output tibble( date = seq.Date(from = ymd("1970-01-01"), to = ymd("2021-12-31"), by = 1) ) |> mutate(year = year(date)) |> summarise(n_hrs = n() * 24, .by = year) -> hrs_per_year # combine nameplate and generation to get CF bind_rows( gen_1970_2000, EIA_hydro_netgen_2001_2021 |> rename(gen_MWh = MWh) ) |> left_join(plant_nameplate_MW_interpolated, by = join_by(EIA_ID, year)) |> left_join(hrs_per_year, join_by(year)) |> mutate(cap_MWh = nameplate * n_hrs, CF = gen_MWh / cap_MWh) -> gen_cap_CF_1970_2021 return(gen_cap_CF_1970_2021) }
_targets.R +12 −3 Original line number Diff line number Diff line Loading @@ -13,7 +13,9 @@ tar_option_set( "purrr", "furrr", "future", "sf") "sf", "foreign", "zoo") ) #options(clustermq.scheduler = "multisession") Loading @@ -30,7 +32,14 @@ list( format = "file" ), tar_target( EIA_annual_gen, get_EIA_annual_gen(xl_dir = EIA_529_906_920_923) EIA_860, "./data/EIA/Plant/", format = "file" ), tar_target( EIA_annual_gen_cap_CF_1970_2021, get_EIA_annual_gen(gnr_dir = EIA_529_906_920_923, plt_dir = EIA_860), format = "parquet" ) )
_targets/meta/meta +5 −2 Original line number Diff line number Diff line name|type|data|command|depend|seed|path|time|size|bytes|format|repository|iteration|parent|children|seconds|warnings|error .Random.seed|object|1ce8be4dd88ddeeb||||||||||||||| EIA_529_906_920_923|stem|429fb55d18257b0e|7e8ad8e942ac6d8d|ef46db3751d8e999|-1754950433|./data/EIA/Generation/|t19552.6038571127s|db7d75b1b9e45804|24576|file|local|vector|||0.82|| EIA_annual_gen|stem|d131862dc333587a|058b1fa983426efc|7647f84d89c236d8|-1955140278||t19552.6216109002s|44e327d1ee1978d7|43|rds|local|vector|||0|| get_EIA_annual_gen|function|6f020b783a1d9451||||||||||||||| EIA_860|stem|db95ac5d1da1bd03|fd2da67a7010fb85|ef46db3751d8e999|-1646985544|./data/EIA/Plant/|t19552.6038846689s|c8fc69c6c41e109f|12288|file|local|vector|||2.19|| EIA_annual_gen|stem|8df8ad9ee42d49d6|922aefb19c709325|b0d9bfb57fa52bff|-1955140278||t19555.5959348734s|c08769dc4ce04be3|812175|parquet|local|vector|||69.36|| EIA_annual_gen_cap_CF_1970_2021|stem|8df8ad9ee42d49d6|922aefb19c709325|b0d9bfb57fa52bff|-623511298||t19555.6015050991s|c08769dc4ce04be3|812175|parquet|local|vector|||68.46|| get_EIA_annual_gen|function|1f87eeb76f308b73|||||||||||||||
