Update methodology for co2 footprint per benchmark (#45)

* Update methodology for co2 footprint per benchmark * refactor * refactor
2DegreesInvesting · Sep 2, 2024 · 994d70a · 994d70a
1 parent c0a9905
commit 994d70a
Show file tree

Hide file tree

Showing 5 changed files with 37 additions and 34 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -11,7 +11,7 @@ URL: https://github.com/2DegreesInvesting/tiltDataAnalysis,
 BugReports: https://github.com/2DegreesInvesting/tiltDataAnalysis/issues
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
 Suggests: 
     testthat (>= 3.0.0)
 Config/testthat/edition: 3

diff --git a/R/calculate_co2_descriptive_analysis_per_benchmark.R b/R/calculate_co2_descriptive_analysis_per_benchmark.R
@@ -1,10 +1,10 @@
-#' Calculate the descriptive analysis of co2_footprint per benchmark
+#' Calculate the descriptive analysis of co2_footprint per grouping_emission
 #'
 #' This function calculates the descriptive analysis of co2_footprint per
-#' benchmark using product-level output of Emissions profile indicator.
+#' grouping_emission using product-level output of Emissions profile indicator.
 #'
 #' @param emission_product A dataframe. Product-level output of Emissions profile
-#' @param benchmark A string. Benchmarks of Emissions profile
+#' @param grouping_emission A string. Benchmarks of Emissions profile
 #'
 #' @return A dataframe
 #' @export
@@ -14,37 +14,37 @@
 #' emission_product_example <- example_emission_product_co2_des_analysis()
 #' emission_product_example
 #'
-#' # Calculates the descriptive analysis for benchmark "tilt_subsector"
+#' # Calculates the descriptive analysis for grouping_emission "tilt_subsector"
 #' calculate_co2_descriptive_analysis_per_benchmark(
 #'   emission_product_example,
 #'   "tilt_subsector"
 #' )
-calculate_co2_descriptive_analysis_per_benchmark <- function(emission_product, benchmark) {
-  if (benchmark == "all") {
-    select_benchmarks <- c("benchmark", "co2_footprint", "ep_product")
+calculate_co2_descriptive_analysis_per_benchmark <- function(emission_product, grouping_emission) {
+  if (grouping_emission == "all") {
+    select_benchmarks <- c("grouping_emission", "co2_footprint", "activity_uuid_product_uuid")
     group_benchmark <- NULL
-  } else if (benchmark == "unit_isic_4digit") {
-    select_benchmarks <- c("unit", "isic_4digit", "benchmark", "co2_footprint", "ep_product")
+  } else if (grouping_emission == "unit_isic_4digit") {
+    select_benchmarks <- c("unit", "isic_4digit", "grouping_emission", "co2_footprint", "activity_uuid_product_uuid")
     group_benchmark <- c("unit", "isic_4digit")
-  } else if (benchmark == "unit_tilt_subsector") {
-    select_benchmarks <- c("tilt_sector", "unit", "tilt_subsector", "benchmark", "co2_footprint", "ep_product")
+  } else if (grouping_emission == "unit_tilt_subsector") {
+    select_benchmarks <- c("tilt_sector", "unit", "tilt_subsector", "grouping_emission", "co2_footprint", "activity_uuid_product_uuid")
     group_benchmark <- c("unit", "tilt_subsector")
   } else {
-    select_benchmarks <- c("tilt_sector", benchmark, "benchmark", "co2_footprint", "ep_product")
-    group_benchmark <- benchmark
+    select_benchmarks <- c("tilt_sector", grouping_emission, "grouping_emission", "co2_footprint", "activity_uuid_product_uuid")
+    group_benchmark <- grouping_emission
   }
 
   output <- emission_product |>
     select(all_of(select_benchmarks)) |>
     distinct() |>
-    filter(benchmark == benchmark) |>
-    select(-c("benchmark")) |>
-    mutate("# of distinct products" = n_distinct(.data$ep_product, na.rm = TRUE), .by = group_benchmark) |>
+    filter(grouping_emission == grouping_emission) |>
+    select(-c("grouping_emission")) |>
+    mutate("# of distinct products" = n_distinct(.data$activity_uuid_product_uuid, na.rm = TRUE), .by = group_benchmark) |>
     mutate("min CO2e" = min(.data$co2_footprint, na.rm = TRUE), .by = group_benchmark) |>
     mutate("max CO2e" = max(.data$co2_footprint, na.rm = TRUE), .by = group_benchmark) |>
     mutate("mean CO2e" = mean(.data$co2_footprint, na.rm = TRUE), .by = group_benchmark) |>
     mutate("median CO2e" = median(.data$co2_footprint, na.rm = TRUE), .by = group_benchmark) |>
-    select(-all_of(c("ep_product", "co2_footprint"))) |>
+    select(-all_of(c("activity_uuid_product_uuid", "co2_footprint"))) |>
     distinct()
 
   output[order(output[[1]], output[[2]]), ]

diff --git a/R/example_data.R b/R/example_data.R
@@ -24,15 +24,15 @@
 example_emission_product_co2_des_analysis <- function() {
   tribble(
   # styler: off
-          ~benchmark, ~tilt_sector, ~tilt_subsector, ~unit, ~isic_4digit, ~co2_footprint,   ~ep_product,
-    "tilt_subsector",      "group",     "chemicals",  "kg",     "'5555'",              1,       "water",
-    "tilt_subsector",      "group",     "chemicals",  "kg",     "'5555'",              4,  "television",
-    "tilt_subsector",      "group",     "chemicals",  "kg",     "'5555'",              9,      "tables",
-    "tilt_subsector",      "group",     "chemicals",  "kg",     "'5555'",              8, "electricity",
-    "tilt_subsector",      "group",     "chemicals",  "kg",     "'5555'",       NA_real_,        "meat",
-    "tilt_subsector",      "group",  "iron & steel",  "m3",     "'6666'",              1,      "tables",
-    "tilt_subsector",      "group",  "iron & steel",  "m3",     "'6666'",              2,       "water",
-    "tilt_subsector",      "group",  "iron & steel",  "m3",     "'6666'",              4,        "tent"
+  ~grouping_emission, ~tilt_sector, ~tilt_subsector, ~unit, ~isic_4digit, ~co2_footprint,      ~product, ~activity_uuid_product_uuid,
+    "tilt_subsector",      "group",     "chemicals",  "kg",     "'5555'",              1,       "water",                     "uuid1",
+    "tilt_subsector",      "group",     "chemicals",  "kg",     "'5555'",              4,  "television",                     "uuid2",
+    "tilt_subsector",      "group",     "chemicals",  "kg",     "'5555'",              9,      "tables",                     "uuid3",
+    "tilt_subsector",      "group",     "chemicals",  "kg",     "'5555'",              8, "electricity",                     "uuid4",
+    "tilt_subsector",      "group",     "chemicals",  "kg",     "'5555'",       NA_real_,        "meat",                     "uuid5",
+    "tilt_subsector",      "group",  "iron & steel",  "m3",     "'6666'",              1,      "tables",                     "uuid3",
+    "tilt_subsector",      "group",  "iron & steel",  "m3",     "'6666'",              2,       "water",                     "uuid1",
+    "tilt_subsector",      "group",  "iron & steel",  "m3",     "'6666'",              4,        "tent",                     "uuid6"
     # styler: on
   )
 }

diff --git a/man/calculate_co2_descriptive_analysis_per_benchmark.Rd b/man/calculate_co2_descriptive_analysis_per_benchmark.Rd
diff --git a/vignettes/articles/descriptive-analysis-co2_footprint_per_benchmark.Rmd b/vignettes/articles/descriptive-analysis-co2_footprint_per_benchmark.Rmd
@@ -71,7 +71,7 @@ kable(co2_tilt_subsector, align = "llccccc", caption = "Descriptive analysis for
 
 ```{r, echo=FALSE}
 lowest_co2 <- emission_product_example |>
-  select(all_of(c("ep_product", "co2_footprint"))) |>
+  select(all_of(c("product", "co2_footprint"))) |>
   distinct() |>
   arrange(.data$co2_footprint) |>
   head(5)
@@ -85,7 +85,7 @@ kable(lowest_co2, align = "lc", caption = "Five products with lowest CO2e values
 
 ```{r, echo=FALSE}
 highest_co2 <- emission_product_example |>
-  select(all_of(c("ep_product", "co2_footprint"))) |>
+  select(all_of(c("product", "co2_footprint"))) |>
   distinct() |>
   arrange(desc(.data$co2_footprint)) |>
   head(5)