changes 09/10

- I added a “the” for "USA", "GBR", "CZE", "SVK", "NLD" in the file fig3_text_FINAL.xlsx - Canada, Chile, Ireland and Mexico I made sure figures are using the most update sources (countryprofile_fig3_alt.xlsx and countryprofile_fig4_alt.xlsx)
oecd-cfe-eds · Oct 9, 2023 · 800b50c · 800b50c
1 parent b793d0a
commit 800b50c
Show file tree

Hide file tree

Showing 5 changed files with 130 additions and 138 deletions.
diff --git a/data/fig3_text_FINAL.xlsx b/data/fig3_text_FINAL.xlsx
diff --git a/tl0-irl.qmd b/tl0-irl.qmd
@@ -59,19 +59,25 @@ read_html_table(ctry)
 
 ```{r fig3}
 # read ----
-
-finp <- if (any(ctry %in% c("AUS", "CAN", "COL", "CHE", "CHL", "IRL", "MEX"))) {
-  "data/countryprofile_option1_addon.xlsx"
-} else {
-  "data/countryprofile_option1.xlsx"
-}
-
-dp1 <- read_excel(finp, sheet = ctry) %>%
+# 
+# finp <- if (any(ctry %in% c("AUS", "CAN", "COL", "CHE", "CHL", "IRL", "MEX"))) {
+#   "data/countryprofile_option1_addon.xlsx"
+# } else {
+#   "data/countryprofile_option1.xlsx"
+# }
+# 
+# dp1 <- read_excel(finp, sheet = ctry) %>%
+#   clean_names()
+# 
+# # tidy ----
+# 
+# colnames(dp1) <- str_replace(colnames(dp1), tolower(ctry), "country")
+
+dp1 <- read_excel("data/countryprofile_fig3_alt.xlsx", sheet = ctry) %>%
+  select(time, pw_lp, pw_hp) %>% 
   clean_names()
 
-# tidy ----
-
-colnames(dp1) <- str_replace(colnames(dp1), tolower(ctry), "country")
+colnames(dp1) <- c("time", "pw_lp_country", "pw_hp_country")
 
 dp11 <- dp1 %>%
   select(time, matches("country")) %>%
@@ -154,28 +160,24 @@ ggplotly(fig3_1) %>%
 
 ```{r fig4}
 # read ----
-# %%%% WE NEED THIS FILE AND NOT countryprofile_fig3_alt.xlsx WITH 2 CATEGORIES %%%%
-dp2 <- read_excel("data/countryprofile_option2_addon.xlsx", sheet = ctry) %>%
+
+dp2 <- read_excel("data/countryprofile_fig4_alt.xlsx", sheet = ctry) %>%
   clean_names()
 
 # tidy ----
 
-colnames(dp2) <- str_replace(colnames(dp2), tolower(ctry), "country")
-
-# colnames(dp2) <- c("time", "pw_lp_country", "pw_hp_country")
-
 dp21 <- dp2 %>%
-  select(time, matches("country")) %>%
+  select(time, starts_with("share_")) %>%
   pivot_longer(-time) %>%
   rename(value_country = value)
 
 dp21 <- dp21 %>%
   mutate(
     name = case_when(
-      name == "share_tgoods_lp_country" ~ paste(ctry, "TG LP"),
-      name == "share_tgoods_hp_country" ~ paste(ctry, "TG HP"),
-      name == "share_tserv_lp_country" ~ paste(ctry, "TS LP"),
-      name == "share_tserv_hp_country" ~ paste(ctry, "TS HP")
+      name == "share_tgoods_lp" ~ paste(ctry, "TG LP"),
+      name == "share_tgoods_hp" ~ paste(ctry, "TG HP"),
+      name == "share_tserv_lp" ~ paste(ctry, "TS LP"),
+      name == "share_tserv_hp" ~ paste(ctry, "TS HP")
     )
   )
 
@@ -257,8 +259,6 @@ dp21_2 <- dp21 %>%
     category2 = str_replace_all(category2, as.character(min(yrs)), "minyr"),
     category2 = str_replace_all(category2, as.character(max(yrs)), "maxyr")
   ) %>%
-  # remove all after productivy in category2
-  # mutate(category2 = str_replace_all(category2, "productivity.*", "productivity")) %>%
   pivot_wider(names_from = category2, values_from = value_country) %>%
   clean_names()
 

diff --git a/tl2-can.qmd b/tl2-can.qmd
@@ -328,18 +328,24 @@ ggplotly(fig1) %>%
 ```{r can_fig2}
 # read ----
 
-finp <- if (any(ctry %in% c("AUS", "CAN", "COL", "CHE", "CHL", "IRL", "MEX"))) {
-  "data/countryprofile_option1_addon.xlsx"
-} else {
-  "data/countryprofile_option1.xlsx"
-}
-
-dp1 <- read_excel(finp, sheet = ctry) %>%
+# finp <- if (any(ctry %in% c("AUS", "CAN", "COL", "CHE", "CHL", "IRL", "MEX"))) {
+#   "data/countryprofile_option1_addon.xlsx"
+# } else {
+#   "data/countryprofile_option1.xlsx"
+# }
+# 
+# dp1 <- read_excel(finp, sheet = ctry) %>%
+#   clean_names()
+# 
+# # tidy ----
+# 
+# colnames(dp1) <- str_replace(colnames(dp1), tolower(ctry), "country")
+
+dp1 <- read_excel("data/countryprofile_fig3_alt.xlsx", sheet = ctry) %>%
+  select(time, pw_lp, pw_hp) %>% 
   clean_names()
 
-# tidy ----
-
-colnames(dp1) <- str_replace(colnames(dp1), tolower(ctry), "country")
+colnames(dp1) <- c("time", "pw_lp_country", "pw_hp_country")
 
 dp11 <- dp1 %>%
   select(time, matches("country")) %>%
@@ -440,28 +446,24 @@ ggplotly(fig2) %>%
 
 ```{r can_fig3}
 # read ----
-# %%%% WE NEED THIS FILE AND NOT countryprofile_fig3_alt.xlsx WITH 2 CATEGORIES %%%%
-dp2 <- read_excel("data/countryprofile_option2_addon.xlsx", sheet = ctry) %>%
+
+dp2 <- read_excel("data/countryprofile_fig4_alt.xlsx", sheet = ctry) %>%
   clean_names()
 
 # tidy ----
 
-colnames(dp2) <- str_replace(colnames(dp2), tolower(ctry), "country")
-
-# colnames(dp2) <- c("time", "pw_lp_country", "pw_hp_country")
-
 dp21 <- dp2 %>%
-  select(time, matches("country")) %>%
+  select(time, starts_with("share_")) %>%
   pivot_longer(-time) %>%
   rename(value_country = value)
 
 dp21 <- dp21 %>%
   mutate(
     name = case_when(
-      name == "share_tgoods_lp_country" ~ paste(ctry, "TG LP"),
-      name == "share_tgoods_hp_country" ~ paste(ctry, "TG HP"),
-      name == "share_tserv_lp_country" ~ paste(ctry, "TS LP"),
-      name == "share_tserv_hp_country" ~ paste(ctry, "TS HP")
+      name == "share_tgoods_lp" ~ paste(ctry, "TG LP"),
+      name == "share_tgoods_hp" ~ paste(ctry, "TG HP"),
+      name == "share_tserv_lp" ~ paste(ctry, "TS LP"),
+      name == "share_tserv_hp" ~ paste(ctry, "TS HP")
     )
   )
 
@@ -470,57 +472,57 @@ dp21 <- dp21 %>%
 yrs <- sort(unique(dp21$time))
 yrs <- seq(min(yrs), max(yrs), 1)
 
-# tghpgrew <- dp21 %>%
-#   filter(
-#     name == paste(ctry, "TG HP"),
-#     time %in% c(min(yrs), max(yrs))
-#   ) %>%
-#   summarise(grew = value_country - lag(value_country)) %>%
-#   drop_na() %>%
-#   pull() %>%
-#   round(1)
-
-# tglpgrew <- dp21 %>%
-#   filter(
-#     name == paste(ctry, "TG LP"),
-#     time %in% c(min(yrs), max(yrs))
-#   ) %>%
-#   summarise(grew = value_country - lag(value_country)) %>%
-#   drop_na() %>%
-#   pull() %>%
-#   round(1)
-
-# tghpdiff <- tghpgrew - tglpgrew
-# tghpmore <- ifelse(tghpdiff > 0, "grew", "declined")
-
-# tglpdiff <- tglpgrew - tglpgrew
-# tglpmore <- ifelse(tglpdiff > 0, "grew", "declined")
-
-# tshpgrew <- dp21 %>%
-#   filter(
-#     name == paste(ctry, "TS HP"),
-#     time %in% c(min(yrs), max(yrs))
-#   ) %>%
-#   summarise(grew = value_country - lag(value_country)) %>%
-#   drop_na() %>%
-#   pull() %>%
-#   round(1)
-
-# tslpgrew <- dp21 %>%
-#   filter(
-#     name == paste(ctry, "TS LP"),
-#     time %in% c(min(yrs), max(yrs))
-#   ) %>%
-#   summarise(grew = value_country - lag(value_country)) %>%
-#   drop_na() %>%
-#   pull() %>%
-#   round(1)
-
-# tshpdiff <- tshpgrew - tslpgrew
-# tshpmore <- ifelse(tshpdiff > 0, "grew", "declined")
-
-# tslpdiff <- tslpgrew - tslpgrew
-# tslpmore <- ifelse(tslpdiff > 0, "grew", "declined")
+tghpgrew <- dp21 %>%
+  filter(
+    name == paste(ctry, "TG HP"),
+    time %in% c(min(yrs), max(yrs))
+  ) %>%
+  summarise(grew = value_country - lag(value_country)) %>%
+  drop_na() %>%
+  pull() %>%
+  round(1)
+
+tglpgrew <- dp21 %>%
+  filter(
+    name == paste(ctry, "TG LP"),
+    time %in% c(min(yrs), max(yrs))
+  ) %>%
+  summarise(grew = value_country - lag(value_country)) %>%
+  drop_na() %>%
+  pull() %>%
+  round(1)
+
+tghpdiff <- tghpgrew - tglpgrew
+tghpmore <- ifelse(tghpdiff > 0, "grew", "declined")
+
+tglpdiff <- tglpgrew - tglpgrew
+tglpmore <- ifelse(tglpdiff > 0, "grew", "declined")
+
+tshpgrew <- dp21 %>%
+  filter(
+    name == paste(ctry, "TS HP"),
+    time %in% c(min(yrs), max(yrs))
+  ) %>%
+  summarise(grew = value_country - lag(value_country)) %>%
+  drop_na() %>%
+  pull() %>%
+  round(1)
+
+tslpgrew <- dp21 %>%
+  filter(
+    name == paste(ctry, "TS LP"),
+    time %in% c(min(yrs), max(yrs))
+  ) %>%
+  summarise(grew = value_country - lag(value_country)) %>%
+  drop_na() %>%
+  pull() %>%
+  round(1)
+
+tshpdiff <- tshpgrew - tslpgrew
+tshpmore <- ifelse(tshpdiff > 0, "grew", "declined")
+
+tslpdiff <- tslpgrew - tslpgrew
+tslpmore <- ifelse(tslpdiff > 0, "grew", "declined")
 
 dp21 <- dp21 %>%
   mutate(category = gsub(paste0("^OECD |^", ctry, " "), "", name))

diff --git a/tl2-chl.qmd b/tl2-chl.qmd
@@ -329,19 +329,25 @@ ggplotly(fig1) %>%
 
 ```{r chl_fig2}
 # read ----
-
-finp <- if (any(ctry %in% c("AUS", "CAN", "COL", "CHE", "CHL", "IRL", "MEX"))) {
-  "data/countryprofile_option1_addon.xlsx"
-} else {
-  "data/countryprofile_option1.xlsx"
-}
-
-dp1 <- read_excel(finp, sheet = ctry) %>%
+# 
+# finp <- if (any(ctry %in% c("AUS", "CAN", "COL", "CHE", "CHL", "IRL", "MEX"))) {
+#   "data/countryprofile_option1_addon.xlsx"
+# } else {
+#   "data/countryprofile_option1.xlsx"
+# }
+# 
+# dp1 <- read_excel(finp, sheet = ctry) %>%
+#   clean_names()
+# 
+# # tidy ----
+# 
+# colnames(dp1) <- str_replace(colnames(dp1), tolower(ctry), "country")
+
+dp1 <- read_excel("data/countryprofile_fig3_alt.xlsx", sheet = ctry) %>%
+  select(time, pw_lp, pw_hp) %>% 
   clean_names()
 
-# tidy ----
-
-colnames(dp1) <- str_replace(colnames(dp1), tolower(ctry), "country")
+colnames(dp1) <- c("time", "pw_lp_country", "pw_hp_country")
 
 dp11 <- dp1 %>%
   select(time, matches("country")) %>%
@@ -442,30 +448,26 @@ ggplotly(fig2) %>%
 <br>
 <br>
 
-```{r chl_fig3}
+```{r fig4}
 # read ----
-# %%%% WE NEED THIS FILE AND NOT countryprofile_fig3_alt.xlsx WITH 2 CATEGORIES %%%%
-dp2 <- read_excel("data/countryprofile_option2_addon.xlsx", sheet = ctry) %>%
+
+dp2 <- read_excel("data/countryprofile_fig4_alt.xlsx", sheet = ctry) %>%
   clean_names()
 
 # tidy ----
 
-colnames(dp2) <- str_replace(colnames(dp2), tolower(ctry), "country")
-
-# colnames(dp2) <- c("time", "pw_lp_country", "pw_hp_country")
-
 dp21 <- dp2 %>%
-  select(time, matches("country")) %>%
+  select(time, starts_with("share_")) %>%
   pivot_longer(-time) %>%
   rename(value_country = value)
 
 dp21 <- dp21 %>%
   mutate(
     name = case_when(
-      name == "share_tgoods_lp_country" ~ paste(ctry, "TG LP"),
-      name == "share_tgoods_hp_country" ~ paste(ctry, "TG HP"),
-      name == "share_tserv_lp_country" ~ paste(ctry, "TS LP"),
-      name == "share_tserv_hp_country" ~ paste(ctry, "TS HP")
+      name == "share_tgoods_lp" ~ paste(ctry, "TG LP"),
+      name == "share_tgoods_hp" ~ paste(ctry, "TG HP"),
+      name == "share_tserv_lp" ~ paste(ctry, "TS LP"),
+      name == "share_tserv_hp" ~ paste(ctry, "TS HP")
     )
   )
 
@@ -547,8 +549,6 @@ dp21_2 <- dp21 %>%
     category2 = str_replace_all(category2, as.character(min(yrs)), "minyr"),
     category2 = str_replace_all(category2, as.character(max(yrs)), "maxyr")
   ) %>%
-  # remove all after productivy in category2
-  # mutate(category2 = str_replace_all(category2, "productivity.*", "productivity")) %>%
   pivot_wider(names_from = category2, values_from = value_country) %>%
   clean_names()
 

diff --git a/tl2-mex.qmd b/tl2-mex.qmd
@@ -437,34 +437,26 @@ ggplotly(fig2) %>%
 <br>
 <br>
 
-```{r mex_fig3}
+```{r fig4}
 # read ----
 
-finp <- if (any(ctry %in% c("AUS", "CAN", "COL", "CHE", "CHL", "IRL", "MEX"))) {
-  "data/countryprofile_option2_addon.xlsx"
-} else {
-  "data/countryprofile_option2.xlsx"
-}
-
-dp2 <- read_excel(finp, sheet = ctry) %>%
+dp2 <- read_excel("data/countryprofile_fig4_alt.xlsx", sheet = ctry) %>%
   clean_names()
 
 # tidy ----
 
-colnames(dp2) <- str_replace(colnames(dp2), tolower(ctry), "country")
-
 dp21 <- dp2 %>%
-  select(time, matches("country")) %>%
+  select(time, starts_with("share_")) %>%
   pivot_longer(-time) %>%
   rename(value_country = value)
 
 dp21 <- dp21 %>%
   mutate(
     name = case_when(
-      name == "share_tgoods_lp_country" ~ paste(ctry, "TG LP"),
-      name == "share_tgoods_hp_country" ~ paste(ctry, "TG HP"),
-      name == "share_tserv_lp_country" ~ paste(ctry, "TS LP"),
-      name == "share_tserv_hp_country" ~ paste(ctry, "TS HP")
+      name == "share_tgoods_lp" ~ paste(ctry, "TG LP"),
+      name == "share_tgoods_hp" ~ paste(ctry, "TG HP"),
+      name == "share_tserv_lp" ~ paste(ctry, "TS LP"),
+      name == "share_tserv_hp" ~ paste(ctry, "TS HP")
     )
   )
 
@@ -546,8 +538,6 @@ dp21_2 <- dp21 %>%
     category2 = str_replace_all(category2, as.character(min(yrs)), "minyr"),
     category2 = str_replace_all(category2, as.character(max(yrs)), "maxyr")
   ) %>%
-  # remove all after productivy in category2
-  # mutate(category2 = str_replace_all(category2, "productivity.*", "productivity")) %>%
   pivot_wider(names_from = category2, values_from = value_country) %>%
   clean_names()