Commit: 149f52fc5c3943c54eda036fdc1a9af05328ac1a - myprojects-hg-reborn (hg)

Commit MetaInfo

• Revision: 149f52fc5c3943c54eda036fdc1a9af05328ac1a (tree)
• Zeit: 2023-05-03 20:59:31
• Autor: Lorenzo Isella <lorenzo.isella@gmai...>
• Commiter: Lorenzo Isella

Log Message

Now the code can process the large tam from PL.

Ändern Zusammenfassung

• modified: R-codes/read_polish_tam_new.R

Diff

diff -r aaf0cf2df644 -r 149f52fc5c39 R-codes/read_polish_tam_new.R
--- a/R-codes/read_polish_tam_new.R	Mon Apr 24 11:09:10 2023 +0200
+++ b/R-codes/read_polish_tam_new.R	Wed May 03 13:59:31 2023 +0200
@@ -17,14 +17,20 @@
 
 read_estat <- 0
 
-df_ini1 <- read_csv("State_aid_in_Poland-2018-2019_above_500K_euro,_2020_above_100K_euro.csv"  ## , locale = readr::locale(encoding = "latin1")
-                   ) |>
-    clean_names()
+## df_ini1 <- read_csv("State_aid_in_Poland-2018-2019_above_500K_euro,_2020_above_100K_euro.csv"  ## , locale = readr::locale(encoding = "latin1")
+##                    ) |>
+##     clean_names()
 
-df_ini2 <- read_csv("2021-data/State_aid_in_Poland-2021_above_100K_euro.csv") |>
-    clean_names()
+## df_ini2 <- read_csv("2021-data/State_aid_in_Poland-2021_above_100K_euro.csv") |>
+##     clean_names()
 
-df_ini <- bind_rows(df_ini1, df_ini2)
+## df_ini <- bind_rows(df_ini1, df_ini2)
+
+
+df_ini <- read_csv("all-PL.csv", locale = readr::locale(encoding = "UTF-8" ## "latin1"
+                                                        ))
+
+## df_ini <- readRDS("all-PL.RDS")
 
 query <-     "ert_bil_eur_a/A.AVG.NAC.PLN"
 
@@ -112,6 +118,8 @@
     select(all_of(column_selection)) |>
     rename_many( new_columns## [1:14]
               , column_selection) |>
+    mutate(aid_award_created_date=parse_date_time(aid_award_created_date,c("dmy", "ymd"))) |> 
+    mutate(aid_award_granted_date=parse_date_time(aid_award_granted_date, c("dmy", "ymd"))) |> 
     mutate(year=year(aid_award_granted_date ),
            beneficiary_country="Poland") |>
     left_join(y=all_rates_ini, by=c("year"="time_period")) |>
@@ -164,7 +172,7 @@
     pull(aid_award_instrument) |>
     su()
 
-nace <- readRDS("../../nace_codes/df_nace.RDS") |>
+nace <- readRDS("df_nace.RDS") |>
     select(-code2)
 
 df_nace <- tibble(macro=seq_fixed_width(1:99,2),
@@ -199,8 +207,8 @@
 
 df_sel2 <- df_sel |>
     mutate(aid_award_ga_original=df_ini$udzielajacy_nazwa) |>
-    mutate(aid_award_instrument=recode_many(aid_award_instrument, aid_instr,
-                                            aid_instr_new)) |>
+    ## mutate(aid_award_instrument=recode_many(aid_award_instrument, aid_instr,
+    ##                                         aid_instr_new)) |>
     mutate(beneficiary_type=if_else(beneficiary_type %in% c("0","1","2"),
                                     "Small and medium-sized enterprises",
                                     "Only large enterprises")) |>
@@ -215,17 +223,20 @@
     left_join(y=df_nace, by=c("ben_sec2"="macro")) |>
     mutate(beneficiary_sector=paste(macro2, " - ", beneficiary_sector,
                                     sep="")) |>
-    select(-c(ben_sec2, macro2))
+    select(-c(ben_sec2, macro2)) |>
+    mutate(aid_award_granted_date=as.Date(aid_award_granted_date),
+           aid_award_created_date=as.Date(aid_award_created_date),
+           national_identification_type=as.character(national_identification_type))
 
     
 
 
-saveRDS(df_sel2,"tam_PL_matched.RDS")
-write_csv(df_sel2, "tam_PL_matched.csv.gz")
-save_excel(df_sel2, "tam_PL_matched.xlsx")
+## saveRDS(df_sel2,"tam_PL_matched.RDS")
+## write_csv(df_sel2, "tam_PL_matched.csv.gz")
+## save_excel(df_sel2, "tam_PL_matched.xlsx")
 
 
-saveRDS(df_sel2,"tam_PL_matched_extended.RDS")
+## saveRDS(df_sel2,"tam_PL_matched_extended.RDS")
 write_parquet(df_sel2,"tam_PL_matched_extended.parquet")