Commit: 7ad70b93c0eb3ab7b535f564e08518313d4eaa1a - myprojects-hg-reborn (hg)

Commit MetaInfo

• Revision: 7ad70b93c0eb3ab7b535f564e08518313d4eaa1a (tree)
• Time: 2023-05-05 19:28:32
• Author: Lorenzo Isella <lorenzo.isella@gmai...>
• Commiter: Lorenzo Isella

Log Message

I merged some heads.

Change Summary

• modified: R-codes/read_polish_tam_new.R

Incremental Difference

diff -r e946b59fa3b6 -r 7ad70b93c0eb R-codes/read_polish_tam_new.R
--- a/R-codes/read_polish_tam_new.R	Fri May 05 12:27:18 2023 +0200
+++ b/R-codes/read_polish_tam_new.R	Fri May 05 12:28:32 2023 +0200
@@ -6,7 +6,7 @@
 library(stringr)
 library(lubridate)
 library(RJSDMX)
-library(haven)
+## library(haven)
 library(arrow)
 
 
@@ -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")) |>
@@ -134,37 +142,41 @@
 
 
 
-aid_instr_new <- c(
-"Interest subsidy",
-"Direct grant/ Interest rate subsidy",
-"Guarantee",
-"Other",
-"Soft loan",
-"Other forms of tax advantage",
-"Other forms of tax advantage",
-"Other",
-"Other",
-"Other forms of tax advantage",
-"Loan/ Repayable advances",
-"Loan/ Repayable advances",
-"Direct grant/ Interest rate subsidy",
-"Other",
-"Other forms of tax advantage",
-"Other forms of tax advantage",
-"Soft loan",
-"Provision of risk capital",
-"Repayable advances",
-"Other",
-"Direct grant",
-"Tax advantage or tax exemption"
-)
+## aid_instr_new <- c(
+## "Interest subsidy",
+## "Direct grant/ Interest rate subsidy",
+## "Guarantee",
+## "Other",
+## "Soft loan",
+## "Other forms of tax advantage",
+## "Other forms of tax advantage",
+## "Other",
+## "Other",
+## "Other forms of tax advantage",
+## "Loan/ Repayable advances",
+## "Loan/ Repayable advances",
+## "Direct grant/ Interest rate subsidy",
+## "Other",
+## "Other forms of tax advantage",
+## "Other forms of tax advantage",
+## "Soft loan",
+## "Provision of risk capital",
+## "Repayable advances",
+## "Other",
+## "Direct grant",
+## "Tax advantage or tax exemption"
+## )
+
+
+aid_instr_new <- read_csv("instruments.csv") |>
+    pull(Interpretation)
 
 
 aid_instr <- df_sel |>
     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),
@@ -215,17 +227,20 @@
     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")