提交: 171bb0230e69fb3df7af8ab5f22703244d890119 - myprojects-hg-reborn (hg)

Commit MetaInfo

• 修订版: 171bb0230e69fb3df7af8ab5f22703244d890119 (tree)
• 时间: 2023-01-31 06:19:29
• 作者: Lorenzo Isella <lorenzo.isella@gmai...>
• Commiter: Lorenzo Isella

Log Message

I added the option to save/read the ESTAT downloaded data.

更改概述

• modified: R-codes/process_tam_RO.R

差异

diff -r 570dc39f106f -r 171bb0230e69 R-codes/process_tam_RO.R
--- a/R-codes/process_tam_RO.R	Sun Jan 29 21:39:00 2023 +0100
+++ b/R-codes/process_tam_RO.R	Mon Jan 30 22:19:29 2023 +0100
@@ -21,10 +21,15 @@
 ##     clean_names
 
 
+read_estat <- 0
+
 df_ro_ini <- read_csv("Copy_of_ExportTransparenta_20220919.csv")  |> 
     clean_names()
 
+repeated_entries <- df_ro_ini |>
+    get_dupes_short()
 
+save_excel(repeated_entries, "repeated_entries_Romania.xlsx")
 
 ## tam <- read_parquet("tam.parquet") |> 
 ##     slice(1:5)
@@ -63,7 +68,8 @@
 
 df_ro_name <- df_ro |> 
     rename_many(df_name$english,ini_names) |> 
-    clean_data() |> 
+    clean_data( remove_duplicated_rows=F
+               ) |> 
     select(-national_identification_for_other_categories_foreign_undertakings) |> 
     mutate(aid_award_granted_date=dmy(aid_award_granted_date)) |> 
     mutate(year=year(aid_award_granted_date),
@@ -83,12 +89,21 @@
 
 
 
-
+if (read_estat!=1){
 
 all_rates_ini <- estat_retrieval(query) |> 
     clean_names() |> 
     select(time_period, obs_value) |> 
     mutate(time_period=as.numeric(time_period))
+    saveRDS(all_rates_ini, "all_rates.RDS")
+
+
+    
+} else{
+
+all_rates_ini <- readRDS("all_rates.RDS")
+    
+}
 
 
 
@@ -166,6 +181,8 @@
 covid <- read_excel("SA-Covid19.xlsx") |>
     clean_names()
 
+nace <- readRDS("../nace_codes/df_nace.RDS") |>
+    select(-code)
 
 df.out <- df_temp  |>
     rename("aid_award_instrument"="aid_award_instrument_other_english") |> 
@@ -175,8 +192,16 @@
            granted_value_extended_eur=granted_aid_absolute_eur,
            is_covid_case=if_else(case_reference %in% covid$case_reference, "Yes", "No")) |>
     mutate(granted_value_extended_eur=if_else(is_covid_case=="No", granted_value_extended_eur, NA_real_)) |>
-    filter(year!=2022)
+    filter(year!=2022) |>
+    mutate(beneficiary_sector=if_else(nchar(beneficiary_sector)==3,
+             paste("0", beneficiary_sector, sep=""), beneficiary_sector)) |> 
+    left_join(y=nace, by=c("beneficiary_sector"="code2")) |>
+    mutate(beneficiary_sector=paste(beneficiary_sector, description,
+                                    sep=" - ")) |>
+    select(-description)
 
+## test <- df.out |>
+##     filter(is.na(description))
 
 
 save_excel(df.out, "romania_extra_tam.xlsx")