提交: 4d0a0af349fed4acb9398346163be6281370ab6c - myprojects-hg-reborn (hg)

Commit MetaInfo

• 修订版: 4d0a0af349fed4acb9398346163be6281370ab6c (tree)
• 时间: 2024-09-18 02:59:18
• 作者: Lorenzo Isella <lorenzo.isella@gmai...>
• Commiter: Lorenzo Isella

Log Message

A cleanup of the script and its file management.

更改概述

• modified: R-codes/process_tam_RO.R

差异

diff -r 7fab32ec9541 -r 4d0a0af349fe R-codes/process_tam_RO.R
--- a/R-codes/process_tam_RO.R	Tue Sep 17 19:52:57 2024 +0200
+++ b/R-codes/process_tam_RO.R	Tue Sep 17 19:59:18 2024 +0200
@@ -26,14 +26,14 @@
 ## df_ro_ini <- read_csv("ExportTransparenta_20230403.csv")  |> 
 ##     clean_names()
 
-df_ro_ini <- read_csv("ExportTransparency.csv")  |> 
+df_ro_ini <- read_csv("../input/ExportTransparency.csv")  |> 
     clean_names()
 
 
 repeated_entries <- df_ro_ini |>
     get_dupes_short()
 
-save_excel(repeated_entries, "repeated_entries_Romania.xlsx")
+save_excel(repeated_entries, "../output/repeated_entries_Romania.xlsx")
 
 ## tam <- read_parquet("tam.parquet") |> 
 ##     slice(1:5)
@@ -56,29 +56,17 @@
     clean_names()  |> 
     select(-c(text_integral_masura, executanti))
 
-df_name <- read_csv("correspondence_modified.csv") |> 
+df_name <- read_csv("../input/correspondence_modified.csv") |> 
     clean_names()  |> 
     pattern_to_na("...")  |> 
     complete_data()
 
-## tam_names <- c("id", "case_reference", "aid_award_created_date", "aid_award_granted_date", 
-## "aid_award_published_date", "aid_award_reference", "case_title_original", 
-## "case_title_english", "main_procedure_type_code", "is_co_finance", 
-## "aid_award_objective", "aid_award_objective_other_english", "aid_award_instrument", 
-## "aid_award_instrument_other_english", "beneficiary_name", "beneficiary_name_english", 
-## "national_identification", "national_identification_type", "beneficiary_type", 
-## "beneficiary_country", "beneficiary_region", "beneficiary_sector", 
-## "granted_aid_absolute_eur", "nominal_aid_absolute_eur", "granted_range_eur", 
-## "aid_award_ga_original", "aid_award_ga_english", "aid_award_nuts_code", 
-## "creator_country", "year", "granted_value_extended_eur", "nominal_value_extended_eur", 
-## "is_covid_case")
-    ## names(tam)
 
 
 ini_names <- names(df_ro)
 
 
-covid <- read_excel("SA-Covid19.xlsx") |> 
+covid <- read_csv("../../tam_arrow/input/csv_files/SA-Covid19.csv") |> 
     clean_names() |> 
     filter(member_state_2_letter_code=="RO")
 
@@ -119,19 +107,19 @@
     clean_names() |> 
     select(time_period, obs_value) |> 
     mutate(time_period=as.numeric(time_period))
-    saveRDS(all_rates_ini, "all_rates.RDS")
+    saveRDS(all_rates_ini, "../input/all_rates.RDS")
 
 
     
 } else{
 
-all_rates_ini <- readRDS("all_rates.RDS")
+all_rates_ini <- readRDS("../input/all_rates.RDS")
     
 }
 
 
 
-aid <- read_csv("aid_type_modified.csv") |> 
+aid <- read_csv("../input/aid_type_modified.csv") |> 
     complete_data()  |> 
     mutate(aid_instrument_rom=tolower(aid_instrument_rom))
 
@@ -202,10 +190,10 @@
 ##     slice(6:nrow(.)) 
 
 
-covid <- read_excel("SA-Covid19.xlsx") |>
-    clean_names()
+## covid <- read_excel("SA-Covid19.xlsx") |>
+##     clean_names()
 
-nace <- readRDS("../nace_codes/df_nace.RDS") |>
+nace <- readRDS("../input/df_nace.RDS") |>
     select(-code)
 
 df_nace <- tibble(macro=seq_fixed_width(1:99,2),
@@ -260,13 +248,19 @@
 
 
 
-save_excel(df.out, "romania_extra_tam.xlsx")
+save_excel(df.out, "../output/romania_extra_tam.xlsx")
 
-write_csv(df.out, "romania_extra_tam.csv.gz")
-write_csv(df.out, "romania_extra_tam.csv")
+write_csv(df.out, "../output/romania_extra_tam.csv.gz")
+write_csv(df.out, "../output/romania_extra_tam.csv")
 ## write_dta(df.out, "romania_extra_tam.dta")
-saveRDS(df.out, "romania_extra_tam.RDS")
+saveRDS(df.out, "../output/romania_extra_tam.RDS")
 
-write_parquet(df.out, "romania_extra.parquet")
+remove_file("../output/romania_extra.parquet")
+write_parquet(df.out, "../output/romania_extra.parquet")
+
+remove_file("../../tam_arrow/input/parquet-files/romania/romania_extra.parquet")
+
+write_parquet(df.out, "../../tam_arrow/input/parquet-files/romania/romania_extra.parquet")
+
 
 print("So far so good")