Description and few other things

rOpenGov · Jun 6, 2024 · 00e9ed9 · 00e9ed9
1 parent 268ea3a
commit 00e9ed9
Show file tree

Hide file tree

Showing 5 changed files with 22 additions and 53 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,12 +1,11 @@
 Package: kelaopendata
 Type: Package
-Title: What the Package Does (Title Case)
-Version: 0.1.0001
-Date: 2024-04-12
+Title: Access open data by National social insurance institution of Finland
+Version: 0.1.0002
+Date: 2024-06-06
 Author: Markus Kainu
 Maintainer: Markus Kainu <markus.kainu@kapsi.fi>
-Description: More about what it does (maybe more than one line)
-    Use four spaces when indenting paragraphs within the Description.
+Description: Designed to simplify and speed up access to open data from National social insurance institution of Finland (KELA) published at <https://www.avoindata.fi/data/fi/organization/kela>, the kelaopendata package offers researchers and analysts a set of tools to obtain data and metadata for a wide range of applications.
 License: Artistic-2.0 | file LICENSE
 URL: https://ropengov.github.io/kelaopendata/, https://github.com/rOpenGov/kelaopendata
 BugReports: https://github.com/rOpenGov/kelaopendata/issues

diff --git a/NAMESPACE b/NAMESPACE
@@ -13,8 +13,10 @@ importFrom(DBI,dbGetQuery)
 importFrom(ckanr,ckanr_setup)
 importFrom(ckanr,package_search)
 importFrom(dplyr,"%>%")
+importFrom(dplyr,arrange)
 importFrom(dplyr,as_tibble)
 importFrom(dplyr,bind_rows)
 importFrom(dplyr,filter)
+importFrom(dplyr,mutate)
 importFrom(glue,glue)
 importFrom(jsonlite,fromJSON)
diff --git a/R/ckan.R b/R/ckan.R
@@ -47,7 +47,7 @@ list_ckan <- function(org = "Kansaneläkelaitos", n = 100){
 #'
 #' @return data.frame
 #'
-#' @importFrom dplyr bind_rows
+#' @importFrom dplyr bind_rows arrange mutate
 #'
 #' @export
 #'
@@ -57,12 +57,15 @@ list_datasets <- function(){
   for (i in seq(dsets$results)){
     tmp <- dsets$results[i]
     dlist[[i]] <- data.frame(
+      modified = tmp[[1]]$metadata_modified,
       name = tmp[[1]]$name,
-      id = tmp[[1]]$id,
-      modified = tmp[[1]]$metadata_modified
+      id = tmp[[1]]$id
     )
   }
-  res <- do.call("bind_rows", dlist) %>% as_tibble()
+  res <- do.call("bind_rows", dlist) %>%
+    as_tibble() %>%
+    mutate(modified = as.Date(modified)) %>%
+    arrange(desc(modified))
   return(res)
 }
 

diff --git a/README.Rmd b/README.Rmd
@@ -14,54 +14,18 @@ Install
 remotes::install_github("rOpenGov/kelaopendata")
 ```
 
-
-
 ## List datasets
 
 ```{r}
 library(kelaopendata)
 dsets <- list_datasets()
-dsets
-```
-
-## Metadata
-
-Get metadata 
-
-```{r}
-meta <- get_metadata(data_id = dsets$id[1])
-meta[1:4]
-```
-
-
-Resources
-
-```{r}
-jsonlite::toJSON(meta$resources, pretty = T)
+print(dsets, n = 50)
 ```
 
-
-## Download data
-
-Get first 10 rows of data
-
-```{r}
-get_data(data_id = dsets$id[1], sql = "LIMIT 10")
-```
-
-
-Whole dataset
-
-```{r}
-whole_data <- get_data(data_id = dsets$id[1])
-whole_data
-```
-
-
-Subset only men from municipality Veteli from year 2023
+Download the first 10 rows of the most recently modified data
 
 ```{r}
-veteli23 <- get_data(data_id = dsets$id[1], sql = "WHERE kunta_nro = 924 AND vuosi = 2023 AND sukupuoli = 'Mies'")
-veteli23
+first_ten_rows <- get_data(data_id = dsets$id[1], sql = "LIMIT 10")
+first_ten_rows
 ```
 
diff --git a/vignettes/read_data.Rmd b/vignettes/read_data.Rmd
@@ -1,5 +1,5 @@
 ---
-title: "Reading data using kelaopendata"
+title: "Fetching data using kelaopendata"
 author: "Markus Kainu"
 date: "`r Sys.Date()`"
 output: rmarkdown::html_vignette
@@ -66,18 +66,19 @@ First 10 rows
 
 ```{r}
 get_data(data_id = id_opintotuki, sql = "LIMIT 10")
+dat <- get_data(data_id = id_opintotuki)
 ```
 
 Filter using SQL
 
 ```{r}
 yliopistot <- get_data(data_id = id_opintotuki, 
                        sql = "WHERE kunta_nro = 853 AND 
-                       aikatyyppi = 'Kuukausi' AND 
-                       etuus = 'Opintolainan valtiontakaus' AND 
+                       aikatyyppi = 'Vuosi' AND 
+                       etuus = 'Yhteensä' AND 
                        oppilaitos_peruste = 'Viimeisin oppilaitos' AND 
                        oppilaitosaste = 'Yliopistot'")
-yliopistot
+yliopistot %>% count(vuosi)
 ```
 
 Plot