Merge pull request #96 from statisticsnorway/derive-external

Inital setup

Author: Kss2k

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ssb-nudb-config"
-version = "2026.2.9"  # Year.Month.Patch - So the last number is not day of month, but patch number within month
+version = "2026.2.11"  # Year.Month.Patch - So the last number is not day of month, but patch number within month
 description = "The config for NUDB - Nasjonal utdanningsdatabase"
 authors = [{ name = "Markus Storeide", email = "rku@ssb.no" }]
 maintainers = [{ name = "Statistics Norway, Education statistics Department (360)" }]

src/nudb_config/config_tomls/variables.toml

@@ -41,14 +41,6 @@ variables_sort_unit = [
 		klass_codelist = 0  # This means that the variable is never supposed to have a klass_codelist or klass_variant or similar.
 
 
-	[variables.pers_kjoenn]
-		unit = "pers"
-		dtype = "STRING"
-		description_short = "kjønn"
-		length = [1]
-		klass_codelist = 2
-		renamed_from = ["kjoenn"]
-
 #################
 # Datavariabler #
 #################
@@ -72,14 +64,6 @@ variables_sort_unit = [
 # Tidskolonner #
 ################
 
-	[variables.pers_foedselsdato]
-		unit = "tid"
-		dtype = "DATETIME"
-		description_short = "fødselsdato"
-		renamed_from = ["fodt_dato", "fodtdato", "fodselsdato", "foedselsdato"]
-		klass_codelist = 0  # This means that the variable is never supposed to have a klass_codelist or klass_variant or similar.
-
-
 
     [variables.utd_aktivitet_start]
         unit = "tid"

src/nudb_config/config_tomls/variables_derived_external.toml

@@ -0,0 +1,33 @@
+[variables.pers_kjoenn]
+	unit = "pers"
+	dtype = "STRING"
+	description_short = "kjønn"
+	length = [1]
+	klass_codelist = 2
+	renamed_from = ["kjoenn"]
+    derived_from = ["snr"]
+    derived_join_keys = ["snr"]
+    derived_uses_datasets = ["freg_situttak"]
+
+
+[variables.pers_foedselsdato]
+	unit = "tid"
+	dtype = "DATETIME"
+	description_short = "fødselsdato"
+	renamed_from = ["fodt_dato", "fodtdato", "fodselsdato", "foedselsdato"]
+	klass_codelist = 0  # This means that the variable is never supposed to have a klass_codelist or klass_variant or similar.
+    derived_from = ["snr"]
+    derived_join_keys = ["snr"]
+    derived_uses_datasets = ["freg_situttak"]
+
+
+[variables.pers_invkat]
+    unit = "pers"
+    dtype = "STRING"
+    description_short = "innvandringskategori"
+    length = [1]
+    renamed_from = ["invkat"]
+    klass_codelist = 82
+    derived_from = ["snr"]
+    derived_join_keys = ["snr"]
+    derived_uses_datasets = ["innvbef"]

src/nudb_config/config_tomls/variables_label.toml

@@ -8,9 +8,10 @@
 	dtype = "STRING"
 	derived_from = ["utd_datakilde"]
 
-
-
-
+[variables.pers_invkat_label]
+    unit = "pers"
+    dtype = "STRING"
+    derived_from = ["pers_invkat"]
 
 #############################
 # Fagvariabler / nuskatalog #