Update

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ssb-arbmark-fagfunksjoner"
-version = "0.0.24"
+version = "0.0.25"
 description = "SSB Arbeidsmarked og lønn Fag-fellesfunksjoner"
 authors = ["Jan Sebastian Rothe <[email protected]>"]
 license = "MIT"

src/arbmark/__init__.py

@@ -2,7 +2,6 @@
 
 from arbmark.functions.aggregation import proc_sums
 from arbmark.functions.categorize_ranges import categorize_ranges
-from arbmark.functions.files import read_latest
 from arbmark.functions.interval import pinterval
 from arbmark.functions.merge import indicate_merge
 from arbmark.functions.quarter import first_last_date_quarter

src/arbmark/groups/sector.py

@@ -9,44 +9,35 @@
 import pandas as pd
 
 if TYPE_CHECKING:
-    PdSeriesInt = pd.Series[int]  # type: ignore[misc]
     PdSeriesStr = pd.Series[str]  # type: ignore[misc]
-    NpArrayInt = npt.NDArray[np.int_]  # type: ignore[misc]
     NpArrayStr = npt.NDArray[np.str_]  # type: ignore[misc]
 else:
-    PdSeriesInt = pd.Series
     PdSeriesStr = pd.Series
-    NpArrayInt = npt.NDArray
     NpArrayStr = npt.NDArray
 
 
-def sektor2_grp(
-    sektor: PdSeriesStr, undersektor: PdSeriesStr, display: str = "label"
-) -> NpArrayStr:
-    """Categorize a pandas Series of sectors and subsectors into predefined groups.
+def sektor2_grp(sektor: PdSeriesStr, display: str = "label") -> NpArrayStr:
+    """Categorize a pandas Series of sectors into predefined groups.
 
     Parameters:
         sektor: A pandas Series containing the sector codes.
-        undersektor: A pandas Series containing the subsector codes.
         display: If 'label', returns group labels; if 'number', returns keys;
                        for any other string, returns a combination of keys and labels.
 
     Returns:
-        A numpy Array where the original sector and subsectors are replaced by group labels or keys.
+        A numpy Array where the original sector is replaced by group labels or keys.
     """
     # Define the conditions for each group
     conditions = [
         (sektor == "6100").to_numpy(),
-        np.logical_and(sektor == "6500", undersektor != "007"),
-        np.logical_and(sektor == "6500", undersektor == "007"),
+        (sektor == "6500").to_numpy(),
         (sektor == "1510").to_numpy(),
         (sektor == "1520").to_numpy(),
     ]
 
     groups = {
         "110": "Statlig forvaltning",
         "550": "Kommunal forvaltning",
-        "510": "Fylkeskommunal forvaltning",
         "660": "Kommunale foretak med ubegrenset ansvar",
         "680": "Kommunalt eide aksjeselskaper m.v.",
     }

tests/test_sector.py

@@ -10,20 +10,17 @@ def sample_df() -> pd.DataFrame:
     return pd.DataFrame(
         {
             "sektor": np.random.choice(["6100", "6500", "1510", "1520"], size=100),
-            "undersektor": np.random.choice(["007", "008", "009"], size=100),
         }
     )
 
 
 def test_sektor2_grp(sample_df):
     df = sample_df
-    df["sektor2_grp"] = sektor2_grp(df["sektor"], df["undersektor"]).astype(str)
+    df["sektor2_grp"] = sektor2_grp(df["sektor"]).astype(str)
     assert not df["sektor2_grp"].isnull().any(), "Sector 2 group contains null values"
 
 
 def test_sektor2_grp_number(sample_df):
     df = sample_df
-    df["sektor2_grp"] = sektor2_grp(
-        df["sektor"], df["undersektor"], display="number"
-    ).astype(str)
+    df["sektor2_grp"] = sektor2_grp(df["sektor"], display="number").astype(str)
     assert not df["sektor2_grp"].isnull().any(), "Sector 2 group contains null values"