Remove tax unit groupings.

docs/geps/gep-01.md

@@ -42,7 +42,7 @@ a nutshell and without explanations, these conventions are:
      Internal variables should be used sparingly.
 
 1. If names need to be concatenated for making clear what a column name refers to (e.g.,
-   `arbeitsl_geld_2_vermög_freib_bg` vs. `grunds_im_alter_vermög_freib_hh`), the group
+   `arbeitsl_geld_2_vermög_freib_bg` vs. `grunds_im_alter_vermög_freib_eg`), the group
    (i.e., the tax or transfer) that a variable refers to appears first.
 
 1. Because of the necessity of concatenated column names, there will be conflicts
@@ -112,7 +112,7 @@ changed, even if it leads to long variable names (e.g., `kinderfreib`,
 less error-prone.
 
 If names need to be concatenated for making clear what a column name refers to (e.g.,
-`arbeitsl_geld_2_vermög_freib_bg` vs. `grunds_im_alter_vermög_freib_hh`), the group
+`arbeitsl_geld_2_vermög_freib_bg` vs. `grunds_im_alter_vermög_freib_eg`), the group
 (i.e., the tax or transfer) that a variable refers to appears first.
 
 If a column has a reference to a time unit (i.e., any flow variable like earnings or

docs/geps/gep-04.md

@@ -80,7 +80,7 @@ is able to replace this function with her own version.
 See the following example for capital income taxes.
 
 ```python
-def abgelt_st_y_tu(zu_verst_kapitaleink_y_tu: float, abgelt_st_params: dict) -> float:
+def abgelt_st_y_sn(zu_verst_kapitaleink_y_tu: float, abgelt_st_params: dict) -> float:
     """Calculate Abgeltungssteuer on tax unit level.
 
     Parameters
@@ -97,26 +97,26 @@ def abgelt_st_y_tu(zu_verst_kapitaleink_y_tu: float, abgelt_st_params: dict) ->
     return abgelt_st_params["satz"] * zu_verst_kapitaleink_y_tu
 ```
 
-The function {func}`abgelt_st_y_tu` requires the variable `zu_verst_kapital_eink_y_tu`,
+The function {func}`abgelt_st_y_sn` requires the variable `zu_verst_kapital_eink_y_tu`,
 which is the amount of taxable capital income on tax unit level (the latter is implied
 by the `_tu` suffix, see {ref}`gep-1`). `zu_verst_kapital_eink_y_tu` must be provided by
 the user as a column of the input data or it has to be the name of another function.
 `abgelt_st_params` is a dictionary of parameters related to the calculation of
-`abgelt_st_y_tu`.
+`abgelt_st_y_sn`.
 
 Another function, say
 
 ```python
-def soli_st_y_tu(
-    eink_st_mit_kinderfreib_y_tu: float,
+def soli_st_y_sn(
+    eink_st_mit_kinderfreib_y_sn: float,
     anz_erwachsene_tu: int,
-    abgelt_st_y_tu: float,
+    abgelt_st_y_sn: float,
     soli_st_params: dict,
 ) -> float: ...
 ```
 
-may use `abgelt_st_y_tu` as an input argument. The DAG backend ensures that the function
-`abgelt_st_y_tu` will be executed first.
+may use `abgelt_st_y_sn` as an input argument. The DAG backend ensures that the function
+`abgelt_st_y_sn` will be executed first.
 
 Note that the type annotations (e.g. `float`) indicate the expected type of each input
 and the output of a function, see {ref}`gep-2`.

docs/gettsim_objects/variables_out.md

@@ -20,9 +20,9 @@ You can find their individual calculation in the documentation of all {ref}`func
   - Monthly amount of unemployment assistance
 * - {func}`entgeltp_update <_gettsim.functions.entgeltp_update>`
   - Updated earning points for pension claim
-* - {func}`abgelt_st_y_tu <_gettsim.functions.abgelt_st_y_tu>`
+* - {func}`abgelt_st_y_sn <_gettsim.functions.abgelt_st_y_sn>`
   - Capital income tax on tax unit level
-* - {func}`soli_st_y_tu <_gettsim.functions.soli_st_y_tu>`
+* - {func}`soli_st_y_sn <_gettsim.functions.soli_st_y_sn>`
   - Solidarity surcharge on tax unit level
 * - {func}`kindergeld_m <_gettsim.functions.kindergeld_m>`
   - Monthly child benefit
@@ -42,6 +42,6 @@ You can find their individual calculation in the documentation of all {ref}`func
   - Monthly parental leave benefit
 * - {func}`wohngeld_m_hh <_gettsim.functions.wohngeld_m_hh>`
   - Monthly housing benefit on household level
-* - {func}`grunds_im_alter_m_hh <_gettsim.functions.grunds_im_alter_m_hh>`
+* - {func}`grunds_im_alter_m_eg <_gettsim.functions.grunds_im_alter_m_eg>`
   - Monthly subsistence payment for retirees on household level
 ```

environment.yml

@@ -29,7 +29,7 @@ dependencies:
   - pyyaml
   - setuptools_scm
   - sphinx
-  - sphinx-automodapi
+  - sphinx-automodapi<0.17.0
   - sphinx-copybutton
   - toml
   - pip:

src/_gettsim/aggregation_numpy.py

@@ -17,7 +17,8 @@ def grouped_count(group_id):
 def grouped_sum(column, group_id):
     fail_if_dtype_not_int(group_id, agg_func="grouped_sum")
     fail_if_dtype_not_numeric_or_boolean(column, agg_func="grouped_sum")
-
+    if column.dtype == bool:
+        column = column.astype(int)
     out_on_hh = npg.aggregate(group_id, column, func="sum", fill_value=0)
 
     # Expand to individual level

src/_gettsim/config.py

@@ -99,6 +99,15 @@ def set_array_backend(backend: str):
         "description": "Spouses filing taxes jointly or individuals.",
         "potentially_endogenous": True,
     },
+    "ehe": {
+        "name": "Ehepartner",
+        "description": "Couples that are either married or in a civil union.",
+        "potentially_endogenous": False,
+    },
+    "eg": {
+        "name": "Einstandsgemeinschaft / Einstandspartner",
+        "description": "Couples that live together but are not necessarily married.",
+    },
 }
 
 SUPPORTED_TIME_UNITS = {
@@ -118,20 +127,20 @@ def set_array_backend(backend: str):
 
 DEFAULT_TARGETS = [
     "eink_st_y_tu",
-    "soli_st_y_tu",
-    "abgelt_st_y_tu",
+    "soli_st_y_sn",
+    "abgelt_st_y_sn",
     "sozialv_beitr_m",
     "ges_rentenv_beitr_m",
     "arbeitsl_v_beitr_m",
     "ges_krankenv_beitr_m",
     "ges_pflegev_beitr_m",
     "arbeitsl_geld_m",
-    "kindergeld_m_tu",
+    "kindergeld_m",
     "arbeitsl_geld_2_m_bg",
     "kinderzuschl_m_bg",
     "wohngeld_m_hh",
     "unterhaltsvors_m_hh",
-    "grunds_im_alter_m_hh",
+    "grunds_im_alter_m_eg",
     "ges_rente_m",
     "erwerbsm_rente_m",
 ]

src/_gettsim/demographic_vars.py

@@ -8,31 +8,54 @@
 
 import numpy
 
-aggregate_by_group_demographic_vars = {
-    "anz_erwachsene_tu": {"source_col": "erwachsen", "aggr": "sum"},
-    "anz_erwachsene_hh": {"source_col": "erwachsen", "aggr": "sum"},
-    "anz_rentner_hh": {"source_col": "rentner", "aggr": "sum"},
-    "anz_kinder_hh": {"source_col": "kind", "aggr": "sum"},
-    "anz_kinder_tu": {"source_col": "kind", "aggr": "sum"},
-    "anz_kinder_bis_5_hh": {"source_col": "kind_bis_5", "aggr": "sum"},
-    "anz_kinder_bis_6_hh": {"source_col": "kind_bis_6", "aggr": "sum"},
-    "anz_kinder_bis_15_hh": {"source_col": "kind_bis_15", "aggr": "sum"},
-    "anz_kinder_bis_17_hh": {"source_col": "kind_bis_17", "aggr": "sum"},
-    "anz_kinder_ab_6_bis_13_hh": {"source_col": "kind_ab_6_bis_13", "aggr": "sum"},
-    "anz_kinder_ab_14_bis_24_hh": {"source_col": "kind_ab_14_bis_24", "aggr": "sum"},
-    "anz_kinder_ab_14_bis_17_hh": {"source_col": "kind_ab_14_bis_17", "aggr": "sum"},
-    "anz_kinder_ab_18_bis_24_hh": {"source_col": "kind_ab_18_bis_24", "aggr": "sum"},
-    "anz_kinder_bis_10_tu": {"source_col": "kind_bis_10", "aggr": "sum"},
-    "alleinerz_tu": {"source_col": "alleinerz", "aggr": "any"},
-    "alleinerz_hh": {"source_col": "alleinerz", "aggr": "any"},
-    "haushaltsgröße_hh": {"aggr": "count"},
-    "tax_unit_größe_tu": {"aggr": "count"},
-    "alter_monate_jüngstes_mitglied_hh": {"source_col": "alter_monate", "aggr": "min"},
-    "anz_mehrlinge_jüngstes_kind_hh": {
-        "source_col": "jüngstes_kind_oder_mehrling",
-        "aggr": "sum",
-    },
-}
+from _gettsim.config import SUPPORTED_GROUPINGS
+
+
+def _add_grouping_suffixes_to_keys(group_dict: dict[str, dict]) -> dict[str, dict]:
+    """Add grouping suffixes to keys of a dictionary.
+
+    Parameters
+    ----------
+    group_dict
+        Dictionary with keys to be suffixed.
+
+    Returns
+    -------
+    Dictionary with suffixed keys.
+    """
+    out = {}
+
+    for key, value in group_dict.items():
+        for suffix in SUPPORTED_GROUPINGS:
+            new_key = key + "_" + suffix
+            out[new_key] = value
+
+    return out
+
+
+aggregate_by_group_demographic_vars = _add_grouping_suffixes_to_keys(
+    {
+        "anz_erwachsene": {"source_col": "erwachsen", "aggr": "sum"},
+        "anz_rentner": {"source_col": "rentner", "aggr": "sum"},
+        "anz_kinder": {"source_col": "kind", "aggr": "sum"},
+        "anz_kinder_bis_5": {"source_col": "kind_bis_5", "aggr": "sum"},
+        "anz_kinder_bis_6": {"source_col": "kind_bis_6", "aggr": "sum"},
+        "anz_kinder_bis_15": {"source_col": "kind_bis_15", "aggr": "sum"},
+        "anz_kinder_bis_17": {"source_col": "kind_bis_17", "aggr": "sum"},
+        "anz_kinder_ab_6_bis_13": {"source_col": "kind_ab_6_bis_13", "aggr": "sum"},
+        "anz_kinder_ab_14_bis_24": {"source_col": "kind_ab_14_bis_24", "aggr": "sum"},
+        "anz_kinder_ab_14_bis_17": {"source_col": "kind_ab_14_bis_17", "aggr": "sum"},
+        "anz_kinder_ab_18_bis_24": {"source_col": "kind_ab_18_bis_24", "aggr": "sum"},
+        "alleinerz": {"source_col": "alleinerz", "aggr": "any"},
+        "haushaltsgröße": {"aggr": "count"},
+        "tax_unit_größe": {"aggr": "count"},
+        "alter_monate_jüngstes_mitglied": {"source_col": "alter_monate", "aggr": "min"},
+        "anz_mehrlinge_jüngstes_kind": {
+            "source_col": "jüngstes_kind_oder_mehrling",
+            "aggr": "sum",
+        },
+    }
+)
 
 
 def kind_bis_5(alter: int, kind: bool) -> bool:
@@ -71,7 +94,7 @@ def kind_bis_6(alter: int, kind: bool) -> bool:
     return out
 
 
-def kind_bis_10(alter: int, kind: bool) -> bool:
+def kind_bis_12(alter: int, kind: bool) -> bool:
     """Calculate if child under the age of 11.
 
     Parameters

src/_gettsim/groupings.py

@@ -5,7 +5,13 @@
 
 
 def create_groupings() -> dict[str, Callable]:
-    return {"bg_id": bg_id_numpy, "fg_id": fg_id_numpy, "sn_id": sn_id_numpy}
+    return {
+        "bg_id": bg_id_numpy,
+        "eg_id": eg_id_numpy,
+        "fg_id": fg_id_numpy,
+        "sn_id": sn_id_numpy,
+        "ehe_id": ehe_id_numpy,
+    }
 
 
 def bg_id_numpy(
@@ -33,6 +39,61 @@ def bg_id_numpy(
     return numpy.asarray(result)
 
 
+def eg_id_numpy(
+    p_id: numpy.ndarray,
+    p_id_einstandspartner: numpy.ndarray,
+) -> numpy.ndarray:
+    """
+    Compute the ID of the Einstandsgemeinschaft for each person.
+    """
+    p_id_to_eg_id = {}
+    next_eg_id = 0
+    result = []
+
+    for index, current_p_id in enumerate(p_id):
+        current_p_id_einstandspartner = p_id_einstandspartner[index]
+
+        if (
+            current_p_id_einstandspartner >= 0
+            and current_p_id_einstandspartner in p_id_to_eg_id
+        ):
+            result.append(p_id_to_eg_id[current_p_id_einstandspartner])
+            continue
+
+        # New Einstandsgemeinschaft
+        result.append(next_eg_id)
+        p_id_to_eg_id[current_p_id] = next_eg_id
+        next_eg_id += 1
+
+    return numpy.asarray(result)
+
+
+def ehe_id_numpy(
+    p_id: numpy.ndarray,
+    p_id_ehepartner: numpy.ndarray,
+):
+    """
+    Compute the ID of the Ehe for each person.
+    """
+    p_id_to_ehe_id = {}
+    next_ehe_id = 0
+    result = []
+
+    for index, current_p_id in enumerate(p_id):
+        current_p_id_ehepartner = p_id_ehepartner[index]
+
+        if current_p_id_ehepartner >= 0 and current_p_id_ehepartner in p_id_to_ehe_id:
+            result.append(p_id_to_ehe_id[current_p_id_ehepartner])
+            continue
+
+        # New Steuersubjekt
+        result.append(next_ehe_id)
+        p_id_to_ehe_id[current_p_id] = next_ehe_id
+        next_ehe_id += 1
+
+    return numpy.asarray(result)
+
+
 def fg_id_numpy(  # noqa: PLR0913
     p_id: numpy.ndarray,
     hh_id: numpy.ndarray,
@@ -123,27 +184,24 @@ def sn_id_numpy(
     result = []
 
     for index, current_p_id in enumerate(p_id):
-        current_p_id_einstandspartner = p_id_ehepartner[index]
+        current_p_id_ehepartner = p_id_ehepartner[index]
         current_gemeinsam_veranlagt = gemeinsam_veranlagt[index]
 
-        if (
-            current_p_id_einstandspartner >= 0
-            and current_p_id_einstandspartner in p_id_to_sn_id
-        ):
+        if current_p_id_ehepartner >= 0 and current_p_id_ehepartner in p_id_to_sn_id:
             gemeinsam_veranlagt_ehepartner = p_id_to_gemeinsam_veranlagt[
-                current_p_id_einstandspartner
+                current_p_id_ehepartner
             ]
 
             if current_gemeinsam_veranlagt != gemeinsam_veranlagt_ehepartner:
                 message = (
-                    f"{current_p_id_einstandspartner} and {current_p_id} are "
+                    f"{current_p_id_ehepartner} and {current_p_id} are "
                     "married, but have different values for "
                     "gemeinsam_veranlagt."
                 )
                 raise ValueError(message)
 
             if current_gemeinsam_veranlagt:
-                result.append(p_id_to_sn_id[current_p_id_einstandspartner])
+                result.append(p_id_to_sn_id[current_p_id_ehepartner])
                 continue
 
         # New Steuersubjekt

src/_gettsim/parameters/eink_st_abzuege.yaml

@@ -747,14 +747,14 @@ vorsorgepauschale_kv_max:
     steuerklasse_nicht3: 1900
     reference: Art. 1 G. v. 16.07.2009 BGBl. I S. 1959
 rounding:
-  vorsorgeaufw_y_tu:
+  vorsorgeaufw_y_sn:
     note:
       en: Starting date unclear
     reference: § 10 Abs. 3 EStG
     1984-01-01:
       base: 1
       direction: up
-  sonderausgaben_betreuung_y_tu:
+  sonderausgaben_betreuung_y_sn:
     note:
       en: Starting date unclear
     1984-01-01: