added feature mapping

src/delta_barth/analysis/parse.py

@@ -0,0 +1,41 @@
+from __future__ import annotations
+
+from collections.abc import Mapping, Set
+from typing import TYPE_CHECKING
+
+from delta_barth.errors import FeaturesMissingError
+
+if TYPE_CHECKING:
+    import pandas as pd
+
+
+def check_needed_features(
+    data: pd.DataFrame,
+    features: Set,
+) -> None:
+    data_feats = set(data.columns)
+    missing_features = features - data_feats
+
+    if missing_features:
+        raise FeaturesMissingError(
+            f"The datset does not contain all needed features: "
+            f"Missing features are: {missing_features}"
+        )
+
+
+def map_features_to_targets(
+    data: pd.DataFrame,
+    feature_map: Mapping[str, str],
+) -> pd.DataFrame:
+    data_feats = data.columns
+    mapped_feats: list[str] = []
+
+    for feat in data_feats:
+        if feat in feature_map:
+            mapped_feats.append(feature_map[feat])
+        else:
+            mapped_feats.append(feat)
+
+    data.columns = mapped_feats
+
+    return data

src/delta_barth/constants.py

@@ -3,6 +3,7 @@ from typing import Final
 
 from delta_barth.types import CurrentConnection, HttpContentHeaders
 
+# ** API connection management
 HTTP_BASE_CONTENT_HEADERS: Final[HttpContentHeaders] = {
     "Content-type": "application/json",
     "Accept": "application/json",
@@ -15,3 +16,23 @@ HTTP_CURRENT_CONNECTION: Final[CurrentConnection] = CurrentConnection(
 
 class KnownApiErrorCodes(enum.Enum):
     COMMON = frozenset((400, 401, 409, 500))
+
+
+# ** API response parsing
+# ** column mapping [API-Response --> Target-Features]
+COL_MAP_SALES_PROGNOSIS: Final[dict[str, str]] = {
+    "artikelId": "artikel_refid",
+    "firmaId": "firma_refid",
+    "betrag": "betrag",
+    "menge": "menge",
+    "buchungsDatum": "buchungs_datum",
+}
+FEATURES_SALES_PROGNOSIS: Final[frozenset[str]] = frozenset(
+    (
+        "firma_refid",
+        "beleg_typ",
+        "betrag",
+        "vorgang_refid",
+        "buchungs_datum",
+    )
+)

src/delta_barth/errors.py

@@ -8,3 +8,7 @@ class UnknownApiErrorCode(Exception):
 
 class ApiConnectionError(Exception):
     """exception raised if an established connection is needed, but the current session is not connected"""
+
+
+class FeaturesMissingError(Exception):
+    """exception raised if needed features are missing"""

tests/analysis/test_parse.py

@@ -0,0 +1,34 @@
+import pandas as pd
+import pytest
+
+from delta_barth.analysis import parse
+from delta_barth.errors import FeaturesMissingError
+
+
+def test_check_needed_features():
+    target_features = set(("feat1", "feat2", "feat3"))
+    data = pd.DataFrame(
+        data=[[1, 2, 3, 4, 5]], columns=["feat1", "feat2", "feat3", "feat4", "feat5"]
+    )
+    parse.check_needed_features(data, target_features)
+    data = pd.DataFrame(
+        data=[[1, 2, 3, 4, 5]], columns=["featX", "feat2", "feat3", "feat4", "feat5"]
+    )
+    with pytest.raises(FeaturesMissingError):
+        parse.check_needed_features(data, target_features)
+
+
+def test_map_features_to_targets():
+    feature_map = dict(feat1="feat10", feat2="feat20", feat5="feat50")
+    data = pd.DataFrame(
+        data=[[1, 2, 3, 4, 5]], columns=["feat1", "feat2", "feat3", "feat4", "feat5"]
+    )
+    data = parse.map_features_to_targets(data, feature_map)
+    assert "feat10" in data.columns
+    assert "feat20" in data.columns
+    assert "feat50" in data.columns
+    assert "feat3" in data.columns
+    assert "feat4" in data.columns
+    assert "feat1" not in data.columns
+    assert "feat2" not in data.columns
+    assert "feat5" not in data.columns