add preprocessing steps

tests/analysis/test_forecast.py

@@ -1,3 +1,5 @@
+import pytest
+
 from delta_barth.analysis import forecast as fc
 
 
@@ -15,3 +17,44 @@ def test_sales_per_customer_too_few_data_points(sales_data):
 
     assert err == 1
     assert res is None
+
+
+def test_parse_api_resp_to_df(exmpl_api_sales_prognosis_resp):
+    resp = exmpl_api_sales_prognosis_resp
+    df = fc.parse_api_resp_to_df(resp)
+    features = set(
+        (
+            "artikelId",
+            "warengruppeId",
+            "firmaId",
+            "betrag",
+            "menge",
+            "buchungsDatum",
+        )
+    )
+    assert all(col in features for col in df.columns)
+
+
+def test_preprocess_sales_per_customer(exmpl_api_sales_prognosis_resp):
+    resp = exmpl_api_sales_prognosis_resp
+    feat_mapping: dict[str, str] = {
+        "artikelId": "artikel_refid",
+        "firmaId": "firma_refid",
+        "betrag": "betrag",
+        "menge": "menge",
+        "buchungsDatum": "buchungs_datum",
+    }
+    target_features: frozenset[str] = frozenset(
+        (
+            "firma_refid",
+            "betrag",
+            "buchungs_datum",
+        )
+    )
+    df = fc.preprocess_sales_per_customer(
+        resp,
+        feature_map=feat_mapping,
+        target_features=target_features,
+    )
+    assert len(df.columns) == 5
+    assert any(feat not in df.columns for feat in feat_mapping.keys())

tests/analysis/test_parse.py

@@ -1,7 +1,7 @@
 import pandas as pd
 import pytest
 
-from delta_barth.analysis import parse
+from delta_barth.analysis import forecast, parse
 from delta_barth.errors import FeaturesMissingError
 
 
@@ -10,12 +10,12 @@ def test_check_needed_features():
     data = pd.DataFrame(
         data=[[1, 2, 3, 4, 5]], columns=["feat1", "feat2", "feat3", "feat4", "feat5"]
     )
-    parse.check_needed_features(data, target_features)
+    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)
+        parse._check_needed_features(data, target_features)
 
 
 def test_map_features_to_targets():
@@ -23,7 +23,7 @@ def test_map_features_to_targets():
     data = pd.DataFrame(
         data=[[1, 2, 3, 4, 5]], columns=["feat1", "feat2", "feat3", "feat4", "feat5"]
     )
-    data = parse.map_features_to_targets(data, feature_map)
+    data = parse._map_features_to_targets(data, feature_map)
     assert "feat10" in data.columns
     assert "feat20" in data.columns
     assert "feat50" in data.columns
@@ -32,3 +32,28 @@ def test_map_features_to_targets():
     assert "feat1" not in data.columns
     assert "feat2" not in data.columns
     assert "feat5" not in data.columns
+
+
+def test_preprocess_features(exmpl_api_sales_prognosis_resp):
+    resp = exmpl_api_sales_prognosis_resp
+    df = forecast.parse_api_resp_to_df(resp)
+    feat_mapping: dict[str, str] = {
+        "artikelId": "artikel_refid",
+        "firmaId": "firma_refid",
+        "betrag": "betrag",
+        "menge": "menge",
+        "buchungsDatum": "buchungs_datum",
+    }
+    target_features: frozenset[str] = frozenset(
+        (
+            "firma_refid",
+            "betrag",
+            "buchungs_datum",
+        )
+    )
+
+    assert all(feat in df.columns for feat in feat_mapping.keys())
+    data = parse.preprocess_features(df, feat_mapping, target_features)
+    assert len(data.columns) == len(df.columns)
+    assert (data.columns != df.columns).any()
+    assert any(feat not in data.columns for feat in feat_mapping.keys())