Mise à jour de la colonne Statut (#1078)

incubateur-ademe · Nov 27, 2024 · 237895d · 237895d
1 parent 561a1ea
commit 237895d
Show file tree

Hide file tree

Showing 3 changed files with 57 additions and 4 deletions.
diff --git a/dags/sources/tasks/business_logic/serialize_to_json.py b/dags/sources/tasks/business_logic/serialize_to_json.py
@@ -109,8 +109,8 @@ def db_data_prepare(
     )
 
     df_joined.loc[
-        df_joined["proposition_services"].apply(lambda x: x == []), "status"
-    ] = "SUPPRIME"
+        df_joined["proposition_services"].apply(lambda x: x == []), "statut"
+    ] = "INACTIF"
 
     df_joined.drop("acteur_id", axis=1, inplace=True)
 

diff --git a/dags/sources/tasks/business_logic/source_data_normalize.py b/dags/sources/tasks/business_logic/source_data_normalize.py
@@ -125,7 +125,18 @@ def source_data_normalize(
             df[["adresse", "code_postal", "ville"]] = df.apply(extract_details, axis=1)
 
     if "statut" in df.columns:
-        df["statut"] = df["statut"].map({1: "ACTIF", 0: "SUPPRIME"})
+        df["statut"] = df["statut"].map(
+            {
+                1: "ACTIF",
+                0: "SUPPRIME",
+                "ACTIF": "ACTIF",
+                "INACTIF": "INACTIF",
+                "SUPPRIME": "SUPPRIME",
+            }
+        )
+        df["statut"] = df["statut"].fillna("ACTIF")
+    else:
+        df["statut"] = "ACTIF"
 
     if "public_accueilli" in df.columns:
 

diff --git a/dags_unit_tests/sources/tasks/business_logic/test_source_data_normalize.py b/dags_unit_tests/sources/tasks/business_logic/test_source_data_normalize.py
@@ -249,7 +249,7 @@ class TestSourceDataNormalize:
     - [ ] test merge_duplicated_acteurs
     - [ ] test columns_to_add_by_default
     - [ ] test adresse_format_ban
-    - [ ] test statut
+    - [x] test statut
     - [x] test public_accueilli (+ suppression des pro)
     - [x] test uniquement_sur_rdv
     - [x] test exclusivite_de_reprisereparation
@@ -281,6 +281,48 @@ def source_data_normalize_kwargs(self, acteurtype_id_by_code, source_id_by_code)
             "source_id_by_code": source_id_by_code,
         }
 
+    @pytest.mark.parametrize(
+        "statut, statut_expected",
+        [
+            (None, "ACTIF"),
+            ("fake", "ACTIF"),
+            (np.nan, "ACTIF"),
+            (0, "SUPPRIME"),
+            (1, "ACTIF"),
+            ("ACTIF", "ACTIF"),
+            ("INACTIF", "INACTIF"),
+            ("SUPPRIME", "SUPPRIME"),
+        ],
+    )
+    def test_statut(self, statut, statut_expected, source_data_normalize_kwargs):
+        source_data_normalize_kwargs["df_acteur_from_source"] = pd.DataFrame(
+            {
+                "identifiant_externe": ["1"],
+                "ecoorganisme": ["source1"],
+                "source_id": ["source_id1"],
+                "acteur_type_id": ["decheterie"],
+                "produitsdechets_acceptes": ["Plastic Box"],
+                "statut": [statut],
+            }
+        )
+        df = source_data_normalize(**source_data_normalize_kwargs)
+
+        assert df["statut"].iloc[0] == statut_expected
+
+    def test_statut_no_column(self, source_data_normalize_kwargs):
+        source_data_normalize_kwargs["df_acteur_from_source"] = pd.DataFrame(
+            {
+                "identifiant_externe": ["1"],
+                "ecoorganisme": ["source1"],
+                "source_id": ["source_id1"],
+                "acteur_type_id": ["decheterie"],
+                "produitsdechets_acceptes": ["Plastic Box"],
+            }
+        )
+        df = source_data_normalize(**source_data_normalize_kwargs)
+
+        assert df["statut"].iloc[0] == "ACTIF"
+
     @pytest.mark.parametrize(
         "label_et_bonus, label_et_bonus_expected",
         [