matching ha50

etl/eligibility/ha_15_32/ha_analysis_batch_3.py

@@ -172,7 +172,8 @@ class DataLoader:
     }
 
     UNMATCHED_ECO3 = {
-        "HA25": 154
+        "HA25": 154,
+        "HA50": 5
     }
 
     def __init__(self, directories, december_figures_filepath, use_cache, rebuild):
@@ -262,6 +263,10 @@ class DataLoader:
                                              asset_list["add_5"].astype(str).str.lower().str.strip() + ", " + \
                                              asset_list["post_code"].astype(str).str.lower().str.strip()
             asset_list["matching_postcode"] = asset_list["post_code"].astype(str).str.lower().str.strip()
+        elif ha_name == "HA50":
+            asset_list["matching_address"] = asset_list["Address Line 1"].astype(str).str.lower().str.strip() + ", " + \
+                                             asset_list["Post Code"].astype(str).str.lower().str.strip()
+            asset_list["matching_postcode"] = asset_list["Post Code"].astype(str).str.lower().str.strip()
         elif ha_name == "HA107":
             # Create matching_address by concatenating House No, Street, Town, District, Postcode
             asset_list["matching_address"] = asset_list["House No"].astype(str).str.lower().str.strip() + ", " + \
@@ -433,6 +438,8 @@ class DataLoader:
             return "ECO Surveys"
         elif "ECO Survey" in workbook.sheetnames:
             return "ECO Survey"
+        elif "ECO 4 Surveys completed" in workbook.sheetnames:
+            return "ECO 4 Surveys completed"
         else:
             return "ECO surveys"
 
@@ -1289,6 +1296,34 @@ class DataLoader:
 
         return survey_list
 
+    @staticmethod
+    def correct_ha50_survey_list(survey_list):
+
+        survey_list["Post Code"] = np.where(
+            (survey_list["Street / Block Name"] == 'COSELEY STREET') &
+            (survey_list["Post Code"] == 'ST16 1LR'),
+            "ST6 1JU",
+            survey_list["Post Code"]
+        )
+
+        # Remove some of COSELEY STREET, as we have surveys done, outside of the asset list
+        survey_list = survey_list[
+            ~((survey_list["Street / Block Name"] == "COSELEY STREET") &
+              (survey_list["Post Code"] == "ST6 1JU") &
+              (survey_list["NO."].isin([96])))
+        ]
+
+        survey_list["Post Code"] = survey_list["Post Code"].str.replace("ST33JZ", "ST3 3JZ")
+
+        # Remove some of Jesmond drive as we have surveys done outside of the asset list
+        survey_list = survey_list[
+            ~((survey_list["Street / Block Name"] == "Jesmond Drive") &
+              (survey_list["Post Code"] == "ST3 3JZ") &
+              (survey_list["NO."].isin([29])))
+        ]
+
+        return survey_list
+
     @staticmethod
     def correct_ha107_survey_list(survey_list):
         # Replace Front Street, East Stockham with Front Street, East Stockwith
@@ -1503,6 +1538,10 @@ class DataLoader:
         )
         return eco3_list
 
+    @staticmethod
+    def correct_ha50_eco3_list(eco3_list):
+        return eco3_list
+
     def merge_eco3_to_assets(self, asset_list, eco3_list, ha_name):
 
         eco3_list_correction_function = getattr(self, f"correct_{ha_name.lower()}_eco3_list")
@@ -1517,6 +1556,7 @@ class DataLoader:
                 postcode for postcode in eco3_list["postcode_no_space"] if
                 postcode not in asset_list["matching_postcode_nospace"].values
             }
+
             eco3_list = eco3_list[~eco3_list["postcode_no_space"].isin(missed_postcodes)]
 
         # For the asset list, we create a matching address without any punctuation
@@ -4199,16 +4239,18 @@ def app():
     # Grab the December HA figures filepath
     december_figures_filepath = "local_data/ha_data/HA_December_figures.csv"
 
-    # Add in: "HA25"
+    # Add in:
     # TODO: Remove ECO3 sales from HA25
     priority_has = [
-        "HA1", "HA6", "HA7", "HA14", "HA15", "HA16", "HA20", "HA24", "HA25", "HA28", "HA32", "HA39", "HA107",
+        "HA1", "HA6", "HA7", "HA14", "HA15", "HA16", "HA24", "HA25", "HA28", "HA32", "HA39", "HA50", "HA107",
     ]
-    # Next HAs to do: 15[DONE], 32 [DONE], 33 [Input format is 4 parts and no eco4 jobs identified - come back on this],
+    # Next HAs to do: 14 [DONE], 15[DONE], 32 [DONE], 33 [Input format is 4 parts and no eco4 jobs identified - come
+    # back on this],
     # Then: 28 [DONE],
-    # 41, 10, 14 [DONE], 20, 48, 50
-    # 38[problematic, but no ECO4]
-    # TODO - do 50 and 25 next
+    # 41, 48, 50
+    # 38[problematic, but no ECO4], 10 problematic (no eligibility),
+    # 20 has barely any in
+    # TODO - do 50
     # Filter down the directories to only the priority HAs
     directories = [d for d in directories if d.split("/")[2] in priority_has]