diff --git a/etl/eligibility/ha_15_32/ha_analysis_batch_3.py b/etl/eligibility/ha_15_32/ha_analysis_batch_3.py index 53ce69e2..9462642f 100644 --- a/etl/eligibility/ha_15_32/ha_analysis_batch_3.py +++ b/etl/eligibility/ha_15_32/ha_analysis_batch_3.py @@ -5119,7 +5119,9 @@ def forecast_remaining_sales(loader): def fml_data_pull(loader): - has_bruh = ["HA7", "HA14", "HA25", "HA39", "HA16"] + has_bruh = ["HA7", "HA14", "HA25", "HA39", "HA16", + # Do these + "HA1", "HA13", "HA50", "HA24"] # DO from backend.SearchEpc import SearchEpc epc_api_key = "a2Nvbm5rb3dsZXNzYXJAZ21haWwuY29tOjY5MGJiMWM0NmIyOGI5ZDUxYzAxMzQzYzNiZGNlZGJjZDNmODQwMzA=" @@ -5197,9 +5199,19 @@ def fml_analysis(loader): no_ciga_cavity_descriptions = [ "Cavity wall, as built, insulated (assumed)", "Cavity wall, as built, no insulation (assumed)", - "Cavity wall, as built, partial insulation (assumed)" + "Cavity wall, as built, partial insulation (assumed)", + "Cavity wall, no insulation (assumed)", + "Cavity wall, partial insulation (assumed)", + "Cavity wall,", + "Cavity wall, insulated (assumed)", + "Cavity wall, no insulation (assumed)", + "Cavity wall, as built, insulated (assumed)", + "Cavity wall, partial insulation (assumed)", ] + # TODO: There will be some properties that are subject to CIGA that do not look like they ned a CIGA check! pass + # them! + codes = [ "HA39", "HA14", "HA24", "HA15", "HA32", "HA28", "HA6", "HA1", "HA7", "HA16", "HA107", "HA25", "HA50", "HA41", "HA48", "HA2", "HA63", "HA12", @@ -5217,6 +5229,7 @@ def fml_analysis(loader): remaining_eligible_mapping = dict(zip(codes, values)) results = [] + wall_descriptions = [] for ha_name in has_bruh: original_figures = loader.december_figures[ @@ -5236,6 +5249,7 @@ def fml_analysis(loader): # We make sure we don't have duplicated. We do a super basic drop duplicates because it shouldn't be a huge # issue at this point epc_data = epc_data.drop_duplicates("uprn") + wall_descriptions.extend(epc_data["walls-description"].unique().tolist()) # time from the inspection to now epc_data["epc_age"] = (datetime.now() - pd.to_datetime(epc_data["inspection-date"])).dt.days @@ -5464,6 +5478,10 @@ def fml_analysis(loader): results_df = pd.DataFrame(results) + wall_descriptions = list(set(wall_descriptions)) + from pprint import pprint + pprint(wall_descriptions) + # results_df["Delta vs November"] = 100 * ( # results_df["Of which ECO4 Eligible - Remaining"] - results_df["Original ECO4 Estimate - Remaining"] # ) / results_df["Original ECO4 Estimate - Remaining"] diff --git a/etl/epc_clean/app.py b/etl/epc_clean/app.py index 53c1a329..3f1a1a80 100644 --- a/etl/epc_clean/app.py +++ b/etl/epc_clean/app.py @@ -36,8 +36,11 @@ def app(): cleaned_data = {} epc_directories = [entry for entry in EPC_DIRECTORY.iterdir() if entry.is_dir()] + WALLS = [] for directory in tqdm(epc_directories): data = pd.read_csv(directory / "certificates.csv", low_memory=False) + z = data["WALLS_DESCRIPTION"].unique().tolist() + WALLS.extend(z) # Rename the columns to the same format as the api returns data.columns = [c.replace("_", "-").lower() for c in data.columns] # Take just date before the date threshold