From 3bdd4a4a97efc87fc24eeded8e6f3a2f58cf70f6 Mon Sep 17 00:00:00 2001 From: Jun-te Kim Date: Thu, 12 Feb 2026 15:03:38 +0000 Subject: [PATCH] test first with just 5 --- .devcontainer/backend/Dockerfile | 2 + .devcontainer/backend/devcontainer.json | 3 +- backend/address2UPRN/main.py | 52 ++++++++----------------- 3 files changed, 20 insertions(+), 37 deletions(-) diff --git a/.devcontainer/backend/Dockerfile b/.devcontainer/backend/Dockerfile index 99cd66d6..f48fb99f 100644 --- a/.devcontainer/backend/Dockerfile +++ b/.devcontainer/backend/Dockerfile @@ -3,6 +3,8 @@ FROM python:3.11.10-bullseye ARG USER=vscode ARG DEBIAN_FRONTEND=noninteractive +ARG DOCKER_GID=1003 + # 1) Toolchain + utilities for building libpostal RUN apt-get update && apt-get install -y --no-install-recommends \ diff --git a/.devcontainer/backend/devcontainer.json b/.devcontainer/backend/devcontainer.json index 6e2edc93..73348c4d 100644 --- a/.devcontainer/backend/devcontainer.json +++ b/.devcontainer/backend/devcontainer.json @@ -6,7 +6,8 @@ "workspaceFolder": "/workspaces/model", "postStartCommand": "bash .devcontainer/backend/post-install.sh", "mounts": [ - "source=${localEnv:HOME},target=/home/vscode,type=bind" + "source=${localEnv:HOME},target=/home/vscode,type=bind", + "source=/var/run/docker.sock,target=/var/run/docker.sock,type=bind" ], "customizations": { "vscode": { diff --git a/backend/address2UPRN/main.py b/backend/address2UPRN/main.py index 0aedd082..e635b305 100644 --- a/backend/address2UPRN/main.py +++ b/backend/address2UPRN/main.py @@ -329,9 +329,6 @@ def get_uprn_candidates( def get_uprn_with_epc_df( user_inputed_address: str, epc_df: pd.DataFrame, - return_address=False, - return_EPC=False, - return_score=True, ): """ Return uprn (str) using a pre-fetched EPC dataframe. @@ -371,8 +368,6 @@ def get_uprn_with_epc_df( return None address = top_rank_df["address"].values[0] - lexiscore = float(top_rank_df["lexiscore"].values[0]) - epc = top_rank_df["current-energy-efficiency"].values[0] score = float(top_rank_df["lexiscore"].values[0]) # logger.info(f"Address found to be: {address}, with lexiscore {lexiscore}") @@ -382,20 +377,7 @@ def get_uprn_with_epc_df( if found_uprn == "": return None - if return_address: - if return_EPC is False: - return found_uprn, address - else: - if return_score is False: - return found_uprn, address, epc - else: - return ( - found_uprn, - address, - epc, - score, - ) - return found_uprn + return (found_uprn, address, score) def get_uprn( @@ -688,7 +670,11 @@ def handler(event, context, local=False): # Create user_input column by concatenating Address 1 and Address 2 df["user_input"] = ( - df["Address 1"].fillna("") + " " + df["Address 2"].fillna("") + df["Address 1"].fillna("") + + " " + + df["Address 2"].fillna("") + + " " + + df["Address 3"].fillna("") ).str.strip() logger.info(f"Created user_input column from Address 1 and Address 2") @@ -743,14 +729,11 @@ def handler(event, context, local=False): result = get_uprn_with_epc_df( user_inputed_address=user_input, epc_df=epc_df, - return_address=True, - return_EPC=True, - return_score=True, ) # Parse result tuple if successful if result: - uprn, found_address, epc, score = result + uprn, found_address, score = result uprns_found += 1 logger.info( f"Found UPRN for {user_input} in {postcode}: {uprn} (score: {score})" @@ -759,10 +742,9 @@ def handler(event, context, local=False): results_data.append( { **row, # Include all original data - "found_uprn": uprn, - "found_address": found_address, - "epc_rating": epc, - "lexiscore": score, + "uprn": uprn, + "domna_found_address": found_address, + "domna_lexiscore": score, } ) else: @@ -772,10 +754,9 @@ def handler(event, context, local=False): results_data.append( { **row, # Include all original data - "found_uprn": None, - "found_address": None, - "epc_rating": None, - "lexiscore": None, + "uprn": None, + "domna_found_address": None, + "domna_lexiscore": None, } ) @@ -789,10 +770,9 @@ def handler(event, context, local=False): results_data.append( { **row, - "found_uprn": None, - "found_address": None, - "epc_rating": None, - "score": None, + "uprn": None, + "domna_found_address": None, + "domna_lexiscore": None, "error": str(e), } )