import pandas as pd
import json
from pprint import pprint

def handler(event, context):
    # read data for houses only
    print("waltham forest set up correctly")
    return None
    df = pd.read_excel("../../home/Downloads/data.xlsx", sheet_name="Houses Asset Data")

    element_cols = [
        "ELEMENT GROUP", "ELEMENT CODE", "ELEMENT CODE DESCRIPTION",
        "ATTRIBUTE CODE", "ATTRIBUTE CODE DESCRIPTION",
        "ELEMENT DATE VALUE", "ELEMENT NUMERIC VALUE",
        "ELEMENT TEXT VALUE", "QUANTITY",
        "INSTALL DATE", "REMAINING LIFE", "ELEMENT COMMENTS"
    ]

    property_cols = [
        "PROP REF", "Domna", "ADDRESS", "OWNERSHIP",
        "PROP STATUS", "PROP TYPE", "PROP SUB TYPE"
    ]

    # Group by ADDRESS (and other identifiers if needed)
    result = (
        df.groupby(["ADDRESS"])
        .apply(lambda g: {
            "property_info": g[property_cols].drop_duplicates().iloc[0].to_dict(),
            "elements_info": [
                {
                    "ELEMENT GROUP": eg_name,
                    "elements": eg_df.drop(columns=["ELEMENT GROUP"]).to_dict(orient="records")
                }
                for eg_name, eg_df in g[element_cols].groupby("ELEMENT GROUP")
            ]
        })
        .reset_index()
        .rename(columns={0: "data"})
    )

    # Convert to list of dicts
    records = []
    for _, row in result.iterrows():
        records.append({
            "ADDRESS": row["ADDRESS"],
            **row["data"]
        })

    json_output = json.dumps(records, ensure_ascii=False, default=str)
    pprint(json_output)