Creating load data function for ha24

etl/eligibility/ha_15_32/ha24_app.py

@@ -0,0 +1,55 @@
+import msgpack
+import openpyxl
+from openpyxl.styles.colors import COLOR_INDEX
+from pathlib import Path
+from datetime import datetime
+import pandas as pd
+import numpy as np
+from utils.s3 import read_from_s3
+from utils.logger import setup_logger
+from dotenv import load_dotenv
+from backend.app.utils import read_parquet_from_s3
+from tqdm import tqdm
+from backend.SearchEpc import SearchEpc
+from etl.eligibility.Eligibility import Eligibility
+from etl.eligibility.ha_15_32.app import prepare_model_data_row
+from etl.epc.DataProcessor import DataProcessor
+from etl.epc.settings import COLUMNS_TO_MERGE_ON
+from backend.ml_models.api import ModelApi
+
+import re
+
+ENV_FILE = Path(__file__).parent / "etl" / "eligibility" / "ha_15_32" / ".env"
+
+logger = setup_logger()
+load_dotenv(ENV_FILE)
+
+
+def load_data():
+    workbook = openpyxl.load_workbook(f'etl/eligibility/ha_15_32/HESTIA - HA 24 ASSET LIST.xlsx')
+    sheet = workbook.active
+    sheet_colnames = [cell.value for cell in sheet[1]]
+
+    rows_data = []
+    rows_colors = []
+    for row in sheet.iter_rows(min_row=2, values_only=False):  # Assuming the first row is headers
+        row_data = [cell.value for cell in row]  # This will get you the cell values
+        row_color = row[0].fill.start_color.index if row[0].fill.start_color.index != '00000000' else None
+        # row_color = COLOR_INDEX[row_color]
+        rows_data.append(row_data)
+        rows_colors.append(row_color)
+
+    asset_list = pd.DataFrame(rows_data, columns=sheet_colnames)
+    # Remove None columns
+    asset_list = asset_list.iloc[:, 0:10]
+    asset_list['row_color'] = rows_colors
+
+    asset_list["row_colour_name"] = np.where(
+        asset_list["row_color"] == "FFFF0000", "red",
+        np.where(asset_list["row_color"] == "FF92D050", "green", "yellow")
+    )
+
+    asset_list["row_colour_code"] = np.where(
+        asset_list["row_colour_name"] == "red", "does not meet criteria",
+        np.where(asset_list["row_colour_name"] == "green", "identified potential eco", "maybe in the future")
+    )