junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-06-08 11:17:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

extracting heating systems from summary report

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-10-29 14:21:01 +00:00
parent b7f402ba9d
commit 753bda6cb0
1 changed files with 84 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

86
etl/customers/stonewater/Wave 3 Preparation.py
View file

@ -19,10 +19,26 @@ def extract_summary_report(pdf_path):
data = {
"Address": None,
"Current SAP Rating": None,
"Number of Storeys": None,
"Space Heating": None,
"Water Heating": None,
"Fuel Bill": None,
"Window Age Description": None,
"Window Age Description Proportion (%)": None,
"Secondary Window Age Description": None,
"Secondary Window Age Description Proportion (%)": None,
"Number of Windows": None,
"Total Number of Doors": None,
"Number of Insulated Doors": None,
"Existing Primary Heating System": None,
"Existing Primary Heating PCDF Reference": None,
"Existing Primary Heating Controls": None,
"Existing Primary Heating % of Heat": None,
"Existing Secondary Heating System": None,
"Existing Secondary Heating PCDF Reference": None,
"Existing Secondary Heating Controls": None,
"Existing Secondary Heating % of Heat": None,
"Secondary Heating Code": None,
"Water Heating Code": None,
}
with open(pdf_path, "rb") as file:
@ -39,6 +55,10 @@ def extract_summary_report(pdf_path):
storeys_match = re.search(r"Number of Storeys:\s*(\d+)", text)
data["Number of Storeys"] = int(storeys_match.group(1))
# Extract Carbon Emissions
carbon_match = re.search(r"Emissions \(t/year\):\s*([\d.]+)\s*tonnes", text)
data["Carbon Emissions (t/year)"] = float(carbon_match.group(1))
# Extract Fuel Bill
fuel_bill_match = re.search(r"Fuel Bill:\s*£(\d+)", text)
data["Fuel Bill"] = f"£{fuel_bill_match.group(1)}"
@ -66,12 +86,58 @@ def extract_summary_report(pdf_path):
# Join non-empty parts with a comma
data["Address"] = ", ".join([part for part in address_parts if part])
data["Postcode"] = postcode.group(1).strip()
windows_section = re.search(r"Windows\s*(.*?)\s*Draught Proofing", text, re.DOTALL)
windows_text = windows_section.group(1)
window_data = extract_window_age_description(windows_text)
data.update(window_data)
# Extract Total Number of Doors
total_doors_match = re.search(r"Total Number of Doors\s*(\d+)", text)
data["Total Number of Doors"] = int(total_doors_match.group(1))
# Extract Number of Insulated Doors
insulated_doors_match = re.search(r"Number of Insulated Doors\s*(\d+)", text)
data["Number of Insulated Doors"] = int(insulated_doors_match.group(1))
# Extract heating system
# Extract Primary Heating Data
# Extract Primary Heating Section
primary_heating_section = re.search(r"Main\s*Heating1\s*(.*?)\s*Main\s*Heating2", text, re.DOTALL)
primary_text = primary_heating_section.group(1)
data["Existing Primary Heating System"] = re.search(r"Main Heating Code\s*(.*?)\n", primary_text).group(
1).strip()
data["Existing Primary Heating PCDF Reference"] = re.search(r"PCDF boiler Reference\s*(\d+)",
primary_text).group(1)
data["Existing Primary Heating Controls"] = re.search(r"Main Heating Controls\s*(.*?)\n", primary_text).group(
1).strip()
data["Existing Primary Heating % of Heat"] = int(
re.search(r"Percentage of Heat\s*(\d+)\s*%", primary_text).group(1)
)
# Extract Secondary Heating Section
secondary_heating_section = re.search(r"Main\s*Heating2\s*(.*?)\s*Water\s*Heating", text, re.DOTALL)
secondary_text = secondary_heating_section.group(1)
data["Existing Secondary Heating System"] = re.search(r"Main Heating Code\s*(.*?)\n", secondary_text).group(
1).strip()
data["Existing Secondary Heating PCDF Reference"] = re.search(r"PCDF boiler Reference\s*(\d+)",
secondary_text).group(1)
data["Existing Secondary Heating Controls"] = re.search(r"Main Heating Controls\s*(.*?)\n",
secondary_text).group(1).strip()
data["Existing Secondary Heating % of Heat"] = int(
re.search(r"Percentage of Heat\s*(\d+)\s*%", secondary_text).group(1)
)
# Extract Secondary Heating and Water Heating Codes
secondary_heating_code_match = re.search(r"Secondary Heating Code\s*(.*?)\n", text)
water_heating_code_match = re.search(r"Water Heating Code\s*(.*?)\n", text)
data["Secondary Heating Code"] = secondary_heating_code_match.group(1).strip()
data["Water Heating Code"] = water_heating_code_match.group(1).strip()
return data
@ -111,9 +177,20 @@ def extract_window_age_description(windows_text):
most_common_description, window_count = description_counts.most_common(1)[0]
window_proportion = window_count / sum(description_counts.values()) * 100
# Get the second most common and the proportion
if window_proportion == 100:
second_most_common_description = None
second_most_common_proportion = 0
else:
second_most_common_description, second_window_count = description_counts.most_common(2)[1]
second_most_common_proportion = second_window_count / sum(description_counts.values()) * 100
return {
"Window Age Description": most_common_description,
"Window Age Description Proportion (%)": window_proportion
"Window Age Description Proportion (%)": window_proportion,
"Secondary Window Age Description": second_most_common_description,
"Secondary Window Age Description Proportion (%)": second_most_common_proportion,
"Number of Windows": sum(description_counts.values())
}
@ -129,6 +206,11 @@ def extract_epr(pdf_path):
"Fuel Bill": None,
"Window Age Description": None,
"Window Age Description Proportion (%)": None,
"Secondary Window Age Description": None,
"Secondary Window Age Description Proportion (%)": None,
"Number of Windows": None,
"Total Number of Doors": None,
"Number of Insulated Doors": None,
}
with open(pdf_path, "rb") as file: