mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-06-08 11:17:27 +00:00
KhalimCK
GitHub
commit
1e80656904
6 changed files with 2593 additions and 16 deletions
|
|
@ -256,16 +256,12 @@ class SearchEpc:
|
|||
else:
|
||||
params = {"address": self.address1, "postcode": self.postcode}
|
||||
|
||||
url = os.path.join(self.client.domestic.host, "search")
|
||||
|
||||
for retry in range(self.max_retries):
|
||||
try:
|
||||
|
||||
if "uprn" in params:
|
||||
# We use the direct call method inside, since we need to implement uprn as a valid
|
||||
# parameter for the search function
|
||||
url = os.path.join(self.client.domestic.host, "search")
|
||||
response = self.client.domestic.call(method="get", url=url, params=params)
|
||||
else:
|
||||
response = self.client.domestic.search(params=params, size=size)
|
||||
response = self.client.domestic.call(method="get", url=url, params=params)
|
||||
|
||||
if response:
|
||||
self.data = response
|
||||
|
|
|
|||
984
etl/customers/aiha/xml_extraction.py
Normal file
984
etl/customers/aiha/xml_extraction.py
Normal file
|
|
@ -0,0 +1,984 @@
|
|||
import os
|
||||
from io import BytesIO
|
||||
|
||||
import pandas as pd
|
||||
|
||||
from etl.xml_survey_extraction.XmlParser import XmlParser
|
||||
|
||||
SURVEY_FOLDER_PATH = "/Users/khalimconn-kowlessar/Documents/hestia/Customers/AIHA/RESIDENT SURVEYS"
|
||||
CONTINGENCY_RATE = 0.26
|
||||
|
||||
|
||||
def sap_to_epc(sap_points: int | float):
|
||||
"""
|
||||
Simple utility function to convert SAP points to EPC rating.
|
||||
:param sap_points: numerical value of SAP points, typically between 0 and 100
|
||||
:return:
|
||||
"""
|
||||
|
||||
if sap_points <= 0:
|
||||
raise ValueError("SAP points should be above 0.")
|
||||
|
||||
if sap_points >= 92:
|
||||
return "A"
|
||||
elif sap_points >= 81:
|
||||
return "B"
|
||||
elif sap_points >= 69:
|
||||
return "C"
|
||||
elif sap_points >= 55:
|
||||
return "D"
|
||||
elif sap_points >= 39:
|
||||
return "E"
|
||||
elif sap_points >= 21:
|
||||
return "F"
|
||||
else:
|
||||
return "G"
|
||||
|
||||
|
||||
def main():
|
||||
"""
|
||||
This script handles the extraction of data from the XML files in the survey folders.
|
||||
:return:
|
||||
"""
|
||||
# Step 1: List all subfolders inside SURVEY_FOLDER_PATH.
|
||||
subfolders = [f.path for f in os.scandir(SURVEY_FOLDER_PATH) if f.is_dir()]
|
||||
|
||||
# Step 2: Loop through each subfolder and find the XML files.
|
||||
extracted_surveys = []
|
||||
for subfolder in subfolders:
|
||||
print(f"Searching in subfolder: {subfolder}")
|
||||
|
||||
# Find all XML files in the current subfolder.
|
||||
xml_files = [f for f in os.listdir(subfolder) if f.endswith('.xml')]
|
||||
|
||||
if not xml_files:
|
||||
print(f"No XML files found in subfolder: {subfolder}")
|
||||
continue
|
||||
|
||||
# If any XML files are found, perform the data extraction. We use the subfolder name as the survey key.
|
||||
for xml_file in xml_files:
|
||||
xml_path = os.path.join(subfolder, xml_file)
|
||||
print(f"Processing XML file: {xml_path}")
|
||||
|
||||
# Read in the XML and parse it using the XmlParser class.
|
||||
with open(xml_path, 'rb') as file:
|
||||
xml_data_io = BytesIO(file.read())
|
||||
uprn = None # Set the UPRN if available.
|
||||
|
||||
# Create an XmlParser instance
|
||||
xml_parser = XmlParser(
|
||||
file=xml_data_io,
|
||||
filekey=xml_path,
|
||||
surveyor_company="",
|
||||
uprn=uprn,
|
||||
)
|
||||
|
||||
# Run the parser to extract the data
|
||||
xml_parser.run()
|
||||
if not xml_parser.epc:
|
||||
# If we don't have a lig xml
|
||||
continue
|
||||
|
||||
# Store the extracted data for further processing
|
||||
extracted_surveys.append({
|
||||
"survey_key": subfolder.split("/")[-1],
|
||||
**xml_parser.epc,
|
||||
**xml_parser.additional_data
|
||||
})
|
||||
|
||||
print(f"Extracted {len(extracted_surveys)} surveys.")
|
||||
# Process the extracted_surveys as needed, for example, save to a database or write to a file.
|
||||
extracted_surveys = pd.DataFrame(extracted_surveys)
|
||||
|
||||
# THis is the data we need for the AIHA project
|
||||
measures_data = extracted_surveys[
|
||||
["survey_key", "address", "postcode", "current-energy-efficiency", "current-energy-rating", "number_of_floors"]
|
||||
]
|
||||
measures_data = measures_data.sort_values("survey_key", ascending=True)
|
||||
|
||||
# Note:
|
||||
# The properties will still have "Very poor" ratings for their hot water
|
||||
|
||||
# TODO
|
||||
# - AIH001-03 has a loft that is inaccessible - ask Chenai about why this property didn't have access to the loft
|
||||
# [Can't remember, not clear - Chenai will check]
|
||||
# - AIH001-08 and AIH001-09, check if it's freehold - could solar work as both of these units are part of the same
|
||||
# buulding [Question for Lewis & Kevin]
|
||||
# - AIH001-09 - Is it not possible to install a loft hatch? [IT IS NOT, NO ACCESS - would need to accessed from
|
||||
# the other unit]
|
||||
# - AIH001-09 - Is there definitely an immersion water heater? Is this definitely the case for the other units?
|
||||
# [Question for Lewis & Kevin] - [YES - ASHP!!!!]
|
||||
|
||||
# TODO: Check which properties are in a conservation area
|
||||
# TODO: AIH001-16 - Is the loft insulation suitable (already has 100mm in the RIR)
|
||||
# TODO: Adjust Archetype 14 homes to exclude double glazing? Or should we exclude entirely
|
||||
|
||||
recommended_measures = [
|
||||
{
|
||||
"survey_key": "AIH001-01",
|
||||
"starting_sap": 69,
|
||||
"recommended_measures": [],
|
||||
"notes": "Is EPC C"
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-02",
|
||||
"starting_sap": 65,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "2.4kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "2.4W",
|
||||
"orientation": "Horizontal",
|
||||
"elavation": 30,
|
||||
"overshading": "None or little",
|
||||
}
|
||||
],
|
||||
"sap_points": 7,
|
||||
"ending_sap": 72,
|
||||
"notes": "The array can be mounted on the flat roof, so that panels are south facing"
|
||||
},
|
||||
{
|
||||
"measure": "TTZC",
|
||||
"description": "Smart Thermostat",
|
||||
"sap_points": 4,
|
||||
"ending_sap": 76
|
||||
}
|
||||
],
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-03",
|
||||
"starting_sap": 43,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Cylinder Insulation",
|
||||
"description": "80mm cylinder insulation",
|
||||
"sap_points": 1,
|
||||
"ending_sap": 44,
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "4kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "4kWp",
|
||||
"orientation": "East",
|
||||
"elavation": 30,
|
||||
"overshading": "None or little",
|
||||
},
|
||||
],
|
||||
"sap_points": 10,
|
||||
"ending_sap": 54
|
||||
},
|
||||
{
|
||||
"measure": "Air Source Heat Pump",
|
||||
"description": "Ecoforest ecoAIR EVI 4-20 20kW air source heat pump (+TTZC)",
|
||||
"sap_points": 20,
|
||||
"ending_sap": 74
|
||||
},
|
||||
{
|
||||
"measure": "Tariff Review",
|
||||
"description": "Switch to 24-hour tariff",
|
||||
"sap_points": 15,
|
||||
"ending_sap": 89
|
||||
}
|
||||
],
|
||||
"notes": "Unclear if the loft is accessible"
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-04",
|
||||
"starting_sap": 48,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Flat Roof Insulation",
|
||||
"description": "100mm flat roof insulation",
|
||||
"floor_area": 39.1482, # based on area of top floor
|
||||
"sap_points": 4,
|
||||
"ending_sap": 52
|
||||
},
|
||||
{
|
||||
"measure": "TTZC",
|
||||
"description": "Smart Thermostat",
|
||||
"sap_points": 3,
|
||||
"ending_sap": 55
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "4kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "4kWp",
|
||||
"orientation": "South",
|
||||
"elavation": 30,
|
||||
"overshading": "None or little",
|
||||
}
|
||||
],
|
||||
"sap_points": 15,
|
||||
"ending_sap": 70
|
||||
}
|
||||
],
|
||||
"notes": "Roof is flat, PV array should be installed south facing with elevation"
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-05",
|
||||
"starting_sap": 54,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Flat Roof Insulation",
|
||||
"description": "100mm flat roof insulation",
|
||||
"floor_area": 49.48, # based on area of top floor
|
||||
"sap_points": 5,
|
||||
"ending_sap": 59,
|
||||
},
|
||||
{
|
||||
"measure": "Cylinder Insulation",
|
||||
"description": "80mm cylinder insulation",
|
||||
"sap_points": 2,
|
||||
"ending_sap": 61,
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "4kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "4kW",
|
||||
"orientation": "Horizontal",
|
||||
"elavation": 30,
|
||||
"overshading": "Modest",
|
||||
}
|
||||
],
|
||||
"sap_points": 9,
|
||||
"ending_sap": 70
|
||||
},
|
||||
{
|
||||
"measure": "TTZC",
|
||||
"description": "Smart Thermostat",
|
||||
"sap_points": 3,
|
||||
"ending_sap": 73
|
||||
}
|
||||
],
|
||||
"notes": ""
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-06",
|
||||
"starting_sap": 62,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Cylinder Insulation",
|
||||
"description": "80mm cylinder insulation",
|
||||
"sap_points": 2,
|
||||
"ending_sap": 64,
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "2kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "2kW",
|
||||
"orientation": "South",
|
||||
"elavation": 30,
|
||||
"overshading": "Modest",
|
||||
}
|
||||
],
|
||||
"sap_points": 6,
|
||||
"ending_sap": 70
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-07",
|
||||
"starting_sap": 74,
|
||||
"recommended_measures": [],
|
||||
"notes": "Is EPC C"
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-08",
|
||||
"starting_sap": 56,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Loft Insulation",
|
||||
"description": "300mm loft insulation",
|
||||
"floor_area": 54.2864, # Based on area of top floor
|
||||
"sap_points": 2,
|
||||
"ending_sap": 58,
|
||||
},
|
||||
{
|
||||
"measure": "Cylinder Insulation",
|
||||
"description": "80mm cylinder insulation",
|
||||
"sap_points": 4,
|
||||
"ending_sap": 62,
|
||||
},
|
||||
{
|
||||
"measure": "Internal Wall Insulation",
|
||||
"description": "100mm internal wall insulation",
|
||||
"hlp": 24.13 * 2.63,
|
||||
"sap_points": 7,
|
||||
"ending_sap": 69,
|
||||
},
|
||||
{
|
||||
"measure": "Ventilation",
|
||||
"description": "2x DMEV fans",
|
||||
"sap_points": 0,
|
||||
"ending_sap": 69,
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-09",
|
||||
"starting_sap": 44,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Internal Wall Insulation",
|
||||
"description": "100mm internal wall insulation",
|
||||
"hlp": (22.35 * 3.24) + (22.13 * 2.53),
|
||||
"sap_points": 8,
|
||||
"ending_sap": 52,
|
||||
},
|
||||
{
|
||||
"measure": "Cavity Wall Insulation",
|
||||
"description": "CWI to rdSAP default standard",
|
||||
"hlp": (2.68 * 2.39) + (5.93 * 2.63) + (6.13 * 2.39), # 1st & 2nd extension
|
||||
"sap_points": 1,
|
||||
"ending_sap": 53,
|
||||
},
|
||||
{
|
||||
"measure": "Ventilation",
|
||||
"description": "2x DMEV fans",
|
||||
"sap_points": 0,
|
||||
"ending_sap": 53,
|
||||
},
|
||||
{
|
||||
"measure": "TTZC",
|
||||
"description": "Smart Thermostat",
|
||||
"sap_points": 3,
|
||||
"ending_sap": 56,
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "1.6kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "1.6W",
|
||||
"orientation": "South-East",
|
||||
"elavation": 30,
|
||||
"overshading": "None or little",
|
||||
}
|
||||
],
|
||||
"sap_points": 6,
|
||||
"ending_sap": 62
|
||||
},
|
||||
{
|
||||
"measure": "Loft Insulation",
|
||||
"description": "300mm loft insulation",
|
||||
"floor_area": 63.59 + 12.31, # Based on area of main building and 1st extension
|
||||
"sap_points": 8,
|
||||
"ending_sap": 70,
|
||||
"notes": "Loft is inaccessible from this unit - would need to be accessed from the other unit, "
|
||||
"which is also owned by AIHA"
|
||||
}
|
||||
],
|
||||
"notes": "This property is a house split into 2 flats. We can install a PV array for both units (one array"
|
||||
"per unit). Area on south-east part of roof is ~22m2 with no overshadowing. Flat roof area is 8m2"
|
||||
"with modest overshadowing. We suggest a 3.2kWp system, across two units"
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-11",
|
||||
"starting_sap": 59,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "TTZC",
|
||||
"description": "Smart Thermostat",
|
||||
"sap_points": 4,
|
||||
"ending_sap": 63,
|
||||
},
|
||||
{
|
||||
"measure": "Internal Wall Insulation",
|
||||
"description": "100mm internal wall insulation",
|
||||
"hlp": (18.50 * 3.12) + (19.00 * 2.75),
|
||||
"sap_points": 5,
|
||||
"ending_sap": 68,
|
||||
},
|
||||
{
|
||||
"measure": "Cylinder Insulation",
|
||||
"description": "80mm cylinder insulation",
|
||||
"sap_points": 1,
|
||||
"ending_sap": 69,
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-12",
|
||||
"starting_sap": 46,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Double Glazing",
|
||||
"description": "Installation of double glazing",
|
||||
"n_windows": 20, # Counted the bay windows each as 3
|
||||
"windows_area": 10.66,
|
||||
"sap_points": 3,
|
||||
"ending_sap": 49,
|
||||
},
|
||||
# {
|
||||
# "measure": "Solar PV",
|
||||
# "description": "3.2kWp Solar PV system",
|
||||
# "config": [
|
||||
# {
|
||||
# "size": "3.2W",
|
||||
# "orientation": "East",
|
||||
# "elavation": 30,
|
||||
# "overshading": "Little or none",
|
||||
# }
|
||||
# ],
|
||||
# "sap_points": 9,
|
||||
# "ending_sap": 58
|
||||
# },
|
||||
{
|
||||
"measure": "Air Source Heat Pump",
|
||||
"description": "Ecoforest ecoAIR EVI 4-20 20kW air source heat pump (+TTZC)",
|
||||
"sap_points": 15,
|
||||
"ending_sap": 65
|
||||
},
|
||||
{
|
||||
"measure": "Tariff Review",
|
||||
"description": "Switch to 24-hour tariff",
|
||||
"sap_points": 15,
|
||||
"ending_sap": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-13",
|
||||
"starting_sap": 53,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Roof Insulation",
|
||||
"description": "100mm+ RIR insulation on all surfaces (ceiling u=0.16, walls u=0.3)",
|
||||
"floor_area": 39.75, # based on the floor area of the RIR
|
||||
"sap_points": 6,
|
||||
"ending_sap": 59,
|
||||
},
|
||||
{
|
||||
"measure": "Flat Roof Insulation",
|
||||
"description": "100mm flat roof insulation",
|
||||
"floor_area": 33.06, # Based on area of the extension
|
||||
"sap_points": 2,
|
||||
"ending_sap": 61,
|
||||
},
|
||||
{
|
||||
"measure": "Cavity Wall Insulation",
|
||||
"description": "CWI to rdSAP default standard",
|
||||
"hlp": (35.40 * 2.65) + (26.70 * 2.73) + (16.30 * 2.71), # 1st & 2nd extension
|
||||
"sap_points": 6,
|
||||
"ending_sap": 67,
|
||||
},
|
||||
{
|
||||
"measure": "Ventilation",
|
||||
"description": "2x DMEV fans",
|
||||
"sap_points": 0,
|
||||
"ending_sap": 67,
|
||||
},
|
||||
{
|
||||
"measure": "TTZC",
|
||||
"description": "Smart Thermostat",
|
||||
"sap_points": 2,
|
||||
"ending_sap": 69,
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "4kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "4kW",
|
||||
"orientation": "Horizontal",
|
||||
"elavation": 30,
|
||||
"overshading": "None or little",
|
||||
}
|
||||
],
|
||||
"sap_points": 9,
|
||||
"ending_sap": 78
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-14",
|
||||
"starting_sap": 63,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Cavity Wall Insulation",
|
||||
"description": "CWI to rdSAP default standard",
|
||||
"hlp": (11.00 * 2.6) + (11.00 * 2.65) + (4.60 * 2.7),
|
||||
"sap_points": 5,
|
||||
"ending_sap": 68,
|
||||
},
|
||||
{
|
||||
"measure": "Ventilation",
|
||||
"description": "2x DMEV fans",
|
||||
"sap_points": 0,
|
||||
"ending_sap": 68,
|
||||
},
|
||||
{
|
||||
"measure": "Loft Insulation",
|
||||
"description": "300mm loft insulation", # Based on area of main building
|
||||
"floor_area": 59.20,
|
||||
"sap_points": 1,
|
||||
"ending_sap": 69,
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "3.2kWp Solar PV system",
|
||||
"sap_points": 10,
|
||||
"ending_sap": 79,
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-15",
|
||||
"starting_sap": 60,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Loft Insulation",
|
||||
"description": "300mm loft insulation",
|
||||
"floor_area": 73.81, # Based on area of main building
|
||||
"sap_points": 1,
|
||||
"ending_sap": 61,
|
||||
},
|
||||
{
|
||||
"measure": "TTZC",
|
||||
"description": "Smart Thermostat",
|
||||
"sap_points": 3,
|
||||
"ending_sap": 64,
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "3.2kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "3.2W",
|
||||
"orientation": "North-West",
|
||||
"elavation": 30,
|
||||
"overshading": "None or little",
|
||||
}
|
||||
],
|
||||
"sap_points": 7,
|
||||
"ending_sap": 71,
|
||||
"notes": "The array is North-west facing and therefore will be slightly less efficient than south"
|
||||
"facing, however the impact is not so severe as to make the installation not worthwhile."
|
||||
"Ground mounted"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-16",
|
||||
"starting_sap": 60,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Cavity Wall Insulation",
|
||||
"description": "CWI to rdSAP default standard",
|
||||
"hlp": (21.56 * 2.60) + (26.79 * 2.8) + (6.74 * 2.60),
|
||||
"sap_points": 4,
|
||||
"ending_sap": 64,
|
||||
},
|
||||
{
|
||||
"measure": "Ventilation",
|
||||
"description": "2x DMEV fans",
|
||||
"sap_points": 0,
|
||||
"ending_sap": 64,
|
||||
},
|
||||
{
|
||||
"measure": "Loft Insulation",
|
||||
"description": "300mm loft insulation",
|
||||
"floor_area": 20.92, # Based on floor area of RIR
|
||||
"sap_points": 1,
|
||||
"ending_sap": 65,
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "2.4kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "2.4W",
|
||||
"orientation": "South-East",
|
||||
"elavation": 30,
|
||||
"overshading": "Modest",
|
||||
}
|
||||
],
|
||||
"sap_points": 5,
|
||||
"ending_sap": 70,
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-17",
|
||||
"starting_sap": 62,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Cylinder Insulation",
|
||||
"description": "80mm cylinder insulation",
|
||||
"sap_points": 1,
|
||||
"ending_sap": 63,
|
||||
},
|
||||
{
|
||||
"measure": "TTZC",
|
||||
"description": "Smart Thermostat",
|
||||
"sap_points": 3,
|
||||
"ending_sap": 66,
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "4kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "3.2kW",
|
||||
"orientation": "East",
|
||||
"elavation": 30,
|
||||
"overshading": "None or little",
|
||||
},
|
||||
{
|
||||
"size": "0.8kW",
|
||||
"orientation": "West",
|
||||
"elavation": 30,
|
||||
"overshading": "None or little",
|
||||
}
|
||||
],
|
||||
"sap_points": 12,
|
||||
"ending_sap": 78,
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-18",
|
||||
"starting_sap": 58,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Loft Insulation",
|
||||
"description": "300mm loft insulation",
|
||||
"floor_area": 37.52, # Based on area of main building and 1st extension
|
||||
"sap_points": 7,
|
||||
"ending_sap": 65,
|
||||
},
|
||||
{
|
||||
"measure": "Cylinder Insulation",
|
||||
"description": "80mm cylinder insulation",
|
||||
"sap_points": 1,
|
||||
"ending_sap": 66,
|
||||
},
|
||||
{
|
||||
"measure": "TTZC",
|
||||
"description": "Smart Thermostat",
|
||||
"sap_points": 2,
|
||||
"ending_sap": 68,
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "3.2kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "3.2W",
|
||||
"orientation": "North-East",
|
||||
"elavation": 30,
|
||||
"overshading": "None or little",
|
||||
}
|
||||
],
|
||||
"sap_points": 7,
|
||||
"ending_sap": 75,
|
||||
}
|
||||
],
|
||||
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-19",
|
||||
"starting_sap": 76,
|
||||
"recommended_measures": []
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-20",
|
||||
"starting_sap": 82,
|
||||
"recommended_measures": []
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-21",
|
||||
"starting_sap": 53,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Cyliner Insulation",
|
||||
"description": "80mm cylinder insulation",
|
||||
"sap_points": 2,
|
||||
"ending_sap": 55,
|
||||
},
|
||||
{
|
||||
"measure": "Roof Insulation",
|
||||
"description": "100mm+ RIR insulation on all surfaces (ceiling u=0.16, walls u=0.3)",
|
||||
"floor_area": 22.80, # Based on floor area of RIR
|
||||
"sap_points": 7,
|
||||
"ending_sap": 62,
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "2.4kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "1.6kWp",
|
||||
"orientation": "Horizontal",
|
||||
"elavation": 30,
|
||||
"overshading": "None or little",
|
||||
},
|
||||
{
|
||||
"size": "0.8kWp",
|
||||
"orientation": "South-East",
|
||||
"elavation": 30,
|
||||
"overshading": "None or little",
|
||||
}
|
||||
],
|
||||
"sap_points": 9,
|
||||
"ending_sap": 71,
|
||||
},
|
||||
{
|
||||
"measure": "TTZC",
|
||||
"description": "Smart Thermostat",
|
||||
"sap_points": 3,
|
||||
"ending_sap": 74,
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-SIMULATED-01",
|
||||
"elmhurst_reference": "000020",
|
||||
"starting_sap": None,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Internal Wall Insulation",
|
||||
"description": "100mm internal wall insulation",
|
||||
"hlp": (22.35 * 3.24) + (22.13 * 2.53),
|
||||
"sap_points": 8,
|
||||
"ending_sap": 52,
|
||||
},
|
||||
{
|
||||
"measure": "Cavity Wall Insulation",
|
||||
"description": "CWI to rdSAP default standard",
|
||||
"hlp": (2.68 * 2.39) + (5.93 * 2.63) + (6.13 * 2.39), # 1st & 2nd extension
|
||||
"sap_points": 1,
|
||||
"ending_sap": 53,
|
||||
},
|
||||
{
|
||||
"measure": "Ventilation",
|
||||
"description": "2x DMEV fans",
|
||||
"sap_points": 0,
|
||||
"ending_sap": 53,
|
||||
},
|
||||
{
|
||||
"measure": "TTZC",
|
||||
"description": "Smart Thermostat",
|
||||
"sap_points": 3,
|
||||
"ending_sap": 56,
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "1.6kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "1.6W",
|
||||
"orientation": "South-East",
|
||||
"elavation": 30,
|
||||
"overshading": "None or little",
|
||||
}
|
||||
],
|
||||
"sap_points": 6,
|
||||
"ending_sap": 62
|
||||
},
|
||||
{
|
||||
"measure": "Loft Insulation",
|
||||
"description": "300mm loft insulation",
|
||||
"floor_area": 63.59 + 12.31, # Based on area of main building and 1st extension
|
||||
"sap_points": 8,
|
||||
"ending_sap": 70,
|
||||
"notes": "Loft is inaccessible from this unit - would need to be accessed from the other unit, "
|
||||
"which is also owned by AIHA"
|
||||
}
|
||||
],
|
||||
"notes": "This was cloned from 80A. There is no existing data for 80B"
|
||||
},
|
||||
{
|
||||
"survey_key": "AIH001-SIMULATED-05",
|
||||
"starting_sap": 68,
|
||||
"recommended_measures": [
|
||||
{
|
||||
"measure": "Loft Insulation",
|
||||
"description": "300mm loft insulation",
|
||||
"floor_area": 42.5,
|
||||
"sap_points": 1,
|
||||
"ending_sap": 69,
|
||||
},
|
||||
{
|
||||
"measure": "Solar PV",
|
||||
"description": "3.2kWp Solar PV system",
|
||||
"config": [
|
||||
{
|
||||
"size": "3.2W",
|
||||
"orientation": "North-East",
|
||||
"elavation": 30,
|
||||
"overshading": "None or little",
|
||||
}
|
||||
],
|
||||
"sap_points": 8,
|
||||
"ending_sap": 77,
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
|
||||
scaffolding_data = [
|
||||
{
|
||||
"number_of_floors": 2,
|
||||
"price": 841,
|
||||
},
|
||||
{
|
||||
"number_of_floors": 3,
|
||||
"price": 1077,
|
||||
}
|
||||
]
|
||||
|
||||
# TODO - Need an update cost for cylinder insulation
|
||||
pricing_data = [
|
||||
{'item': '80mm cylinder insulation', 'unit_price': 50, 'unit': 'unit'},
|
||||
{'item': '100mm internal wall insulation', 'unit_price': 244.8, 'unit': 'hlp_m2'},
|
||||
{'item': 'CWI to rdSAP default standard', 'unit_price': 14.21, 'unit': 'hlp_m2'},
|
||||
{'item': 'Window draught proofing improvements', 'unit_price': 63, 'unit': 'window'},
|
||||
{'item': '100mm flat roof insulation', 'unit_price': 195, 'unit': 'floor_m2'},
|
||||
{'item': 'Switch to 24-hour tariff', 'unit_price': 0, 'unit': None},
|
||||
{'item': 'Installation of double glazing', 'unit_price': 1074, 'unit': 'window'},
|
||||
{'item': 'Ecoforest ecoAIR EVI 4-20 20kW air source heat pump (+TTZC)', 'unit_price': 21189 + 1200,
|
||||
'unit': 'unit'},
|
||||
{'item': '100mm+ RIR insulation on all surfaces (ceiling u=0.16, walls u=0.3)', 'unit_price': 244.80,
|
||||
'unit': 'floor_m2'},
|
||||
{'item': '300mm loft insulation', 'unit_price': 16.07, 'unit': 'floor_m2'},
|
||||
{'item': 'Smart Thermostat', 'unit_price': 1200, 'unit': 'unit'},
|
||||
{'item': '2x DMEV fans', 'unit_price': 1070, 'unit': 'unit'},
|
||||
{'item': '1.6kWp Solar PV system', 'unit_price': 3040, 'unit': 'unit_needs_scaffolding'},
|
||||
{'item': '2kWp Solar PV system', 'unit_price': 3201, 'unit': 'unit_needs_scaffolding'},
|
||||
{'item': '2.4kWp Solar PV system', 'unit_price': 3363, 'unit': 'unit_needs_scaffolding'},
|
||||
{'item': '3.2kWp Solar PV system', 'unit_price': 3686, 'unit': 'unit_needs_scaffolding'},
|
||||
{'item': '4kWp Solar PV system', 'unit_price': 4009, 'unit': 'unit_needs_scaffolding'},
|
||||
{'item': '5.6kWp Solar PV system', 'unit_price': 5015, 'unit': 'unit_needs_scaffolding'},
|
||||
]
|
||||
pricing_data = pd.DataFrame(pricing_data)
|
||||
|
||||
for recommendation in recommended_measures:
|
||||
property_data = measures_data[measures_data["survey_key"] == recommendation["survey_key"]].squeeze()
|
||||
total_cost = 0
|
||||
|
||||
for measure in recommendation["recommended_measures"]:
|
||||
measure_pricing = pricing_data[pricing_data["item"] == measure["description"]]
|
||||
measure_unit = measure_pricing["unit"].values[0]
|
||||
|
||||
if measure_unit in ["unit", None]:
|
||||
measure_cost = float(measure_pricing["unit_price"].values[0])
|
||||
elif measure_unit == "unit_needs_scaffolding":
|
||||
n_floors = property_data["number_of_floors"]
|
||||
scaffolding_cost = [x for x in scaffolding_data if x["number_of_floors"] == n_floors][0]["price"]
|
||||
measure_cost = float(measure_pricing["unit_price"].values[0]) + scaffolding_cost
|
||||
elif measure_unit == "floor_m2":
|
||||
measure_cost = float(measure_pricing["unit_price"].values[0]) * measure["floor_area"]
|
||||
elif measure_unit == "hlp_m2":
|
||||
measure_cost = float(measure_pricing["unit_price"].values[0]) * measure["hlp"]
|
||||
elif measure_unit == "window":
|
||||
measure_cost = float(measure_pricing["unit_price"].values[0]) * measure["n_windows"]
|
||||
else:
|
||||
raise Exception("Unknown unit type")
|
||||
|
||||
measure["Total Cost"] = measure_cost
|
||||
total_cost += measure_cost
|
||||
|
||||
recommendation["total_cost"] = total_cost
|
||||
|
||||
# Step 1: Normalize the recommended_measures data into a DataFrame.
|
||||
normalized_measures = []
|
||||
for survey in recommended_measures:
|
||||
survey_key = survey["survey_key"]
|
||||
starting_sap = survey["starting_sap"]
|
||||
total_cost = survey.get("total_cost", 0)
|
||||
|
||||
for measure in survey.get("recommended_measures", []):
|
||||
# Include hlp and floor_area for each measure if available
|
||||
hlp = measure.get("hlp", None)
|
||||
floor_area = measure.get("floor_area", None)
|
||||
|
||||
normalized_measures.append({
|
||||
"survey_key": survey_key,
|
||||
"hlp": hlp,
|
||||
"floor_area": floor_area,
|
||||
"starting_sap": starting_sap,
|
||||
"measure": measure["measure"],
|
||||
"description": measure.get("description", ""),
|
||||
"sap_points": measure.get("sap_points", 0),
|
||||
"measure_cost": measure.get("Total Cost", 0),
|
||||
"total_cost": total_cost
|
||||
})
|
||||
|
||||
# Convert the normalized list into a DataFrame.
|
||||
measures_df = pd.DataFrame(normalized_measures)
|
||||
|
||||
# Step 2: Pivot the measures_df to have a column for each measure type, using the description as values.
|
||||
pivoted_measures = measures_df.pivot_table(
|
||||
index="survey_key",
|
||||
columns="measure",
|
||||
values="description",
|
||||
aggfunc=lambda x: ' '.join(x), # Concatenate descriptions if there are multiple entries.
|
||||
fill_value=None
|
||||
).reset_index()
|
||||
|
||||
measures_columns = [x for x in pivoted_measures.columns if x not in ["survey_key"]]
|
||||
# We add a "Cost of" column for each measure
|
||||
for measure in measures_columns:
|
||||
pivoted_measures[f"Cost of {measure}"] = None
|
||||
|
||||
pivoted_floor_area = measures_df.pivot_table(
|
||||
index="survey_key",
|
||||
columns="measure",
|
||||
values="floor_area",
|
||||
aggfunc="first" # Use 'first' since each measure should only appear once per survey_key
|
||||
).add_prefix("floor_area - ").reset_index()
|
||||
|
||||
pivoted_hlp = measures_df.pivot_table(
|
||||
index="survey_key",
|
||||
columns="measure",
|
||||
values="hlp",
|
||||
aggfunc="first"
|
||||
).add_prefix("hlp - ").reset_index()
|
||||
|
||||
# Merge hlp and floor_area data
|
||||
pivoted_measures = pivoted_measures.merge(pivoted_hlp, on="survey_key", how="left")
|
||||
pivoted_measures = pivoted_measures.merge(pivoted_floor_area, on="survey_key", how="left")
|
||||
|
||||
# Step 3: Calculate the total sap points and total cost for each survey.
|
||||
totals = measures_df.groupby("survey_key").agg(
|
||||
total_sap_points=("sap_points", "sum"),
|
||||
).reset_index()
|
||||
|
||||
# Merge total sap points into the pivoted measures.
|
||||
pivoted_measures = pd.merge(pivoted_measures, totals, on="survey_key", how="left")
|
||||
# pivoted_measures["Cost Contingency"] = pivoted_measures["total_cost_of_measures"] * CONTINGENCY_RATE
|
||||
# pivoted_measures["Total Cost"] = pivoted_measures["total_cost_of_measures"] + pivoted_measures["Cost Contingency"]
|
||||
|
||||
# Step 4: Extract starting SAP for each survey key.
|
||||
starting_sap_df = measures_df.drop_duplicates(subset=["survey_key"])[["survey_key", "starting_sap"]]
|
||||
|
||||
# Merge starting SAP back onto pivoted measures.
|
||||
result_df = pd.merge(pivoted_measures, starting_sap_df, on="survey_key", how="left")
|
||||
|
||||
# Step 5: Calculate the ending SAP.
|
||||
result_df["Ending SAP"] = result_df["starting_sap"] + result_df["total_sap_points"]
|
||||
result_df["Ending EPC Rating"] = result_df["Ending SAP"].apply(sap_to_epc)
|
||||
|
||||
# Step 6: Merge the result with the measures_data to get the final DataFrame.
|
||||
final_measures = measures_data.merge(
|
||||
result_df, how="left", on="survey_key"
|
||||
)
|
||||
|
||||
final_measures.to_csv("/Users/khalimconn-kowlessar/Documents/hestia/Customers/AIHA/Measures packages.csv")
|
||||
|
||||
# Store costs
|
||||
pricing_data.to_csv("/Users/khalimconn-kowlessar/Documents/hestia/Customers/AIHA/Pricing data.csv")
|
||||
|
||||
# if __name__ == "__main__":
|
||||
# main()
|
||||
225
etl/customers/livewest/route_march_2024_10_28.py
Normal file
225
etl/customers/livewest/route_march_2024_10_28.py
Normal file
|
|
@ -0,0 +1,225 @@
|
|||
import os
|
||||
import time
|
||||
|
||||
import pandas as pd
|
||||
from tqdm import tqdm
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from utils.s3 import read_excel_from_s3
|
||||
from backend.SearchEpc import SearchEpc
|
||||
from etl.epc_clean.epc_attributes.RoofAttributes import RoofAttributes
|
||||
|
||||
from recommendations.recommendation_utils import (
|
||||
estimate_perimeter,
|
||||
estimate_external_wall_area,
|
||||
estimate_number_of_floors
|
||||
)
|
||||
|
||||
load_dotenv(dotenv_path="backend/.env")
|
||||
EPC_AUTH_TOKEN = os.getenv("EPC_AUTH_TOKEN")
|
||||
|
||||
|
||||
def get_data(asset_list):
|
||||
epc_data = []
|
||||
errors = []
|
||||
for _, home in tqdm(asset_list.iterrows(), total=len(asset_list)):
|
||||
try:
|
||||
postcode = home["Postcode"]
|
||||
house_number = home["Number"]
|
||||
full_address = home["Full Address"]
|
||||
|
||||
searcher = SearchEpc(
|
||||
address1=str(house_number),
|
||||
postcode=postcode,
|
||||
auth_token=EPC_AUTH_TOKEN,
|
||||
os_api_key="",
|
||||
property_type=None,
|
||||
fast=True,
|
||||
full_address=full_address,
|
||||
max_retries=5
|
||||
)
|
||||
# Force the skipping of estimating the EPC
|
||||
searcher.ordnance_survey_client.property_type = None
|
||||
searcher.ordnance_survey_client.built_form = None
|
||||
|
||||
searcher.find_property(skip_os=True)
|
||||
if searcher.newest_epc is None:
|
||||
continue
|
||||
|
||||
# Look for EPC recommendatons
|
||||
try:
|
||||
property_recommendations = searcher.client.domestic.recommendations(searcher.newest_epc["lmk-key"])
|
||||
except:
|
||||
property_recommendations = {"rows": []}
|
||||
|
||||
epc = {
|
||||
"row_id": home["row_id"],
|
||||
**searcher.newest_epc.copy(),
|
||||
"recommendations": property_recommendations["rows"]
|
||||
}
|
||||
|
||||
epc_data.append(epc)
|
||||
except Exception as e:
|
||||
errors.append(home["row_id"])
|
||||
time.sleep(5)
|
||||
|
||||
return epc_data, errors
|
||||
|
||||
|
||||
def app():
|
||||
"""
|
||||
This app is EPC pulling data for some properties owned by Livewest
|
||||
|
||||
Data request contents:
|
||||
Date of last EPC
|
||||
Reason for EPC
|
||||
SAP score on register
|
||||
Property Type
|
||||
Property Area
|
||||
Property Age
|
||||
Any Dimensions (HLP,PW,RH)
|
||||
Property Wall Construction
|
||||
Heating Type
|
||||
Secondary Heating
|
||||
Loft Insulation Depth
|
||||
|
||||
Additional if possible:
|
||||
Heat loss calculations
|
||||
EPC recommendations
|
||||
Property UPRN
|
||||
|
||||
"""
|
||||
asset_list = pd.read_excel(
|
||||
"/Users/khalimconn-kowlessar/Downloads/LIVEWEST 3578 ECO4 ECO PLUS GBIS.xlsx", header=0
|
||||
)
|
||||
asset_list["row_id"] = asset_list.index
|
||||
|
||||
epc_data, errors = get_data(asset_list)
|
||||
|
||||
# We now retrieve any failed properties
|
||||
asset_list_failed = asset_list[asset_list["row_id"].isin(errors)]
|
||||
epc_data_failed, _ = get_data(asset_list_failed)
|
||||
|
||||
# Append the failed data to the main data
|
||||
epc_data.extend(epc_data_failed)
|
||||
|
||||
epc_df = pd.DataFrame(epc_data)
|
||||
|
||||
# We expand out the recommendations
|
||||
recommendations_df = epc_df[["row_id", "recommendations"]]
|
||||
|
||||
unique_recommendations = set()
|
||||
for _, row in recommendations_df.iterrows():
|
||||
unique_recommendations.update([rec["improvement-summary-text"] for rec in row["recommendations"]])
|
||||
|
||||
columns = ["row_id"] + list(unique_recommendations)
|
||||
transformed_data = []
|
||||
for _, row in recommendations_df.iterrows():
|
||||
# Initialize a dictionary for this row with False for all recommendations
|
||||
row_data = {col: False for col in columns}
|
||||
row_data["row_id"] = row["row_id"]
|
||||
|
||||
# Set True for each recommendation present in this row
|
||||
for rec in row["recommendations"]:
|
||||
recommendation_text = rec["improvement-summary-text"]
|
||||
row_data[recommendation_text] = True
|
||||
|
||||
# Append the row data to transformed_data
|
||||
transformed_data.append(row_data)
|
||||
|
||||
transformed_df = pd.DataFrame(transformed_data)
|
||||
# Drop the column that is ""
|
||||
transformed_df = transformed_df.drop(columns=[""])
|
||||
|
||||
# Retrieve just the data we need
|
||||
epc_df = epc_df[
|
||||
[
|
||||
"row_id",
|
||||
"uprn",
|
||||
"property-type",
|
||||
"built-form",
|
||||
"inspection-date",
|
||||
"current-energy-rating",
|
||||
"current-energy-efficiency",
|
||||
"roof-description",
|
||||
"walls-description",
|
||||
"transaction-type",
|
||||
# New fields needed
|
||||
"secondheat-description",
|
||||
"total-floor-area",
|
||||
"construction-age-band",
|
||||
"floor-height",
|
||||
"number-habitable-rooms",
|
||||
"mainheat-description",
|
||||
#
|
||||
"energy-consumption-current", # kwh/m2
|
||||
]
|
||||
]
|
||||
|
||||
asset_list = asset_list.merge(
|
||||
epc_df,
|
||||
how="left",
|
||||
on="row_id"
|
||||
).merge(
|
||||
transformed_df,
|
||||
how="left",
|
||||
on="row_id"
|
||||
)
|
||||
|
||||
asset_list = asset_list.drop(columns=["row_id"])
|
||||
|
||||
# Rename the columns
|
||||
asset_list = asset_list.rename(columns={
|
||||
"inspection-date": "Date of last EPC",
|
||||
"current-energy-efficiency": "SAP score on register",
|
||||
"current-energy-rating": "EPC rating on register",
|
||||
"property-type": "Property Type",
|
||||
"built-form": "Archetype",
|
||||
"total-floor-area": "Property Floor Area",
|
||||
"construction-age-band": "Property Age Band",
|
||||
"floor-height": "Property Floor Height",
|
||||
"number-habitable-rooms": "Number of Habitable Rooms",
|
||||
"walls-description": "Wall Construction",
|
||||
"roof-description": "Roof Construction",
|
||||
"mainheat-description": "Heating Type",
|
||||
"secondheat-description": "Secondary Heating",
|
||||
"transaction-type": "Reason for last EPC",
|
||||
"energy-consumption-current": "Heat Demand (kWh/m2)"
|
||||
})
|
||||
|
||||
asset_list["Estimated Number of Floors"] = asset_list.apply(
|
||||
lambda x: estimate_number_of_floors(property_type=x["Property Type"]) if not pd.isnull(
|
||||
x["Property Type"]) else None, axis=1
|
||||
)
|
||||
|
||||
asset_list["Property Floor Area"] = asset_list["Property Floor Area"].astype(float)
|
||||
# Replace "" value with None
|
||||
asset_list["Number of Habitable Rooms"] = asset_list["Number of Habitable Rooms"].replace("", None)
|
||||
asset_list["Number of Habitable Rooms"] = asset_list["Number of Habitable Rooms"].astype(float)
|
||||
|
||||
asset_list["Estimated Perimeter (m)"] = asset_list.apply(
|
||||
lambda x: estimate_perimeter(
|
||||
floor_area=x["Property Floor Area"] / x["Estimated Number of Floors"],
|
||||
num_rooms=x["Number of Habitable Rooms"] / x["Estimated Number of Floors"],
|
||||
), axis=1
|
||||
)
|
||||
|
||||
asset_list["Estimated Heat Loss Perimeter (m2)"] = asset_list.apply(
|
||||
lambda x: estimate_external_wall_area(
|
||||
num_floors=x["Estimated Number of Floors"],
|
||||
floor_height=float(x["Property Floor Height"]) if x["Property Floor Height"] else 2.5,
|
||||
perimeter=x["Estimated Perimeter (m)"],
|
||||
built_form=x["Archetype"]
|
||||
),
|
||||
axis=1
|
||||
)
|
||||
|
||||
asset_list["Roof Insulation Thickness"] = asset_list.apply(
|
||||
lambda x: RoofAttributes(description=x["Roof Construction"]).process()["insulation_thickness"] if not pd.isnull(
|
||||
x["Roof Construction"]) else None,
|
||||
axis=1
|
||||
)
|
||||
|
||||
# Store as an excel
|
||||
filename = "livewest EPC Data pull - 29 Oct.xlsx"
|
||||
asset_list.to_excel(filename, index=False)
|
||||
1320
etl/customers/stonewater/Wave 3 Preparation.py
Normal file
1320
etl/customers/stonewater/Wave 3 Preparation.py
Normal file
File diff suppressed because it is too large
Load diff
|
|
@ -0,0 +1,4 @@
|
|||
PyPDF2
|
||||
pandas
|
||||
tqdm
|
||||
openpyxl
|
||||
|
|
@ -9,7 +9,8 @@ from etl.xml_survey_extraction.pcdb import heating_data
|
|||
PROPERTY_TYPE_LOOKUP = {
|
||||
"0": "House",
|
||||
"House": "House",
|
||||
"2": "Flat"
|
||||
"2": "Flat",
|
||||
"3": "Maisonette",
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -107,11 +108,13 @@ class XmlParser:
|
|||
|
||||
BUILT_FORM_MAP = {
|
||||
"1": "Detached",
|
||||
"2": "Semi-Detached",
|
||||
"3": "End-Terrace",
|
||||
"4": "Mid-Terrace",
|
||||
}
|
||||
|
||||
GLAZED_AREA_MAP = {
|
||||
"2": "More than Typical",
|
||||
"4": "Much More Than Typical"
|
||||
}
|
||||
|
||||
|
|
@ -120,7 +123,9 @@ class XmlParser:
|
|||
}
|
||||
|
||||
TRANSACTION_TYPE_MAP = {
|
||||
"13": "ECO assessment"
|
||||
"5": "Rented (social)",
|
||||
"13": "ECO assessment",
|
||||
"14": "Stock condition survey",
|
||||
}
|
||||
|
||||
TENURE_MAP = {
|
||||
|
|
@ -131,7 +136,8 @@ class XmlParser:
|
|||
|
||||
TARIFF_MAP = {
|
||||
"1": "Dual",
|
||||
"2": "Single"
|
||||
"2": "Single",
|
||||
"3": "Unknown"
|
||||
}
|
||||
|
||||
def __init__(self, file, filekey, surveyor_company, uprn=None):
|
||||
|
|
@ -400,8 +406,13 @@ class XmlParser:
|
|||
]
|
||||
|
||||
wall_areas = sum([float(f["heat_loss_perimeter"]) * float(f["room_height"]) for f in main_dwelling_floors])
|
||||
window_areas = sum([float(w["window_area"]) for w in main_dwelling_windows])
|
||||
return wall_areas - window_areas
|
||||
window_areas = [float(w["window_area"]) for w in main_dwelling_windows if w["window_area"] is not None]
|
||||
if not window_areas:
|
||||
# We discount 10% of the wall area
|
||||
insulation_wall_area = wall_areas * 0.9
|
||||
else:
|
||||
insulation_wall_area = wall_areas - sum(window_areas)
|
||||
return insulation_wall_area
|
||||
|
||||
def extract_additional_data(self):
|
||||
|
||||
|
|
@ -415,7 +426,8 @@ class XmlParser:
|
|||
main_dwelling_windows = [w for w in self.windows if w["window_location"] == "0"]
|
||||
|
||||
number_of_windows = len(main_dwelling_windows)
|
||||
windows_area = sum([float(w["window_area"]) for w in main_dwelling_windows])
|
||||
windows_area = [float(w["window_area"]) for w in main_dwelling_windows if w["window_area"] is not None]
|
||||
windows_area = sum(windows_area) if windows_area else None
|
||||
|
||||
boolean_lookup = {
|
||||
"true": True,
|
||||
|
|
@ -427,6 +439,7 @@ class XmlParser:
|
|||
cylinder_insulation_type = {
|
||||
None: "",
|
||||
"1": "Foam",
|
||||
"2": "Jacket"
|
||||
}
|
||||
|
||||
cylinder_insulation_thickness = int(
|
||||
|
|
@ -461,7 +474,7 @@ class XmlParser:
|
|||
"cylinder_thermostat": cylinder_thermostat,
|
||||
"main_dwelling_ground_floor_area": float(main_dwelling_ground_floor_area),
|
||||
"number_of_windows": int(number_of_windows),
|
||||
"windows_area": float(windows_area),
|
||||
"windows_area": float(windows_area) if windows_area is not None else windows_area,
|
||||
}
|
||||
|
||||
def get_node_value(self, tag_name):
|
||||
|
|
@ -769,9 +782,10 @@ class XmlParser:
|
|||
:return:
|
||||
"""
|
||||
|
||||
sap_windows = self.xml.getElementsByTagName("SAP-Windows")[0].getElementsByTagName("SAP-Window")
|
||||
|
||||
glazing_type_lookup = {
|
||||
"ND": "Single glazing",
|
||||
"1": "double glazing installed before 2002",
|
||||
"2": "double glazing installed during or after 2002",
|
||||
"3": "double glazing, unknown install date",
|
||||
"5": "Single glazing",
|
||||
}
|
||||
|
|
@ -787,6 +801,40 @@ class XmlParser:
|
|||
"8": "North West"
|
||||
}
|
||||
|
||||
sap_windows = self.xml.getElementsByTagName("SAP-Windows")
|
||||
|
||||
if not sap_windows:
|
||||
# We look for Multi-Glazed-Proportion
|
||||
multiple_glazing_type = self.xml.getElementsByTagName("SAP-Property-Details")[0].getElementsByTagName(
|
||||
"Multiple-Glazing-Type"
|
||||
)[0].firstChild.nodeValue
|
||||
|
||||
pvc_frame = self.xml.getElementsByTagName("SAP-Property-Details")[0].getElementsByTagName(
|
||||
"PVC-Window-Frames"
|
||||
)
|
||||
|
||||
pvc_frame = pvc_frame[0].firstChild.nodeValue if pvc_frame else None
|
||||
|
||||
multple_glazed_proportion = self.xml.getElementsByTagName("SAP-Property-Details")[0].getElementsByTagName(
|
||||
"Multiple-Glazed-Proportion"
|
||||
)[0].firstChild.nodeValue
|
||||
|
||||
self.windows = [
|
||||
{
|
||||
"window_location": "0",
|
||||
"window_area": None,
|
||||
"window_type": None,
|
||||
"glazing_type": glazing_type_lookup[multiple_glazing_type],
|
||||
"pvc_frame": pvc_frame,
|
||||
"glazing_gap": None,
|
||||
"orientation": None,
|
||||
"multple_glazed_proportion": multple_glazed_proportion
|
||||
}
|
||||
]
|
||||
return
|
||||
|
||||
sap_windows = sap_windows[0].getElementsByTagName("SAP-Window")
|
||||
|
||||
self.windows = [
|
||||
self._parse_windows_content(
|
||||
window=window,
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue