implemented estimation method for homes without epc

backend/SearchEpc.py

@@ -4,6 +4,7 @@ import re
 
 import usaddress
 import pandas as pd
+import numpy as np
 from epc_api.client import EpcClient
 from utils.logger import setup_logger
 from typing import List
@@ -11,6 +12,101 @@ from fuzzywuzzy import process
 
 logger = setup_logger()
 
+vartypes = {
+    'low-energy-fixed-light-count': "Int64",
+    # 'address': 'str',
+    # 'uprn-source': 'str',
+    'floor-height': 'float',
+    'heating-cost-potential': 'float',
+    'unheated-corridor-length': 'float',
+    'hot-water-cost-potential': 'float',
+    'construction-age-band': 'str',
+    'potential-energy-rating': 'str',
+    'mainheat-energy-eff': 'str',
+    'windows-env-eff': 'str',
+    'lighting-energy-eff': 'str',
+    'environment-impact-potential': "Int64",
+    'glazed-type': 'str',
+    'heating-cost-current': 'float',
+    'address3': 'str',
+    'mainheatcont-description': 'str',
+    'sheating-energy-eff': 'str',
+    'property-type': 'str',
+    'local-authority-label': 'str',
+    'fixed-lighting-outlets-count': "Int64",
+    'energy-tariff': 'str',
+    'mechanical-ventilation': 'str',
+    'hot-water-cost-current': 'str',
+    'county': 'str',
+    'postcode': 'str',
+    'solar-water-heating-flag': 'str',
+    'constituency': 'str',
+    'co2-emissions-potential': 'float',
+    'number-heated-rooms': 'float',
+    'floor-description': 'str',
+    'energy-consumption-potential': 'float',
+    'local-authority': 'str',
+    'built-form': 'str',
+    'number-open-fireplaces': "Int64",
+    'windows-description': 'str',
+    'glazed-area': 'str',
+    # 'inspection-date': str,
+    'mains-gas-flag': 'str',
+    'co2-emiss-curr-per-floor-area': 'float',
+    'address1': 'str',
+    'heat-loss-corridor': 'str',
+    'flat-storey-count': "Int64",
+    'constituency-label': 'str',
+    'roof-energy-eff': 'str',
+    'total-floor-area': 'float',
+    'building-reference-number': 'str',
+    'environment-impact-current': 'float',
+    'co2-emissions-current': 'float',
+    'roof-description': 'str',
+    'floor-energy-eff': 'str',
+    'number-habitable-rooms': 'float',
+    'address2': 'str',
+    'hot-water-env-eff': 'str',
+    'posttown': 'str',
+    'mainheatc-energy-eff': 'str',
+    'main-fuel': 'str',
+    'lighting-env-eff': 'str',
+    'windows-energy-eff': 'str',
+    'floor-env-eff': 'str',
+    'sheating-env-eff': 'str',
+    'lighting-description': 'str',
+    'roof-env-eff': 'str',
+    'walls-energy-eff': 'str',
+    'photo-supply': 'float',
+    'lighting-cost-potential': 'float',
+    'mainheat-env-eff': 'str',
+    'multi-glaze-proportion': 'float',
+    'main-heating-controls': 'str',
+    # 'lodgement-datetime',
+    'flat-top-storey': 'str',
+    'current-energy-rating': 'str',
+    'secondheat-description': 'str',
+    'walls-env-eff': 'str',
+    'transaction-type': 'str',
+    # 'uprn': "Int64",
+    'current-energy-efficiency': 'float',
+    'energy-consumption-current': 'float',
+    'mainheat-description': 'str',
+    'lighting-cost-current': 'float',
+    # 'lodgement-date',
+    'extension-count': "Int64",
+    'mainheatc-env-eff': 'str',
+    'lmk-key': 'str',
+    'wind-turbine-count': "Int64",
+    'tenure': 'str',
+    'floor-level': 'str',
+    'potential-energy-efficiency': "Int64",
+    'hot-water-energy-eff': 'str',
+    'low-energy-lighting': 'float',
+    'walls-description': 'str',
+    'hotwater-description': 'str'
+}
+
 
 class SearchEpc:
     """
@@ -1953,9 +2049,51 @@ class SearchEpc:
             (epc_data["built-form"] == estimation_built_form) & (epc_data["property-type"] == estimation_property_type)
             ]
 
+        epc_data["weight"] = 1 / epc_data["house_number_distance"]
+
         # We use house_number_distance as a weighting where closer homes are upweighted when interpolating
 
         # For each attribute, we need to determine the datatype and use an appropriate method
         # to interpolate.
-        for attribute in epc_data.columns:
-            estimation_data = epc_data[[attribute, "house_number_distance"]]
+
+        estimated_epc = {}
+        for key, vartype in vartypes.items():
+            epc_data[key] = np.where(pd.isnull(epc_data[key]), None, epc_data[key])
+            epc_data[key] = np.where(epc_data[key] == "", None, epc_data[key])
+            epc_data[key] = epc_data[key].astype(vartype)
+            estimation_data = epc_data[[key, "weight"]]
+            estimation_data = estimation_data[~pd.isnull(estimation_data[key])]
+
+            if estimation_data.shape[0] == 0:
+                estimated_epc[key] = None
+                continue
+
+            if vartype == "Int64":
+                estimated_value = self._estimate_int(estimation_data, key)
+            elif vartype == "float":
+                estimated_value = self._estimate_float(estimation_data, key)
+            elif vartype == "str":
+                estimated_value = self._estimate_str(estimation_data, key)
+            else:
+                raise NotImplementedError("estimation method not implemented for type")
+
+            estimated_epc[key] = estimated_value
+
+        return estimated_epc
+
+    @staticmethod
+    def _estimate_int(estimation_data, key):
+        return round(np.average(a=estimation_data[key], weights=estimation_data["weight"]))
+
+    @staticmethod
+    def _estimate_float(estimation_data, key):
+        return np.average(a=estimation_data[key], weights=estimation_data["weight"])
+
+    @staticmethod
+    def _estimate_str(estimation_data, key):
+        agg = estimation_data.groupby(key)["weight"].sum().reset_index()
+        agg = agg[agg["weight"] == agg["weight"].max()]
+        if agg.shape[0] != 1:
+            raise NotImplementedError("implement me")
+
+        return agg[key].values[0]