working on MainheatControlAttributes

epc_data/app.py

@@ -56,20 +56,18 @@ def handler():
     df = df.reset_index(drop=True)
 
     import numpy as np
-    idx = 88
+    idx = 5
     record = df[df.index == idx].to_dict("records")[0]
     record = {k: v for k, v in record.items() if v not in [None, np.nan, False]}
     from pprint import pprint
     pprint(record)
 
-    # This has has_electric as true and not sure if we want that
+    # Issues:
-    description = 'Boiler and radiators, mains gas, Electric storage heaters'
+    # 1) '2207 Time and temperature zone control' - we don't pick up any reference to the fact this is a time and
-    # This has has_electric as true and has has_underfloor_heating as true and has_electric_underfloor_heating as true
+    # temperature zone control
-    # and not sure if we want that but might be fine
+    #     and we only pick up temperature zone control at the moment. Can we capture this too
-    description = 'Boiler and radiators, mains gas, Electric underfloor heating'
+    # 2) 'Charging system linked to use of community heating, programmer and at least two room stats' - what are room
-
+    # stats and how should
-    z = df[df["original_description"] == 'Air source heat pump, radiators and underfloor, electric']
+    #     we capture this?
-
-    # LPG boiler
 
     df.to_dict("records")

epc_data/attributes/MainheatControlAttributes.py

@@ -3,51 +3,83 @@ from epc_data.attributes.attribute_utils import clean_description
 
 
 class MainheatControlAttributes:
-    CONTROL_SYSTEM_KEYWORDS = [
+    # These systems allow for the automatic regulation of temperature
-        "charging system", "flat rate charging", "no thermostatic control",
+    THERMOSTATIC_CONTROL_KEYWORDS = [
-        "programmer", "room thermostats", "trvs", "bypass", "flow switch",
+        'room thermostats',
-        "automatic charge control", "manual charge control",
+        'appliance thermostats',
-        "temperature zone control", "time and temperature zone control",
+        'trvs',
-        "high heat retention storage heaters", "appliance thermostats", "dhw only",
+        'room thermostat',
-        "no time or thermostatic control", "room thermostat"
+        'temperature zone control',
+        'time and temperature zone control',
+        'no thermostatic control'
     ]
 
-    # These systems allow for the automatic regulation of temperature
-    THERMOSTATIC_CONTROL_KEYWORDS = []
-
     # These systems provide a way to store and manage energy usage
-    CHARGING_SYSTEM_KEYWORDS = []
+    CHARGING_SYSTEM_KEYWORDS = [
+        'charging system',
+        'automatic charge control',
+        'manual charge control',
+        'flat rate charging',
+        'high heat retention storage heaters'
+    ]
 
     # These systems are mainly focused on on/off operations
-    SWITCH_SYSTEM_KEYWORDS = []
+    SWITCH_SYSTEM_KEYWORDS = [
+        'programmer',
+        'flow switch',
+        'bypass'
+    ]
 
-    # hese keywords indicate a lack of control system
+    # These keywords indicate a lack of control system
-    NO_CONTROL_SYSTEM_KEYWORDS = ["none"]
+    NO_CONTROL_SYSTEM_KEYWORDS = [
+        'no time or thermostatic control',
+        'none'
+    ]
 
     # These systems provide control specifically for Domestic Hot Water
-    DHW_CONTROL_KEYWORDS = []
+    DHW_CONTROL_KEYWORDS = [
+        'dhw only'
+    ]
+
+    # This system indicates the use of community heating
+    COMMUNITY_HEATING_KEYWORDS = [
+        'use of community heating'
+    ]
 
     def __init__(self, description: str):
         self.description: str = clean_description(description.lower())
 
-        # In the case of an empty description, we want to return a dictionary with all values set to False
+        self.nodata = not description or any(keyword in self.description for keyword in self.NO_CONTROL_SYSTEM_KEYWORDS)
-        # and indicate there was no data
-        self.nodata = not description or self.description in self.NO_CONTROL_SYSTEM_KEYWORDS
 
-        if not self.nodata:
+        if not self.nodata and not any(
-            if not any(keyword in self.description for keyword in self.CONTROL_SYSTEM_KEYWORDS):
+            self._keyword_in_description(keywords)
-                raise ValueError('Invalid description')
+            for keywords in [
+                self.THERMOSTATIC_CONTROL_KEYWORDS,
+                self.CHARGING_SYSTEM_KEYWORDS,
+                self.SWITCH_SYSTEM_KEYWORDS,
+                self.DHW_CONTROL_KEYWORDS
+            ]
+        ):
+            raise ValueError('Invalid description')
+
+    def _keyword_in_description(self, keywords):
+        return any(keyword in self.description for keyword in keywords)
 
     def process(self) -> Dict[str, Union[str, bool]]:
         result: Dict[str, Union[str, bool]] = {
-            "no_data": self.nodata
+            "thermostatic_control": self._find_keyword(self.THERMOSTATIC_CONTROL_KEYWORDS),
+            "charging_system": self._find_keyword(self.CHARGING_SYSTEM_KEYWORDS),
+            "switch_system": self._find_keyword(self.SWITCH_SYSTEM_KEYWORDS),
+            "no_control": self._find_keyword(self.NO_CONTROL_SYSTEM_KEYWORDS),
+            "dhw_control": self._find_keyword(self.DHW_CONTROL_KEYWORDS),
+            "community_heating": self._find_keyword(self.COMMUNITY_HEATING_KEYWORDS),
         }
 
-        if self.nodata:
-            return result
-
-        # We consolidate CONTROL_SYSTEM_KEYWORDS into separate attributes
-        for keyword in self.CONTROL_SYSTEM_KEYWORDS:
-            result[f'has_{keyword.replace(" ", "_")}'] = keyword in self.description
-
         return result
+
+    def _find_keyword(self, keywords):
+        for keyword in keywords:
+            if keyword in self.description:
+                return keyword
+
+        return None