Update StatisticalBaseModel.py

StatisticalBaseModel.py

@@ -23,6 +23,7 @@ class ProcessedSynapse(TypedDict):
     last_sale_date: Optional[str]
     hoa_dues: Optional[float]
     query_date: Optional[str]
+    market: Optional[str]
 
 
 class StatisticalBaseModel:
@@ -39,29 +40,81 @@ class StatisticalBaseModel:
         # Optional model loading
         print("Model loaded.")
 
-    def _sale_date_predictor(self, days_on_market: int):
+    def _get_average_for_market(self, market: str) -> int:
+        """
+        Get the average days on market for a house in a given market
+        :param market: the housing market
+        :return: the average days on market
+        """
+        # You probably want to update this based on the current season. Houses sell faster in the summer.
+        if market == 'San Francisco':
+            return 23
+        elif market == 'Los Angeles':
+            return 68
+        elif market == 'Seattle':
+            return 27
+        elif market == 'Austin':
+            return 78
+        elif market == 'Houston':
+            return 73
+        elif market == 'Chicago':
+            return 25
+
+
+    def _sale_date_predictor(self, input_data: ProcessedSynapse):
         """
         Calculate the expected sale date based on the national average
         :param days_on_market: number of days this house has been on the market
         :return: the predicted sale date, based on the national average of 34 days
         """
-        national_average = 34
-        if days_on_market < national_average:
-            days_until_sale = national_average - days_on_market
+        if 'days_on_market' not in input_data:
+            return datetime.date.today() + datetime.timedelta(days=1)
+
+        if 'market' not in input_data:
+            average = 34
+
+        else:
+            average = self._get_average_for_market(input_data['market'])
+
+        days_on_market = input_data['days_on_market']
+        if days_on_market < average:
+            days_until_sale = average - days_on_market
             sale_date = datetime.date.today() + datetime.timedelta(days=days_until_sale)
             return sale_date
         else:
             return datetime.date.today() + datetime.timedelta(days=1)
 
+    def _get_price_multiplier(self, market: str) -> float:
+        """
+        Calculate the price multiplier based on the market
+        :param market: the marked the house is in
+        :return: the multiplier for the predicted price
+        """
+        # You may want to add more logic to check zipcode for more precise price multipliers
+        if market == 'San Francisco':
+            return 1.18  # 20% above listing
+        elif market == 'Los Angeles':
+            return 1.2  # 22% above listing
+        elif market == 'Seattle':
+            return 1.13  # 13% above listing
+        elif market == 'Austin':
+            return 1.11  # 11% above listing
+        elif market == 'Houston':
+            return 1.15  # 15% above listing
+        elif market == 'Chicago':
+            return 1.12  # 12% above listing
+
     def run_inference(self, input_data: ProcessedSynapse) -> Tuple[float, str]:
         """
         Predict the sale price and sale date for the house represented by `input_data`
         :param input_data: a formatted Synapse from the validator, representing a currently listed house
         :return: the predicted sale price and predicted sale date for this home
         """
-        predicted_sale_price = float(input_data['price']) if ('price' in input_data) else 1.0
-        predicted_sale_date = self._sale_date_predictor(input_data['days_on_market']) if ('days_on_market' in input_data) else datetime.date.today() + datetime.timedelta(days=1)
+        listing_price = float(input_data['price']) if 'price' in input_data else 1.0
+        sale_multiplier = self._get_price_multiplier(input_data['market']) if 'market' in input_data else 1.0
+        predicted_sale_price = listing_price * sale_multiplier
+        predicted_sale_date = self._sale_date_predictor(input_data)
         predicted_sale_date = predicted_sale_date.strftime("%Y-%m-%d")
         print(f"Predicted sale price: {predicted_sale_price}")
         print(f"Predicted sale date: {predicted_sale_date}")
-        return predicted_sale_price, predicted_sale_date
+        return predicted_sale_price, predicted_sale_date