Update StatisticalBaseModel.py

StatisticalBaseModel.py

@@ -1,131 +1,119 @@
-from typing import Tuple, TypedDict, Optional
-import datetime
-
-
-class ProcessedSynapse(TypedDict):
-    id: Optional[str]
-    nextplace_id: Optional[str]
-    property_id: Optional[str]
-    listing_id: Optional[str]
-    address: Optional[str]
-    city: Optional[str]
-    state: Optional[str]
-    zip_code: Optional[str]
-    price: Optional[float]
-    beds: Optional[int]
-    baths: Optional[float]
-    sqft: Optional[int]
-    lot_size: Optional[int]
-    year_built: Optional[int]
-    days_on_market: Optional[int]
-    latitude: Optional[float]
-    longitude: Optional[float]
-    property_type: Optional[str]
-    last_sale_date: Optional[str]
-    hoa_dues: Optional[float]
-    query_date: Optional[str]
-    market: Optional[str]
-
-
-class StatisticalBaseModel:
-
-    def __init__(self):
-        self._load_model()
-
-    def _load_model(self):
-        """
-        Perform any actions needed to load the model.
-        EX: Establish API connections, download an ML model for inference, etc...
-        """
-        print("Loading model...")
-        # Optional model loading
-        print("Model loaded.")
-
-    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.
-        # Add more logic for other housing markets!
-        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
-        elif market == 'New York':
-            return 20
-        elif market == 'Denver':
-            return 24
-        return 34
-
-
-    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
-        """
-        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
-        # Add more logic for other housing markets!
-        if market == 'San Francisco':
-            return 1.18  # 18% 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
-        elif market == 'New York':
-            return 1.05  # 5% above listing
-        elif market == 'Denver':
-            return 1.11  # 11% above listing
-        return 1.0
-
-    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
-        """
-        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")
+from typing import Tuple, TypedDict, Optional
+import datetime
+
+
+class ProcessedSynapse(TypedDict):
+    id: Optional[str]
+    nextplace_id: Optional[str]
+    property_id: Optional[str]
+    listing_id: Optional[str]
+    address: Optional[str]
+    city: Optional[str]
+    state: Optional[str]
+    zip_code: Optional[str]
+    price: Optional[float]
+    beds: Optional[int]
+    baths: Optional[float]
+    sqft: Optional[int]
+    lot_size: Optional[int]
+    year_built: Optional[int]
+    days_on_market: Optional[int]
+    latitude: Optional[float]
+    longitude: Optional[float]
+    property_type: Optional[str]
+    last_sale_date: Optional[str]
+    hoa_dues: Optional[float]
+    query_date: Optional[str]
+    market: Optional[str]
+
+
+class StatisticalBaseModel:
+
+    def __init__(self):
+        self._load_model()
+
+    def _load_model(self):
+        """
+        Perform any actions needed to load the model.
+        EX: Establish API connections, download an ML model for inference, etc...
+        """
+        print("Loading model...")
+        # Optional model loading
+        print("Model loaded.")
+
+    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.
+        # Add more logic for other housing markets!
+        if not market:
+            return 34
+        market = market.strip()
+        return {
+            'San Francisco': 23,
+            'Los Angeles': 68,
+            'Seattle': 27,
+            'Austin': 78,
+            'Houston': 73,
+            'Chicago': 25,
+            'New York': 20,
+            'Denver': 24
+        }.get(market, 34)
+
+
+    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
+        """
+        
+        average = self._get_average_for_market(input_data.get('market'))
+        days_on_market = input_data.get('days_on_market')
+
+        if days_on_market is None:
+            return datetime.date.today() + datetime.timedelta(days=average)
+
+        if days_on_market < average:
+            days_until_sale = average - days_on_market
+            return datetime.date.today() + datetime.timedelta(days=days_until_sale)
+        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
+        # Add more logic for other housing markets!
+        if not market:
+            return 1.0
+        market = market.strip()
+        return {
+            'San Francisco': 1.18,
+            'Los Angeles': 1.20,
+            'Seattle': 1.13,
+            'Austin': 1.11,
+            'Houston': 1.15,
+            'Chicago': 1.12,
+            'New York': 1.05,
+            'Denver': 1.11
+        }.get(market, 1.0)
+
+    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
+        """
+        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")
         return predicted_sale_price, predicted_sale_date