From d586441769c9926f5f620cdfbda617cb794a2015 Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Mon, 3 Jul 2023 18:46:55 +0100
Subject: [PATCH] prepared sap model dataset

---
 model_data/analysis/SapModel.py | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/model_data/analysis/SapModel.py b/model_data/analysis/SapModel.py
index 426a56c5..d18429dc 100644
--- a/model_data/analysis/SapModel.py
+++ b/model_data/analysis/SapModel.py
@@ -72,6 +72,7 @@ class SalModel:
         self.df = pd.DataFrame(data)
         self.cleaner = cleaner
 
+        self.model_data = None
         self.train_x = None
         self.train_y = None
         self.results = None
@@ -128,6 +129,15 @@ class SalModel:
             how="left",
             left_on="roof-description",
             right_on="original_description"
+        ).drop(
+            columns=["original_description"]
+        ).merge(
+            lighting_proportions,
+            how="left",
+            left_on="lighting-description",
+            right_on="original_description"
+        ).drop(
+            columns=["original_description"]
         )
 
         return model_data
@@ -141,13 +151,11 @@ class SalModel:
     @staticmethod
     def _clean_numericals(model_data):
 
-        for col in ["photo-supply", "multi-glaze-proportion", "low-energy-lighting"]:
+        for col in ["photo-supply", "multi-glaze-proportion", "low-energy-lighting", "number-open-fireplaces"]:
             model_data[col] = np.where(
                 model_data[col] == "", "0", model_data["photo-supply"]
             ).astype(float)
 
-        # We need to clean lighting
-
         return model_data
 
     def create_dataset(self):
@@ -176,9 +184,9 @@ class SalModel:
         exclude_features = ["walls-description", "floor-description", "roof-description", "transaction-type"]
 
         features = [
-            x for x in self.BASE_FEATURES +
-                       self.COMPONENT_FEATURES +
-                       ["walls_u_value", "floor_u_value", "roof_u_value", self.RESPONSE] if x not in exclude_features
+            x for x in self.BASE_FEATURES + self.COMPONENT_FEATURES + [
+                "walls_u_value", "floor_u_value", "roof_u_value", self.RESPONSE
+            ] if x not in exclude_features
         ]
 
         model_data = model_data[features]
@@ -186,6 +194,11 @@ class SalModel:
         for col in self.CATEGORICAL_COLS:
             model_data[col] = model_data[col].astype('category')
 
+        # Convert response
+        self.model_data[self.RESPONSE] = self.model_data[self.RESPONSE].astype(float)
+
+        self.model_data = model_data
+
     def make_training_test(self):
         # Split into training and test
         # Dummy data