First commit of UvalueEstimations class

model_data/analysis/UvalueEstimations.py

@@ -0,0 +1,99 @@
+import pandas as pd
+import numpy as np
+from model_data.EpcClean import EpcClean
+
+
+class UvalueEstimations:
+
+    def __init__(self, data):
+        self.data = pd.DataFrame(data)
+        self.walls = None
+        self.walls_decile_data = {}
+        self.roofs = None
+        self.floors = None
+
+    def set_walls(self, cleaner: EpcClean):
+        walls_columns = [
+            "local-authority", "property-type", "walls-description", "walls-energy-eff", "walls-env-eff",
+            "total-floor-area", "number-habitable-rooms", "number-heated-rooms"
+        ]
+
+        walls_df = self.data[self.data["walls-description"].str.contains("Average thermal transmittance")]
+
+        # Take just the columns we want
+        walls_df = walls_df[walls_columns]
+        walls_df["total-floor-area"] = walls_df["total-floor-area"].astype(float)
+
+        walls_df, decile_labels, decile_boundaries = self.classify_into_deciles(walls_df, "total-floor-area")
+
+        # We now get the U-values
+        walls_df = walls_df.merge(
+            pd.DataFrame(cleaner.cleaned['walls-description'])[["original_description", "thermal_transmittance"]],
+            how="left",
+            right_on="original_description",
+            left_on="walls-description"
+        )
+
+        u_value_summary = walls_df.groupby(
+            [
+                "local-authority",
+                "property-type",
+                "walls-energy-eff",
+                "walls-env-eff",
+                "number-habitable-rooms",
+                "number-heated-rooms",
+                "total-floor-area_group"
+            ],
+            observed=True
+        ).agg({"thermal_transmittance": ["median", "size"]}).reset_index()
+
+        u_value_summary.columns = [
+            "local-authority",
+            "property-type",
+            "walls-energy-eff",
+            "walls-env-eff",
+            "number-habitable-rooms",
+            "number-heated-rooms",
+            "total-floor-area_group",
+            "median_thermal_transmittance",
+            "n_samples"
+        ]
+
+        self.walls = u_value_summary
+        self.walls_decile_data = {
+            "decile_labels": decile_labels,
+            "decile_boundaries": decile_boundaries
+        }
+
+    @staticmethod
+    def classify_into_deciles(df: pd.DataFrame, column: str) -> (pd.DataFrame, list, list):
+        """
+        Break a column in a Pandas DataFrame into deciles and classify new values into the existing deciles.
+
+        Args:
+            df: The input Pandas DataFrame.
+            column: The column name to break into deciles.
+            new_values: A list of new values to classify.
+
+        Returns:
+            A list of classifications for the new values.
+
+        """
+
+        # Calculate decile boundaries
+        decile_boundaries = np.percentile(df[column], np.arange(0, 101, 10))
+
+        # Create decile labels
+        decile_labels = [f"Decile {i + 1}" for i in range(10)]
+
+        # Assign decile labels to existing values
+        df[column + "_group"] = pd.cut(df[column], bins=decile_boundaries, labels=decile_labels,
+                                       include_lowest=True)
+
+        return df, decile_labels, decile_boundaries
+
+    @staticmethod
+    def classify_decile_newvalues(decile_boundaries, decile_labels, new_values: list) -> list:
+        # Classify new values based on decile definitions
+        classifications = pd.cut(new_values, bins=decile_boundaries, labels=decile_labels, include_lowest=True)
+        return classifications.tolist()

model_data/app.py

@@ -154,9 +154,6 @@ def handler():
 
     # We need to deduce a U-value for "Good" energy effieciency
 
-    df = pd.DataFrame(data)
-    df = df[df["walls-description"].str.contains("Average thermal transmittance")]
-
     mainheating = pd.DataFrame(
         [{"address1": p.address1, "postcode": p.postcode, **p.main_heating} for p in input_properties])
     hotwater = pd.DataFrame([{"address1": p.address1, **p.hotwater} for p in input_properties])
@@ -167,3 +164,6 @@ def handler():
     #  'Flat 28, 22 Adelina Grove' 'Solid brick, as built, insulated (assumed)'
     #    so to do this, filter on the local authority code and property type, where we have U
     #   values for the wall and take a median!
+
+    p = input_properties[6]
+    df = pd.DataFrame(data)