From cbfb9a5a93d867ba8b1422e31c987e41b7b053cb Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Fri, 30 Jun 2023 10:03:41 +0100
Subject: [PATCH] scrappy code testing out modelling affect of thermal
 transmittance on EPC

---
 model_data/app.py           | 38 ++++++++++++++++++++++++++++++++++++-
 model_data/requirements.txt |  3 ++-
 2 files changed, 39 insertions(+), 2 deletions(-)

diff --git a/model_data/app.py b/model_data/app.py
index a19635e3..4ebad3d2 100644
--- a/model_data/app.py
+++ b/model_data/app.py
@@ -237,6 +237,7 @@ def handler():
         "built-form",
         # "construction-age-band",
         "number-habitable-rooms",
+        "constituency",
     ]
 
     component_features = [
@@ -245,8 +246,43 @@ def handler():
     ]
 
     model_data = df[[response] + component_features + base_features]
-    model_data = model_data.reset_index()
+    model_data = model_data.reset_index(drop=True)
     model_data["idx"] = model_data.index.copy()
+
+    # Append on u-value estimates
+    model_data = model_data.merge(
+        pd.DataFrame(cleaner.cleaned["walls-description"])[["original_description", "thermal_transmittance"]],
+        how="left",
+        left_on="walls-description",
+        right_on="original_description"
+    )
+    # Take just entries with U-values
+    model_data = model_data[~pd.isnull(model_data["thermal_transmittance"])]
+
+    # We need to split the data into a train and test set for model build
+
+    import statsmodels.api as sm
+
+    # Assuming 'df' is your DataFrame
+    X = model_data[base_features + ["thermal_transmittance"]]
+    Y = model_data[response]
+
+    # Add a constant to the independent value
+    X1 = sm.add_constant(X)
+
+    # make regression model
+    model = sm.OLS(Y, X1)
+
+    # fit model and print results
+    results = model.fit()
+    print(results.summary())
+
+    model_data[["thermal_transmittance", response]].corr()
+
+    summary = model_data.groupby(["property-type", "built-form"], observed=True)[
+        ["thermal_transmittance", response]
+    ].corr()
+
     summary = (
         model_data
         .groupby(component_features + base_features)
diff --git a/model_data/requirements.txt b/model_data/requirements.txt
index c4fbd083..609cb528 100644
--- a/model_data/requirements.txt
+++ b/model_data/requirements.txt
@@ -14,4 +14,5 @@ pyproj
 pint
 geopandas
 mip
-seaborn
\ No newline at end of file
+seaborn
+statsmodels
\ No newline at end of file