Bug fixing

deepcave/evaluators/mo_fanova.py

@@ -149,13 +149,11 @@ def calculate(
         df = df.dropna(subset=objectives_normed)
         X = df[self.hp_names].to_numpy()
         weightings = self.get_weightings(objectives_normed, df)
-        print(weightings)
         df_all = pd.DataFrame([])
 
         # calculate importance for each weighting generated from the pareto efficient points
         for w in weightings:
             Y = sum(df[obj] * weighting for obj, weighting in zip(objectives_normed, w)).to_numpy()
-            print(Y)
 
             self._model = FanovaForest(self.cs, n_trees=n_trees, seed=seed)
             self._model.train(X, Y)
@@ -164,13 +162,11 @@ def calculate(
                 .loc[0:1]
                 .T.reset_index()
             )
-            print(df_res)
             df_res["weight"] = w[0]
             df_all = pd.concat([df_all, df_res])
         self.importances_ = df_all.rename(
             columns={0: "importance", 1: "variance", "index": "hp_name"}
         ).reset_index(drop=True)
-        print(self.importances_)
 
     def get_importances(
         self, hp_names: Optional[List[str]] = None, sort: bool = True

deepcave/evaluators/mo_lpi.py

@@ -162,7 +162,7 @@ def calculate(
         df = self.run.get_encoded_data(
             objectives=objectives, budget=budget, specific=True, include_combined_cost=True
         )
-        X = df[self.hp_names].to_numpy()
+
 
         # normalize objectives
         assert isinstance(objectives, list)
@@ -173,7 +173,8 @@ def calculate(
                 df[obj.name].max() - df[obj.name].min()
             )
             objectives_normed.append(normed)
-
+        df = df.dropna(subset=objectives_normed)
+        X = df[self.hp_names].to_numpy()
         df_all = pd.DataFrame([])
         weightings = self.get_weightings(objectives_normed, df)