set fill value to max of full dataset + 1

automl · Mar 22, 2020 · 907279a · 907279a
1 parent b76a902
commit 907279a
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/autoPyTorch/pipeline/nodes/imputation.py b/autoPyTorch/pipeline/nodes/imputation.py
@@ -29,7 +29,7 @@ def fit(self, hyperparameter_config, X, train_indices, dataset_info):
         dataset_info.categorical_features = [dataset_info.categorical_features[i] for i, is_nan in enumerate(all_nan) if not is_nan]
 
         strategy = hyperparameter_config['strategy']
-        fill_value = int(np.nanmax(X[train_indices])) + 1 if not dataset_info.is_sparse else 0
+        fill_value = int(np.nanmax(X)) + 1 if not dataset_info.is_sparse else 0
         numerical_imputer = SimpleImputer(strategy=strategy, copy=False)
         categorical_imputer = SimpleImputer(strategy='constant', copy=False, fill_value=fill_value)
         transformer = ColumnTransformer(
@@ -63,4 +63,4 @@ def get_pipeline_config_options(self):
             ConfigOption(name='imputation_strategies', default=Imputation.strategies, type=str, list=True, choices=Imputation.strategies)
         ]
         return options
-
+