diff --git a/toolkit.py b/toolkit.py
index d366a560728d9ec1f5f95f93cd88f13f62a6012f..29adbfb84cef516a9dc6eb3259b5a60690f75655 100755
--- a/toolkit.py
+++ b/toolkit.py
@@ -559,6 +559,14 @@ class ClassificationProject(object):
         return self._scaler
 
 
+    def transform(self, x):
+        return self.scaler.transform(x)
+
+
+    def inverse_transform(self, x):
+        return self.scaler.inverse_transform(x)
+
+
     @property
     def history(self):
         params_file = os.path.join(self.project_dir, "history_params.json")
@@ -592,7 +600,6 @@ class ClassificationProject(object):
 
     def _transform_data(self):
         if not self.data_transformed:
-            # todo: what to do about the outliers? Where do they come from?
             if logger.level <= logging.DEBUG:
                 logger.debug("training data before transformation: {}".format(self.x_train))
                 logger.debug("minimum values: {}".format([np.min(self.x_train[:,i][~np.isnan(self.x_train[:,i])])
@@ -929,7 +936,7 @@ class ClassificationProject(object):
 
     def evaluate(self, x_eval, mode=None):
         logger.debug("Evaluate score for {}".format(x_eval))
-        x_eval = self.scaler.transform(x_eval)
+        x_eval = self.transform(x_eval)
         logger.debug("Evaluate for transformed array: {}".format(x_eval))
         return self.predict(x_eval, mode=mode)
 
@@ -1697,12 +1704,30 @@ class ClassificationProjectRNN(ClassificationProject):
             eval_score("train")
 
 
+    def _batch_transform(self, x, fn, batch_size):
+        "Transform array in batches, temporarily setting mask_values to nan"
+        transformed = np.empty(len(x))
+        for start in range(0, len(x), batch_size):
+            stop = start+batch_size
+            x_batch = np.array(x[start:stop]) # copy
+            x_batch[x_batch == self.mask_value] = np.nan
+            x_batch = fn(x_batch)
+            x_batch[np.isnan(x_batch)] = self.mask_value
+            transformed[start:stop] = x_batch
+        return transformed
+
+
+    def transform(self, x, batch_size=10000):
+        return self._batch_transform(x, self.scaler.transform, batch_size)
+
+
+    def inverse_transform(self, x, batch_size=10000):
+        return self._batch_transform(x, self.scaler.inverse_transform, batch_size)
+
+
     def evaluate(self, x_eval, mode=None):
         logger.debug("Evaluate score for {}".format(x_eval))
-        x_eval = np.array(x_eval) # copy
-        x_eval[x_eval==self.mask_value] = np.nan
-        x_eval = self.scaler.transform(x_eval)
-        x_eval[np.isnan(x_eval)] = self.mask_value
+        x_eval = self.transform(x_eval)
         logger.debug("Evaluate for transformed array: {}".format(x_eval))
         return self.predict(self.get_input_list(x_eval), mode=mode)