diff --git a/optimus/dataframe/columns.py b/optimus/dataframe/columns.py
index 8853952f..823df6b3 100644
--- a/optimus/dataframe/columns.py
+++ b/optimus/dataframe/columns.py
@@ -2117,17 +2117,20 @@ def join_all(_dfs):
         return join_all(combined)
 
     @add_attr(cols)
-    def string_to_index(input_cols, output_cols=None):
+    def string_to_index(input_cols=None, output_cols=None, columns=None):
         """
         Encodes a string column of labels to a column of label indices
         :param input_cols:
         :param output_cols:
+        :param columns:
         :return:
         """
         df = self
 
-        input_cols = parse_columns(df, input_cols)
-        # output_cols = get_output_cols(input_cols, output_cols)
+        if columns is None:
+            input_cols = parse_columns(df, input_cols)
+        else:
+            input_cols, output_cols = zip(*columns)
 
         df = ml_string_to_index(df, input_cols, output_cols)
 
diff --git a/optimus/ml/feature.py b/optimus/ml/feature.py
index df1e827d..481da052 100644
--- a/optimus/ml/feature.py
+++ b/optimus/ml/feature.py
@@ -28,26 +28,28 @@ def n_gram(df, input_col, n=2):
     return df_model, tfidf_model
 
 
-def string_to_index(df, input_cols, output_col=None, **kargs):
+def string_to_index(df, input_cols, output_cols=None, **kargs):
     """
     Maps a string column of labels to an ML column of label indices. If the input column is
     numeric, we cast it to string and index the string values.
     :param df: Dataframe to be transformed
     :param input_cols: Columns to be indexed.
-    :param output_col:Column where the ouput is going to be saved
+    :param output_cols:Column where the ouput is going to be saved
     :return: Dataframe with indexed columns.
     """
 
-    input_cols = parse_columns(df, input_cols)
-    if output_col is None:
-        output_col = name_col(input_cols, "index_to_string")
+    # input_cols = parse_columns(df, input_cols)
+    if output_cols is None:
 
-    indexers = [StringIndexer(inputCol=input_col, outputCol=output_col, **kargs).fit(df) for input_col
-                in list(set(input_cols))]
+        output_cols = [name_col(input_col, "index_to_string") for input_col in input_cols]
+    print(output_cols)
+
+    indexers = [StringIndexer(inputCol=input_col, outputCol=output_col, **kargs).fit(df) for input_col, output_col
+                in zip(list(set(input_cols)), list(set(output_cols)))]
 
     pipeline = Pipeline(stages=indexers)
     df = pipeline.fit(df).transform(df)
-
+    # df.show()
     return df