Return a column of tuples, not strings (#720)

* Return a column of tuples, not strings, as it makes using in a multiindex easier * Fix styling * Changelog
blue-yonder · Jun 24, 2020 · 0d1c62e · 0d1c62e
1 parent e867d74
commit 0d1c62e
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 5 deletions.
diff --git a/CHANGES.rst b/CHANGES.rst
@@ -9,6 +9,7 @@ Unreleased
 
 - Breaking Change
     - Changed constructed id in roll_time_series from string to tuple (#700)
+    - Same for add_sub_time_series_index (#720)
 - Added Features
     - Implemented the Lempel-Ziv-Complexity and the Fourier Entropy (#688)
     - Prevent #524 by adding an assert for common identifiers (#690)

diff --git a/tests/units/utilities/test_dataframe_functions.py b/tests/units/utilities/test_dataframe_functions.py
@@ -839,7 +839,7 @@ def test_id_parameters(self):
         extended_dataframe = dataframe_functions.add_sub_time_series_index(dataframe, 2, column_id="id")
 
         self.assertEqual(list(extended_dataframe["id"]),
-                         ["0,1", "0,1", "1,1", "1,1", "0,2", "0,2", "1,2", "1,2", "2,2"])
+                         [(0, 1), (0, 1), (1, 1), (1, 1), (0, 2), (0, 2), (1, 2), (1, 2), (2, 2)])
         assert_series_equal(dataframe["value"], extended_dataframe["value"])
 
     def test_kind_parameters(self):
@@ -852,7 +852,7 @@ def test_kind_parameters(self):
                                                                            column_kind="kind")
 
         self.assertEqual(list(extended_dataframe["id"]),
-                         ["0,1", "0,1", "0,1", "0,1", "0,2", "0,2", "0,2", "0,2", "1,2"])
+                         [(0, 1), (0, 1), (0, 1), (0, 1), (0, 2), (0, 2), (0, 2), (0, 2), (1, 2)])
         assert_series_equal(dataframe["value"], extended_dataframe["value"])
         assert_series_equal(dataframe["kind"], extended_dataframe["kind"])
 
@@ -868,7 +868,7 @@ def test_sort_parameters(self):
                                                                            column_sort="sort")
 
         self.assertEqual(list(extended_dataframe["id"]),
-                         ["0,2", "0,2", "0,2", "0,2", "1,2", "0,1", "0,1", "0,1", "0,1"])
+                         [(0, 2), (0, 2), (0, 2), (0, 2), (1, 2), (0, 1), (0, 1), (0, 1), (0, 1)])
         self.assertEqual(list(extended_dataframe["value"]),
                          [9, 8, 7, 6, 5, 4, 3, 2, 1])
         self.assertEqual(list(extended_dataframe["kind"]),
@@ -888,7 +888,7 @@ def test_dict_input(self):
         extended_dataframe = extended_dataframe["1"]
 
         self.assertEqual(list(extended_dataframe["id"]),
-                         ["0,1", "0,1", "1,1", "1,1", "0,2", "0,2", "1,2", "1,2", "2,2"])
+                         [(0, 1), (0, 1), (1, 1), (1, 1), (0, 2), (0, 2), (1, 2), (1, 2), (2, 2)])
         assert_series_equal(dataframe["value"], extended_dataframe["value"])
 
 

diff --git a/tsfresh/utilities/dataframe_functions.py b/tsfresh/utilities/dataframe_functions.py
@@ -624,7 +624,7 @@ def _add_id_column(df_chunk):
         assert(len(indices) == chunk_length)
 
         if column_id:
-            indices = [str(id) + "," + str(old_id) for id, old_id in zip(indices, df_chunk[column_id])]
+            indices = list(zip(indices, df_chunk[column_id]))
 
         if column_sort:
             df_chunk = df_chunk.sort_values(column_sort)