Merge pull request #10845 from soupault/timedelta-bugfix

BUG: Error while saving DataFrame with TimedeltaIndex to .csv #10833
pandas-dev · Aug 21, 2015 · 2c5b458 · 2c5b458
2 parents a6ee127 + 2093cc5
commit 2c5b458
Show file tree

Hide file tree

Showing 3 changed files with 18 additions and 2 deletions.
diff --git a/doc/source/whatsnew/v0.17.0.txt b/doc/source/whatsnew/v0.17.0.txt
@@ -761,3 +761,4 @@ Bug Fixes
 - Bug in ``iloc`` allowing memory outside bounds of a Series to be accessed with negative integers (:issue:`10779`)
 - Bug in ``read_msgpack`` where encoding is not respected (:issue:`10580`)
 - Bug preventing access to the first index when using ``iloc`` with a list containing the appropriate negative integer (:issue:`10547`, :issue:`10779`)
+- Bug in ``TimedeltaIndex`` formatter causing error while trying to save ``DataFrame`` with ``TimedeltaIndex`` using ``to_csv`` (:issue:`10833`)
diff --git a/pandas/core/format.py b/pandas/core/format.py
@@ -2190,7 +2190,7 @@ def __init__(self, values, nat_rep='NaT', box=False, **kwargs):
     def _format_strings(self):
         formatter = self.formatter or _get_format_timedelta64(self.values, nat_rep=self.nat_rep,
                                                               box=self.box)
-        fmt_values = [formatter(x) for x in self.values]
+        fmt_values = np.array([formatter(x) for x in self.values])
         return fmt_values
 
 

diff --git a/pandas/tests/test_frame.py b/pandas/tests/test_frame.py
@@ -6312,7 +6312,6 @@ def test_to_csv_from_csv(self):
                               header=['AA', 'X'])
 
         with ensure_clean(pname) as path:
-            import pandas as pd
             df1 = DataFrame(np.random.randn(3, 1))
             df2 = DataFrame(np.random.randn(3, 1))
 
@@ -6324,6 +6323,22 @@ def test_to_csv_from_csv(self):
             xp.columns = lmap(int,xp.columns)
             assert_frame_equal(xp,rs)
 
+        with ensure_clean() as path:
+            # GH 10833 (TimedeltaIndex formatting)
+            dt = pd.Timedelta(seconds=1)
+            df = pd.DataFrame({'dt_data': [i*dt for i in range(3)]},
+                              index=pd.Index([i*dt for i in range(3)],
+                                             name='dt_index'))
+            df.to_csv(path)
+
+            result = pd.read_csv(path, index_col='dt_index')
+            result.index = pd.to_timedelta(result.index)
+            # TODO: remove renaming when GH 10875 is solved
+            result.index = result.index.rename('dt_index')
+            result['dt_data'] = pd.to_timedelta(result['dt_data'])
+
+            assert_frame_equal(df, result, check_index_type=True)
+
     def test_to_csv_cols_reordering(self):
         # GH3454
         import pandas as pd