From 193f238129648e581ce18cfaa3619b604bd312d7 Mon Sep 17 00:00:00 2001
From: Tom Augspurger <thomas-augspurger@uiowa.edu>
Date: Fri, 25 Apr 2014 09:22:03 -0500
Subject: [PATCH] BUG: Datetime values in DataFrame.quantile()

Closes #6965

previously returned nonsense
---
 doc/source/release.rst     |  1 +
 pandas/core/frame.py       | 44 +++++++++++++++++++++++++++-----------
 pandas/tests/test_frame.py | 19 ++++++++++++++++
 3 files changed, 52 insertions(+), 12 deletions(-)

diff --git a/doc/source/release.rst b/doc/source/release.rst
index b670e6b5cea05..ec8f44f955043 100644
--- a/doc/source/release.rst
+++ b/doc/source/release.rst
@@ -491,6 +491,7 @@ Bug Fixes
 - Bug in ``unstack`` raises ``ValueError`` when ``MultiIndex`` contains ``PeriodIndex`` (:issue:`4342`)
 - Bug in ``boxplot`` and ``hist`` draws unnecessary axes (:issue:`6769`)
 - Regression in ``groupby.nth()`` for out-of-bounds indexers (:issue:`6621`)
+- Bug in ``quantile`` with datetime values (:issue:`6965`)
 
 pandas 0.13.1
 -------------
diff --git a/pandas/core/frame.py b/pandas/core/frame.py
index 4345154437bf5..66ba061ab35ef 100755
--- a/pandas/core/frame.py
+++ b/pandas/core/frame.py
@@ -4188,23 +4188,43 @@ def quantile(self, q=0.5, axis=0, numeric_only=True):
         """
         per = np.asarray(q) * 100
 
+        if not com.is_list_like(per):
+            per = [per]
+            q = [q]
+            squeeze = True
+        else:
+            squeeze = False
+
         def f(arr, per):
-            arr = arr.values
-            if arr.dtype != np.float_:
-                arr = arr.astype(float)
-            arr = arr[notnull(arr)]
-            if len(arr) == 0:
+            if arr._is_datelike_mixed_type:
+                values = _values_from_object(arr).view('i8')
+            else:
+                values = arr.astype(float)
+            values = values[notnull(values)]
+            if len(values) == 0:
                 return NA
             else:
-                return _quantile(arr, per)
+                return _quantile(values, per)
 
         data = self._get_numeric_data() if numeric_only else self
-        if com.is_list_like(per):
-            from pandas.tools.merge import concat
-            return concat([data.apply(f, axis=axis, args=(x,)) for x in per],
-                          axis=1, keys=per/100.).T
-        else:
-            return data.apply(f, axis=axis, args=(per,))
+
+        # need to know which cols are timestamp going in so that we can
+        # map timestamp over them after getting the quantile.
+        is_dt_col = data.dtypes.map(com.is_datetime64_dtype)
+        is_dt_col = is_dt_col[is_dt_col].index
+
+        quantiles = [[f(vals, x) for x in per]
+                     for (_, vals) in data.iteritems()]
+        result = DataFrame(quantiles, index=data._info_axis, columns=q).T
+        if len(is_dt_col) > 0:
+            result[is_dt_col] = result[is_dt_col].applymap(lib.Timestamp)
+        if squeeze:
+            if result.shape == (1, 1):
+                result = result.T.iloc[:, 0]  # don't want scalar
+            else:
+                result = result.T.squeeze()
+            result.name = None  # For groupby, so it can set an index name
+        return result
 
     def rank(self, axis=0, numeric_only=None, method='average',
              na_option='keep', ascending=True, pct=False):
diff --git a/pandas/tests/test_frame.py b/pandas/tests/test_frame.py
index 1e803a46d76de..7365e4be187b0 100644
--- a/pandas/tests/test_frame.py
+++ b/pandas/tests/test_frame.py
@@ -10994,6 +10994,25 @@ def test_quantile_multi(self):
                              index=[.1, .9])
         assert_frame_equal(result, expected)
 
+    def test_quantile_datetime(self):
+        df = DataFrame({'a': pd.to_datetime(['2010', '2011']), 'b': [0, 5]})
+
+        # exclude datetime
+        result = df.quantile(.5)
+        expected = Series([2.5], index=['b'])
+
+        # datetime
+        result = df.quantile(.5, numeric_only=False)
+        expected = Series([Timestamp('2010-07-02 12:00:00'), 2.5],
+                          index=['a', 'b'])
+        assert_series_equal(result, expected)
+
+        # datetime w/ multi
+        result = df.quantile([.5], numeric_only=False)
+        expected = DataFrame([[Timestamp('2010-07-02 12:00:00'), 2.5]],
+                             index=[.5], columns=['a', 'b'])
+        assert_frame_equal(result, expected)
+
     def test_cumsum(self):
         self.tsframe.ix[5:10, 0] = nan
         self.tsframe.ix[10:15, 1] = nan