TST: to_datetime format fixes

CLN/TST: to_datetime cleanup

TST: tests for dayfirst=True

Author: jreback

pandas/tseries/tests/test_timeseries.py

@@ -793,17 +793,40 @@ def test_to_datetime_default(self):
         xp = datetime(2001, 1, 1)
         self.assert_(rs, xp)
 
+    def test_dayfirst(self):
+
+        # GH 3341
+        result = to_datetime('13-01-2012', dayfirst=True)
+        expected = Timestamp('20120113')
+        self.assert_(result == expected)
+
+        #### dayfirst is essentially broken
+        #### to_datetime('01-13-2012', dayfirst=True)
+        #### self.assertRaises(ValueError, to_datetime('01-13-2012', dayfirst=True))
+
     def test_to_datetime_format(self):
         values = ['1/1/2000', '1/2/2000', '1/3/2000']
 
-        def _parse_format(fmt, values):
-            return to_datetime([datetime.strptime(x, fmt)
-                                for x in values])
-
-        for fmt in ['%d/%m/%Y', '%m/%d/%Y']:
-            result = to_datetime(values, format=fmt)
-            expected = _parse_format(fmt, values)
-            self.assert_(result.equals(expected))
+        results1 = [ Timestamp('20000101'), Timestamp('20000201'),
+                     Timestamp('20000301') ]
+        results2 = [ Timestamp('20000101'), Timestamp('20000102'),
+                     Timestamp('20000103') ]
+        for vals, expecteds in [ (values, (Index(results1), Index(results2))),
+                                 (Series(values),(Series(results1), Series(results2))),
+                                 (values[0], (results1[0], results2[0])),
+                                 (values[1], (results1[1], results2[1])),
+                                 (values[2], (results1[2], results2[2])) ]:
+
+            for i, fmt in enumerate(['%d/%m/%Y', '%m/%d/%Y']):
+                result = to_datetime(vals, format=fmt)
+                expected = expecteds[i]
+
+                if isinstance(expected, Series):
+                    assert_series_equal(result, Series(expected))
+                elif isinstance(expected, Timestamp):
+                    self.assert_(result == expected)
+                else:
+                    self.assert_(result.equals(expected))
 
     def test_to_datetime_format_microsecond(self):
         val = '01-Apr-2011 00:00:01.978'
@@ -2812,10 +2835,10 @@ def check(val,unit=None,h=1,s=1,us=0):
         # nan
         result = Timestamp(np.nan)
         self.assert_(result is NaT)
-        
+
         result = Timestamp(None)
         self.assert_(result is NaT)
-        
+
         result = Timestamp(iNaT)
         self.assert_(result is NaT)
 

pandas/tseries/tools.py

@@ -76,12 +76,26 @@ def to_datetime(arg, errors='ignore', dayfirst=False, utc=None, box=True,
     -------
     ret : datetime if parsing succeeded
     """
+    from pandas import Timestamp
     from pandas.core.series import Series
     from pandas.tseries.index import DatetimeIndex
 
-    def _convert_f(arg):
-        arg = com._ensure_object(arg)
+    def _convert_listlike(arg, box):
+
+        if isinstance(arg, (list,tuple)):
+            arg = np.array(arg, dtype='O')
 
+        if com.is_datetime64_dtype(arg):
+            if box and not isinstance(arg, DatetimeIndex):
+                try:
+                    return DatetimeIndex(arg, tz='utc' if utc else None)
+                except ValueError, e:
+                    values, tz = tslib.datetime_to_datetime64(arg)
+                    return DatetimeIndex._simple_new(values, None, tz=tz)
+
+            return arg
+
+        arg = com._ensure_object(arg)
         try:
             if format is not None:
                 result = tslib.array_strptime(arg, format)
@@ -92,44 +106,25 @@ def _convert_f(arg):
             if com.is_datetime64_dtype(result) and box:
                 result = DatetimeIndex(result, tz='utc' if utc else None)
             return result
+
         except ValueError, e:
             try:
                 values, tz = tslib.datetime_to_datetime64(arg)
                 return DatetimeIndex._simple_new(values, None, tz=tz)
             except (ValueError, TypeError):
                 raise e
 
-    def _convert_listlike(arg):        
-        if isinstance(arg, list):
-            arg = np.array(arg, dtype='O')
-
-        if com.is_datetime64_dtype(arg):
-            if box and not isinstance(arg, DatetimeIndex):
-                try:
-                    return DatetimeIndex(arg, tz='utc' if utc else None)
-                except ValueError, e:
-                    try:
-                        values, tz = tslib.datetime_to_datetime64(arg)
-                        return DatetimeIndex._simple_new(values, None, tz=tz)
-                    except (ValueError, TypeError):
-                        raise e
-                return arg
-
-        return _convert_f(arg)
-
     if arg is None:
         return arg
-    elif isinstance(arg, datetime):
+    elif isinstance(arg, Timestamp):
         return arg
     elif isinstance(arg, Series):
-        values = arg.values
-        if not com.is_datetime64_dtype(values):
-            values = _convert_f(values)
+        values = _convert_listlike(arg.values, box=False)
         return Series(values, index=arg.index, name=arg.name)
-    elif isinstance(arg, (np.ndarray, list)):
-        return _convert_listlike(arg)
+    elif com.is_list_like(arg):
+        return _convert_listlike(arg, box=box)
 
-    return _convert_listlike(np.array([ arg ], dtype='O'))[0]
+    return _convert_listlike(np.array([ arg ]), box=box)[0]
 
 class DateParseError(ValueError):
     pass