BUG: inconsistent behavior with invalid dates in to_datetime, #10154

Author: vincentdavis

doc/source/whatsnew/v0.17.0.txt

@@ -103,7 +103,7 @@ Bug Fixes
 ~~~~~~~~~
 
 - Bug in ``DataFrame.apply`` when function returns categorical series. (:issue:`9573`)
-
+- Bug in ``to_datetime`` with invalid dates and formats supplied (:issue:`10154`)
 
 - Bug in ``Index.drop_duplicates`` dropping name(s) (:issue:`10115`)
 

pandas/tseries/tests/test_timeseries.py

@@ -11,7 +11,7 @@
 
 from pandas import (Index, Series, TimeSeries, DataFrame,
                     isnull, date_range, Timestamp, Period, DatetimeIndex,
-                    Int64Index, to_datetime, bdate_range, Float64Index, TimedeltaIndex)
+                    Int64Index, to_datetime, bdate_range, Float64Index, TimedeltaIndex, NaT)
 
 import pandas.core.datetools as datetools
 import pandas.tseries.offsets as offsets
@@ -4461,6 +4461,28 @@ def test_second(self):
         self.assertIsInstance(r2, Float64Index)
         tm.assert_index_equal(r1, r2)
 
+class TestDaysInMonth(tm.TestCase):
+
+    # tests for issue #10154
+
+    def test_day_not_in_month_coerce_true_NaT(self):
+        self.assertTrue(isnull(to_datetime('2015-02-29', coerce=True)))
+        self.assertTrue(isnull(to_datetime('2015-02-29', format="%Y-%m-%d", coerce=True)))
+        self.assertTrue(isnull(to_datetime('2015-02-32', format="%Y-%m-%d", coerce=True)))
+        self.assertTrue(isnull(to_datetime('2015-04-31', format="%Y-%m-%d", coerce=True)))
+
+    def test_day_not_in_month_coerce_false_raise(self):
+        self.assertRaises(ValueError, to_datetime, '2015-02-29', errors='raise', coerce=False)
+        self.assertRaises(ValueError, to_datetime, '2015-02-29', errors='raise', format="%Y-%m-%d", coerce=False)
+        self.assertRaises(ValueError, to_datetime, '2015-02-32', errors='raise', format="%Y-%m-%d", coerce=False)
+        self.assertRaises(ValueError, to_datetime, '2015-04-31', errors='raise', format="%Y-%m-%d", coerce=False)
+
+    def test_day_not_in_month_coerce_false_ignore(self):
+        self.assertEqual(to_datetime('2015-02-29', errors='ignore', coerce=False), '2015-02-29')
+        self.assertRaises(ValueError, to_datetime, '2015-02-29', errors='ignore', format="%Y-%m-%d", coerce=False)
+        self.assertRaises(ValueError, to_datetime, '2015-02-32', errors='ignore', format="%Y-%m-%d", coerce=False)
+        self.assertRaises(ValueError, to_datetime, '2015-04-31', errors='ignore', format="%Y-%m-%d", coerce=False)
+
 if __name__ == '__main__':
     nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],
                    exit=False)

pandas/tslib.pyx

@@ -2760,17 +2760,23 @@ def array_strptime(ndarray[object] values, object fmt, bint exact=True, bint coe
         # Cannot pre-calculate datetime_date() since can change in Julian
         # calculation and thus could have different value for the day of the wk
         # calculation.
-        if julian == -1:
-            # Need to add 1 to result since first day of the year is 1, not 0.
-            julian = datetime_date(year, month, day).toordinal() - \
-                      datetime_date(year, 1, 1).toordinal() + 1
-        else: # Assume that if they bothered to include Julian day it will
-            # be accurate.
-            datetime_result = datetime_date.fromordinal(
-                (julian - 1) + datetime_date(year, 1, 1).toordinal())
-            year = datetime_result.year
-            month = datetime_result.month
-            day = datetime_result.day
+        try:
+            if julian == -1:
+                # Need to add 1 to result since first day of the year is 1, not 0.
+                julian = datetime_date(year, month, day).toordinal() - \
+                          datetime_date(year, 1, 1).toordinal() + 1
+            else: # Assume that if they bothered to include Julian day it will
+                # be accurate.
+                datetime_result = datetime_date.fromordinal(
+                    (julian - 1) + datetime_date(year, 1, 1).toordinal())
+                year = datetime_result.year
+                month = datetime_result.month
+                day = datetime_result.day
+        except ValueError:
+                if coerce:
+                    iresult[i] = iNaT
+                    continue
+                raise
         if weekday == -1:
             weekday = datetime_date(year, month, day).weekday()