BUG: fix a bug when resampling in DST context

Author: hasB4K

pandas/core/resample.py

@@ -1356,7 +1356,7 @@ def __init__(
         self.fill_method = fill_method
         self.limit = limit
 
-        if origin in {"epoch", "start", "start_day"}:
+        if origin in ("epoch", "start", "start_day"):
             self.origin = origin
         else:
             try:
@@ -1705,6 +1705,8 @@ def _get_timestamp_range_edges(
             # So "pretend" the dates are naive when adjusting the endpoints
             first = first.tz_localize(None)
             last = last.tz_localize(None)
+            if isinstance(origin, Timestamp):
+                origin = origin.tz_localize(None)
 
         first, last = _adjust_dates_anchored(
             first, last, freq, closed=closed, origin=origin, offset=offset,

pandas/tests/resample/test_datetime_index.py

@@ -764,21 +764,21 @@ def test_resample_origin():
 
 
 @pytest.mark.parametrize(
-    "origin",
-    ["invalid_value", "epch", "startday", "startt", "2000-30-30", object()],
+    "origin", ["invalid_value", "epch", "startday", "startt", "2000-30-30", object()],
 )
 def test_resample_bad_origin(origin):
     rng = date_range("2000-01-01 00:00:00", "2000-01-01 02:00", freq="s")
     ts = Series(np.random.randn(len(rng)), index=rng)
-    msg = ("'origin' should be equal to 'epoch', 'start', 'start_day' or "
-           f"should be a Timestamp convertible type. Got '{origin}' instead.")
+    msg = (
+        "'origin' should be equal to 'epoch', 'start', 'start_day' or "
+        f"should be a Timestamp convertible type. Got '{origin}' instead."
+    )
     with pytest.raises(ValueError, match=msg):
         ts.resample("5min", origin=origin)
 
 
 @pytest.mark.parametrize(
-    "offset",
-    ["invalid_value", "12dayys", "2000-30-30", object()],
+    "offset", ["invalid_value", "12dayys", "2000-30-30", object()],
 )
 def test_resample_bad_offset(offset):
     rng = date_range("2000-01-01 00:00:00", "2000-01-01 02:00", freq="s")
@@ -846,6 +846,61 @@ def test_resample_origin_with_tz():
         ts.resample("5min", origin="12/31/1999 23:57:00+03:00").mean()
 
 
+def test_resample_origin_with_day_freq_on_dst():
+    # GH 31809
+    tz = "dateutil//usr/share/zoneinfo/America/Chicago"
+
+    def _create_series(values, timestamps, freq="D"):
+        return pd.Series(
+            values,
+            index=pd.DatetimeIndex(
+                [Timestamp(t, tz=tz) for t in timestamps], freq=freq, ambiguous=True
+            ),
+        )
+
+    # test classical behavior of origin in a DST context
+    start = pd.Timestamp("2013-11-02", tz=tz)
+    end = pd.Timestamp("2013-11-03 23:59", tz=tz)
+    rng = pd.date_range(start, end, freq="1h")
+    ts = pd.Series(np.ones(len(rng)), index=rng)
+
+    expected = _create_series([24.0, 25.0], ["2013-11-02", "2013-11-03"])
+    for origin in ["epoch", "start", "start_day", start, None]:
+        result = ts.resample("D", origin=origin).sum()
+        tm.assert_series_equal(result, expected)
+
+    # test complex behavior of origin/offset in a DST context
+    start = pd.Timestamp("2013-11-03", tz=tz)
+    end = pd.Timestamp("2013-11-03 23:59", tz=tz)
+    rng = pd.date_range(start, end, freq="1h")
+    ts = pd.Series(np.ones(len(rng)), index=rng)
+
+    expected_ts = ["2013-11-02 22:00-05:00", "2013-11-03 22:00-06:00"]
+    expected = _create_series([23.0, 2.0], expected_ts)
+    result = ts.resample("D", origin="start", offset="-2H").sum()
+    tm.assert_series_equal(result, expected)
+
+    expected_ts = ["2013-11-02 22:00-05:00", "2013-11-03 21:00-06:00"]
+    expected = _create_series([22.0, 3.0], expected_ts, freq="24H")
+    result = ts.resample("24H", origin="start", offset="-2H").sum()
+    tm.assert_series_equal(result, expected)
+
+    expected_ts = ["2013-11-02 02:00-05:00", "2013-11-03 02:00-06:00"]
+    expected = _create_series([3.0, 22.0], expected_ts)
+    result = ts.resample("D", origin="start", offset="2H").sum()
+    tm.assert_series_equal(result, expected)
+
+    expected_ts = ["2013-11-02 23:00-05:00", "2013-11-03 23:00-06:00"]
+    expected = _create_series([24.0, 1.0], expected_ts)
+    result = ts.resample("D", origin="start", offset="-1H").sum()
+    tm.assert_series_equal(result, expected)
+
+    expected_ts = ["2013-11-02 01:00-05:00", "2013-11-03 01:00:00-0500"]
+    expected = _create_series([1.0, 24.0], expected_ts)
+    result = ts.resample("D", origin="start", offset="1H").sum()
+    tm.assert_series_equal(result, expected)
+
+
 def test_resample_daily_anchored():
     rng = date_range("1/1/2000 0:00:00", periods=10000, freq="T")
     ts = Series(np.random.randn(len(rng)), index=rng)