CLN: add nice message for ValueError of 'origin' and 'offset' in resample

Author: hasB4K

pandas/core/resample.py

@@ -1356,18 +1356,31 @@ def __init__(
         self.fill_method = fill_method
         self.limit = limit
 
-        if origin in {"epoch", "start_day", "start"}:
+        if origin in {"epoch", "start", "start_day"}:
             self.origin = origin
         else:
-            self.origin = Timestamp(origin)
-        self.offset = Timedelta(offset) if offset is not None else None
+            try:
+                self.origin = Timestamp(origin)
+            except Exception as e:
+                raise ValueError(
+                    "'origin' should be equal to 'epoch', 'start', 'start_day' or "
+                    f"should be a Timestamp convertible type. Got '{origin}' instead."
+                ) from e
+
+        try:
+            self.offset = Timedelta(offset) if offset is not None else None
+        except Exception as e:
+            raise ValueError(
+                "'offset' should be a Timedelta convertible type. "
+                f"Got '{offset}' instead."
+            ) from e
 
         # always sort time groupers
         kwargs["sort"] = True
 
         # Handle deprecated arguments since v1.1.0 of `base` and `loffset` (GH #31809)
         if base is not None and offset is not None:
-            raise ValueError("`offset` and `base` cannot be present at the same time")
+            raise ValueError("'offset' and 'base' cannot be present at the same time")
 
         if base and isinstance(freq, Tick):
             # this conversion handle the default behavior of base and the
@@ -1584,8 +1597,8 @@ def _get_period_bins(self, ax):
         bin_shift = 0
 
         if isinstance(self.freq, Tick):
-            # GH 23882 & 31809: get adjusted bin edge labels with `origin`
-            # and `origin` support. This call only makes sense if the freq is a
+            # GH 23882 & 31809: get adjusted bin edge labels with 'origin'
+            # and 'origin' support. This call only makes sense if the freq is a
             # Tick since offset and origin are only used in those cases.
             # Not doing this check could create an extra empty bin.
             p_start, end = _get_period_range_edges(

pandas/tests/resample/test_datetime_index.py

@@ -763,6 +763,31 @@ def test_resample_origin():
     tm.assert_index_equal(resampled.index, exp_rng)
 
 
+@pytest.mark.parametrize(
+    "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.")
+    with pytest.raises(ValueError, match=msg):
+        ts.resample("5min", origin=origin)
+
+
+@pytest.mark.parametrize(
+    "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")
+    ts = Series(np.random.randn(len(rng)), index=rng)
+    msg = f"'offset' should be a Timedelta convertible type. Got '{offset}' instead."
+    with pytest.raises(ValueError, match=msg):
+        ts.resample("5min", offset=offset)
+
+
 def test_resample_origin_prime_freq():
     # GH 31809
     start, end = "2000-10-01 23:30:00", "2000-10-02 00:30:00"

pandas/tests/resample/test_deprecated.py

@@ -55,6 +55,9 @@ def test_deprecating_on_loffset_and_base():
         df.resample("3T", base=0).sum()
     with tm.assert_produces_warning(FutureWarning):
         df.resample("3T", loffset="0s").sum()
+    msg = "'offset' and 'base' cannot be present at the same time"
+    with pytest.raises(ValueError, match=msg):
+        df.groupby("a").resample("3T", base=0, offset=0).sum()
 
 
 @all_ts
@@ -228,7 +231,7 @@ def test_resample_with_non_zero_base(start, end, start_freq, end_freq, base, off
         result = s.resample(end_freq, base=base).mean()
     result = result.to_timestamp(end_freq)
 
-    # test that the replacement argument `offset` works
+    # test that the replacement argument 'offset' works
     result_offset = s.resample(end_freq, offset=offset).mean()
     result_offset = result_offset.to_timestamp(end_freq)
     tm.assert_series_equal(result, result_offset)