BUG: #47350 if else added to add NaT for missing time values

pandas/core/groupby/ops.py

@@ -821,14 +821,37 @@ def apply(
         # This calls DataSplitter.__iter__
         zipped = zip(group_keys, splitter)
 
+        i = 0
         for key, group in zipped:
+            # BUG:47350 if replaced 1 by hamedgibago
+            # if key not in data.index and is_datetime64_any_dtype(data.index):
+            # #or (key not in data.index and f.__name__ in ['idxmax','idxmin']) :
+            # ser=Series(i,[key])
+            # res = None
+            # else:
+            # res = f(group)
+            try:
+                res = f(group)
+            except (ValueError, AttributeError):
+                # except ValueError:
+                res = None
+
             object.__setattr__(group, "name", key)
 
             # group might be modified
             group_axes = group.axes
-            res = f(group)
+
             if not mutated and not _is_indexed_like(res, group_axes, axis):
                 mutated = True
+
+            i = i + 1
+
+            # BUG:47350 if added by hamedgibago
+            # if key in data.index:
+            #     result_values.append(res)
+            # else:
+            #     result_values.append(np.nan)
+
             result_values.append(res)
 
         # getattr pattern for __name__ is needed for functools.partial objects

pandas/core/indexes/base.py

@@ -45,8 +45,8 @@
     tz_compare,
 )
 from pandas._typing import (
+    AnyArrayLike,
     ArrayLike,
-    Axes,
     Dtype,
     DtypeObj,
     F,
@@ -261,10 +261,6 @@ def _new_Index(cls, d):
             # GH#23752 "labels" kwarg has been replaced with "codes"
             d["codes"] = d.pop("labels")
 
-        # Since this was a valid MultiIndex at pickle-time, we don't need to
-        #  check validty at un-pickle time.
-        d["verify_integrity"] = False
-
     elif "dtype" not in d and "data" in d:
         # Prevent Index.__new__ from conducting inference;
         #  "data" key not in RangeIndex
@@ -277,9 +273,8 @@ def _new_Index(cls, d):
 
 class Index(IndexOpsMixin, PandasObject):
     """
-    Immutable sequence used for indexing and alignment.
-
-    The basic object storing axis labels for all pandas objects.
+    Immutable sequence used for indexing and alignment. The basic object
+    storing axis labels for all pandas objects.
 
     Parameters
     ----------
@@ -2297,7 +2292,8 @@ def is_monotonic(self) -> bool:
     @property
     def is_monotonic_increasing(self) -> bool:
         """
-        Return a boolean if the values are equal or increasing.
+        Return if the index is monotonic increasing (only equal or
+        increasing) values.
 
         Examples
         --------
@@ -2313,7 +2309,8 @@ def is_monotonic_increasing(self) -> bool:
     @property
     def is_monotonic_decreasing(self) -> bool:
         """
-        Return a boolean if the values are equal or decreasing.
+        Return if the index is monotonic decreasing (only equal or
+        decreasing) values.
 
         Examples
         --------
@@ -3815,9 +3812,8 @@ def get_loc(self, key, method=None, tolerance=None):
     _index_shared_docs[
         "get_indexer"
     ] = """
-        Compute indexer and mask for new index given the current index.
-
-        The indexer should be then used as an input to ndarray.take to align the
+        Compute indexer and mask for new index given the current index. The
+        indexer should be then used as an input to ndarray.take to align the
         current data to the new index.
 
         Parameters
@@ -4586,7 +4582,8 @@ def join(
         sort: bool = False,
     ) -> Index | tuple[Index, npt.NDArray[np.intp] | None, npt.NDArray[np.intp] | None]:
         """
-        Compute join_index and indexers to conform data structures to the new index.
+        Compute join_index and indexers to conform data
+        structures to the new index.
 
         Parameters
         ----------
@@ -4687,7 +4684,6 @@ def join(
                 not isinstance(self, ABCMultiIndex)
                 or not any(is_categorical_dtype(dtype) for dtype in self.dtypes)
             )
-            and not is_categorical_dtype(self.dtype)
         ):
             # Categorical is monotonic if data are ordered as categories, but join can
             #  not handle this in case of not lexicographically monotonic GH#38502
@@ -5983,9 +5979,8 @@ def set_value(self, arr, key, value) -> None:
     _index_shared_docs[
         "get_indexer_non_unique"
     ] = """
-        Compute indexer and mask for new index given the current index.
-
-        The indexer should be then used as an input to ndarray.take to align the
+        Compute indexer and mask for new index given the current index. The
+        indexer should be then used as an input to ndarray.take to align the
         current data to the new index.
 
         Parameters
@@ -7283,7 +7278,7 @@ def ensure_index_from_sequences(sequences, names=None) -> Index:
         return MultiIndex.from_arrays(sequences, names=names)
 
 
-def ensure_index(index_like: Axes, copy: bool = False) -> Index:
+def ensure_index(index_like: AnyArrayLike | Sequence, copy: bool = False) -> Index:
     """
     Ensure that we have an index from some index-like object.
 

pandas/core/resample.py

@@ -1982,6 +1982,12 @@ def _get_timestamp_range_edges(
     -------
     A tuple of length 2, containing the adjusted pd.Timestamp objects.
     """
+    if isinstance(origin, Timestamp):
+        first, last = _adjust_dates_anchored(
+            first, last, freq, closed=closed, origin=origin, offset=offset
+        )
+        return first, last
+
     if isinstance(freq, Tick):
         index_tz = first.tz
         if isinstance(origin, Timestamp) and (origin.tz is None) != (index_tz is None):
@@ -2116,7 +2122,10 @@ def _adjust_dates_anchored(
         origin_nanos = origin.value
     elif origin in ["end", "end_day"]:
         origin = last if origin == "end" else last.ceil("D")
-        sub_freq_times = (origin.value - first.value) // freq.nanos
+        if isinstance(freq, Tick):
+            sub_freq_times = (origin.value - first.value) // freq.nanos
+        else:
+            sub_freq_times = origin.value - first.value
         if closed == "left":
             sub_freq_times += 1
         first = origin - sub_freq_times * freq
@@ -2133,19 +2142,29 @@ def _adjust_dates_anchored(
     if last_tzinfo is not None:
         last = last.tz_convert("UTC")
 
-    foffset = (first.value - origin_nanos) % freq.nanos
-    loffset = (last.value - origin_nanos) % freq.nanos
+    if isinstance(freq, Tick):
+        foffset = (first.value - origin_nanos) % freq.nanos
+        loffset = (last.value - origin_nanos) % freq.nanos
+    else:
+        foffset = first.value - origin_nanos
+        loffset = last.value - origin_nanos
 
     if closed == "right":
         if foffset > 0:
             # roll back
             fresult_int = first.value - foffset
         else:
-            fresult_int = first.value - freq.nanos
+            if isinstance(freq, Tick):
+                fresult_int = first.value - freq.nanos
+            else:
+                fresult_int = first.value
 
         if loffset > 0:
-            # roll forward
-            lresult_int = last.value + (freq.nanos - loffset)
+            if isinstance(freq, Tick):
+                # roll forward
+                lresult_int = last.value + (freq.nanos - loffset)
+            else:
+                lresult_int = last.value - loffset
         else:
             # already the end of the road
             lresult_int = last.value
@@ -2157,10 +2176,16 @@ def _adjust_dates_anchored(
             fresult_int = first.value
 
         if loffset > 0:
-            # roll forward
-            lresult_int = last.value + (freq.nanos - loffset)
+            if isinstance(freq, Tick):
+                # roll forward
+                lresult_int = last.value + (freq.nanos - loffset)
+            else:
+                lresult_int = last.value - loffset
         else:
-            lresult_int = last.value + freq.nanos
+            if isinstance(freq, Tick):
+                lresult_int = last.value + freq.nanos
+            else:
+                lresult_int = last.value
     fresult = Timestamp(fresult_int)
     lresult = Timestamp(lresult_int)
     if first_tzinfo is not None:

pandas/core/series.py

@@ -2175,7 +2175,7 @@ def unique(self) -> ArrayLike:
         Examples
         --------
         >>> pd.Series([2, 1, 3, 3], name='A').unique()
-        array([2, 1, 3])
+        array([2, 1, 3], dtype=int64)
 
         >>> pd.Series([pd.Timestamp('2016-01-01') for _ in range(3)]).unique()
         array(['2016-01-01T00:00:00.000000000'], dtype='datetime64[ns]')

pandas/tests/groupby/test_groupby.py

@@ -39,6 +39,31 @@ def test_repr():
     assert result == expected
 
 
+def test_origin_param_no_effect():
+    # GH 47653
+    df = DataFrame(
+        [
+            {"A": A, "datadate": datadate}
+            for A in range(1, 3)
+            for datadate in date_range(start="1/2/2022", end="2/1/2022", freq="D")
+        ]
+    )
+
+    result = df.groupby(["A", Grouper(key="datadate", freq="W", origin="start")])
+
+    # for i, dfg in result:
+    #     print(dfg[["A", "datadate"]])..
+    #     print("-----------------------")
+
+    expected = df.groupby(["A", Grouper(key="datadate", freq="W", origin="1/5/2022")])
+
+    # for i, dfg in expected:
+    #     print(dfg[["A", "datadate"]])
+    #     print("-----------------------")
+
+    tm.assert_series_equal(result, expected)
+
+
 @pytest.mark.parametrize("dtype", ["int64", "int32", "float64", "float32"])
 def test_basic(dtype):
 

pandas/tests/resample/test_resampler_grouper.py

@@ -45,6 +45,17 @@ async def test_tab_complete_ipython6_warning(ip):
             list(ip.Completer.completions("rs.", 1))
 
 
+def test_dataframe_missing_a_day():
+    # GH 47350
+    dates = pd.DatetimeIndex(["2022-01-01", "2022-01-02", "2022-01-04"])
+    df = DataFrame([0, 1, 2], index=dates)
+    result = df.resample("D")[0].idxmax()  # raises value error
+
+    expected = df.resample("D")[0].apply(lambda x: x.idxmax() if len(x) else None)
+
+    tm.assert_series_equal(result, expected)
+
+
 def test_deferred_with_groupby():
 
     # GH 12486