ENH: Implement __iter__ for Rolling and Expanding

doc/source/whatsnew/v1.1.0.rst

@@ -235,6 +235,7 @@ Other enhancements
   :class:`~pandas.io.stata.StataWriter`, :class:`~pandas.io.stata.StataWriter117`,
   and :class:`~pandas.io.stata.StataWriterUTF8` (:issue:`26599`).
 - :meth:`HDFStore.put` now accepts `track_times` parameter. Parameter is passed to ``create_table`` method of ``PyTables`` (:issue:`32682`).
+- Make :class:`pandas.core.window.Rolling` and :class:`pandas.core.window.Expanding` iterable（:issue:`11704`)
 
 .. ---------------------------------------------------------------------------
 

pandas/core/window/rolling.py

@@ -247,8 +247,33 @@ def __repr__(self) -> str:
         return f"{self._window_type} [{attrs}]"
 
     def __iter__(self):
-        url = "https://github.com/pandas-dev/pandas/issues/11704"
-        raise NotImplementedError(f"See issue #11704 {url}")
+        window = self._get_window(win_type=None)
+
+        blocks, obj = self._create_blocks()
+        block_list = list(blocks)
+        index = self._get_window_indexer(window=window)
+
+        # Choose the min between min_periods and window to determine the output size
+        if self.min_periods is None:
+            iter_threshold = window
+        else:
+            iter_threshold = min(window, self.min_periods)
+
+        for block in block_list:
+            start, end = index.get_window_bounds(
+                num_values=len(block),
+                min_periods=self.min_periods,
+                center=self.center,
+                closed=self.closed,
+            )
+            # From get_window_bounds, those two should be equal in length of array
+            assert len(start) == len(end)
+
+            window_size = len(start)
+            for i in range(window_size):
+                result = block.iloc[slice(start[i], end[i])]
+                if result.count().min() >= iter_threshold:
+                    yield result
 
     def _prep_values(self, values: Optional[np.ndarray] = None) -> np.ndarray:
         """Convert input to numpy arrays for Cython routines"""

pandas/tests/window/test_expanding.py

@@ -88,15 +88,6 @@ def test_missing_minp_zero():
     tm.assert_series_equal(result, expected)
 
 
-@pytest.mark.parametrize("klass", [pd.Series, pd.DataFrame])
-def test_iter_raises(klass):
-    # https://github.com/pandas-dev/pandas/issues/11704
-    # Iteration over a Window
-    obj = klass([1, 2, 3, 4])
-    with pytest.raises(NotImplementedError):
-        iter(obj.expanding(2))
-
-
 def test_expanding_axis(axis_frame):
     # see gh-23372.
     df = DataFrame(np.ones((10, 20)))
@@ -131,3 +122,77 @@ def test_expanding_count_default_min_periods_with_null_values(constructor):
     result = constructor(values).expanding().count()
     expected = constructor(expected_counts)
     tm.assert_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "df,expected,min_periods",
+    [
+        (
+            DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]}),
+            [({"A": [1, 2, 3], "B": [4, 5, 6]}, [0, 1, 2])],
+            3,
+        ),
+        (
+            DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]}),
+            [
+                ({"A": [1, 2], "B": [4, 5]}, [0, 1]),
+                ({"A": [1, 2, 3], "B": [4, 5, 6]}, [0, 1, 2]),
+            ],
+            2,
+        ),
+        (
+            DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]}),
+            [
+                ({"A": [1], "B": [4]}, [0]),
+                ({"A": [1, 2], "B": [4, 5]}, [0, 1]),
+                ({"A": [1, 2, 3], "B": [4, 5, 6]}, [0, 1, 2]),
+            ],
+            1,
+        ),
+        (DataFrame({"A": [1], "B": [4]}), [], 2),
+        (DataFrame(), [({}, [])], 1),
+        (
+            DataFrame({"A": [1, np.nan, 3], "B": [np.nan, 5, 6]}),
+            [({"A": [1, np.nan, 3], "B": [np.nan, 5, 6]}, [0, 1, 2])],
+            3,
+        ),
+        (
+            DataFrame({"A": [1, np.nan, 3], "B": [np.nan, 5, 6]}),
+            [({"A": [1, np.nan, 3], "B": [np.nan, 5, 6]}, [0, 1, 2])],
+            2,
+        ),
+        (
+            DataFrame({"A": [1, np.nan, 3], "B": [np.nan, 5, 6]}),
+            [
+                ({"A": [1, np.nan], "B": [np.nan, 5]}, [0, 1]),
+                ({"A": [1, np.nan, 3], "B": [np.nan, 5, 6]}, [0, 1, 2]),
+            ],
+            1,
+        ),
+    ],
+)
+def test_iter_expanding_dataframe(df, expected, min_periods):
+    # GH 11704
+    expected = [DataFrame(values, index=index) for (values, index) in expected]
+
+    for (expected, actual) in zip(expected, df.expanding(min_periods)):
+        tm.assert_frame_equal(actual, expected)
+
+
+@pytest.mark.parametrize(
+    "ser,expected,min_periods",
+    [
+        (Series([1, 2, 3]), [([1, 2, 3], [0, 1, 2])], 3),
+        (Series([1, 2, 3]), [([1, 2], [0, 1]), ([1, 2, 3], [0, 1, 2])], 2),
+        (Series([1, 2, 3]), [([1], [0]), ([1, 2], [0, 1]), ([1, 2, 3], [0, 1, 2])], 1),
+        (Series([1, 2]), [([1, 2], [0, 1])], 2),
+        (Series([np.nan, 2]), [([np.nan, 2], [0, np.nan])], 2),
+        (Series([], dtype="int64"), [], 2),
+    ],
+)
+def test_iter_expanding_series(ser, expected, min_periods):
+    # GH 11704
+    expected = [Series(values, index=index) for (values, index) in expected]
+
+    for (expected, actual) in zip(expected, ser.expanding(min_periods)):
+        tm.assert_series_equal(actual, expected)

pandas/tests/window/test_rolling.py

@@ -310,18 +310,6 @@ def test_multi_index_names():
     assert result.index.names == [None, "1", "2"]
 
 
-@pytest.mark.parametrize("klass", [pd.Series, pd.DataFrame])
-def test_iter_raises(klass):
-    # https://github.com/pandas-dev/pandas/issues/11704
-    # Iteration over a Window
-    obj = klass([1, 2, 3, 4])
-
-    msg = "See issue #11704 https://github.com/pandas-dev/pandas/issues/11704"
-
-    with pytest.raises(NotImplementedError, match=msg):
-        iter(obj.rolling(2))
-
-
 def test_rolling_axis_sum(axis_frame):
     # see gh-23372.
     df = DataFrame(np.ones((10, 20)))
@@ -470,3 +458,87 @@ def test_rolling_count_default_min_periods_with_null_values(constructor):
     result = constructor(values).rolling(3).count()
     expected = constructor(expected_counts)
     tm.assert_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "df,expected,window,min_periods",
+    [
+        (
+            DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]}),
+            [({"A": [1, 2, 3], "B": [4, 5, 6]}, [0, 1, 2])],
+            3,
+            None,
+        ),
+        (
+            DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]}),
+            [
+                ({"A": [1], "B": [4]}, [0]),
+                ({"A": [1, 2], "B": [4, 5]}, [0, 1]),
+                ({"A": [2, 3], "B": [5, 6]}, [1, 2]),
+            ],
+            2,
+            1,
+        ),
+        (
+            DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]}),
+            [
+                ({"A": [1, 2], "B": [4, 5]}, [0, 1]),
+                ({"A": [2, 3], "B": [5, 6]}, [1, 2]),
+            ],
+            2,
+            3,
+        ),
+        (
+            DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]}),
+            [
+                ({"A": [1], "B": [4]}, [0]),
+                ({"A": [2], "B": [5]}, [1]),
+                ({"A": [3], "B": [6]}, [2]),
+            ],
+            1,
+            1,
+        ),
+        (DataFrame({"A": [1], "B": [4]}), [], 2, None),
+        (DataFrame({"A": [1], "B": [4]}), [], 2, 1),
+        (DataFrame(), [({}, [])], 2, None),
+        (DataFrame(), [({}, [])], 1, 2),
+        (
+            DataFrame({"A": [1, np.nan, 3], "B": [np.nan, 5, 6]}),
+            [({"A": [1, np.nan, 3], "B": [np.nan, 5, 6]}, [0, 1, 2])],
+            3,
+            2,
+        ),
+    ],
+)
+def test_iter_rolling_dataframe(df, expected, window, min_periods):
+    # GH 11704
+    expected = [DataFrame(values, index=index) for (values, index) in expected]
+
+    for (expected, actual) in zip(
+        expected, df.rolling(window, min_periods=min_periods)
+    ):
+        tm.assert_frame_equal(actual, expected)
+
+
+@pytest.mark.parametrize(
+    "ser,expected,window, min_periods",
+    [
+        (Series([1, 2, 3]), [([1, 2, 3], [0, 1, 2])], 3, None),
+        (Series([1, 2, 3]), [([1], [0]), ([1, 2], [0, 1]), ([2, 3], [1, 2])], 2, 1),
+        (Series([1, 2, 3]), [([1, 2], [0, 1]), ([2, 3], [1, 2])], 2, 3),
+        (Series([1, 2, 3]), [([1], [0]), ([2], [1]), ([3], [2])], 1, 0),
+        (Series([1, 2, 3]), [([1], [0]), ([2], [1]), ([3], [2])], 1, 2),
+        (Series([1, 2]), [([1], [0]), ([1, 2], [0, 1])], 2, 0),
+        (Series([1, 2]), [([1, 2], [0, 1])], 2, 3),
+        (Series([], dtype="int64"), [], 2, 1),
+        (Series([], dtype="int64"), [], 2, 3),
+    ],
+)
+def test_iter_rolling_series(ser, expected, window, min_periods):
+    # GH 11704
+    expected = [Series(values, index=index) for (values, index) in expected]
+
+    for (expected, actual) in zip(
+        expected, ser.rolling(window, min_periods=min_periods)
+    ):
+        tm.assert_series_equal(actual, expected)