microdf-python 1.1.2__py3-none-any.whl → 1.2.1__py3-none-any.whl

microdf/microdataframe.py

@@ -278,18 +278,18 @@ class MicroDataFrame(pd.DataFrame):
         self._link_all_weights()
 
     def _link_weights(self, column) -> None:
-        # self[column] = ... triggers __setitem__, which forces pd.Series
-        # this workaround avoids that
-        self[column].__class__ = MicroSeries
-        self[column].set_weights(self.weights)
+        # In pandas 3.0+, we can't modify column classes in-place due to CoW.
+        # Instead, we rely on __getitem__ to wrap columns as MicroSeries on
+        # access. This method is kept for backward compatibility but is now
+        # a no-op.
+        pass
 
     def _link_all_weights(self) -> None:
         if self.weights is None:
             if len(self) > 0:
                 self.set_weights(np.ones((len(self))))
-        for column in self.columns:
-            if column != self.weights_col:
-                self._link_weights(column)
+        # In pandas 3.0+, columns are wrapped as MicroSeries on access via
+        # __getitem__, not stored as MicroSeries internally.
 
     def set_weights(
         self,
@@ -365,7 +365,7 @@ class MicroDataFrame(pd.DataFrame):
 
     def __getitem__(
         self, key: Union[str, List]
-    ) -> Union[pd.Series, pd.DataFrame]:
+    ) -> Union[MicroSeries, "MicroDataFrame"]:
         # Let pandas handle the initial slicing
         result = super().__getitem__(key)
 
@@ -374,17 +374,22 @@ class MicroDataFrame(pd.DataFrame):
             new_weights = self.weights.reindex(result.index)
             return MicroDataFrame(result, weights=new_weights)
 
-        # Otherwise, the result is a Series or a scalar, so just return it
+        # If the result is a Series (single column), wrap as MicroSeries
+        if isinstance(result, pd.Series):
+            return MicroSeries(result, weights=self.weights)
+
+        # Otherwise, the result is a scalar, so just return it
         return result
 
     def catch_series_relapse(self) -> None:
-        for col in self.columns:
-            if self[col].__class__ == pd.Series:
-                self._link_weights(col)
+        # In pandas 3.0+, we don't need to track series class changes since
+        # __getitem__ always wraps columns as MicroSeries on access.
+        pass
 
     def __setattr__(self, key, value) -> None:
         super().__setattr__(key, value)
-        self.catch_series_relapse()
+        # No need to call catch_series_relapse in pandas 3.0+ since we wrap
+        # on access rather than store MicroSeries internally.
 
     def reset_index(
         self,

microdf/tests/test_pandas3_compatibility.py

@@ -0,0 +1,248 @@
+"""Tests for pandas 3.0.0 compatibility in microdf.
+
+These tests verify that microdf works correctly with pandas 3.0.0,
+which introduces:
+1. PyArrow-backed strings as default (StringDtype)
+2. Copy-on-Write by default
+3. Changes to how Series subclasses are handled
+"""
+
+import numpy as np
+import pandas as pd
+
+from microdf.microdataframe import MicroDataFrame
+from microdf.microseries import MicroSeries
+
+
+class TestMicroSeriesSubclassPreservation:
+    """Test that MicroSeries subclass is preserved across operations."""
+
+    def test_microseries_set_weights_after_creation(self):
+        """Ensure set_weights works on MicroSeries.
+
+        This is the error reported in pandas 3:
+        AttributeError: 'Series' object has no attribute 'set_weights'
+        """
+        ms = MicroSeries([1, 2, 3], weights=np.array([1.0, 1.0, 1.0]))
+        assert hasattr(ms, "set_weights")
+        assert hasattr(ms, "weights")
+
+        # Should be able to call set_weights
+        ms.set_weights(np.array([2.0, 2.0, 2.0]))
+        assert np.allclose(ms.weights, [2.0, 2.0, 2.0])
+
+    def test_microseries_preserved_after_arithmetic(self):
+        """Arithmetic operations should return MicroSeries, not plain
+        Series."""
+        ms = MicroSeries([1, 2, 3], weights=np.array([1.0, 2.0, 3.0]))
+
+        # Addition
+        result = ms + 1
+        assert isinstance(
+            result, MicroSeries
+        ), f"Got {type(result)} instead of MicroSeries"
+        assert hasattr(result, "weights")
+        assert hasattr(result, "set_weights")
+
+        # Multiplication
+        result = ms * 2
+        assert isinstance(
+            result, MicroSeries
+        ), f"Got {type(result)} instead of MicroSeries"
+
+        # Division
+        result = ms / 2
+        assert isinstance(
+            result, MicroSeries
+        ), f"Got {type(result)} instead of MicroSeries"
+
+    def test_microseries_preserved_after_comparison(self):
+        """Comparison operations should return MicroSeries, not plain
+        Series."""
+        ms = MicroSeries([1, 2, 3], weights=np.array([1.0, 2.0, 3.0]))
+
+        # Greater than
+        result = ms > 1
+        assert isinstance(
+            result, MicroSeries
+        ), f"Got {type(result)} instead of MicroSeries"
+        assert hasattr(result, "weights")
+
+        # Less than
+        result = ms < 3
+        assert isinstance(
+            result, MicroSeries
+        ), f"Got {type(result)} instead of MicroSeries"
+
+    def test_microseries_preserved_after_indexing(self):
+        """Indexing operations should return MicroSeries, not plain Series."""
+        ms = MicroSeries(
+            [1, 2, 3, 4, 5], weights=np.array([1.0, 2.0, 3.0, 4.0, 5.0])
+        )
+
+        # Boolean indexing
+        result = ms[ms > 2]
+        assert isinstance(
+            result, MicroSeries
+        ), f"Got {type(result)} instead of MicroSeries"
+        assert hasattr(result, "weights")
+
+        # Slice indexing
+        result = ms[1:3]
+        assert isinstance(
+            result, MicroSeries
+        ), f"Got {type(result)} instead of MicroSeries"
+
+
+class TestMicroDataFrameSubclassPreservation:
+    """Test that MicroDataFrame column access returns MicroSeries."""
+
+    def test_microdataframe_column_returns_microseries(self):
+        """Accessing a column from MicroDataFrame should return MicroSeries."""
+        mdf = MicroDataFrame(
+            {"a": [1, 2, 3], "b": [4, 5, 6]}, weights=np.array([1.0, 2.0, 3.0])
+        )
+
+        # Column access
+        col = mdf["a"]
+        assert isinstance(
+            col, MicroSeries
+        ), f"Got {type(col)} instead of MicroSeries"
+        assert hasattr(col, "weights")
+        assert hasattr(col, "set_weights")
+
+    def test_microdataframe_operations_preserve_type(self):
+        """Operations on MicroDataFrame columns should preserve MicroSeries
+        type."""
+        mdf = MicroDataFrame(
+            {"a": [1, 2, 3], "b": [4, 5, 6]}, weights=np.array([1.0, 2.0, 3.0])
+        )
+
+        # Column operations
+        result = mdf["a"] + mdf["b"]
+        assert isinstance(
+            result, MicroSeries
+        ), f"Got {type(result)} instead of MicroSeries"
+        assert hasattr(result, "weights")
+
+
+class TestStringDtypeHandling:
+    """Test that MicroSeries/MicroDataFrame handle pandas 3 string dtypes."""
+
+    def test_microseries_with_string_data(self):
+        """MicroSeries should work with string data in pandas 3."""
+        # Create with string data
+        ms = MicroSeries(["a", "b", "c"], weights=np.array([1.0, 2.0, 3.0]))
+        assert len(ms) == 3
+        assert hasattr(ms, "weights")
+
+    def test_microdataframe_with_string_columns(self):
+        """MicroDataFrame should work with string columns in pandas 3."""
+        mdf = MicroDataFrame(
+            {"names": ["alice", "bob", "charlie"], "values": [1, 2, 3]},
+            weights=np.array([1.0, 2.0, 3.0]),
+        )
+        assert len(mdf) == 3
+
+        # String column access should still work
+        names = mdf["names"]
+        assert len(names) == 3
+
+
+class TestWeightedOperationsWithPandas3:
+    """Test that weighted operations work correctly with pandas 3."""
+
+    def test_weighted_sum(self):
+        """Weighted sum should work correctly."""
+        ms = MicroSeries([1, 2, 3], weights=np.array([1.0, 2.0, 3.0]))
+        # Weighted sum: 1*1 + 2*2 + 3*3 = 1 + 4 + 9 = 14
+        assert ms.sum() == 14
+
+    def test_weighted_mean(self):
+        """Weighted mean should work correctly."""
+        ms = MicroSeries([1, 2, 3], weights=np.array([1.0, 2.0, 3.0]))
+        # Weighted mean: (1*1 + 2*2 + 3*3) / (1 + 2 + 3) = 14 / 6 ≈ 2.333
+        assert np.isclose(ms.mean(), 14 / 6)
+
+    def test_weighted_count(self):
+        """Weighted count should return sum of weights."""
+        ms = MicroSeries([1, 2, 3], weights=np.array([1.0, 2.0, 3.0]))
+        assert ms.count() == 6.0
+
+
+class TestCopyOnWriteCompatibility:
+    """Test compatibility with pandas 3 Copy-on-Write."""
+
+    def test_microseries_copy_independent(self):
+        """Copying a MicroSeries should create an independent copy."""
+        ms = MicroSeries([1, 2, 3], weights=np.array([1.0, 2.0, 3.0]))
+        ms_copy = ms.copy()
+
+        # Modify original
+        ms.set_weights(np.array([4.0, 5.0, 6.0]))
+
+        # Copy should be unchanged
+        assert np.allclose(ms_copy.weights, [1.0, 2.0, 3.0])
+
+    def test_microdataframe_copy_independent(self):
+        """Copying a MicroDataFrame should create an independent copy."""
+        mdf = MicroDataFrame(
+            {"a": [1, 2, 3]}, weights=np.array([1.0, 2.0, 3.0])
+        )
+        mdf_copy = mdf.copy()
+
+        # Modify original
+        mdf.set_weights(np.array([4.0, 5.0, 6.0]))
+
+        # Copy should be unchanged
+        assert np.allclose(mdf_copy.weights, [1.0, 2.0, 3.0])
+
+    def test_column_set_weights_after_access_regression(self):
+        """Regression test for pandas 3.0 CoW compatibility.
+
+        In pandas 3.0 with Copy-on-Write, modifying column.__class__ doesn't
+        persist because each access returns a copy. This test verifies the fix
+        that wraps columns as MicroSeries on access in __getitem__.
+        """
+        mdf = MicroDataFrame(
+            {"income": [10000, 20000, 30000]},
+            weights=np.array([1.0, 2.0, 3.0]),
+        )
+
+        # This was the exact error that occurred:
+        # AttributeError: 'Series' object has no attribute 'set_weights'
+        col = mdf["income"]
+        col.set_weights(np.array([4.0, 5.0, 6.0]))  # Would fail before fix
+
+        # Verify the new weights took effect
+        assert np.allclose(col.weights, [4.0, 5.0, 6.0])
+
+
+class TestGroupByWithPandas3:
+    """Test groupby operations with pandas 3."""
+
+    def test_microseries_groupby_preserves_weights(self):
+        """GroupBy operations should preserve weights."""
+        ms = MicroSeries([1, 2, 3, 4], weights=np.array([1.0, 2.0, 3.0, 4.0]))
+        groups = pd.Series(["a", "a", "b", "b"])
+
+        gb = ms.groupby(groups)
+        # Should be able to call weighted operations
+        result = gb.sum()
+        # Group a: 1*1 + 2*2 = 5
+        # Group b: 3*3 + 4*4 = 25
+        assert result["a"] == 5
+        assert result["b"] == 25
+
+    def test_microdataframe_groupby_preserves_weights(self):
+        """MicroDataFrame groupby should preserve weights on columns."""
+        mdf = MicroDataFrame(
+            {"group": ["a", "a", "b", "b"], "value": [1, 2, 3, 4]},
+            weights=np.array([1.0, 2.0, 3.0, 4.0]),
+        )
+
+        gb = mdf.groupby("group")
+        result = gb.sum()
+
+        # Check that weighted sum was computed
+        assert "value" in result.columns

{microdf_python-1.1.2.dist-info → microdf_python-1.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: microdf-python
-Version: 1.1.2
+Version: 1.2.1
 Summary: Weighted pandas DataFrames and Series for survey microdata
 Author-email: Max Ghenis <max@policyengine.org>
 License: MIT

microdf_python-1.2.1.dist-info/RECORD

@@ -0,0 +1,11 @@
+microdf/__init__.py,sha256=ldRvhE8t4cD7qlxQ5yLndMnWEUYpDw4m-jCDV_psXkY,319
+microdf/microdataframe.py,sha256=2lZU3FAtVCgKiVD-iD_3xu3NMEEl-7Tbn-T-aOR_ihc,33920
+microdf/microseries.py,sha256=YRnSHVm3mGGd1_-D29BAUDaqWoIiwGjJPKYUrnWbinY,23376
+microdf/tests/conftest.py,sha256=u-EMyX1-u_nM-YO0RJYCzYHQDXxUI2WQE6GkyJlErqg,150
+microdf/tests/test_microseries_dataframe.py,sha256=lG2_3lJqTdGekbbJRFl0Vp0b4DEQwTk6scXr-ncOHgs,14647
+microdf/tests/test_pandas3_compatibility.py,sha256=p4SZoW59REA5GV84HH9InfCdKQ1nEBGmatnRK84GiGY,8623
+microdf_python-1.2.1.dist-info/licenses/LICENSE,sha256=uPs-ASYnzlldpf2z8jeRgQFeEH3FLhSuX0rw0OKWoDU,1067
+microdf_python-1.2.1.dist-info/METADATA,sha256=_2sK8uH_um7Pir-OpT5eT3Utfv9jFnYNYYV-p4aYNbE,2420
+microdf_python-1.2.1.dist-info/WHEEL,sha256=qELbo2s1Yzl39ZmrAibXA2jjPLUYfnVhUNTlyF1rq0Y,92
+microdf_python-1.2.1.dist-info/top_level.txt,sha256=T2WFPTygQQMdS3GF8YpZ12DKfMGrspbZ3r7z-e3KfiM,8
+microdf_python-1.2.1.dist-info/RECORD,,

{microdf_python-1.1.2.dist-info → microdf_python-1.2.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: setuptools (80.10.1)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

microdf_python-1.1.2.dist-info/RECORD

@@ -1,10 +0,0 @@
-microdf/__init__.py,sha256=ldRvhE8t4cD7qlxQ5yLndMnWEUYpDw4m-jCDV_psXkY,319
-microdf/microdataframe.py,sha256=h0vIuCACMo1BuV3VKDIEfhc_UwMUV5kUsnlQe3bHfgM,33539
-microdf/microseries.py,sha256=YRnSHVm3mGGd1_-D29BAUDaqWoIiwGjJPKYUrnWbinY,23376
-microdf/tests/conftest.py,sha256=u-EMyX1-u_nM-YO0RJYCzYHQDXxUI2WQE6GkyJlErqg,150
-microdf/tests/test_microseries_dataframe.py,sha256=lG2_3lJqTdGekbbJRFl0Vp0b4DEQwTk6scXr-ncOHgs,14647
-microdf_python-1.1.2.dist-info/licenses/LICENSE,sha256=uPs-ASYnzlldpf2z8jeRgQFeEH3FLhSuX0rw0OKWoDU,1067
-microdf_python-1.1.2.dist-info/METADATA,sha256=MNlbpTktwqMoFlf-CImA-Xsi-ix7Zv1XAYZ09W1YRcY,2420
-microdf_python-1.1.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-microdf_python-1.1.2.dist-info/top_level.txt,sha256=T2WFPTygQQMdS3GF8YpZ12DKfMGrspbZ3r7z-e3KfiM,8
-microdf_python-1.1.2.dist-info/RECORD,,