Fix pandas 3.0 compatibility issues with MicroSeries method access

The previous approach of modifying `__class__` on DataFrame columns no longer
works in pandas 3.0 due to Copy-on-Write behavior. Each column access returns
a new copy, so class modifications don't persist.

This fix changes the strategy:
- `__getitem__` now wraps all Series results as MicroSeries on access
- Removed the broken `_link_weights` and `catch_series_relapse` logic
- Simplified `_link_all_weights` since columns are wrapped on access

This resolves the "AttributeError: 'Series' object has no attribute
'set_weights'" error that occurred when using MicroDataFrame with pandas 3.0.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Author: MaxGhenis

changelog_entry.yaml

@@ -0,0 +1,4 @@
+- bump: patch
+  changes:
+    fixed:
+      - Fixed pandas 3.0 compatibility issues with MicroSeries method access and Copy-on-Write behavior

microdf/microdataframe.py

@@ -278,18 +278,18 @@ def __setitem__(self, *args, **kwargs) -> None:
         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 @@ def nullify_weights(self) -> None:
 
     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 @@ def __getitem__(
             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

@@ -1,5 +1,4 @@
-"""
-Tests for pandas 3.0.0 compatibility in microdf.
+"""Tests for pandas 3.0.0 compatibility in microdf.
 
 These tests verify that microdf works correctly with pandas 3.0.0,
 which introduces:
@@ -10,18 +9,17 @@
 
 import numpy as np
 import pandas as pd
-import pytest
 
-from microdf.microseries import MicroSeries
 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.
+        """Ensure set_weights works on MicroSeries.
+
         This is the error reported in pandas 3:
         AttributeError: 'Series' object has no attribute 'set_weights'
         """
@@ -34,108 +32,115 @@ def test_microseries_set_weights_after_creation(self):
         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.
-        """
+        """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 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"
+        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"
+        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.
-        """
+        """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 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"
+        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]))
+        """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 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"
+        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.
-        """
+        """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])
+            {"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 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.
-        """
+        """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])
+            {"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 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.
-        """
+        """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.
-        """
+        """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])
+            weights=np.array([1.0, 2.0, 3.0]),
         )
         assert len(mdf) == 3
 
@@ -169,9 +174,7 @@ class TestCopyOnWriteCompatibility:
     """Test compatibility with pandas 3 Copy-on-Write."""
 
     def test_microseries_copy_independent(self):
-        """
-        Copying a MicroSeries should create an independent copy.
-        """
+        """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()
 
@@ -182,12 +185,9 @@ def test_microseries_copy_independent(self):
         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.
-        """
+        """Copying a MicroDataFrame should create an independent copy."""
         mdf = MicroDataFrame(
-            {"a": [1, 2, 3]},
-            weights=np.array([1.0, 2.0, 3.0])
+            {"a": [1, 2, 3]}, weights=np.array([1.0, 2.0, 3.0])
         )
         mdf_copy = mdf.copy()
 
@@ -202,9 +202,7 @@ class TestGroupByWithPandas3:
     """Test groupby operations with pandas 3."""
 
     def test_microseries_groupby_preserves_weights(self):
-        """
-        GroupBy operations should preserve weights.
-        """
+        """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"])
 
@@ -217,12 +215,10 @@ def test_microseries_groupby_preserves_weights(self):
         assert result["b"] == 25
 
     def test_microdataframe_groupby_preserves_weights(self):
-        """
-        MicroDataFrame groupby should preserve weights on columns.
-        """
+        """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])
+            weights=np.array([1.0, 2.0, 3.0, 4.0]),
         )
 
         gb = mdf.groupby("group")