microdf-python 1.3.3__tar.gz → 1.3.4__tar.gz

{microdf_python-1.3.3/microdf_python.egg-info → microdf_python-1.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: microdf-python
-Version: 1.3.3
+Version: 1.3.4
 Summary: Weighted pandas DataFrames and Series for survey microdata
 Author-email: Max Ghenis <max@policyengine.org>
 License: MIT

{microdf_python-1.3.3 → microdf_python-1.3.4}/microdf/microdataframe.py

@@ -310,8 +310,9 @@ class MicroDataFrame(pd.DataFrame):
 
         if isinstance(weights, str):
             self.weights_col = weights
+            # Keep stored weights independent from edits to the source column.
             self.weights = pd.Series(
-                np.asarray(self[weights]),
+                np.array(self[weights], copy=True),
                 index=self.index,
                 dtype=float,
             )
@@ -362,9 +363,9 @@ class MicroDataFrame(pd.DataFrame):
         if preserve_old and self.weights_col is not None:
             self["old_" + self.weights_col] = self.weights
 
-        self.weights = np.array(self[column])
-        self.weights_col = column
-        self._link_all_weights()
+        # Delegate to set_weights: it validates length and builds an
+        # index-aligned float Series rather than a bare ndarray.
+        self.set_weights(column)
 
     def nullify_weights(self) -> None:
         """Set all weights to 1, effectively making the DataFrame unweighted.
@@ -372,8 +373,10 @@ class MicroDataFrame(pd.DataFrame):
         This is useful for comparing weighted and unweighted statistics or when
         you want to temporarily ignore weights.
         """
-        self.weights = np.ones(len(self))
-        self._link_all_weights()
+        # Route through set_weights so self.weights stays an index-aligned
+        # float Series. Assigning a bare ndarray here broke every caller
+        # that treats it as a Series (equals(), reindex() in __getitem__).
+        self.set_weights(np.ones(len(self)))
 
     def __getitem__(
         self, key: Union[str, List]

microdf_python-1.3.4/microdf/tests/test_dataframe_weight_storage.py

@@ -0,0 +1,61 @@
+import warnings
+
+import numpy as np
+import pandas as pd
+import pytest
+
+import microdf as mdf
+
+
+def test_weights_stay_a_series_after_nullify():
+    """nullify_weights must leave weights as an index-aligned Series."""
+    df = mdf.MicroDataFrame(pd.DataFrame({"x": [1, 2, 3]}), weights=[4, 5, 6])
+    df.nullify_weights()
+    assert isinstance(df.weights, pd.Series)
+    assert list(df.weights.index) == list(df.index)
+    assert df.equals(df)
+    assert df.sum()["x"] == 6
+
+
+def test_weights_stay_a_series_after_set_weight_col():
+    """The deprecated set_weight_col must also produce a Series."""
+    df = mdf.MicroDataFrame(pd.DataFrame({"x": [1, 2, 3], "w": [1.0, 2.0, 3.0]}))
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore", DeprecationWarning)
+        df.set_weight_col("w")
+    assert isinstance(df.weights, pd.Series)
+    assert df.weights_col == "w"
+    assert df.equals(df)
+    assert df.sum()["x"] == 14
+
+
+@pytest.mark.parametrize("dtype", ["int64", "float64"])
+def test_weight_column_edits_do_not_change_stored_weights(dtype):
+    """Selecting a weight column takes a copy of its current values."""
+    df = mdf.MicroDataFrame(
+        {"x": [10, 20], "w": np.array([1, 2], dtype=dtype)},
+        index=[10, 20],
+    )
+    with pytest.warns(DeprecationWarning):
+        df.set_weight_col("w")
+
+    df.loc[10, "w"] = 100
+
+    np.testing.assert_array_equal(df.weights, [1, 2])
+    assert df.sum()["x"] == 10 * 1 + 20 * 2
+
+
+@pytest.mark.parametrize("dtype", ["int64", "float64"])
+def test_stored_weight_edits_do_not_change_weight_column(dtype):
+    """Changing stored weights leaves the source column values intact."""
+    df = mdf.MicroDataFrame(
+        {"x": [10, 20], "w": np.array([1, 2], dtype=dtype)},
+        index=[10, 20],
+    )
+    with pytest.warns(DeprecationWarning):
+        df.set_weight_col("w")
+
+    df.weights.iloc[0] = 100
+
+    np.testing.assert_array_equal(df["w"], [1, 2])
+    assert df.sum()["x"] == 10 * 100 + 20 * 2

{microdf_python-1.3.3 → microdf_python-1.3.4/microdf_python.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: microdf-python
-Version: 1.3.3
+Version: 1.3.4
 Summary: Weighted pandas DataFrames and Series for survey microdata
 Author-email: Max Ghenis <max@policyengine.org>
 License: MIT

{microdf_python-1.3.3 → microdf_python-1.3.4}/microdf_python.egg-info/SOURCES.txt

@@ -5,6 +5,7 @@ microdf/__init__.py
 microdf/microdataframe.py
 microdf/microseries.py
 microdf/tests/conftest.py
+microdf/tests/test_dataframe_weight_storage.py
 microdf/tests/test_microseries_dataframe.py
 microdf/tests/test_nullify_weights_index.py
 microdf/tests/test_pandas3_compatibility.py

{microdf_python-1.3.3 → microdf_python-1.3.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "microdf-python"
-version = "1.3.3"
+version = "1.3.4"
 description = "Weighted pandas DataFrames and Series for survey microdata"
 readme = "README.md"
 authors = [