microdf-python 1.2.1__tar.gz → 1.2.2__tar.gz

{microdf_python-1.2.1/microdf_python.egg-info → microdf_python-1.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: microdf-python
-Version: 1.2.1
+Version: 1.2.2
 Summary: Weighted pandas DataFrames and Series for survey microdata
 Author-email: Max Ghenis <max@policyengine.org>
 License: MIT
@@ -20,6 +20,7 @@ Requires-Dist: linecheck; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-cov; extra == "dev"
 Requires-Dist: setuptools; extra == "dev"
+Requires-Dist: towncrier>=24.8.0; extra == "dev"
 Dynamic: license-file
 
 [![Build](https://github.com/PolicyEngine/microdf/workflows/Pull%20request/badge.svg)](https://github.com/PolicyEngine/microdf/actions)

{microdf_python-1.2.1 → microdf_python-1.2.2}/microdf/microseries.py

@@ -1,4 +1,5 @@
 import logging
+import warnings
 from functools import wraps
 from typing import Callable, List, Optional, Union
 
@@ -19,6 +20,50 @@ class MicroSeries(pd.Series):
         super().__init__(*args, **kwargs)
         self.set_weights(weights)
 
+    @property
+    def _values(self):
+        """Internal access to underlying numpy array without warning."""
+        return super().values
+
+    @property
+    def values(self):
+        """Access underlying numpy array.
+
+        .. warning::
+            Returns a plain numpy array without weights. Operations
+            like ``.mean()`` on the result will be unweighted. Use
+            MicroSeries methods directly for weighted calculations
+            (e.g., ``ms.mean()`` instead of ``ms.values.mean()``).
+        """
+        warnings.warn(
+            "Accessing .values on a MicroSeries returns a plain numpy "
+            "array without weights. Operations like .mean() on the "
+            "result will be unweighted. Use MicroSeries methods "
+            "directly for weighted calculations (e.g., ms.mean() "
+            "instead of ms.values.mean()).",
+            UserWarning,
+            stacklevel=2,
+        )
+        return super().values
+
+    def to_numpy(self, *args, **kwargs):
+        """Convert to numpy array.
+
+        .. warning::
+            Returns a plain numpy array without weights. Operations
+            like ``.mean()`` on the result will be unweighted. Use
+            MicroSeries methods directly for weighted calculations.
+        """
+        warnings.warn(
+            "Calling .to_numpy() on a MicroSeries returns a plain "
+            "numpy array without weights. Operations like .mean() on "
+            "the result will be unweighted. Use MicroSeries methods "
+            "directly for weighted calculations.",
+            UserWarning,
+            stacklevel=2,
+        )
+        return super().to_numpy(*args, **kwargs)
+
     def weighted_function(fn: Callable) -> Callable:
         @wraps(fn)
         def safe_fn(*args, **kwargs):
@@ -52,7 +97,7 @@ class MicroSeries(pd.Series):
         if weights is None:
             if len(self) > 0:
                 self.weights = pd.Series(
-                    np.ones_like(self.values), dtype=float
+                    np.ones_like(self._values), dtype=float
                 )
         else:
             if len(weights) != len(self):
@@ -110,7 +155,7 @@ class MicroSeries(pd.Series):
         :returns: The weighted mean.
         :rtype: float
         """
-        values = self.values
+        values = self._values
         weights = self.weights
 
         if skipna:
@@ -141,7 +186,7 @@ class MicroSeries(pd.Series):
         :return: Weighted quantile value(s).
         :rtype: float or pd.Series
         """
-        values = np.array(self.values)
+        values = np.array(self._values)
         quantiles = np.atleast_1d(q)
         sample_weight = np.array(self.weights)
         assert np.all(quantiles >= 0) and np.all(
@@ -313,7 +358,7 @@ class MicroSeries(pd.Series):
                 "in division by zero."
             )
 
-        order = np.argsort(self.values)
+        order = np.argsort(self._values)
         inverse_order = np.argsort(order)
         ranks = np.array(self.weights.values)[order].cumsum()[inverse_order]
         if pct:
@@ -506,7 +551,7 @@ class MicroSeries(pd.Series):
         return MicroSeries(super().__rxor__(other), weights=self.weights)
 
     def sqrt(self) -> "MicroSeries":
-        sqrt_values = np.sqrt(self.values)
+        sqrt_values = np.sqrt(self._values)
         return MicroSeries(sqrt_values, index=self.index, weights=self.weights)
 
     # comparators
@@ -590,7 +635,7 @@ class MicroSeries(pd.Series):
 
     def __repr__(self) -> str:
         return pd.DataFrame(
-            dict(value=self.values, weight=self.weights.values)
+            dict(value=self._values, weight=self.weights.values)
         ).__repr__()
 
 

{microdf_python-1.2.1 → microdf_python-1.2.2}/microdf/tests/test_microseries_dataframe.py

@@ -1,3 +1,5 @@
+import warnings
+
 import numpy as np
 import pandas as pd
 
@@ -423,3 +425,45 @@ def test_groupby_column_selection() -> None:
     result_all = d.groupby("g").sum()
     assert "weight" not in result_all.columns
     assert list(result_all.columns) == ["y"]
+
+
+def test_values_warns() -> None:
+    """Accessing .values on a MicroSeries should emit a UserWarning."""
+    ms = mdf.MicroSeries([1, 2, 3], weights=[4, 5, 6])
+    with warnings.catch_warnings(record=True) as w:
+        warnings.simplefilter("always")
+        _ = ms.values
+        assert len(w) == 1
+        assert issubclass(w[0].category, UserWarning)
+        assert "weights" in str(w[0].message).lower()
+
+
+def test_to_numpy_warns() -> None:
+    """Calling .to_numpy() on a MicroSeries should emit a UserWarning."""
+    ms = mdf.MicroSeries([1, 2, 3], weights=[4, 5, 6])
+    with warnings.catch_warnings(record=True) as w:
+        warnings.simplefilter("always")
+        _ = ms.to_numpy()
+        assert len(w) == 1
+        assert issubclass(w[0].category, UserWarning)
+        assert "weights" in str(w[0].message).lower()
+
+
+def test_mean_no_warning() -> None:
+    """Internal .values usage in .mean() should NOT emit a warning."""
+    ms = mdf.MicroSeries([1, 2, 3], weights=[4, 5, 6])
+    with warnings.catch_warnings(record=True) as w:
+        warnings.simplefilter("always")
+        _ = ms.mean()
+        user_warnings = [x for x in w if issubclass(x.category, UserWarning)]
+        assert len(user_warnings) == 0
+
+
+def test_repr_no_warning() -> None:
+    """Internal .values usage in __repr__ should NOT emit a warning."""
+    ms = mdf.MicroSeries([1, 2, 3], weights=[4, 5, 6])
+    with warnings.catch_warnings(record=True) as w:
+        warnings.simplefilter("always")
+        _ = repr(ms)
+        user_warnings = [x for x in w if issubclass(x.category, UserWarning)]
+        assert len(user_warnings) == 0

{microdf_python-1.2.1 → microdf_python-1.2.2/microdf_python.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: microdf-python
-Version: 1.2.1
+Version: 1.2.2
 Summary: Weighted pandas DataFrames and Series for survey microdata
 Author-email: Max Ghenis <max@policyengine.org>
 License: MIT
@@ -20,6 +20,7 @@ Requires-Dist: linecheck; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-cov; extra == "dev"
 Requires-Dist: setuptools; extra == "dev"
+Requires-Dist: towncrier>=24.8.0; extra == "dev"
 Dynamic: license-file
 
 [![Build](https://github.com/PolicyEngine/microdf/workflows/Pull%20request/badge.svg)](https://github.com/PolicyEngine/microdf/actions)

{microdf_python-1.2.1 → microdf_python-1.2.2}/microdf_python.egg-info/requires.txt

@@ -12,3 +12,4 @@ linecheck
 pytest
 pytest-cov
 setuptools
+towncrier>=24.8.0

{microdf_python-1.2.1 → microdf_python-1.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "microdf-python"
-version = "1.2.1"
+version = "1.2.2"
 description = "Weighted pandas DataFrames and Series for survey microdata"
 readme = "README.md"
 authors = [
@@ -28,7 +28,8 @@ dev = [
     "linecheck",
     "pytest",
     "pytest-cov",
-    "setuptools",
+    "setuptools",    "towncrier>=24.8.0",
+
 ]
 # Note: Documentation uses MyST (Jupyter Book 2.0) which is installed via npm
 # Run: cd docs && myst build --html
@@ -48,3 +49,36 @@ target-version = ["py313"]
 [tool.flake8]
 max-line-length = 79
 extend-ignore = ["E203", "W503"]
+
+[tool.towncrier]
+package = "microdf_python"
+directory = "changelog.d"
+filename = "CHANGELOG.md"
+title_format = "## [{version}] - {project_date}"
+issue_format = ""
+underlines = ["", "", ""]
+
+[[tool.towncrier.type]]
+directory = "breaking"
+name = "Breaking changes"
+showcontent = true
+
+[[tool.towncrier.type]]
+directory = "added"
+name = "Added"
+showcontent = true
+
+[[tool.towncrier.type]]
+directory = "changed"
+name = "Changed"
+showcontent = true
+
+[[tool.towncrier.type]]
+directory = "fixed"
+name = "Fixed"
+showcontent = true
+
+[[tool.towncrier.type]]
+directory = "removed"
+name = "Removed"
+showcontent = true