microdf-python 1.3.5__tar.gz → 1.3.7__tar.gz

{microdf_python-1.3.5 → microdf_python-1.3.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: microdf-python
-Version: 1.3.5
+Version: 1.3.7
 Summary: Weighted pandas DataFrames and Series for survey microdata
 Author-email: Max Ghenis <max@policyengine.org>
 License: MIT
@@ -20,7 +20,7 @@ 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)
-[![Codecov](https://codecov.io/gh/PolicyEngine/microdf/branch/master/graph/badge.svg)](https://codecov.io/gh/PolicyEngine/microdf)
+[![Codecov](https://codecov.io/gh/PolicyEngine/microdf/branch/main/graph/badge.svg)](https://codecov.io/gh/PolicyEngine/microdf)
 
 # microdf
 Weighted pandas DataFrames and Series for survey microdata analysis.

{microdf_python-1.3.5 → microdf_python-1.3.7}/README.md

@@ -1,5 +1,5 @@
 [![Build](https://github.com/PolicyEngine/microdf/workflows/Pull%20request/badge.svg)](https://github.com/PolicyEngine/microdf/actions)
-[![Codecov](https://codecov.io/gh/PolicyEngine/microdf/branch/master/graph/badge.svg)](https://codecov.io/gh/PolicyEngine/microdf)
+[![Codecov](https://codecov.io/gh/PolicyEngine/microdf/branch/main/graph/badge.svg)](https://codecov.io/gh/PolicyEngine/microdf)
 
 # microdf
 Weighted pandas DataFrames and Series for survey microdata analysis.

microdf_python-1.3.7/microdf/__init__.py

@@ -0,0 +1,22 @@
+from importlib.metadata import PackageNotFoundError, version
+
+from .microdataframe import MicroDataFrame, MicroDataFrameGroupBy
+from .microseries import MicroSeries, MicroSeriesGroupBy
+
+name = "microdf"
+
+# Read the version from package metadata so it can't drift from
+# pyproject.toml (the automated bump only touches pyproject).
+try:
+    __version__ = version("microdf-python")
+except PackageNotFoundError:  # pragma: no cover - running from a source tree
+    __version__ = "unknown"
+
+__all__ = [
+    # microseries.py
+    "MicroSeries",
+    "MicroSeriesGroupBy",
+    # microdataframe.py
+    "MicroDataFrame",
+    "MicroDataFrameGroupBy",
+]

{microdf_python-1.3.5 → microdf_python-1.3.7}/microdf/microdataframe.py

@@ -150,9 +150,13 @@ class MicroDataFrame(pd.DataFrame):
                 if pd.api.types.is_numeric_dtype(self[col]):
                     try:
                         results[col] = getattr(self[col], name)(*args, **kwargs)
-                    except Exception:
-                        # Skip columns that can't be aggregated
-                        pass
+                    except TypeError as exc:
+                        # Skip columns whose dtype can't take this aggregation.
+                        # Deliberately narrow: catching every Exception here also
+                        # swallowed real errors (e.g. the ValueError from
+                        # gini(negatives=...)) and returned a silently truncated
+                        # result instead of raising.
+                        logger.debug("skipping column %s in %s: %s", col, name, exc)
             return pd.Series(results)
 
         return fn
@@ -173,9 +177,13 @@ class MicroDataFrame(pd.DataFrame):
                         result = getattr(self[col], name)(*args, **kwargs)
                         results.append(result)
                         columns.append(col)
-                    except Exception:
-                        # Skip columns that can't be aggregated
-                        pass
+                    except TypeError as exc:
+                        # Skip columns whose dtype can't take this aggregation.
+                        # Deliberately narrow: catching every Exception here also
+                        # swallowed real errors (e.g. the ValueError from
+                        # gini(negatives=...)) and returned a silently truncated
+                        # result instead of raising.
+                        logger.debug("skipping column %s in %s: %s", col, name, exc)
 
             if results:
                 df = pd.DataFrame(results)
@@ -208,9 +216,13 @@ class MicroDataFrame(pd.DataFrame):
                             result = getattr(self[col], name)(*args, **kwargs)
                             results.append(result)
                             columns.append(col)
-                        except Exception:
-                            # Skip columns that can't be aggregated
-                            pass
+                        except TypeError as exc:
+                            # Skip columns whose dtype can't take this aggregation.
+                            # Deliberately narrow: catching every Exception here also
+                            # swallowed real errors (e.g. the ValueError from
+                            # gini(negatives=...)) and returned a silently truncated
+                            # result instead of raising.
+                            logger.debug("skipping column %s in %s: %s", col, name, exc)
 
                 if results:
                     df = pd.DataFrame(results)
@@ -225,9 +237,13 @@ class MicroDataFrame(pd.DataFrame):
                     if pd.api.types.is_numeric_dtype(self[col]):
                         try:
                             results[col] = getattr(self[col], name)(*args, **kwargs)
-                        except Exception:
-                            # Skip columns that can't be aggregated
-                            pass
+                        except TypeError as exc:
+                            # Skip columns whose dtype can't take this aggregation.
+                            # Deliberately narrow: catching every Exception here also
+                            # swallowed real errors (e.g. the ValueError from
+                            # gini(negatives=...)) and returned a silently truncated
+                            # result instead of raising.
+                            logger.debug("skipping column %s in %s: %s", col, name, exc)
                 return pd.Series(results)
 
         return fn
@@ -839,9 +855,13 @@ class MicroDataFrameGroupBy(pd.core.groupby.generic.DataFrameGroupBy):
                             results[col] = getattr(getattr(self, col), name)(
                                 *args, **kwargs
                             )
-                        except Exception:
-                            # Skip columns that can't be aggregated
-                            pass
+                        except TypeError as exc:
+                            # Skip columns whose dtype can't take this aggregation.
+                            # Deliberately narrow: catching every Exception here also
+                            # swallowed real errors (e.g. the ValueError from
+                            # gini(negatives=...)) and returned a silently truncated
+                            # result instead of raising.
+                            logger.debug("skipping column %s in %s: %s", col, name, exc)
                     # Return plain DataFrame - aggregated results don't have
                     # per-row weights (weights were already applied)
                     return pd.DataFrame(results) if results else pd.DataFrame()
@@ -859,9 +879,13 @@ class MicroDataFrameGroupBy(pd.core.groupby.generic.DataFrameGroupBy):
                             results[col] = getattr(getattr(self, col), name)(
                                 *args, **kwargs
                             )
-                        except Exception:
-                            # Skip columns that can't be aggregated
-                            pass
+                        except TypeError as exc:
+                            # Skip columns whose dtype can't take this aggregation.
+                            # Deliberately narrow: catching every Exception here also
+                            # swallowed real errors (e.g. the ValueError from
+                            # gini(negatives=...)) and returned a silently truncated
+                            # result instead of raising.
+                            logger.debug("skipping column %s in %s: %s", col, name, exc)
                     # Return plain DataFrame - aggregated results don't have
                     # per-row weights (weights were already applied)
                     return pd.DataFrame(results) if results else pd.DataFrame()
@@ -921,8 +945,15 @@ class MicroDataFrameGroupBy(pd.core.groupby.generic.DataFrameGroupBy):
                                 results[col] = getattr(getattr(res, col), name)(
                                     *args, **kwargs
                                 )
-                            except Exception:
-                                pass
+                            except TypeError as exc:
+                                # Skip columns whose dtype can't take this aggregation.
+                                # Deliberately narrow: catching every Exception here also
+                                # swallowed real errors (e.g. the ValueError from
+                                # gini(negatives=...)) and returned a silently truncated
+                                # result instead of raising.
+                                logger.debug(
+                                    "skipping column %s in %s: %s", col, name, exc
+                                )
                         # Return plain DataFrame - aggregated results don't
                         # have per-row weights (weights were already applied)
                         return pd.DataFrame(results) if results else pd.DataFrame()
@@ -940,8 +971,15 @@ class MicroDataFrameGroupBy(pd.core.groupby.generic.DataFrameGroupBy):
                                 results[col] = getattr(getattr(res, col), name)(
                                     *args, **kwargs
                                 )
-                            except Exception:
-                                pass
+                            except TypeError as exc:
+                                # Skip columns whose dtype can't take this aggregation.
+                                # Deliberately narrow: catching every Exception here also
+                                # swallowed real errors (e.g. the ValueError from
+                                # gini(negatives=...)) and returned a silently truncated
+                                # result instead of raising.
+                                logger.debug(
+                                    "skipping column %s in %s: %s", col, name, exc
+                                )
                         # Return plain DataFrame - aggregated results don't
                         # have per-row weights (weights were already applied)
                         return pd.DataFrame(results) if results else pd.DataFrame()

{microdf_python-1.3.5 → microdf_python-1.3.7}/microdf/microseries.py

@@ -403,8 +403,9 @@ class MicroSeries(pd.Series):
         w = np.asarray(self.weights.values, dtype=float)
         if negatives == "zero":
             x = np.where(x < 0, 0.0, x)
-        elif negatives == "shift" and len(x) > 0 and np.amin(x) < 0:
-            x = x - np.amin(x)
+        elif negatives == "shift":
+            if len(x) > 0 and np.amin(x) < 0:
+                x = x - np.amin(x)
         elif negatives is not None:
             raise ValueError(
                 f"Unknown negatives option {negatives!r}; expected "

microdf_python-1.3.7/microdf/tests/test_aggregation_errors.py

@@ -0,0 +1,57 @@
+import microdf as mdf
+import numpy as np
+import pandas as pd
+import pytest
+
+
+def test_aggregation_surfaces_real_errors():
+    """A genuine argument error must raise, not be swallowed per column."""
+    df = mdf.MicroDataFrame(pd.DataFrame({"x": [1, 2, 3]}), weights=[1, 1, 1])
+    with pytest.raises(ValueError, match="Unknown negatives option"):
+        df.gini(negatives="bogus")
+
+
+def test_aggregation_still_skips_non_numeric_columns():
+    """Narrowing the guard must not change which columns aggregate."""
+    df = mdf.MicroDataFrame(
+        pd.DataFrame(
+            {
+                "x": [1, 2, 3],
+                "s": ["a", "b", "c"],
+                "dt": pd.to_datetime(["2020-01-01"] * 3),
+            }
+        ),
+        weights=[1, 2, 3],
+    )
+    assert list(df.sum().index) == ["x"]
+    assert df.sum()["x"] == 14
+    assert list(df.mean().index) == ["x"]
+
+
+def test_gini_shift_accepts_nonnegative_and_negative_columns():
+    frame = mdf.MicroDataFrame(
+        {"positive": [1, 2, 3], "negative": [-1, 1, 3]}, weights=[1, 1, 1]
+    )
+    # Shift leaves [1, 2, 3] unchanged and changes [-1, 1, 3] to [0, 2, 4].
+    # The pairwise-difference Ginis are 2/9 and 4/9, respectively.
+    expected = pd.Series({"positive": 2 / 9, "negative": 4 / 9})
+    pd.testing.assert_series_equal(frame.gini(negatives="shift"), expected)
+
+
+@pytest.mark.parametrize("selected", [False, True])
+def test_grouped_gini_shift_accepts_positive_groups(selected):
+    frame = mdf.MicroDataFrame(
+        {"group": ["a", "a", "a", "b", "b", "b"], "value": [1, 2, 3, -1, 1, 3]},
+        weights=[1, 1, 1, 1, 1, 1],
+    )
+    grouped = frame.groupby("group")
+    if selected:
+        grouped = grouped[["value"]]
+    expected = pd.DataFrame(
+        {"value": [2 / 9, 4 / 9]}, index=pd.Index(["a", "b"], name="group")
+    )
+    pd.testing.assert_frame_equal(grouped.gini(negatives="shift"), expected)
+
+
+def test_gini_shift_accepts_empty_series():
+    assert np.isnan(mdf.MicroSeries([], weights=[]).gini(negatives="shift"))

microdf_python-1.3.7/microdf/tests/test_version_metadata.py

@@ -0,0 +1,8 @@
+import microdf as mdf
+
+
+def test_version_matches_package_metadata():
+    """__version__ must not drift from pyproject.toml."""
+    from importlib.metadata import version
+
+    assert mdf.__version__ == version("microdf-python")

{microdf_python-1.3.5 → microdf_python-1.3.7}/microdf_python.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: microdf-python
-Version: 1.3.5
+Version: 1.3.7
 Summary: Weighted pandas DataFrames and Series for survey microdata
 Author-email: Max Ghenis <max@policyengine.org>
 License: MIT
@@ -20,7 +20,7 @@ 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)
-[![Codecov](https://codecov.io/gh/PolicyEngine/microdf/branch/master/graph/badge.svg)](https://codecov.io/gh/PolicyEngine/microdf)
+[![Codecov](https://codecov.io/gh/PolicyEngine/microdf/branch/main/graph/badge.svg)](https://codecov.io/gh/PolicyEngine/microdf)
 
 # microdf
 Weighted pandas DataFrames and Series for survey microdata analysis.

{microdf_python-1.3.5 → microdf_python-1.3.7}/microdf_python.egg-info/SOURCES.txt

@@ -5,11 +5,13 @@ microdf/__init__.py
 microdf/microdataframe.py
 microdf/microseries.py
 microdf/tests/conftest.py
+microdf/tests/test_aggregation_errors.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/tests/test_quantile_missing_values.py
+microdf/tests/test_version_metadata.py
 microdf_python.egg-info/PKG-INFO
 microdf_python.egg-info/SOURCES.txt
 microdf_python.egg-info/dependency_links.txt

{microdf_python-1.3.5 → microdf_python-1.3.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "microdf-python"
-version = "1.3.5"
+version = "1.3.7"
 description = "Weighted pandas DataFrames and Series for survey microdata"
 readme = "README.md"
 authors = [

microdf_python-1.3.5/microdf/__init__.py

@@ -1,14 +0,0 @@
-from .microdataframe import MicroDataFrame, MicroDataFrameGroupBy
-from .microseries import MicroSeries, MicroSeriesGroupBy
-
-name = "microdf"
-__version__ = "0.1.0"
-
-__all__ = [
-    # microseries.py
-    "MicroSeries",
-    "MicroSeriesGroupBy",
-    # microdataframe.py
-    "MicroDataFrame",
-    "MicroDataFrameGroupBy",
-]