Handle an empty subset selector (__getitem__)

changelog_entry.yaml

@@ -0,0 +1,4 @@
+- bump: patch 
+  changes:
+    fixed:
+    - Allowed a MicroDataFrame to handle an empty index subset 

docs/gini.ipynb

@@ -27,7 +27,7 @@
     "# Create sample data\n",
     "x = [10, 20, 30, 40, 100]\n",
     "w = [1, 2, 3, 4, 5]\n",
-    "df = pd.DataFrame({'x': x, 'w': w})"
+    "df = pd.DataFrame({\"x\": x, \"w\": w})"
    ]
   },
   {
@@ -80,7 +80,7 @@
    "outputs": [],
    "source": [
     "# Create a MicroDataFrame\n",
-    "mdf_df = mdf.MicroDataFrame(df, weights='w')\n",
+    "mdf_df = mdf.MicroDataFrame(df, weights=\"w\")\n",
     "\n",
     "# Access column as MicroSeries and calculate gini\n",
     "print(f\"Gini from MicroDataFrame column: {mdf_df.x.gini():.4f}\")"

microdf/microdataframe.py

@@ -218,13 +218,15 @@ def set_weight_col(
     def __getitem__(
         self, key: Union[str, List]
     ) -> Union[pd.Series, pd.DataFrame]:
+        # Let pandas handle the initial slicing
         result = super().__getitem__(key)
+
+        # If the result is a DataFrame, re-synchronize the weights
         if isinstance(result, pd.DataFrame):
-            try:
-                weights = self.weights[key]
-            except Exception:
-                weights = self.weights
-            return MicroDataFrame(result, weights=weights)
+            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
         return result
 
     def catch_series_relapse(self) -> None:

microdf/tests/test_microseries_dataframe.py

@@ -24,6 +24,15 @@ def test_df_init() -> None:
     assert df.a.mean() == np.average(arr, weights=w)
 
 
+def test_handles_empty_index() -> None:
+    arr = np.array([0, 1, 1])
+    w = np.array([3, 0, 9])
+    df = mdf.MicroDataFrame({"a": arr}, weights=w)
+
+    empty_index = pd.Index([])
+    df[empty_index]  # Implicit assert; checking for ValueError
+
+
 def test_series_getitem() -> None:
     arr = np.array([0, 1, 1])
     w = np.array([3, 0, 9])