Custom HTML Rendering for Nested Columns

README.md

@@ -27,7 +27,7 @@ Nested-Pandas allows data like this:
 To instead be represented like this:
 
 <p align="center">
-    <img src="./docs/intro_images/nestedframe.png" alt="nestedframe" width="400"/>
+    <img src="./docs/intro_images/nestedframe_example.png" alt="nestedframe" width="300"/>
 </p>
 
 Where the nested data is represented as nested dataframes:

docs/gettingstarted/quickstart.ipynb

@@ -99,7 +99,7 @@
    "source": [
     "The above dataframe is a `NestedFrame`, which extends the capabilities of the Pandas `DataFrame` to support columns with nested information. \n",
     "\n",
-    "We now have the top level dataframe with 3 rows, each of which corresponds to a single object. The table has three columns beyond \"id\". Two columns, \"ra\" and \"dec\", have a single value for the object (in this case the position on the sky). The last column \"lightcurve\" contains a nested table with a series of observation times and observation brightnesses for the object. As we will see below, this nested table allows the user to easily access to the all of the observations for a given object.\n",
+    "We now have the top level dataframe with 3 rows, each of which corresponds to a single object. The table has three columns beyond \"id\". Two columns, \"ra\" and \"dec\", have a single value for the object (in this case the position on the sky). The last column \"lightcurve\" contains a nested table with a series of observation times and observation brightnesses for the object. The first row of this nested table is provided along with dimensions to provide a sense for the contents of the nested data. As we will see below, this nested table allows the user to easily access to the all of the observations for a given object.\n",
     "\n",
     "## Accessing Nested Data\n",
     "\n",

docs/index.rst

@@ -23,8 +23,8 @@ Nested-Pandas allows data like this:
 
 To instead be represented like this:
 
-.. image:: ./intro_images/nestedframe.png
-  :width: 400
+.. image:: ./intro_images/nestedframe_example.png
+  :width: 300
   :align: center
   :alt: pandas dataframes
 
@@ -36,7 +36,7 @@ Where the nested data is represented as nested dataframes:
    object_nf.loc[0]["nested_sources"]
 
 .. image:: ./intro_images/loc_into_nested.png
-  :width: 225
+  :width: 300
   :align: center
   :alt: pandas dataframes
 

docs/tutorials/nested_spectra.ipynb

@@ -53,6 +53,7 @@
    "outputs": [],
    "source": [
     "# Query SDSS for the corresponding spectra\n",
+    "SDSS.clear_cache()\n",
     "sp = SDSS.get_spectra(matches=xid)\n",
     "sp"
    ]
@@ -161,7 +162,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "lsdb",
    "language": "python",
    "name": "python3"
   },
@@ -175,7 +176,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.6"
+   "version": "3.12.8"
   }
  },
  "nbformat": 4,

src/nested_pandas/nestedframe/core.py

@@ -19,6 +19,9 @@
 from nested_pandas.series.dtype import NestedDtype
 from nested_pandas.series.packer import pack, pack_lists, pack_sorted_df_into_struct
 
+pd.set_option("display.max_rows", 30)
+pd.set_option("display.min_rows", 5)
+
 # Used to identify backtick-protected names in the expressions
 # used in NestedFrame.eval() and NestedFrame.query().
 _backtick_protected_names = re.compile(r"`[^`]+`", re.MULTILINE)
@@ -274,6 +277,52 @@
                 nest_cols.append(column)
         return nest_cols
 
+    def _repr_html_(self) -> str | None:
+        """Override html representation"""
+
+        # Without nested columns, just do representation as normal
+        if len(self.nested_columns) == 0:
+            # This mimics pandas behavior
+            if self.shape[0] > pd.get_option("display.max_rows"):
+                return super().to_html(max_rows=pd.get_option("display.min_rows"), show_dimensions=True)
+            else:
+                return super().to_html(max_rows=pd.get_option("display.max_rows"), show_dimensions=True)
+
+        # Nested Column Formatting
+        # first cell shows the nested df header and a preview row
+        def repack_first_cell(chunk):
+            # Render header separately to keep data aligned
+            output = chunk.head(0).to_html(
+                max_rows=0, max_cols=5, show_dimensions=False, index=False, header=True
+            )
+            # Then add a preview row
+            output += repack_row(chunk)
+            return output
+
+        # remaining cells show only a preview row
+        def repack_row(chunk):
+            return chunk.to_html(max_rows=1, max_cols=5, show_dimensions=True, index=False, header=False)
+
+        # Apply repacking to all nested columns
+        repr = self.style.format(
+            {col: repack_first_cell for col in self.nested_columns}, subset=self.index[0]
+        )
+        repr = repr.format(
+            {col: repack_row for col in self.nested_columns}, subset=pd.IndexSlice[self.index[1] :]
+        )
+
+        # Recover some truncation formatting, limited to head truncation
+        if repr.data.shape[0] > pd.get_option("display.max_rows"):
+            html_repr = repr.to_html(max_rows=pd.get_option("display.min_rows"))
+        else:
+            # when under the max_rows threshold, display all rows (behavior of 0 here)
+            html_repr = repr.to_html(max_rows=0)
+
+        # Manually append dimensionality to a styler output
+        html_repr += f"{repr.data.shape[0]} rows x {repr.data.shape[1]} columns"
+
+        return html_repr
+
     def _parse_hierarchical_components(self, delimited_path: str, delimiter: str = ".") -> list[str]:
         """
         Given a string that may be a delimited path, parse it into its components,

tests/nested_pandas/nestedframe/test_nestedframe.py

@@ -34,6 +34,32 @@ def test_nestedseries_construction():
     assert (frame[0] == [1, 2, 3]).all()
 
 
+def test_html_repr():
+    """Just make sure the html representation code doesn't throw any errors"""
+
+    base = NestedFrame(data={"a": [1, 2, 3], "b": [2, 4, 6]}, index=[0, 1, 2])
+
+    assert list(base.all_columns.keys()) == ["base"]
+    assert list(base.all_columns["base"]) == list(base.columns)
+
+    nested = pd.DataFrame(
+        data={"c": [0, 2, 4, 1, 4, 3, 1, 4, 1], "d": [5, 4, 7, 5, 3, 1, 9, 3, 4]},
+        index=[0, 0, 0, 1, 1, 1, 2, 2, 2],
+    )
+
+    base = base.add_nested(nested, "nested")
+
+    # Check nested repr
+    base._repr_html_()
+
+    # Check repr path without nested cols
+    base[["a", "b"]]._repr_html_()
+
+    # Check repr truncation for larger nf
+    nf = generate_data(100, 2)
+    nf._repr_html_()
+
+
 def test_all_columns():
     """Test the all_columns function"""