ENH: Enable short_caption in to_latex

doc/source/whatsnew/v1.2.0.rst

@@ -96,6 +96,32 @@ For example:
    buffer = io.BytesIO()
    data.to_csv(buffer, mode="w+b", encoding="utf-8", compression="gzip")
 
+Support for short caption and table position in ``to_latex``
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+:meth:`DataFrame.to_latex` now allows one to specify
+a floating table position (:issue:`35281`)
+and a short caption (:issue:`36267`).
+
+New keyword ``position`` is implemented to set the position.
+
+.. ipython:: python
+
+   data = pd.DataFrame({'a': [1, 2], 'b': [3, 4]})
+   table = data.to_latex(position='ht')
+   print(table)
+
+Usage of keyword ``caption`` is extended.
+Besides taking a single string as an argument,
+one can optionally provide a tuple of ``(full_caption, short_caption)``
+to add a short caption macro.
+
+.. ipython:: python
+
+   data = pd.DataFrame({'a': [1, 2], 'b': [3, 4]})
+   table = data.to_latex(caption=('the full long caption', 'short caption'))
+   print(table)
+
 :.. _whatsnew_read_csv_table_precision_default:
 
 Change in default floating precision for ``read_csv`` and ``read_table``

pandas/core/generic.py

@@ -3002,6 +3002,9 @@ def to_latex(
         .. versionchanged:: 1.0.0
            Added caption and label arguments.
 
+        .. versionchanged:: 1.2.0
+           Added position argument, changed meaning of caption argument.
+
         Parameters
         ----------
         buf : str, Path or StringIO-like, optional, default None
@@ -3063,11 +3066,16 @@ def to_latex(
             centered labels (instead of top-aligned) across the contained
             rows, separating groups via clines. The default will be read
             from the pandas config module.
-        caption : str, optional
-            The LaTeX caption to be placed inside ``\caption{{}}`` in the output.
+        caption : str or tuple, optional
+            Tuple (full_caption, short_caption),
+            which results in ``\caption[short_caption]{{full_caption}}``;
+            if a single string is passed, no short caption will be set.
 
             .. versionadded:: 1.0.0
 
+            .. versionchanged:: 1.2.0
+               Optionally allow caption to be a tuple ``(full_caption, short_caption)``.
+
         label : str, optional
             The LaTeX label to be placed inside ``\label{{}}`` in the output.
             This is used with ``\ref{{}}`` in the main ``.tex`` file.
@@ -3076,6 +3084,8 @@ def to_latex(
         position : str, optional
             The LaTeX positional argument for tables, to be placed after
             ``\begin{{}}`` in the output.
+
+            .. versionadded:: 1.2.0
         {returns}
         See Also
         --------
@@ -3086,8 +3096,8 @@ def to_latex(
         Examples
         --------
         >>> df = pd.DataFrame(dict(name=['Raphael', 'Donatello'],
-        ...                    mask=['red', 'purple'],
-        ...                    weapon=['sai', 'bo staff']))
+        ...                   mask=['red', 'purple'],
+        ...                   weapon=['sai', 'bo staff']))
         >>> print(df.to_latex(index=False))  # doctest: +NORMALIZE_WHITESPACE
         \begin{{tabular}}{{lll}}
          \toprule

pandas/io/formats/format.py

@@ -1027,7 +1027,7 @@ def to_latex(
         multicolumn: bool = False,
         multicolumn_format: Optional[str] = None,
         multirow: bool = False,
-        caption: Optional[str] = None,
+        caption: Optional[Union[str, Tuple[str, str]]] = None,
         label: Optional[str] = None,
         position: Optional[str] = None,
     ) -> Optional[str]:

pandas/io/formats/latex.py

@@ -2,7 +2,7 @@
 Module for formatting output data in Latex.
 """
 from abc import ABC, abstractmethod
-from typing import IO, Iterator, List, Optional, Type
+from typing import IO, Iterator, List, Optional, Tuple, Type, Union
 
 import numpy as np
 
@@ -275,6 +275,8 @@ class TableBuilderAbstract(ABC):
         Use multirow to enhance MultiIndex rows.
     caption: str, optional
         Table caption.
+    short_caption: str, optional
+        Table short caption.
     label: str, optional
         LaTeX label.
     position: str, optional
@@ -289,6 +291,7 @@ def __init__(
         multicolumn_format: Optional[str] = None,
         multirow: bool = False,
         caption: Optional[str] = None,
+        short_caption: Optional[str] = None,
         label: Optional[str] = None,
         position: Optional[str] = None,
     ):
@@ -298,6 +301,7 @@ def __init__(
         self.multicolumn_format = multicolumn_format
         self.multirow = multirow
         self.caption = caption
+        self.short_caption = short_caption
         self.label = label
         self.position = position
 
@@ -384,8 +388,23 @@ def _position_macro(self) -> str:
 
     @property
     def _caption_macro(self) -> str:
-        r"""Caption macro, extracted from self.caption, like \caption{cap}."""
-        return f"\\caption{{{self.caption}}}" if self.caption else ""
+        r"""Caption macro, extracted from self.caption.
+
+        With short caption:
+            \caption[short_caption]{caption_string}.
+
+        Without short caption:
+            \caption{caption_string}.
+        """
+        if self.caption:
+            return f"\\caption{self._short_caption_macro}{{{self.caption}}}"
+        return ""
+
+    @property
+    def _short_caption_macro(self) -> str:
+        if self.short_caption:
+            return f"[{self.short_caption}]"
+        return ""
 
     @property
     def _label_macro(self) -> str:
@@ -596,15 +615,32 @@ def env_end(self) -> str:
 
 
 class LatexFormatter(TableFormatter):
-    """
+    r"""
     Used to render a DataFrame to a LaTeX tabular/longtable environment output.
 
     Parameters
     ----------
     formatter : `DataFrameFormatter`
+    longtable : bool, default False
+        Use longtable environment.
     column_format : str, default None
         The columns format as specified in `LaTeX table format
         <https://en.wikibooks.org/wiki/LaTeX/Tables>`__ e.g 'rcl' for 3 columns
+    multicolumn : bool, default False
+        Use \multicolumn to enhance MultiIndex columns.
+    multicolumn_format : str, default 'l'
+        The alignment for multicolumns, similar to `column_format`
+    multirow : bool, default False
+        Use \multirow to enhance MultiIndex rows.
+    caption : str or tuple, optional
+        Tuple (full_caption, short_caption),
+        which results in \caption[short_caption]{full_caption};
+        if a single string is passed, no short caption will be set.
+    label : str, optional
+        The LaTeX label to be placed inside ``\label{}`` in the output.
+    position : str, optional
+        The LaTeX positional argument for tables, to be placed after
+        ``\begin{}`` in the output.
 
     See Also
     --------
@@ -619,18 +655,18 @@ def __init__(
         multicolumn: bool = False,
         multicolumn_format: Optional[str] = None,
         multirow: bool = False,
-        caption: Optional[str] = None,
+        caption: Optional[Union[str, Tuple[str, str]]] = None,
         label: Optional[str] = None,
         position: Optional[str] = None,
     ):
         self.fmt = formatter
         self.frame = self.fmt.frame
         self.longtable = longtable
-        self.column_format = column_format  # type: ignore[assignment]
+        self.column_format = column_format
         self.multicolumn = multicolumn
         self.multicolumn_format = multicolumn_format
         self.multirow = multirow
-        self.caption = caption
+        self.caption, self.short_caption = self._split_into_long_short_caption(caption)
         self.label = label
         self.position = position
 
@@ -658,6 +694,7 @@ def builder(self) -> TableBuilderAbstract:
             multicolumn_format=self.multicolumn_format,
             multirow=self.multirow,
             caption=self.caption,
+            short_caption=self.short_caption,
             label=self.label,
             position=self.position,
         )
@@ -670,8 +707,26 @@ def _select_builder(self) -> Type[TableBuilderAbstract]:
             return RegularTableBuilder
         return TabularBuilder
 
+    def _split_into_long_short_caption(
+        self, caption: Optional[Union[str, Tuple[str, str]]]
+    ) -> Tuple[str, str]:
+        if caption:
+            if isinstance(caption, str):
+                long_caption = caption
+                short_caption = ""
+            else:
+                try:
+                    long_caption, short_caption = caption
+                except ValueError as err:
+                    msg = "caption must be either a string or a tuple of two strings"
+                    raise ValueError(msg) from err
+        else:
+            long_caption = ""
+            short_caption = ""
+        return long_caption, short_caption
+
     @property
-    def column_format(self) -> str:
+    def column_format(self) -> Optional[str]:
         """Column format."""
         return self._column_format