SNOW-1620315, SNOW-1748326: Add support for DataFrame/Series.to_string (#3340)

Author: sfc-gh-helmeleegy

CHANGELOG.md

@@ -30,6 +30,7 @@
 
 - Added support for dict values in `Series.str.get`, `Series.str.slice`, and `Series.str.__getitem__` (`Series.str[...]`).
 - Added support for `DataFrame.to_html`.
+- Added support for `DataFrame.to_string` and `Series.to_string`.
 
 #### Improvements
 

docs/source/modin/dataframe.rst

@@ -234,4 +234,6 @@ DataFrame
     :toctree: pandas_api/
 
     DataFrame.to_csv
-    DataFrame.to_html
+    DataFrame.to_html
+    DataFrame.to_string
+    

docs/source/modin/series.rst

@@ -327,3 +327,4 @@ Series
     :toctree: pandas_api/
 
     Series.to_csv
+    Series.to_string

docs/source/modin/supported/dataframe_supported.rst

@@ -472,7 +472,7 @@ Methods
 +-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+
 | ``to_stata``                | N                               |                                  |                                                    |
 +-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+
-| ``to_string``               | N                               |                                  |                                                    |
+| ``to_string``               | Y                               |                                  |                                                    |
 +-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+
 | ``to_timestamp``            | N                               |                                  |                                                    |
 +-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+

docs/source/modin/supported/series_supported.rst

@@ -451,7 +451,7 @@ Methods
 +-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+
 | ``to_sql``                  | N                               |                                  |                                                    |
 +-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+
-| ``to_string``               | N                               |                                  |                                                    |
+| ``to_string``               | Y                               |                                  |                                                    |
 +-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+
 | ``to_timestamp``            | N                               |                                  |                                                    |
 +-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+

src/snowflake/snowpark/modin/plugin/docstrings/dataframe.py

@@ -4339,6 +4339,101 @@ def to_records():
         Convert ``DataFrame`` to a NumPy record array.
         """
 
+    def to_string():
+        """
+        Render a DataFrame to a console-friendly tabular output.
+
+        Parameters
+        ----------
+        buf : str, Path or StringIO-like, optional, default None
+            Buffer to write to. If None, the output is returned as a string.
+
+        columns : array-like, optional, default None
+            The subset of columns to write. Writes all columns by default.
+
+        col_space : int, list or dict of int, optional
+            The minimum width of each column. If a list of ints is given every integers corresponds with one column. If a dict is given, the key references the column, while the value defines the space to use..
+
+        header : bool or list of str, optional
+            Write out the column names. If a list of columns is given, it is assumed to be aliases for the column names.
+
+        index : bool, optional, default True
+            Whether to print index (row) labels.
+
+        na_rep : str, optional, default ‘NaN’
+            String representation of NaN to use.
+
+        formatters : list, tuple or dict of one-param. functions, optional
+            Formatter functions to apply to columns’ elements by position or name. The result of each function must be a unicode string. List/tuple must be of length equal to the number of columns.
+
+        float_format : one-parameter function, optional, default None
+            Formatter function to apply to columns’ elements if they are floats. This function must return a unicode string and will be applied only to the non-NaN elements, with NaN being handled by na_rep.
+
+        sparsify : bool, optional, default True
+            Set to False for a DataFrame with a hierarchical index to print every multiindex key at each row.
+
+        index_names : bool, optional, default True
+            Prints the names of the indexes.
+
+        justify : str, default None
+            How to justify the column labels. If None uses the option from the print configuration (controlled by set_option), ‘right’ out of the box. Valid values are
+            - left
+            - right
+            - center
+            - justify
+            - justify-all
+            - start
+            - end
+            - inherit
+            - match-parent
+            - initial
+            - unset.
+
+        max_rows : int, optional
+            Maximum number of rows to display in the console.
+
+        max_cols : int, optional
+            Maximum number of columns to display in the console.
+
+        show_dimensions : bool, default False
+            Display DataFrame dimensions (number of rows by number of columns).
+
+        decimal : str, default ‘.’
+            Character recognized as decimal separator, e.g. ‘,’ in Europe.
+
+        line_width : int, optional
+            Width to wrap a line in characters.
+
+        min_rows : int, optional
+            The number of rows to display in the console in a truncated repr (when number of rows is above max_rows).
+
+        max_colwidth : int, optional
+            Max width to truncate each column in characters. By default, no limit.
+
+        encoding : str, default “utf-8”
+            Set character encoding.
+
+        Returns
+        -------
+        str or None
+            If buf is None, returns the result as a string. Otherwise returns None.
+
+        See also
+        --------
+        to_html
+            Convert DataFrame to HTML.
+
+        Examples
+        --------
+        >>> d = {'col1': [1, 2, 3], 'col2': [4, 5, 6]}
+        >>> df = pd.DataFrame(d)
+        >>> print(df.to_string())
+           col1  col2
+        0     1     4
+        1     2     5
+        2     3     6
+        """
+
     def to_stata():
         pass
 

src/snowflake/snowpark/modin/plugin/docstrings/series.py

@@ -3603,6 +3603,49 @@ def to_period():
     def to_string():
         """
         Render a string representation of the Series.
+
+        Parameters
+        ----------
+        buf : StringIO-like, optional
+            Buffer to write to.
+
+        na_rep : str, optional
+            String representation of NaN to use, default ‘NaN’.
+
+        float_format : one-parameter function, optional
+            Formatter function to apply to columns’ elements if they are floats, default None.
+
+        header : bool, default True
+            Add the Series header (index name).
+
+        index : bool, optional
+            Add index (row) labels, default True.
+
+        length : bool, default False
+            Add the Series length.
+
+        dtype : bool, default False
+            Add the Series dtype.
+
+        name : bool, default False
+            Add the Series name if not None.
+
+        max_rows : int, optional
+            Maximum number of rows to show before truncating. If None, show all.
+
+        min_rows : int, optional
+            The number of rows to display in a truncated repr (when number of rows is above max_rows).
+
+        Returns
+        -------
+        str or None
+            String representation of Series if buf=None, otherwise None.
+
+        Examples
+        --------
+        >>> ser = pd.Series([1, 2, 3]).to_string()
+        >>> ser
+        '0    1\\n1    2\\n2    3'
         """
 
     def to_timestamp():

src/snowflake/snowpark/modin/plugin/extensions/base_overrides.py

@@ -411,32 +411,6 @@ def to_pickle(
     pass  # pragma: no cover
 
 
-@register_base_not_implemented()
-def to_string(
-    self,
-    buf=None,
-    columns=None,
-    col_space=None,
-    header=True,
-    index=True,
-    na_rep="NaN",
-    formatters=None,
-    float_format=None,
-    sparsify=None,
-    index_names=True,
-    justify=None,
-    max_rows=None,
-    min_rows=None,
-    max_cols=None,
-    show_dimensions=False,
-    decimal=".",
-    line_width=None,
-    max_colwidth=None,
-    encoding=None,
-):  # noqa: PR01, RT01, D200
-    pass  # pragma: no cover
-
-
 @register_base_not_implemented()
 def to_sql(
     self,

src/snowflake/snowpark/modin/plugin/extensions/dataframe_overrides.py

@@ -342,6 +342,54 @@ def to_records(
     pass  # pragma: no cover
 
 
+def to_string(
+    self,
+    buf=None,
+    columns=None,
+    col_space=None,
+    header=True,
+    index=True,
+    na_rep="NaN",
+    formatters=None,
+    float_format=None,
+    sparsify=None,
+    index_names=True,
+    justify=None,
+    max_rows=None,
+    min_rows=None,
+    max_cols=None,
+    show_dimensions=False,
+    decimal=".",
+    line_width=None,
+    max_colwidth=None,
+    encoding=None,
+):  # noqa: PR01, RT01, D200
+    WarningMessage.single_warning(
+        "DataFrame.to_string materializes data to the local machine."
+    )
+    return self._to_pandas().to_string(
+        buf=buf,
+        columns=columns,
+        col_space=col_space,
+        header=header,
+        index=index,
+        na_rep=na_rep,
+        formatters=formatters,
+        float_format=float_format,
+        sparsify=sparsify,
+        index_names=index_names,
+        justify=justify,
+        max_rows=max_rows,
+        min_rows=min_rows,
+        max_cols=max_cols,
+        show_dimensions=show_dimensions,
+        decimal=decimal,
+        line_width=line_width,
+        max_colwidth=max_colwidth,
+        encoding=encoding,
+    )
+
+
 @register_dataframe_not_implemented()
 def to_stata(
     self,

src/snowflake/snowpark/modin/plugin/extensions/series_overrides.py

@@ -335,7 +335,6 @@ def to_period(self, freq=None, copy=True):  # noqa: PR01, RT01, D200
     pass  # pragma: no cover
 
 
-@register_series_not_implemented()
 def to_string(
     self,
     buf=None,
@@ -349,7 +348,21 @@ def to_string(
     max_rows=None,
     min_rows=None,
 ):  # noqa: PR01, RT01, D200
-    pass  # pragma: no cover
+    WarningMessage.single_warning(
+        "Series.to_string materializes data to the local machine."
+    )
+    return self._to_pandas().to_string(
+        buf=buf,
+        na_rep=na_rep,
+        float_format=float_format,
+        header=header,
+        index=index,
+        length=length,
+        dtype=dtype,
+        name=name,
+        max_rows=max_rows,
+        min_rows=min_rows,
+    )
 
 
 @register_series_not_implemented()