CLN: Remove tupleize_cols keyword in io methods; from_csv method (#27126)

* Remove tuplize_col keyword in read_html, read_csv, to_csv

* Remove from_csv

* Remove warning check and type

Author: mroeschke

doc/source/reference/frame.rst

@@ -336,7 +336,6 @@ Serialization / IO / conversion
 .. autosummary::
    :toctree: api/
 
-   DataFrame.from_csv
    DataFrame.from_dict
    DataFrame.from_items
    DataFrame.from_records

doc/source/user_guide/io.rst

@@ -340,13 +340,6 @@ dialect : str or :class:`python:csv.Dialect` instance, default ``None``
   `skipinitialspace`, `quotechar`, and `quoting`. If it is necessary to
   override values, a ParserWarning will be issued. See :class:`python:csv.Dialect`
   documentation for more details.
-tupleize_cols : boolean, default ``False``
-    .. deprecated:: 0.21.0
-
-    This argument will be removed and will always convert to MultiIndex
-
-  Leave a list of tuples on columns as is (default is to convert to a MultiIndex
-  on the columns).
 
 Error handling
 ++++++++++++++
@@ -1718,8 +1711,6 @@ function takes a number of arguments. Only the first is required.
 * ``escapechar``: Character used to escape ``sep`` and ``quotechar`` when
   appropriate (default None)
 * ``chunksize``: Number of rows to write at a time
-* ``tupleize_cols``: If False (default), write as a list of tuples, otherwise
-  write in an expanded line format suitable for ``read_csv``
 * ``date_format``: Format string for datetime objects
 
 Writing a formatted string

doc/source/whatsnew/v0.25.0.rst

@@ -630,6 +630,8 @@ Removal of prior version deprecations/changes
 - Removed the previously deprecated behavior of :class:`Series` treated as list-like in :meth:`~Series.cat.rename_categories` (:issue:`17982`)
 - Removed the previously deprecated ``DataFrame.reindex_axis`` and ``Series.reindex_axis``` (:issue:`17842`)
 - Removed the previously deprecated behavior of altering column or index labels with :meth:`Series.rename_axis` or :meth:`DataFrame.rename_axis` (:issue:`17842`)
+- Removed the previously deprecated ``tupleize_cols`` keyword argument in :meth:`read_html`, :meth:`read_csv`, and :meth:`DataFrame.to_csv` (:issue:`17877`, :issue:`17820`)
+- Removed the previously deprecated ``DataFrame.from.csv`` and ``Series.from_csv`` (:issue:`17812`)
 
 .. _whatsnew_0250.performance:
 

pandas/_libs/parsers.pyx

@@ -297,7 +297,6 @@ cdef class TextReader:
         object encoding
         object compression
         object mangle_dupe_cols
-        object tupleize_cols
         object usecols
         list dtype_cast_order
         set unnamed_cols
@@ -351,7 +350,6 @@ cdef class TextReader:
                   skipfooter=0,
                   verbose=False,
                   mangle_dupe_cols=True,
-                  tupleize_cols=False,
                   float_precision=None,
                   skip_blank_lines=True):
 
@@ -370,7 +368,6 @@ cdef class TextReader:
         self.parser.chunksize = tokenize_chunksize
 
         self.mangle_dupe_cols = mangle_dupe_cols
-        self.tupleize_cols = tupleize_cols
 
         # For timekeeping
         self.clocks = []

pandas/core/frame.py

@@ -331,7 +331,7 @@ def _constructor(self):
 
     _constructor_sliced = Series  # type: Type[Series]
     _deprecations = NDFrame._deprecations | frozenset([
-        'get_value', 'set_value', 'from_csv', 'from_items'
+        'get_value', 'set_value', 'from_items'
     ])  # type: FrozenSet[str]
     _accessors = set()  # type: Set[str]
 
@@ -1786,73 +1786,6 @@ def _from_arrays(cls, arrays, columns, index, dtype=None):
         mgr = arrays_to_mgr(arrays, columns, index, columns, dtype=dtype)
         return cls(mgr)
 
-    @classmethod
-    def from_csv(cls, path, header=0, sep=',', index_col=0, parse_dates=True,
-                 encoding=None, tupleize_cols=None,
-                 infer_datetime_format=False):
-        """
-        Read CSV file.
-
-        .. deprecated:: 0.21.0
-            Use :func:`read_csv` instead.
-
-        It is preferable to use the more powerful :func:`read_csv`
-        for most general purposes, but ``from_csv`` makes for an easy
-        roundtrip to and from a file (the exact counterpart of
-        ``to_csv``), especially with a DataFrame of time series data.
-
-        This method only differs from the preferred :func:`read_csv`
-        in some defaults:
-
-        - `index_col` is ``0`` instead of ``None`` (take first column as index
-          by default)
-        - `parse_dates` is ``True`` instead of ``False`` (try parsing the index
-          as datetime by default)
-
-        So a ``pd.DataFrame.from_csv(path)`` can be replaced by
-        ``pd.read_csv(path, index_col=0, parse_dates=True)``.
-
-        Parameters
-        ----------
-        path : string file path or file handle / StringIO
-        header : int, default 0
-            Row to use as header (skip prior rows)
-        sep : string, default ','
-            Field delimiter
-        index_col : int or sequence, default 0
-            Column to use for index. If a sequence is given, a MultiIndex
-            is used. Different default from read_table
-        parse_dates : boolean, default True
-            Parse dates. Different default from read_table
-        tupleize_cols : boolean, default False
-            write multi_index columns as a list of tuples (if True)
-            or new (expanded format) if False)
-        infer_datetime_format : boolean, default False
-            If True and `parse_dates` is True for a column, try to infer the
-            datetime format based on the first datetime string. If the format
-            can be inferred, there often will be a large parsing speed-up.
-
-        Returns
-        -------
-        DataFrame
-
-        See Also
-        --------
-        read_csv
-        """
-
-        warnings.warn("from_csv is deprecated. Please use read_csv(...) "
-                      "instead. Note that some of the default arguments are "
-                      "different, so please refer to the documentation "
-                      "for from_csv when changing your function calls",
-                      FutureWarning, stacklevel=2)
-
-        from pandas.io.parsers import read_csv
-        return read_csv(path, header=header, sep=sep,
-                        parse_dates=parse_dates, index_col=index_col,
-                        encoding=encoding, tupleize_cols=tupleize_cols,
-                        infer_datetime_format=infer_datetime_format)
-
     def to_sparse(self, fill_value=None, kind='block'):
         """
         Convert to SparseDataFrame.

pandas/core/generic.py

@@ -2903,7 +2903,7 @@ def to_csv(self, path_or_buf=None, sep=",", na_rep='', float_format=None,
                columns=None, header=True, index=True, index_label=None,
                mode='w', encoding=None, compression='infer', quoting=None,
                quotechar='"', line_terminator=None, chunksize=None,
-               tupleize_cols=None, date_format=None, doublequote=True,
+               date_format=None, doublequote=True,
                escapechar=None, decimal='.'):
         r"""
         Write object to a comma-separated values (csv) file.
@@ -2976,14 +2976,6 @@ def to_csv(self, path_or_buf=None, sep=",", na_rep='', float_format=None,
             .. versionchanged:: 0.24.0
         chunksize : int or None
             Rows to write at a time.
-        tupleize_cols : bool, default False
-            Write MultiIndex columns as a list of tuples (if True) or in
-            the new, expanded format, where each MultiIndex column is a row
-            in the CSV (if False).
-
-            .. deprecated:: 0.21.0
-               This argument will be removed and will always write each row
-               of the multi-index as a separate row in the CSV file.
         date_format : str, default None
             Format string for datetime objects.
         doublequote : bool, default True
@@ -3017,13 +3009,6 @@ def to_csv(self, path_or_buf=None, sep=",", na_rep='', float_format=None,
 
         df = self if isinstance(self, ABCDataFrame) else self.to_frame()
 
-        if tupleize_cols is not None:
-            warnings.warn("The 'tupleize_cols' parameter is deprecated and "
-                          "will be removed in a future version",
-                          FutureWarning, stacklevel=2)
-        else:
-            tupleize_cols = False
-
         from pandas.io.formats.csvs import CSVFormatter
         formatter = CSVFormatter(df, path_or_buf,
                                  line_terminator=line_terminator, sep=sep,
@@ -3033,7 +3018,6 @@ def to_csv(self, path_or_buf=None, sep=",", na_rep='', float_format=None,
                                  cols=columns, header=header, index=index,
                                  index_label=index_label, mode=mode,
                                  chunksize=chunksize, quotechar=quotechar,
-                                 tupleize_cols=tupleize_cols,
                                  date_format=date_format,
                                  doublequote=doublequote,
                                  escapechar=escapechar, decimal=decimal)

pandas/core/series.py

@@ -137,7 +137,7 @@ class Series(base.IndexOpsMixin, generic.NDFrame):
     # tolist is not actually deprecated, just suppressed in the __dir__
     _deprecations = generic.NDFrame._deprecations | frozenset(
         ['asobject', 'reshape', 'get_value', 'set_value',
-         'from_csv', 'valid', 'tolist'])
+         'valid', 'tolist'])
 
     # Override cache_readonly bc Series is mutable
     hasnans = property(base.IndexOpsMixin.hasnans.func,
@@ -4212,81 +4212,13 @@ def between(self, left, right, inclusive=True):
 
         return lmask & rmask
 
-    @classmethod
-    def from_csv(cls, path, sep=',', parse_dates=True, header=None,
-                 index_col=0, encoding=None, infer_datetime_format=False):
-        """
-        Read CSV file.
-
-        .. deprecated:: 0.21.0
-            Use :func:`pandas.read_csv` instead.
-
-        It is preferable to use the more powerful :func:`pandas.read_csv`
-        for most general purposes, but ``from_csv`` makes for an easy
-        roundtrip to and from a file (the exact counterpart of
-        ``to_csv``), especially with a time Series.
-
-        This method only differs from :func:`pandas.read_csv` in some defaults:
-
-        - `index_col` is ``0`` instead of ``None`` (take first column as index
-          by default)
-        - `header` is ``None`` instead of ``0`` (the first row is not used as
-          the column names)
-        - `parse_dates` is ``True`` instead of ``False`` (try parsing the index
-          as datetime by default)
-
-        With :func:`pandas.read_csv`, the option ``squeeze=True`` can be used
-        to return a Series like ``from_csv``.
-
-        Parameters
-        ----------
-        path : str, file path, or file handle / StringIO
-        sep : str, default ','
-            Field delimiter.
-        parse_dates : bool, default True
-            Parse dates. Different default from read_table.
-        header : int, default None
-            Row to use as header (skip prior rows).
-        index_col : int or sequence, default 0
-            Column to use for index. If a sequence is given, a MultiIndex
-            is used. Different default from read_table.
-        encoding : str, optional
-            A string representing the encoding to use if the contents are
-            non-ascii, for python versions prior to 3.
-        infer_datetime_format : bool, default False
-            If True and `parse_dates` is True for a column, try to infer the
-            datetime format based on the first datetime string. If the format
-            can be inferred, there often will be a large parsing speed-up.
-
-        Returns
-        -------
-        Series
-
-        See Also
-        --------
-        read_csv
-        """
-
-        # We're calling `DataFrame.from_csv` in the implementation,
-        # which will propagate a warning regarding `from_csv` deprecation.
-        from pandas.core.frame import DataFrame
-        df = DataFrame.from_csv(path, header=header, index_col=index_col,
-                                sep=sep, parse_dates=parse_dates,
-                                encoding=encoding,
-                                infer_datetime_format=infer_datetime_format)
-        result = df.iloc[:, 0]
-        if header is None:
-            result.index.name = result.name = None
-
-        return result
-
     @Appender(generic.NDFrame.to_csv.__doc__)
     def to_csv(self, *args, **kwargs):
 
         names = ["path_or_buf", "sep", "na_rep", "float_format", "columns",
                  "header", "index", "index_label", "mode", "encoding",
                  "compression", "quoting", "quotechar", "line_terminator",
-                 "chunksize", "tupleize_cols", "date_format", "doublequote",
+                 "chunksize", "date_format", "doublequote",
                  "escapechar", "decimal"]
 
         old_names = ["path_or_buf", "index", "sep", "na_rep", "float_format",

pandas/io/formats/csvs.py

@@ -24,9 +24,9 @@ class CSVFormatter:
 
     def __init__(self, obj, path_or_buf=None, sep=",", na_rep='',
                  float_format=None, cols=None, header=True, index=True,
-                 index_label=None, mode='w', nanRep=None, encoding=None,
+                 index_label=None, mode='w', encoding=None,
                  compression='infer', quoting=None, line_terminator='\n',
-                 chunksize=None, tupleize_cols=False, quotechar='"',
+                 chunksize=None, quotechar='"',
                  date_format=None, doublequote=True, escapechar=None,
                  decimal='.'):
 
@@ -68,9 +68,7 @@ def __init__(self, obj, path_or_buf=None, sep=",", na_rep='',
 
         self.date_format = date_format
 
-        self.tupleize_cols = tupleize_cols
-        self.has_mi_columns = (isinstance(obj.columns, ABCMultiIndex) and
-                               not self.tupleize_cols)
+        self.has_mi_columns = isinstance(obj.columns, ABCMultiIndex)
 
         # validate mi options
         if self.has_mi_columns:

pandas/io/html.py

@@ -912,7 +912,7 @@ def _parse(flavor, io, match, attrs, encoding, displayed_only, **kwargs):
 
 def read_html(io, match='.+', flavor=None, header=None, index_col=None,
               skiprows=None, attrs=None, parse_dates=False,
-              tupleize_cols=None, thousands=',', encoding=None,
+              thousands=',', encoding=None,
               decimal='.', converters=None, na_values=None,
               keep_default_na=True, displayed_only=True):
     r"""Read HTML tables into a ``list`` of ``DataFrame`` objects.
@@ -976,14 +976,6 @@ def read_html(io, match='.+', flavor=None, header=None, index_col=None,
     parse_dates : bool, optional
         See :func:`~read_csv` for more details.
 
-    tupleize_cols : bool, optional
-        If ``False`` try to parse multiple header rows into a
-        :class:`~pandas.MultiIndex`, otherwise return raw tuples. Defaults to
-        ``False``.
-
-        .. deprecated:: 0.21.0
-           This argument will be removed and will always convert to MultiIndex
-
     thousands : str, optional
         Separator to use to parse thousands. Defaults to ``','``.
 
@@ -1073,7 +1065,7 @@ def read_html(io, match='.+', flavor=None, header=None, index_col=None,
     _validate_header_arg(header)
     return _parse(flavor=flavor, io=io, match=match, header=header,
                   index_col=index_col, skiprows=skiprows,
-                  parse_dates=parse_dates, tupleize_cols=tupleize_cols,
+                  parse_dates=parse_dates,
                   thousands=thousands, attrs=attrs, encoding=encoding,
                   decimal=decimal, converters=converters, na_values=na_values,
                   keep_default_na=keep_default_na,