CLN: Enforce verbose parameter deprecation in read_csv/read_table (#57966)

Author: lithomas1

doc/source/whatsnew/v3.0.0.rst

@@ -256,6 +256,7 @@ Removal of prior version deprecations/changes
 - Removed unused arguments ``*args`` and ``**kwargs`` in :class:`Resampler` methods (:issue:`50977`)
 - Unrecognized timezones when parsing strings to datetimes now raises a ``ValueError`` (:issue:`51477`)
 - Removed the :class:`Grouper` attributes ``ax``, ``groups``, ``indexer``, and ``obj`` (:issue:`51206`, :issue:`51182`)
+- Removed deprecated keyword ``verbose`` on :func:`read_csv` and :func:`read_table` (:issue:`56556`)
 - Removed the attribute ``dtypes`` from :class:`.DataFrameGroupBy` (:issue:`51997`)
 
 .. ---------------------------------------------------------------------------

pandas/_libs/parsers.pyx

@@ -6,7 +6,6 @@ from csv import (
     QUOTE_NONE,
     QUOTE_NONNUMERIC,
 )
-import time
 import warnings
 
 from pandas.util._exceptions import find_stack_level
@@ -344,10 +343,9 @@ cdef class TextReader:
         object true_values, false_values
         object handle
         object orig_header
-        bint na_filter, keep_default_na, verbose, has_usecols, has_mi_columns
+        bint na_filter, keep_default_na, has_usecols, has_mi_columns
         bint allow_leading_cols
         uint64_t parser_start  # this is modified after __init__
-        list clocks
         const char *encoding_errors
         kh_str_starts_t *false_set
         kh_str_starts_t *true_set
@@ -400,7 +398,6 @@ cdef class TextReader:
                   bint allow_leading_cols=True,
                   skiprows=None,
                   skipfooter=0,         # int64_t
-                  bint verbose=False,
                   float_precision=None,
                   bint skip_blank_lines=True,
                   encoding_errors=b"strict",
@@ -417,9 +414,6 @@ cdef class TextReader:
         self.parser = parser_new()
         self.parser.chunksize = tokenize_chunksize
 
-        # For timekeeping
-        self.clocks = []
-
         self.parser.usecols = (usecols is not None)
 
         self._setup_parser_source(source)
@@ -507,8 +501,6 @@ cdef class TextReader:
         self.converters = converters
         self.na_filter = na_filter
 
-        self.verbose = verbose
-
         if float_precision == "round_trip":
             # see gh-15140
             self.parser.double_converter = round_trip_wrapper
@@ -896,8 +888,6 @@ cdef class TextReader:
             int64_t buffered_lines
             int64_t irows
 
-        self._start_clock()
-
         if rows is not None:
             irows = rows
             buffered_lines = self.parser.lines - self.parser_start
@@ -915,12 +905,8 @@ cdef class TextReader:
 
         if self.parser_start >= self.parser.lines:
             raise StopIteration
-        self._end_clock("Tokenization")
 
-        self._start_clock()
         columns = self._convert_column_data(rows)
-        self._end_clock("Type conversion")
-        self._start_clock()
         if len(columns) > 0:
             rows_read = len(list(columns.values())[0])
             # trim
@@ -929,18 +915,8 @@ cdef class TextReader:
                 parser_trim_buffers(self.parser)
             self.parser_start -= rows_read
 
-        self._end_clock("Parser memory cleanup")
-
         return columns
 
-    cdef _start_clock(self):
-        self.clocks.append(time.time())
-
-    cdef _end_clock(self, str what):
-        if self.verbose:
-            elapsed = time.time() - self.clocks.pop(-1)
-            print(f"{what} took: {elapsed * 1000:.2f} ms")
-
     def set_noconvert(self, i: int) -> None:
         self.noconvert.add(i)
 

pandas/io/parsers/base_parser.py

@@ -519,7 +519,6 @@ def _convert_to_ndarrays(
         dct: Mapping,
         na_values,
         na_fvalues,
-        verbose: bool = False,
         converters=None,
         dtypes=None,
     ) -> dict[Any, np.ndarray]:
@@ -596,8 +595,6 @@ def _convert_to_ndarrays(
                     cvals = self._cast_types(cvals, cast_type, c)
 
             result[c] = cvals
-            if verbose and na_count:
-                print(f"Filled {na_count} NA values in column {c!s}")
         return result
 
     @final
@@ -1236,7 +1233,6 @@ def converter(*date_cols, col: Hashable):
     "usecols": None,
     # 'iterator': False,
     "chunksize": None,
-    "verbose": False,
     "encoding": None,
     "compression": None,
     "skip_blank_lines": True,

pandas/io/parsers/python_parser.py

@@ -110,8 +110,6 @@ def __init__(self, f: ReadCsvBuffer[str] | list, **kwds) -> None:
         if "has_index_names" in kwds:
             self.has_index_names = kwds["has_index_names"]
 
-        self.verbose = kwds["verbose"]
-
         self.thousands = kwds["thousands"]
         self.decimal = kwds["decimal"]
 
@@ -372,7 +370,6 @@ def _convert_data(
             data,
             clean_na_values,
             clean_na_fvalues,
-            self.verbose,
             clean_conv,
             clean_dtypes,
         )

pandas/io/parsers/readers.py

@@ -116,7 +116,6 @@ class _read_shared(TypedDict, Generic[HashableT], total=False):
         )
         keep_default_na: bool
         na_filter: bool
-        verbose: bool | lib.NoDefault
         skip_blank_lines: bool
         parse_dates: bool | Sequence[Hashable] | None
         infer_datetime_format: bool | lib.NoDefault
@@ -295,10 +294,6 @@ class _read_shared(TypedDict, Generic[HashableT], total=False):
     Detect missing value markers (empty strings and the value of ``na_values``). In
     data without any ``NA`` values, passing ``na_filter=False`` can improve the
     performance of reading a large file.
-verbose : bool, default False
-    Indicate number of ``NA`` values placed in non-numeric columns.
-
-    .. deprecated:: 2.2.0
 skip_blank_lines : bool, default True
     If ``True``, skip over blank lines rather than interpreting as ``NaN`` values.
 parse_dates : bool, None, list of Hashable, list of lists or dict of {{Hashable : \
@@ -556,7 +551,6 @@ class _Fwf_Defaults(TypedDict):
     "converters",
     "iterator",
     "dayfirst",
-    "verbose",
     "skipinitialspace",
     "low_memory",
 }
@@ -755,7 +749,6 @@ def read_csv(
     | None = None,
     keep_default_na: bool = True,
     na_filter: bool = True,
-    verbose: bool | lib.NoDefault = lib.no_default,
     skip_blank_lines: bool = True,
     # Datetime Handling
     parse_dates: bool | Sequence[Hashable] | None = None,
@@ -845,17 +838,6 @@ def read_csv(
     else:
         delim_whitespace = False
 
-    if verbose is not lib.no_default:
-        # GH#55569
-        warnings.warn(
-            "The 'verbose' keyword in pd.read_csv is deprecated and "
-            "will be removed in a future version.",
-            FutureWarning,
-            stacklevel=find_stack_level(),
-        )
-    else:
-        verbose = False
-
     # locals() should never be modified
     kwds = locals().copy()
     del kwds["filepath_or_buffer"]
@@ -958,7 +940,6 @@ def read_table(
     | None = None,
     keep_default_na: bool = True,
     na_filter: bool = True,
-    verbose: bool | lib.NoDefault = lib.no_default,
     skip_blank_lines: bool = True,
     # Datetime Handling
     parse_dates: bool | Sequence[Hashable] | None = None,
@@ -1039,17 +1020,6 @@ def read_table(
     else:
         delim_whitespace = False
 
-    if verbose is not lib.no_default:
-        # GH#55569
-        warnings.warn(
-            "The 'verbose' keyword in pd.read_table is deprecated and "
-            "will be removed in a future version.",
-            FutureWarning,
-            stacklevel=find_stack_level(),
-        )
-    else:
-        verbose = False
-
     # locals() should never be modified
     kwds = locals().copy()
     del kwds["filepath_or_buffer"]