Enforce boolean types for the inplace keyword (pandas-dev#14318)

Author: rforgione

doc/source/whatsnew/v0.20.0.txt

@@ -247,6 +247,7 @@ Other API Changes
 
 - ``pd.read_csv()`` will now issue a ``ParserWarning`` whenever there are conflicting values provided by the ``dialect`` parameter and the user (:issue:`14898`)
 - ``pd.read_csv()`` will now raise a ``ValueError`` for the C engine if the quote character is larger than than one byte (:issue:`11592`)
+- ``inplace`` arguments now require a boolean value, else a ``ValueError`` is thrown (:issue:`14189`)
 
 .. _whatsnew_0200.deprecations:
 

pandas/computation/eval.py

@@ -11,6 +11,7 @@
 from pandas.computation.scope import _ensure_scope
 from pandas.compat import string_types
 from pandas.computation.engines import _engines
+from pandas.util.validators import validate_bool_kwarg
 
 
 def _check_engine(engine):
@@ -231,6 +232,7 @@ def eval(expr, parser='pandas', engine=None, truediv=True,
     pandas.DataFrame.query
     pandas.DataFrame.eval
     """
+    inplace = validate_bool_kwarg(inplace, 'inplace')
     first_expr = True
     if isinstance(expr, string_types):
         _check_expression(expr)

pandas/computation/tests/test_eval.py

@@ -1970,6 +1970,15 @@ def test_negate_lt_eq_le():
     for engine, parser in product(_engines, expr._parsers):
         yield check_negate_lt_eq_le, engine, parser
 
+class TestValidate(tm.TestCase):
+
+    def test_validate_bool_args(self):
+        invalid_values = [1, "True", [1,2,3], 5.0]
+
+        for value in invalid_values:
+            with self.assertRaises(ValueError):
+                pd.eval("2+2", inplace=value)
+
 
 if __name__ == '__main__':
     nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],

pandas/core/base.py

@@ -8,6 +8,7 @@
 from pandas.types.missing import isnull
 from pandas.types.generic import ABCDataFrame, ABCSeries, ABCIndexClass
 from pandas.types.common import is_object_dtype, is_list_like, is_scalar
+from pandas.util.validators import validate_bool_kwarg
 
 from pandas.core import common as com
 import pandas.core.nanops as nanops
@@ -1178,6 +1179,7 @@ def searchsorted(self, value, side='left', sorter=None):
                                                    False: 'first'})
     @Appender(_shared_docs['drop_duplicates'] % _indexops_doc_kwargs)
     def drop_duplicates(self, keep='first', inplace=False):
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         if isinstance(self, ABCIndexClass):
             if self.is_unique:
                 return self._shallow_copy()

pandas/core/categorical.py

@@ -35,6 +35,7 @@
                                     deprecate_kwarg, Substitution)
 
 from pandas.util.terminal import get_terminal_size
+from pandas.util.validators import validate_bool_kwarg
 from pandas.core.config import get_option
 
 
@@ -615,6 +616,7 @@ def set_ordered(self, value, inplace=False):
            Whether or not to set the ordered attribute inplace or return a copy
            of this categorical with ordered set to the value
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         self._validate_ordered(value)
         cat = self if inplace else self.copy()
         cat._ordered = value
@@ -631,6 +633,7 @@ def as_ordered(self, inplace=False):
            Whether or not to set the ordered attribute inplace or return a copy
            of this categorical with ordered set to True
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         return self.set_ordered(True, inplace=inplace)
 
     def as_unordered(self, inplace=False):
@@ -643,6 +646,7 @@ def as_unordered(self, inplace=False):
            Whether or not to set the ordered attribute inplace or return a copy
            of this categorical with ordered set to False
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         return self.set_ordered(False, inplace=inplace)
 
     def _get_ordered(self):
@@ -702,6 +706,7 @@ def set_categories(self, new_categories, ordered=None, rename=False,
         remove_categories
         remove_unused_categories
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         new_categories = self._validate_categories(new_categories)
         cat = self if inplace else self.copy()
         if rename:
@@ -754,6 +759,7 @@ def rename_categories(self, new_categories, inplace=False):
         remove_unused_categories
         set_categories
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         cat = self if inplace else self.copy()
         cat.categories = new_categories
         if not inplace:
@@ -794,6 +800,7 @@ def reorder_categories(self, new_categories, ordered=None, inplace=False):
         remove_unused_categories
         set_categories
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         if set(self._categories) != set(new_categories):
             raise ValueError("items in new_categories are not the same as in "
                              "old categories")
@@ -832,6 +839,7 @@ def add_categories(self, new_categories, inplace=False):
         remove_unused_categories
         set_categories
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         if not is_list_like(new_categories):
             new_categories = [new_categories]
         already_included = set(new_categories) & set(self._categories)
@@ -877,6 +885,7 @@ def remove_categories(self, removals, inplace=False):
         remove_unused_categories
         set_categories
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         if not is_list_like(removals):
             removals = [removals]
 
@@ -917,6 +926,7 @@ def remove_unused_categories(self, inplace=False):
         remove_categories
         set_categories
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         cat = self if inplace else self.copy()
         idx, inv = np.unique(cat._codes, return_inverse=True)
 
@@ -1322,6 +1332,7 @@ def sort_values(self, inplace=False, ascending=True, na_position='last'):
         [NaN, NaN, 5.0, 2.0, 2.0]
         Categories (2, int64): [2, 5]
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         if na_position not in ['last', 'first']:
             raise ValueError('invalid na_position: {!r}'.format(na_position))
 

pandas/core/frame.py

@@ -23,8 +23,7 @@
 import numpy as np
 import numpy.ma as ma
 
-from pandas.types.cast import (_maybe_upcast,
-                               _infer_dtype_from_scalar,
+from pandas.types.cast import (_maybe_upcast, _infer_dtype_from_scalar,
                                _possibly_cast_to_datetime,
                                _possibly_infer_to_datetimelike,
                                _possibly_convert_platform,
@@ -79,6 +78,7 @@
 from pandas import compat
 from pandas.compat.numpy import function as nv
 from pandas.util.decorators import deprecate_kwarg, Appender, Substitution
+from pandas.util.validators import validate_bool_kwarg
 
 from pandas.tseries.period import PeriodIndex
 from pandas.tseries.index import DatetimeIndex
@@ -2164,6 +2164,7 @@ def query(self, expr, inplace=False, **kwargs):
         >>> df.query('a > b')
         >>> df[df.a > df.b]  # same result as the previous expression
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         if not isinstance(expr, compat.string_types):
             msg = "expr must be a string to be evaluated, {0} given"
             raise ValueError(msg.format(type(expr)))
@@ -2230,6 +2231,7 @@ def eval(self, expr, inplace=None, **kwargs):
         >>> df.eval('a + b')
         >>> df.eval('c = a + b')
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         resolvers = kwargs.pop('resolvers', None)
         kwargs['level'] = kwargs.pop('level', 0) + 1
         if resolvers is None:
@@ -2843,6 +2845,7 @@ def set_index(self, keys, drop=True, append=False, inplace=False,
         -------
         dataframe : DataFrame
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         if not isinstance(keys, list):
             keys = [keys]
 
@@ -2935,6 +2938,7 @@ def reset_index(self, level=None, drop=False, inplace=False, col_level=0,
         -------
         resetted : DataFrame
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         if inplace:
             new_obj = self
         else:
@@ -3039,6 +3043,7 @@ def dropna(self, axis=0, how='any', thresh=None, subset=None,
         -------
         dropped : DataFrame
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         if isinstance(axis, (tuple, list)):
             result = self
             for ax in axis:
@@ -3102,6 +3107,7 @@ def drop_duplicates(self, subset=None, keep='first', inplace=False):
         -------
         deduplicated : DataFrame
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         duplicated = self.duplicated(subset, keep=keep)
 
         if inplace:
@@ -3163,7 +3169,7 @@ def f(vals):
     @Appender(_shared_docs['sort_values'] % _shared_doc_kwargs)
     def sort_values(self, by, axis=0, ascending=True, inplace=False,
                     kind='quicksort', na_position='last'):
-
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         axis = self._get_axis_number(axis)
         other_axis = 0 if axis == 1 else 1
 
@@ -3274,7 +3280,7 @@ def sort(self, columns=None, axis=0, ascending=True, inplace=False,
     def sort_index(self, axis=0, level=None, ascending=True, inplace=False,
                    kind='quicksort', na_position='last', sort_remaining=True,
                    by=None):
-
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         # 10726
         if by is not None:
             warnings.warn("by argument to sort_index is deprecated, pls use "

pandas/core/generic.py

@@ -52,6 +52,7 @@
                            isidentifier, set_function_name)
 import pandas.core.nanops as nanops
 from pandas.util.decorators import Appender, Substitution, deprecate_kwarg
+from pandas.util.validators import validate_bool_kwarg
 from pandas.core import config
 
 # goal is to be able to define the docs close to function, while still being
@@ -733,6 +734,7 @@ def rename_axis(self, mapper, axis=0, copy=True, inplace=False):
         1    2  5
         2    3  6
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         non_mapper = is_scalar(mapper) or (is_list_like(mapper) and not
                                            is_dict_like(mapper))
         if non_mapper:
@@ -1950,6 +1952,7 @@ def drop(self, labels, axis=0, level=None, inplace=False, errors='raise'):
         -------
         dropped : type of caller
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         axis = self._get_axis_number(axis)
         axis_name = self._get_axis_name(axis)
         axis, axis_ = self._get_axis(axis), axis
@@ -2099,6 +2102,7 @@ def sort_values(self, by, axis=0, ascending=True, inplace=False,
     @Appender(_shared_docs['sort_index'] % dict(axes="axes", klass="NDFrame"))
     def sort_index(self, axis=0, level=None, ascending=True, inplace=False,
                    kind='quicksort', na_position='last', sort_remaining=True):
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         axis = self._get_axis_number(axis)
         axis_name = self._get_axis_name(axis)
         labels = self._get_axis(axis)
@@ -2872,6 +2876,7 @@ def consolidate(self, inplace=False):
         -------
         consolidated : type of caller
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         if inplace:
             self._consolidate_inplace()
         else:
@@ -3267,6 +3272,7 @@ def convert_objects(self, convert_dates=True, convert_numeric=False,
     @Appender(_shared_docs['fillna'] % _shared_doc_kwargs)
     def fillna(self, value=None, method=None, axis=None, inplace=False,
                limit=None, downcast=None):
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         if isinstance(value, (list, tuple)):
             raise TypeError('"value" parameter must be a scalar or dict, but '
                             'you passed a "{0}"'.format(type(value).__name__))
@@ -3479,6 +3485,7 @@ def replace(self, to_replace=None, value=None, inplace=False, limit=None,
           and play with this method to gain intuition about how it works.
 
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         if not is_bool(regex) and to_replace is not None:
             raise AssertionError("'to_replace' must be 'None' if 'regex' is "
                                  "not a bool")
@@ -3714,6 +3721,7 @@ def interpolate(self, method='linear', axis=0, limit=None, inplace=False,
         """
         Interpolate values according to different methods.
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
 
         if self.ndim > 2:
             raise NotImplementedError("Interpolate has not been implemented "
@@ -4627,6 +4635,7 @@ def _where(self, cond, other=np.nan, inplace=False, axis=None, level=None,
         Equivalent to public method `where`, except that `other` is not
         applied as a function even if callable. Used in __setitem__.
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
 
         cond = com._apply_if_callable(cond, self)
 
@@ -4894,6 +4903,7 @@ def where(self, cond, other=np.nan, inplace=False, axis=None, level=None,
     def mask(self, cond, other=np.nan, inplace=False, axis=None, level=None,
              try_cast=False, raise_on_error=True):
 
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         cond = com._apply_if_callable(cond, self)
 
         return self.where(~cond, other=other, inplace=inplace, axis=axis,

pandas/core/internals.py

@@ -57,6 +57,7 @@
 import pandas.tslib as tslib
 import pandas.computation.expressions as expressions
 from pandas.util.decorators import cache_readonly
+from pandas.util.validators import validate_bool_kwarg
 
 from pandas.tslib import Timedelta
 from pandas import compat, _np_version_under1p9
@@ -360,6 +361,7 @@ def fillna(self, value, limit=None, inplace=False, downcast=None,
         """ fillna on the block with the value. If we fail, then convert to
         ObjectBlock and try again
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
 
         if not self._can_hold_na:
             if inplace:
@@ -626,6 +628,7 @@ def replace(self, to_replace, value, inplace=False, filter=None,
         compatibility.
         """
 
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         original_to_replace = to_replace
         mask = isnull(self.values)
         # try to replace, if we raise an error, convert to ObjectBlock and
@@ -897,6 +900,9 @@ def interpolate(self, method='pad', axis=0, index=None, values=None,
                     inplace=False, limit=None, limit_direction='forward',
                     fill_value=None, coerce=False, downcast=None, mgr=None,
                     **kwargs):
+
+        inplace = validate_bool_kwarg(inplace, 'inplace')
+
         def check_int_bool(self, inplace):
             # Only FloatBlocks will contain NaNs.
             # timedelta subclasses IntBlock
@@ -944,6 +950,8 @@ def _interpolate_with_fill(self, method='pad', axis=0, inplace=False,
                                downcast=None, mgr=None):
         """ fillna but using the interpolate machinery """
 
+        inplace = validate_bool_kwarg(inplace, 'inplace')
+
         # if we are coercing, then don't force the conversion
         # if the block can't hold the type
         if coerce:
@@ -970,6 +978,7 @@ def _interpolate(self, method=None, index=None, values=None,
                      mgr=None, **kwargs):
         """ interpolate using scipy wrappers """
 
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         data = self.values if inplace else self.values.copy()
 
         # only deal with floats
@@ -1514,6 +1523,7 @@ def putmask(self, mask, new, align=True, inplace=False, axis=0,
         -------
         a new block(s), the result of the putmask
         """
+        inplace = validate_bool_kwarg(inplace, 'inplace')
 
         # use block's copy logic.
         # .values may be an Index which does shallow copy by default
@@ -1801,6 +1811,7 @@ def should_store(self, value):
 
     def replace(self, to_replace, value, inplace=False, filter=None,
                 regex=False, convert=True, mgr=None):
+        inplace = validate_bool_kwarg(inplace, 'inplace')
         to_replace_values = np.atleast_1d(to_replace)
         if not np.can_cast(to_replace_values, bool):
             return self
@@ -1982,6 +1993,9 @@ def replace(self, to_replace, value, inplace=False, filter=None,
 
     def _replace_single(self, to_replace, value, inplace=False, filter=None,
                         regex=False, convert=True, mgr=None):
+
+        inplace = validate_bool_kwarg(inplace, 'inplace')
+
         # to_replace is regex compilable
         to_rep_re = regex and is_re_compilable(to_replace)
 
@@ -3205,6 +3219,8 @@ def replace_list(self, src_list, dest_list, inplace=False, regex=False,
                      mgr=None):
         """ do a list replace """
 
+        inplace = validate_bool_kwarg(inplace, 'inplace')
+
         if mgr is None:
             mgr = self