Python pandas.core.common.is_bool_indexer() Examples

def get_value(self, series, key):
        if com.is_bool_indexer(key):
            loc = key
        elif is_list_like(key):
            loc = self.get_indexer(key)
        elif isinstance(key, slice):

            if not (key.step is None or key.step == 1):
                raise ValueError("cannot support not-default step in a slice")

            try:
                loc = self.get_loc(key)
            except TypeError:
                # we didn't find exact intervals or are non-unique
                msg = "unable to slice with this key: {key}".format(key=key)
                raise ValueError(msg)

        else:
            loc = self.get_loc(key)
        return series.iloc[loc] 

def _multi_take_opportunity(self, tup):
        """
        Check whether there is the possibility to use ``_multi_take``.
        Currently the limit is that all axes being indexed must be indexed with
        list-likes.

        Parameters
        ----------
        tup : tuple
            Tuple of indexers, one per axis

        Returns
        -------
        boolean: Whether the current indexing can be passed through _multi_take
        """
        if not all(is_list_like_indexer(x) for x in tup):
            return False

        # just too complicated
        if any(com.is_bool_indexer(x) for x in tup):
            return False

        return True 

def get_value(self, series, key):
        if com.is_bool_indexer(key):
            loc = key
        elif is_list_like(key):
            loc = self.get_indexer(key)
        elif isinstance(key, slice):

            if not (key.step is None or key.step == 1):
                raise ValueError("cannot support not-default "
                                 "step in a slice")

            try:
                loc = self.get_loc(key)
            except TypeError:

                # we didn't find exact intervals
                # or are non-unique
                raise ValueError("unable to slice with "
                                 "this key: {}".format(key))

        else:
            loc = self.get_loc(key)
        return series.iloc[loc] 

def get_value(self, series, key):
        if com.is_bool_indexer(key):
            loc = key
        elif is_list_like(key):
            loc = self.get_indexer(key)
        elif isinstance(key, slice):

            if not (key.step is None or key.step == 1):
                raise ValueError("cannot support not-default "
                                 "step in a slice")

            try:
                loc = self.get_loc(key)
            except TypeError:

                # we didn't find exact intervals
                # or are non-unique
                raise ValueError("unable to slice with "
                                 "this key: {}".format(key))

        else:
            loc = self.get_loc(key)
        return series.iloc[loc] 

def _multi_take_opportunity(self, tup):
        """
        Check whether there is the possibility to use ``_multi_take``.
        Currently the limit is that all axes being indexed must be indexed with
        list-likes.

        Parameters
        ----------
        tup : tuple
            Tuple of indexers, one per axis

        Returns
        -------
        boolean: Whether the current indexing can be passed through _multi_take
        """
        if not all(is_list_like_indexer(x) for x in tup):
            return False

        # just too complicated
        if any(com.is_bool_indexer(x) for x in tup):
            return False

        return True 

def check_bool_indexer(ax, key):
    # boolean indexing, need to check that the data are aligned, otherwise
    # disallowed

    # this function assumes that is_bool_indexer(key) == True

    result = key
    if isinstance(key, ABCSeries) and not key.index.equals(ax):
        result = result.reindex(ax)
        mask = isna(result._values)
        if mask.any():
            raise IndexingError('Unalignable boolean Series provided as '
                                'indexer (index of the boolean Series and of '
                                'the indexed object do not match')
        result = result.astype(bool)._values
    elif is_sparse(result):
        result = result.to_dense()
        result = np.asarray(result, dtype=bool)
    else:
        # is_bool_indexer has already checked for nulls in the case of an
        # object array key, so no check needed here
        result = np.asarray(result, dtype=bool)

    return result 

def check_bool_indexer(ax, key):
    # boolean indexing, need to check that the data are aligned, otherwise
    # disallowed

    # this function assumes that is_bool_indexer(key) == True

    result = key
    if isinstance(key, ABCSeries) and not key.index.equals(ax):
        result = result.reindex(ax)
        mask = isna(result._values)
        if mask.any():
            raise IndexingError('Unalignable boolean Series provided as '
                                'indexer (index of the boolean Series and of '
                                'the indexed object do not match')
        result = result.astype(bool)._values
    elif is_sparse(result):
        result = result.to_dense()
        result = np.asarray(result, dtype=bool)
    else:
        # is_bool_indexer has already checked for nulls in the case of an
        # object array key, so no check needed here
        result = np.asarray(result, dtype=bool)

    return result 

def check_bool_indexer(ax, key):
    # boolean indexing, need to check that the data are aligned, otherwise
    # disallowed

    # this function assumes that is_bool_indexer(key) == True

    result = key
    if isinstance(key, ABCSeries) and not key.index.equals(ax):
        result = result.reindex(ax)
        mask = isna(result._values)
        if mask.any():
            raise IndexingError('Unalignable boolean Series provided as '
                                'indexer (index of the boolean Series and of '
                                'the indexed object do not match')
        result = result.astype(bool)._values
    elif is_sparse(result):
        result = result.to_dense()
        result = np.asarray(result, dtype=bool)
    else:
        # is_bool_indexer has already checked for nulls in the case of an
        # object array key, so no check needed here
        result = np.asarray(result, dtype=bool)

    return result 

def _validate_key(self, key, axis):
        if isinstance(key, slice):
            return True

        elif com.is_bool_indexer(key):
            return True

        elif is_list_like_indexer(key):
            return True

        else:

            self._convert_scalar_indexer(key, axis)

        return True 

def _getitem_array(self, key):
        if isinstance(key, Series):
            key = key.to_pandas()
        if is_bool_indexer(key):
            if isinstance(key, pd.Series) and not key.index.equals(self.index):
                warnings.warn(
                    "Boolean Series key will be reindexed to match DataFrame index.",
                    PendingDeprecationWarning,
                    stacklevel=3,
                )
            elif len(key) != len(self.index):
                raise ValueError(
                    f"Item wrong length {len(key)} instead of {len(self.index)}."
                )
            key = check_bool_indexer(self.index, key)
            # We convert to a RangeIndex because getitem_row_array is expecting a list
            # of indices, and RangeIndex will give us the exact indices of each boolean
            # requested.
            key = pd.RangeIndex(len(self.index))[key]
            if len(key):
                return DataFrame(
                    _query_compiler=self._query_compiler.getitem_row_array(key)
                )
            else:
                return DataFrame(columns=self.columns)
        else:
            if any(k not in self.columns for k in key):
                raise KeyError(
                    f"{str([k for k in key if k not in self.columns]).replace(',', '')}"
                    f" not index"
                )
            return DataFrame(
                _query_compiler=self._query_compiler.getitem_column_array(key)
            ) 

def _validate_key(self, key, axis):
        ax = self.obj._get_axis(axis)

        # valid for a label where all labels are in the index
        # slice of labels (where start-end in labels)
        # slice of integers (only if in the labels)
        # boolean

        if isinstance(key, slice):
            return

        elif com.is_bool_indexer(key):
            return

        elif not is_list_like_indexer(key):

            def error():
                if isna(key):
                    raise TypeError("cannot use label indexing with a null "
                                    "key")
                raise KeyError(u"the label [{key}] is not in the [{axis}]"
                               .format(key=key,
                                       axis=self.obj._get_axis_name(axis)))

            try:
                key = self._convert_scalar_indexer(key, axis)
                if not ax.contains(key):
                    error()
            except TypeError as e:

                # python 3 type errors should be raised
                if _is_unorderable_exception(e):
                    error()
                raise
            except:
                error() 

def _getitem_axis(self, key, axis=None):
        if axis is None:
            axis = self.axis or 0

        if isinstance(key, slice):
            return self._get_slice_axis(key, axis=axis)

        if isinstance(key, list):
            key = np.asarray(key)

        if com.is_bool_indexer(key):
            self._validate_key(key, axis)
            return self._getbool_axis(key, axis=axis)

        # a list of integers
        elif is_list_like_indexer(key):
            return self._get_list_axis(key, axis=axis)

        # a single integer
        else:
            key = self._convert_scalar_indexer(key, axis)

            if not is_integer(key):
                raise TypeError("Cannot index by location index with a "
                                "non-integer key")

            # validate the location
            self._validate_integer(key, axis)

            return self._get_loc(key, axis=axis) 

def test_mask_with_boolean(index):
    s = Series(range(3))
    idx = Categorical([True, False, True])
    if index:
        idx = CategoricalIndex(idx)

    assert com.is_bool_indexer(idx)
    result = s[idx]
    expected = s[idx.astype('object')]
    tm.assert_series_equal(result, expected) 

def test_mask_with_boolean(index):
    s = Series(range(3))
    idx = Categorical([True, False, True])
    if index:
        idx = CategoricalIndex(idx)

    assert com.is_bool_indexer(idx)
    result = s[idx]
    expected = s[idx.astype('object')]
    tm.assert_series_equal(result, expected) 

def __getitem__(self, key):
        if isinstance(key, tuple):
            if len(key) > 1:
                raise IndexError("too many indices for array.")
            key = key[0]

        if is_integer(key):
            return self._get_val_at(key)
        elif isinstance(key, tuple):
            data_slice = self.values[key]
        elif isinstance(key, slice):
            # special case to preserve dtypes
            if key == slice(None):
                return self.copy()
            # TODO: this logic is surely elsewhere
            # TODO: this could be more efficient
            indices = np.arange(len(self), dtype=np.int32)[key]
            return self.take(indices)
        else:
            # TODO: I think we can avoid densifying when masking a
            # boolean SparseArray with another. Need to look at the
            # key's fill_value for True / False, and then do an intersection
            # on the indicies of the sp_values.
            if isinstance(key, SparseArray):
                if is_bool_dtype(key):
                    key = key.to_dense()
                else:
                    key = np.asarray(key)

            if com.is_bool_indexer(key) and len(self) == len(key):
                return self.take(np.arange(len(key), dtype=np.int32)[key])
            elif hasattr(key, '__len__'):
                return self.take(key)
            else:
                raise ValueError("Cannot slice with '{}'".format(key))

        return type(self)(data_slice, kind=self.kind) 

def __getitem__(self, key):
        """
        Override numpy.ndarray's __getitem__ method to work as desired.

        This function adds lists and Series as valid boolean indexers
        (ndarrays only supports ndarray with dtype=bool).

        If resulting ndim != 1, plain ndarray is returned instead of
        corresponding `Index` subclass.

        """
        # There's no custom logic to be implemented in __getslice__, so it's
        # not overloaded intentionally.
        getitem = self._data.__getitem__
        promote = self._shallow_copy

        if is_scalar(key):
            key = com.cast_scalar_indexer(key)
            return getitem(key)

        if isinstance(key, slice):
            # This case is separated from the conditional above to avoid
            # pessimization of basic indexing.
            return promote(getitem(key))

        if com.is_bool_indexer(key):
            key = np.asarray(key, dtype=bool)

        key = com.values_from_object(key)
        result = getitem(key)
        if not is_scalar(result):
            return promote(result)
        else:
            return result 

def __getitem__(self, key):
        if is_scalar(key):
            key = com.cast_scalar_indexer(key)

            retval = []
            for lev, level_codes in zip(self.levels, self.codes):
                if level_codes[key] == -1:
                    retval.append(np.nan)
                else:
                    retval.append(lev[level_codes[key]])

            return tuple(retval)
        else:
            if com.is_bool_indexer(key):
                key = np.asarray(key, dtype=bool)
                sortorder = self.sortorder
            else:
                # cannot be sure whether the result will be sorted
                sortorder = None

                if isinstance(key, Index):
                    key = np.asarray(key)

            new_codes = [level_codes[key] for level_codes in self.codes]

            return MultiIndex(levels=self.levels, codes=new_codes,
                              names=self.names, sortorder=sortorder,
                              verify_integrity=False) 

def _getitem_axis(self, key, axis=None):
        if axis is None:
            axis = self.axis or 0

        if isinstance(key, slice):
            return self._get_slice_axis(key, axis=axis)

        if isinstance(key, list):
            key = np.asarray(key)

        if com.is_bool_indexer(key):
            self._validate_key(key, axis)
            return self._getbool_axis(key, axis=axis)

        # a list of integers
        elif is_list_like_indexer(key):
            return self._get_list_axis(key, axis=axis)

        # a single integer
        else:
            if not is_integer(key):
                raise TypeError("Cannot index by location index with a "
                                "non-integer key")

            # validate the location
            self._validate_integer(key, axis)

            return self._get_loc(key, axis=axis) 

def _validate_key(self, key, axis):
        if com.is_bool_indexer(key):
            if hasattr(key, 'index') and isinstance(key.index, Index):
                if key.index.inferred_type == 'integer':
                    raise NotImplementedError("iLocation based boolean "
                                              "indexing on an integer type "
                                              "is not available")
                raise ValueError("iLocation based boolean indexing cannot use "
                                 "an indexable as a mask")
            return

        if isinstance(key, slice):
            return
        elif is_integer(key):
            self._validate_integer(key, axis)
        elif isinstance(key, tuple):
            # a tuple should already have been caught by this point
            # so don't treat a tuple as a valid indexer
            raise IndexingError('Too many indexers')
        elif is_list_like_indexer(key):
            # check that the key does not exceed the maximum size of the index
            arr = np.array(key)
            len_axis = len(self.obj._get_axis(axis))

            if len(arr) and (arr.max() >= len_axis or arr.min() < -len_axis):
                raise IndexError("positional indexers are out-of-bounds")
        else:
            raise ValueError("Can only index by location with "
                             "a [{types}]".format(types=self._valid_types)) 

def _validate_key(self, key, axis):
        if isinstance(key, slice):
            return True

        elif com.is_bool_indexer(key):
            return True

        elif is_list_like_indexer(key):
            return True

        else:

            self._convert_scalar_indexer(key, axis)

        return True 

def _validate_key(self, key, axis):

        # valid for a collection of labels (we check their presence later)
        # slice of labels (where start-end in labels)
        # slice of integers (only if in the labels)
        # boolean

        if isinstance(key, slice):
            return

        if com.is_bool_indexer(key):
            return

        if not is_list_like_indexer(key):
            self._convert_scalar_indexer(key, axis) 

def test_mask_with_boolean(index):
    s = Series(range(3))
    idx = Categorical([True, False, True])
    if index:
        idx = CategoricalIndex(idx)

    assert com.is_bool_indexer(idx)
    result = s[idx]
    expected = s[idx.astype('object')]
    tm.assert_series_equal(result, expected) 

def __getitem__(self, key):
        if is_scalar(key):
            retval = []
            for lev, lab in zip(self.levels, self.labels):
                if lab[key] == -1:
                    retval.append(np.nan)
                else:
                    retval.append(lev[lab[key]])

            return tuple(retval)
        else:
            if com.is_bool_indexer(key):
                key = np.asarray(key)
                sortorder = self.sortorder
            else:
                # cannot be sure whether the result will be sorted
                sortorder = None

                if isinstance(key, Index):
                    key = np.asarray(key)

            new_labels = [lab[key] for lab in self.labels]

            return MultiIndex(levels=self.levels, labels=new_labels,
                              names=self.names, sortorder=sortorder,
                              verify_integrity=False) 

def __getitem__(self, key):
        """
        Override numpy.ndarray's __getitem__ method to work as desired.

        This function adds lists and Series as valid boolean indexers
        (ndarrays only supports ndarray with dtype=bool).

        If resulting ndim != 1, plain ndarray is returned instead of
        corresponding `Index` subclass.

        """
        # There's no custom logic to be implemented in __getslice__, so it's
        # not overloaded intentionally.
        getitem = self._data.__getitem__
        promote = self._shallow_copy

        if is_scalar(key):
            return getitem(key)

        if isinstance(key, slice):
            # This case is separated from the conditional above to avoid
            # pessimization of basic indexing.
            return promote(getitem(key))

        if com.is_bool_indexer(key):
            key = np.asarray(key)

        key = com._values_from_object(key)
        result = getitem(key)
        if not is_scalar(result):
            return promote(result)
        else:
            return result 

def __getitem__(self, key):
        if isinstance(key, tuple):
            if len(key) > 1:
                raise IndexError("too many indices for array.")
            key = key[0]

        if is_integer(key):
            return self._get_val_at(key)
        elif isinstance(key, tuple):
            data_slice = self.values[key]
        elif isinstance(key, slice):
            # special case to preserve dtypes
            if key == slice(None):
                return self.copy()
            # TODO: this logic is surely elsewhere
            # TODO: this could be more efficient
            indices = np.arange(len(self), dtype=np.int32)[key]
            return self.take(indices)
        else:
            # TODO: I think we can avoid densifying when masking a
            # boolean SparseArray with another. Need to look at the
            # key's fill_value for True / False, and then do an intersection
            # on the indicies of the sp_values.
            if isinstance(key, SparseArray):
                if is_bool_dtype(key):
                    key = key.to_dense()
                else:
                    key = np.asarray(key)

            if com.is_bool_indexer(key) and len(self) == len(key):
                return self.take(np.arange(len(key), dtype=np.int32)[key])
            elif hasattr(key, '__len__'):
                return self.take(key)
            else:
                raise ValueError("Cannot slice with '{}'".format(key))

        return type(self)(data_slice, kind=self.kind) 

def _getitem_axis(self, key, axis=None):
        if axis is None:
            axis = self.axis or 0

        if isinstance(key, slice):
            return self._get_slice_axis(key, axis=axis)

        if isinstance(key, list):
            key = np.asarray(key)

        if com.is_bool_indexer(key):
            self._validate_key(key, axis)
            return self._getbool_axis(key, axis=axis)

        # a list of integers
        elif is_list_like_indexer(key):
            return self._get_list_axis(key, axis=axis)

        # a single integer
        else:
            if not is_integer(key):
                raise TypeError("Cannot index by location index with a "
                                "non-integer key")

            # validate the location
            self._validate_integer(key, axis)

            return self._get_loc(key, axis=axis) 

def __getitem__(self, key):
        """
        Override numpy.ndarray's __getitem__ method to work as desired.

        This function adds lists and Series as valid boolean indexers
        (ndarrays only supports ndarray with dtype=bool).

        If resulting ndim != 1, plain ndarray is returned instead of
        corresponding `Index` subclass.

        """
        # There's no custom logic to be implemented in __getslice__, so it's
        # not overloaded intentionally.
        getitem = self._data.__getitem__
        promote = self._shallow_copy

        if is_scalar(key):
            key = com.cast_scalar_indexer(key)
            return getitem(key)

        if isinstance(key, slice):
            # This case is separated from the conditional above to avoid
            # pessimization of basic indexing.
            return promote(getitem(key))

        if com.is_bool_indexer(key):
            key = np.asarray(key, dtype=bool)

        key = com.values_from_object(key)
        result = getitem(key)
        if not is_scalar(result):
            return promote(result)
        else:
            return result 

def _validate_key(self, key, axis):
        if com.is_bool_indexer(key):
            if hasattr(key, 'index') and isinstance(key.index, Index):
                if key.index.inferred_type == 'integer':
                    raise NotImplementedError("iLocation based boolean "
                                              "indexing on an integer type "
                                              "is not available")
                raise ValueError("iLocation based boolean indexing cannot use "
                                 "an indexable as a mask")
            return

        if isinstance(key, slice):
            return
        elif is_integer(key):
            self._validate_integer(key, axis)
        elif isinstance(key, tuple):
            # a tuple should already have been caught by this point
            # so don't treat a tuple as a valid indexer
            raise IndexingError('Too many indexers')
        elif is_list_like_indexer(key):
            # check that the key does not exceed the maximum size of the index
            arr = np.array(key)
            len_axis = len(self.obj._get_axis(axis))

            if len(arr) and (arr.max() >= len_axis or arr.min() < -len_axis):
                raise IndexError("positional indexers are out-of-bounds")
        else:
            raise ValueError("Can only index by location with "
                             "a [{types}]".format(types=self._valid_types)) 

def __getitem__(self, key):
        if is_scalar(key):
            key = com.cast_scalar_indexer(key)

            retval = []
            for lev, level_codes in zip(self.levels, self.codes):
                if level_codes[key] == -1:
                    retval.append(np.nan)
                else:
                    retval.append(lev[level_codes[key]])

            return tuple(retval)
        else:
            if com.is_bool_indexer(key):
                key = np.asarray(key, dtype=bool)
                sortorder = self.sortorder
            else:
                # cannot be sure whether the result will be sorted
                sortorder = None

                if isinstance(key, Index):
                    key = np.asarray(key)

            new_codes = [level_codes[key] for level_codes in self.codes]

            return MultiIndex(levels=self.levels, codes=new_codes,
                              names=self.names, sortorder=sortorder,
                              verify_integrity=False) 

def _getitem(self, key):
        key = apply_if_callable(key, self)
        if isinstance(key, Series) and key.dtype == np.bool:
            # This ends up being significantly faster than looping through and getting
            # each item individually.
            key = key._to_pandas()
        if is_bool_indexer(key):
            return self.__constructor__(
                query_compiler=self._query_compiler.getitem_row_array(
                    pandas.RangeIndex(len(self.index))[key]
                )
            )
        # TODO: More efficiently handle `tuple` case for `Series.__getitem__`
        if isinstance(key, tuple):
            return self._default_to_pandas(pandas.Series.__getitem__, key)
        else:
            if not is_list_like(key):
                reduce_dimension = True
                key = [key]
            else:
                reduce_dimension = False
            # The check for whether or not `key` is in `keys()` will throw a TypeError
            # if the object is not hashable. When that happens, we just use the `iloc`.
            try:
                if all(k in self.keys() for k in key):
                    result = self._query_compiler.getitem_row_array(
                        self.index.get_indexer_for(key)
                    )
                else:
                    result = self._query_compiler.getitem_row_array(key)
            except TypeError:
                result = self._query_compiler.getitem_row_array(key)
        if reduce_dimension:
            return self._reduce_dimension(result)
        return self.__constructor__(query_compiler=result)