Python Series.cat方法代码示例

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def set_ordered(self, value, inplace=False):
        """
        Sets the ordered attribute to the boolean value

        Parameters
        ----------
        value : boolean to set whether this categorical is ordered (True) or
           not (False)
        inplace : boolean (default: 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')
        new_dtype = CategoricalDtype(self.categories, ordered=value)
        cat = self if inplace else self.copy()
        cat._dtype = new_dtype
        if not inplace:
            return cat 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def value_counts(self, dropna=True):
        """
        Returns a Series containing counts of each category.

        Every category will have an entry, even those with a count of 0.

        Parameters
        ----------
        dropna : boolean, default True
            Don't include counts of NaN.

        Returns
        -------
        counts : Series

        See Also
        --------
        Series.value_counts

        """
        from numpy import bincount
        from pandas import Series, CategoricalIndex

        code, cat = self._codes, self.categories
        ncat, mask = len(cat), 0 <= code
        ix, clean = np.arange(ncat), mask.all()

        if dropna or clean:
            obs = code if clean else code[mask]
            count = bincount(obs, minlength=ncat or None)
        else:
            count = bincount(np.where(mask, code, ncat))
            ix = np.append(ix, -1)

        ix = self._constructor(ix, dtype=self.dtype,
                               fastpath=True)

        return Series(count, index=CategoricalIndex(ix), dtype='int64') 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def _validate(data):
        if not is_categorical_dtype(data.dtype):
            raise AttributeError("Can only use .cat accessor with a "
                                 "'category' dtype") 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def name(self):
        # Note: Upon deprecation, `test_tab_completion_with_categorical` will
        # need to be updated. `name` will need to be removed from
        # `ok_for_cat`.
        warn("`Series.cat.name` has been deprecated. Use `Series.name` "
             "instead.",
             FutureWarning,
             stacklevel=2)
        return self._name 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def index(self):
        # Note: Upon deprecation, `test_tab_completion_with_categorical` will
        # need to be updated. `index` will need to be removed from
        # ok_for_cat`.
        warn("`Series.cat.index` has been deprecated. Use `Series.index` "
             "instead.",
             FutureWarning,
             stacklevel=2)
        return self._index

# utility routines 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def _factorize_from_iterable(values):
    """
    Factorize an input `values` into `categories` and `codes`. Preserves
    categorical dtype in `categories`.

    *This is an internal function*

    Parameters
    ----------
    values : list-like

    Returns
    -------
    codes : ndarray
    categories : Index
        If `values` has a categorical dtype, then `categories` is
        a CategoricalIndex keeping the categories and order of `values`.
    """
    from pandas.core.indexes.category import CategoricalIndex

    if not is_list_like(values):
        raise TypeError("Input must be list-like")

    if is_categorical(values):
        if isinstance(values, (ABCCategoricalIndex, ABCSeries)):
            values = values._values
        categories = CategoricalIndex(values.categories,
                                      categories=values.categories,
                                      ordered=values.ordered)
        codes = values.codes
    else:
        # The value of ordered is irrelevant since we don't use cat as such,
        # but only the resulting categories, the order of which is independent
        # from ordered. Set ordered to False as default. See GH #15457
        cat = Categorical(values, ordered=False)
        categories = cat.categories
        codes = cat.codes
    return codes, categories 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def test_tab_completion(self):
        # GH 9910
        s = Series(list('abcd'))
        # Series of str values should have .str but not .dt/.cat in __dir__
        assert 'str' in dir(s)
        assert 'dt' not in dir(s)
        assert 'cat' not in dir(s)

        # similarly for .dt
        s = Series(date_range('1/1/2015', periods=5))
        assert 'dt' in dir(s)
        assert 'str' not in dir(s)
        assert 'cat' not in dir(s)

        # Similarly for .cat, but with the twist that str and dt should be
        # there if the categories are of that type first cat and str.
        s = Series(list('abbcd'), dtype="category")
        assert 'cat' in dir(s)
        assert 'str' in dir(s)  # as it is a string categorical
        assert 'dt' not in dir(s)

        # similar to cat and str
        s = Series(date_range('1/1/2015', periods=5)).astype("category")
        assert 'cat' in dir(s)
        assert 'str' not in dir(s)
        assert 'dt' in dir(s)  # as it is a datetime categorical 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def test_tab_completion_with_categorical(self):
        # test the tab completion display
        ok_for_cat = ['categories', 'codes', 'ordered', 'set_categories',
                      'add_categories', 'remove_categories',
                      'rename_categories', 'reorder_categories',
                      'remove_unused_categories', 'as_ordered', 'as_unordered']

        def get_dir(s):
            results = [r for r in s.cat.__dir__() if not r.startswith('_')]
            return list(sorted(set(results)))

        s = Series(list('aabbcde')).astype('category')
        results = get_dir(s)
        tm.assert_almost_equal(results, list(sorted(set(ok_for_cat)))) 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def test_cat_accessor(self):
        s = Series(Categorical(["a", "b", np.nan, "a"]))
        tm.assert_index_equal(s.cat.categories, Index(["a", "b"]))
        assert not s.cat.ordered, False

        exp = Categorical(["a", "b", np.nan, "a"], categories=["b", "a"])
        s.cat.set_categories(["b", "a"], inplace=True)
        tm.assert_categorical_equal(s.values, exp)

        res = s.cat.set_categories(["b", "a"])
        tm.assert_categorical_equal(res.values, exp)

        s[:] = "a"
        s = s.cat.remove_unused_categories()
        tm.assert_index_equal(s.cat.categories, Index(["a"])) 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def test_cat_accessor_api(self):
        # GH 9322
        from pandas.core.arrays.categorical import CategoricalAccessor
        assert Series.cat is CategoricalAccessor
        s = Series(list('aabbcde')).astype('category')
        assert isinstance(s.cat, CategoricalAccessor)

        invalid = Series([1])
        with tm.assert_raises_regex(AttributeError,
                                    "only use .cat accessor"):
            invalid.cat
        assert not hasattr(invalid, 'cat') 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def test_cat_accessor_no_new_attributes(self):
        # https://github.com/pandas-dev/pandas/issues/10673
        c = Series(list('aabbcde')).astype('category')
        with tm.assert_raises_regex(AttributeError,
                                    "You cannot add any new attribute"):
            c.cat.xlabel = "a" 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def reorder_categories(self, new_categories, ordered=None, inplace=False):
        """ Reorders categories as specified in new_categories.

        `new_categories` need to include all old categories and no new category
        items.

        Raises
        ------
        ValueError
            If the new categories do not contain all old category items or any
            new ones

        Parameters
        ----------
        new_categories : Index-like
           The categories in new order.
        ordered : boolean, optional
           Whether or not the categorical is treated as a ordered categorical.
           If not given, do not change the ordered information.
        inplace : boolean (default: False)
           Whether or not to reorder the categories inplace or return a copy of
           this categorical with reordered categories.

        Returns
        -------
        cat : Categorical with reordered categories or None if inplace.

        See also
        --------
        rename_categories
        add_categories
        remove_categories
        remove_unused_categories
        set_categories
        """
        inplace = validate_bool_kwarg(inplace, 'inplace')
        if set(self.dtype.categories) != set(new_categories):
            raise ValueError("items in new_categories are not the same as in "
                             "old categories")
        return self.set_categories(new_categories, ordered=ordered,
                                   inplace=inplace) 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def remove_unused_categories(self, inplace=False):
        """ Removes categories which are not used.

        Parameters
        ----------
        inplace : boolean (default: False)
           Whether or not to drop unused categories inplace or return a copy of
           this categorical with unused categories dropped.

        Returns
        -------
        cat : Categorical with unused categories dropped or None if inplace.

        See also
        --------
        rename_categories
        reorder_categories
        add_categories
        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)

        if idx.size != 0 and idx[0] == -1:  # na sentinel
            idx, inv = idx[1:], inv - 1

        new_categories = cat.dtype.categories.take(idx)
        new_dtype = CategoricalDtype._from_fastpath(new_categories,
                                                    ordered=self.ordered)
        cat._dtype = new_dtype
        cat._codes = coerce_indexer_dtype(inv, new_dtype.categories)

        if not inplace:
            return cat 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def _factorize_from_iterable(values):
    """
    Factorize an input `values` into `categories` and `codes`. Preserves
    categorical dtype in `categories`.

    *This is an internal function*

    Parameters
    ----------
    values : list-like

    Returns
    -------
    codes : ndarray
    categories : Index
        If `values` has a categorical dtype, then `categories` is
        a CategoricalIndex keeping the categories and order of `values`.
    """
    from pandas.core.indexes.category import CategoricalIndex

    if not is_list_like(values):
        raise TypeError("Input must be list-like")

    if is_categorical(values):
        if isinstance(values, (ABCCategoricalIndex, ABCSeries)):
            values = values._values
        categories = CategoricalIndex(values.categories,
                                      categories=values.categories,
                                      ordered=values.ordered)
        codes = values.codes
    else:
        cat = Categorical(values, ordered=True)
        categories = cat.categories
        codes = cat.codes
    return codes, categories 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import cat [as 别名]
def _codes_for_groupby(self, sort):
        """
        If sort=False, return a copy of self, coded with categories as
        returned by .unique(), followed by any categories not appearing in
        the data. If sort=True, return self.

        This method is needed solely to ensure the categorical index of the
        GroupBy result has categories in the order of appearance in the data
        (GH-8868).

        Parameters
        ----------
        sort : boolean
            The value of the sort paramter groupby was called with.

        Returns
        -------
        Categorical
            If sort=False, the new categories are set to the order of
            appearance in codes (unless ordered=True, in which case the
            original order is preserved), followed by any unrepresented
            categories in the original order.
        """

        # Already sorted according to self.categories; all is fine
        if sort:
            return self

        # sort=False should order groups in as-encountered order (GH-8868)
        cat = self.unique()

        # But for groupby to work, all categories should be present,
        # including those missing from the data (GH-13179), which .unique()
        # above dropped
        cat.add_categories(
            self.categories[~self.categories.isin(cat.categories)],
            inplace=True)

        return self.reorder_categories(cat.categories)