Python Series.unique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 unique [as 别名]
def nunique(self, dropna=True):
        """
        Return number of unique elements in the object.

        Excludes NA values by default.

        Parameters
        ----------
        dropna : boolean, default True
            Don't include NaN in the count.

        Returns
        -------
        nunique : int
        """
        uniqs = self.unique()
        n = len(uniqs)
        if dropna and isna(uniqs).any():
            n -= 1
        return n 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import unique [as 别名]
def factorize(self, sort=False, na_sentinel=-1):
        """
        Encode the object as an enumerated type or categorical variable

        Parameters
        ----------
        sort : boolean, default False
            Sort by values
        na_sentinel: int, default -1
            Value to mark "not found"

        Returns
        -------
        labels : the indexer to the original array
        uniques : the unique Index
        """
        from pandas.core.algorithms import factorize
        return factorize(self, sort=sort, na_sentinel=na_sentinel) 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import unique [as 别名]
def from_array(cls, data, **kwargs):
        """
        .. deprecated:: 0.19.0
           Use ``Categorical`` instead.

        Make a Categorical type from a single array-like object.

        For internal compatibility with numpy arrays.

        Parameters
        ----------
        data : array-like
            Can be an Index or array-like. The categories are assumed to be
            the unique values of `data`.
        """
        warn("Categorical.from_array is deprecated, use Categorical instead",
             FutureWarning, stacklevel=2)
        return cls(data, **kwargs) 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import unique [as 别名]
def categories(self):
        """
        The categories of this categorical.

        Setting assigns new values to each category (effectively a rename of
        each individual category).

        The assigned value has to be a list-like object. All items must be
        unique and the number of items in the new categories must be the same
        as the number of items in the old categories.

        Assigning to `categories` is a inplace operation!

        Raises
        ------
        ValueError
            If the new categories do not validate as categories or if the
            number of new categories is unequal the number of old categories

        See Also
        --------
        rename_categories
        reorder_categories
        add_categories
        remove_categories
        remove_unused_categories
        set_categories
        """
        return self.dtype.categories 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import unique [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 unique [as 别名]
def is_unique(self):
        """
        Return if the index has unique values.
        """
        return self._engine.is_unique 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import unique [as 别名]
def unique(self, level=None):
        if level is not None:
            self._validate_index_level(level)
        result = super(Index, self).unique()
        return self._shallow_copy(result) 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import unique [as 别名]
def _get_unique_index(self, dropna=False):
        """
        Returns an index containing unique values.

        Parameters
        ----------
        dropna : bool
            If True, NaN values are dropped.

        Returns
        -------
        uniques : index
        """
        if self.is_unique and not dropna:
            return self

        values = self.values

        if not self.is_unique:
            values = self.unique()

        if dropna:
            try:
                if self.hasnans:
                    values = values[~isna(values)]
            except NotImplementedError:
                pass

        return self._shallow_copy(values)

    # --------------------------------------------------------------------
    # Arithmetic & Logical Methods 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import unique [as 别名]
def get_indexer_for(self, target, **kwargs):
        """
        Guaranteed return of an indexer even when non-unique.

        This dispatches to get_indexer or get_indexer_nonunique
        as appropriate.
        """
        if self.is_unique:
            return self.get_indexer(target, **kwargs)
        indexer, _ = self.get_indexer_non_unique(target, **kwargs)
        return indexer 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import unique [as 别名]
def categories(self):
        """The categories of this categorical.

        Setting assigns new values to each category (effectively a rename of
        each individual category).

        The assigned value has to be a list-like object. All items must be
        unique and the number of items in the new categories must be the same
        as the number of items in the old categories.

        Assigning to `categories` is a inplace operation!

        Raises
        ------
        ValueError
            If the new categories do not validate as categories or if the
            number of new categories is unequal the number of old categories

        See also
        --------
        rename_categories
        reorder_categories
        add_categories
        remove_categories
        remove_unused_categories
        set_categories
        """
        return self.dtype.categories 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import unique [as 别名]
def from_codes(cls, codes, categories, ordered=False):
        """
        Make a Categorical type from codes and categories arrays.

        This constructor is useful if you already have codes and categories and
        so do not need the (computation intensive) factorization step, which is
        usually done on the constructor.

        If your data does not follow this convention, please use the normal
        constructor.

        Parameters
        ----------
        codes : array-like, integers
            An integer array, where each integer points to a category in
            categories or -1 for NaN
        categories : index-like
            The categories for the categorical. Items need to be unique.
        ordered : boolean, (default False)
            Whether or not this categorical is treated as a ordered
            categorical. If not given, the resulting categorical will be
            unordered.
        """
        try:
            codes = coerce_indexer_dtype(np.asarray(codes), categories)
        except (ValueError, TypeError):
            raise ValueError(
                "codes need to be convertible to an arrays of integers")

        categories = CategoricalDtype.validate_categories(categories)

        if len(codes) and (codes.max() >= len(categories) or codes.min() < -1):
            raise ValueError("codes need to be between -1 and "
                             "len(categories)-1")

        return cls(codes, categories=categories, ordered=ordered,
                   fastpath=True) 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import unique [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 unique [as 别名]
def is_unique(self):
        """ return if the index has unique values """
        return self._engine.is_unique 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import unique [as 别名]
def get_indexer_for(self, target, **kwargs):
        """
        guaranteed return of an indexer even when non-unique
        This dispatches to get_indexer or get_indexer_nonunique as appropriate
        """
        if self.is_unique:
            return self.get_indexer(target, **kwargs)
        indexer, _ = self.get_indexer_non_unique(target, **kwargs)
        return indexer 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import unique [as 别名]
def value_counts(self, normalize=False, sort=True, ascending=False,
                     bins=None, dropna=True):
        """
        Returns object containing counts of unique values.

        The resulting object will be in descending order so that the
        first element is the most frequently-occurring element.
        Excludes NA values by default.

        Parameters
        ----------
        normalize : boolean, default False
            If True then the object returned will contain the relative
            frequencies of the unique values.
        sort : boolean, default True
            Sort by values
        ascending : boolean, default False
            Sort in ascending order
        bins : integer, optional
            Rather than count values, group them into half-open bins,
            a convenience for pd.cut, only works with numeric data
        dropna : boolean, default True
            Don't include counts of NaN.

        Returns
        -------
        counts : Series
        """
        from pandas.core.algorithms import value_counts
        result = value_counts(self, sort=sort, ascending=ascending,
                              normalize=normalize, bins=bins, dropna=dropna)
        return result