Python pandas.core.algorithms.unique1d() Examples

def test_nunique(self, float_frame_with_na, float_frame,
                     float_string_frame):
        f = lambda s: len(algorithms.unique1d(s.dropna()))
        assert_stat_op_calc('nunique', f, float_frame_with_na,
                            has_skipna=False, check_dtype=False,
                            check_dates=True)
        assert_stat_op_api('nunique', float_frame, float_string_frame)

        df = DataFrame({'A': [1, 1, 1],
                        'B': [1, 2, 3],
                        'C': [1, np.nan, 3]})
        tm.assert_series_equal(df.nunique(), Series({'A': 1, 'B': 3, 'C': 2}))
        tm.assert_series_equal(df.nunique(dropna=False),
                               Series({'A': 1, 'B': 3, 'C': 3}))
        tm.assert_series_equal(df.nunique(axis=1), Series({0: 1, 1: 2, 2: 2}))
        tm.assert_series_equal(df.nunique(axis=1, dropna=False),
                               Series({0: 1, 1: 3, 2: 2})) 

def test_nunique(self, float_frame_with_na, float_frame,
                     float_string_frame):
        f = lambda s: len(algorithms.unique1d(s.dropna()))
        assert_stat_op_calc('nunique', f, float_frame_with_na,
                            has_skipna=False, check_dtype=False,
                            check_dates=True)
        assert_stat_op_api('nunique', float_frame, float_string_frame)

        df = DataFrame({'A': [1, 1, 1],
                        'B': [1, 2, 3],
                        'C': [1, np.nan, 3]})
        tm.assert_series_equal(df.nunique(), Series({'A': 1, 'B': 3, 'C': 2}))
        tm.assert_series_equal(df.nunique(dropna=False),
                               Series({'A': 1, 'B': 3, 'C': 3}))
        tm.assert_series_equal(df.nunique(axis=1), Series({0: 1, 1: 2, 2: 2}))
        tm.assert_series_equal(df.nunique(axis=1, dropna=False),
                               Series({0: 1, 1: 3, 2: 2})) 

def unique(self):
        values = self._values

        if hasattr(values, 'unique'):

            result = values.unique()
        else:
            from pandas.core.algorithms import unique1d
            result = unique1d(values)

        return result 

def test_nunique(self):
        f = lambda s: len(algorithms.unique1d(s.dropna()))
        self._check_stat_op('nunique', f, has_skipna=False,
                            check_dtype=False, check_dates=True)

        df = DataFrame({'A': [1, 1, 1],
                        'B': [1, 2, 3],
                        'C': [1, np.nan, 3]})
        tm.assert_series_equal(df.nunique(), Series({'A': 1, 'B': 3, 'C': 2}))
        tm.assert_series_equal(df.nunique(dropna=False),
                               Series({'A': 1, 'B': 3, 'C': 3}))
        tm.assert_series_equal(df.nunique(axis=1), Series({0: 1, 1: 2, 2: 2}))
        tm.assert_series_equal(df.nunique(axis=1, dropna=False),
                               Series({0: 1, 1: 3, 2: 2})) 

def unique(self):
        values = self._values

        if hasattr(values, 'unique'):
            result = values.unique()
        else:
            from pandas.core.algorithms import unique1d
            result = unique1d(values)

        return result 

def test_nunique(self):
        f = lambda s: len(algorithms.unique1d(s.dropna()))
        self._check_stat_op('nunique', f, has_skipna=False,
                            check_dtype=False, check_dates=True)

        df = DataFrame({'A': [1, 1, 1],
                        'B': [1, 2, 3],
                        'C': [1, np.nan, 3]})
        tm.assert_series_equal(df.nunique(), Series({'A': 1, 'B': 3, 'C': 2}))
        tm.assert_series_equal(df.nunique(dropna=False),
                               Series({'A': 1, 'B': 3, 'C': 3}))
        tm.assert_series_equal(df.nunique(axis=1), Series({0: 1, 1: 2, 2: 2}))
        tm.assert_series_equal(df.nunique(axis=1, dropna=False),
                               Series({0: 1, 1: 3, 2: 2})) 

def unique(self):
        values = self._values

        if hasattr(values, 'unique'):
            result = values.unique()
        else:
            from pandas.core.algorithms import unique1d
            result = unique1d(values)

        return result 

def unique(self, level=None):
        # override the Index.unique method for performance GH#23083
        if level is not None:
            # this should never occur, but is retained to make the signature
            # match Index.unique
            self._validate_index_level(level)

        values = self._ndarray_values
        result = unique1d(values)
        return self._shallow_copy(result) 

def unique(self):
        values = self._values

        if hasattr(values, 'unique'):

            result = values.unique()
        else:
            from pandas.core.algorithms import unique1d
            result = unique1d(values)

        return result 

def test_nunique(self):
        f = lambda s: len(algorithms.unique1d(s.dropna()))
        self._check_stat_op('nunique', f, has_skipna=False,
                            check_dtype=False, check_dates=True)

        df = DataFrame({'A': [1, 1, 1],
                        'B': [1, 2, 3],
                        'C': [1, np.nan, 3]})
        tm.assert_series_equal(df.nunique(), Series({'A': 1, 'B': 3, 'C': 2}))
        tm.assert_series_equal(df.nunique(dropna=False),
                               Series({'A': 1, 'B': 3, 'C': 3}))
        tm.assert_series_equal(df.nunique(axis=1), Series({0: 1, 1: 2, 2: 2}))
        tm.assert_series_equal(df.nunique(axis=1, dropna=False),
                               Series({0: 1, 1: 3, 2: 2})) 

def unique(self):
        values = self._values

        if hasattr(values, 'unique'):

            result = values.unique()
        else:
            from pandas.core.algorithms import unique1d
            result = unique1d(values)

        return result 

def unique(self, level=None):
        # override the Index.unique method for performance GH#23083
        if level is not None:
            # this should never occur, but is retained to make the signature
            # match Index.unique
            self._validate_index_level(level)

        values = self._ndarray_values
        result = unique1d(values)
        return self._shallow_copy(result) 

def _concat_objects(self, keys, values, not_indexed_same=False):
        from pandas.core.reshape.concat import concat

        def reset_identity(values):
            # reset the identities of the components
            # of the values to prevent aliasing
            for v in com._not_none(*values):
                ax = v._get_axis(self.axis)
                ax._reset_identity()
            return values

        if not not_indexed_same:
            result = concat(values, axis=self.axis)
            ax = self._selected_obj._get_axis(self.axis)

            if isinstance(result, Series):
                result = result.reindex(ax)
            else:

                # this is a very unfortunate situation
                # we have a multi-index that is NOT lexsorted
                # and we have a result which is duplicated
                # we can't reindex, so we resort to this
                # GH 14776
                if isinstance(ax, MultiIndex) and not ax.is_unique:
                    indexer = algorithms.unique1d(
                        result.index.get_indexer_for(ax.values))
                    result = result.take(indexer, axis=self.axis)
                else:
                    result = result.reindex(ax, axis=self.axis)

        elif self.group_keys:

            values = reset_identity(values)
            if self.as_index:

                # possible MI return case
                group_keys = keys
                group_levels = self.grouper.levels
                group_names = self.grouper.names

                result = concat(values, axis=self.axis, keys=group_keys,
                                levels=group_levels, names=group_names,
                                sort=False)
            else:

                # GH5610, returns a MI, with the first level being a
                # range index
                keys = list(range(len(values)))
                result = concat(values, axis=self.axis, keys=keys)
        else:
            values = reset_identity(values)
            result = concat(values, axis=self.axis)

        if (isinstance(result, Series) and
                getattr(self, '_selection_name', None) is not None):

            result.name = self._selection_name

        return result 

def unique(self):
        """
        Return the ``Categorical`` which ``categories`` and ``codes`` are
        unique. Unused categories are NOT returned.

        - unordered category: values and categories are sorted by appearance
          order.
        - ordered category: values are sorted by appearance order, categories
          keeps existing order.

        Returns
        -------
        unique values : ``Categorical``

        Examples
        --------
        An unordered Categorical will return categories in the
        order of appearance.

        >>> pd.Categorical(list('baabc'))
        [b, a, c]
        Categories (3, object): [b, a, c]

        >>> pd.Categorical(list('baabc'), categories=list('abc'))
        [b, a, c]
        Categories (3, object): [b, a, c]

        An ordered Categorical preserves the category ordering.

        >>> pd.Categorical(list('baabc'),
        ...                categories=list('abc'),
        ...                ordered=True)
        [b, a, c]
        Categories (3, object): [a < b < c]

        See Also
        --------
        unique
        CategoricalIndex.unique
        Series.unique

        """

        # unlike np.unique, unique1d does not sort
        unique_codes = unique1d(self.codes)
        cat = self.copy()

        # keep nan in codes
        cat._codes = unique_codes

        # exclude nan from indexer for categories
        take_codes = unique_codes[unique_codes != -1]
        if self.ordered:
            take_codes = np.sort(take_codes)
        return cat.set_categories(cat.categories.take(take_codes)) 

def unique(self):
        """
        Return the ``Categorical`` which ``categories`` and ``codes`` are
        unique. Unused categories are NOT returned.

        - unordered category: values and categories are sorted by appearance
          order.
        - ordered category: values are sorted by appearance order, categories
          keeps existing order.

        Returns
        -------
        unique values : ``Categorical``

        Examples
        --------
        An unordered Categorical will return categories in the
        order of appearance.

        >>> pd.Categorical(list('baabc'))
        [b, a, c]
        Categories (3, object): [b, a, c]

        >>> pd.Categorical(list('baabc'), categories=list('abc'))
        [b, a, c]
        Categories (3, object): [b, a, c]

        An ordered Categorical preserves the category ordering.

        >>> pd.Categorical(list('baabc'),
        ...                categories=list('abc'),
        ...                ordered=True)
        [b, a, c]
        Categories (3, object): [a < b < c]

        See Also
        --------
        unique
        CategoricalIndex.unique
        Series.unique

        """

        # unlike np.unique, unique1d does not sort
        unique_codes = unique1d(self.codes)
        cat = self.copy()

        # keep nan in codes
        cat._codes = unique_codes

        # exclude nan from indexer for categories
        take_codes = unique_codes[unique_codes != -1]
        if self.ordered:
            take_codes = np.sort(take_codes)
        return cat.set_categories(cat.categories.take(take_codes)) 

def _concat_objects(self, keys, values, not_indexed_same=False):
        from pandas.core.reshape.concat import concat

        def reset_identity(values):
            # reset the identities of the components
            # of the values to prevent aliasing
            for v in com._not_none(*values):
                ax = v._get_axis(self.axis)
                ax._reset_identity()
            return values

        if not not_indexed_same:
            result = concat(values, axis=self.axis)
            ax = self._selected_obj._get_axis(self.axis)

            if isinstance(result, Series):
                result = result.reindex(ax)
            else:

                # this is a very unfortunate situation
                # we have a multi-index that is NOT lexsorted
                # and we have a result which is duplicated
                # we can't reindex, so we resort to this
                # GH 14776
                if isinstance(ax, MultiIndex) and not ax.is_unique:
                    indexer = algorithms.unique1d(
                        result.index.get_indexer_for(ax.values))
                    result = result.take(indexer, axis=self.axis)
                else:
                    result = result.reindex(ax, axis=self.axis)

        elif self.group_keys:

            values = reset_identity(values)
            if self.as_index:

                # possible MI return case
                group_keys = keys
                group_levels = self.grouper.levels
                group_names = self.grouper.names

                result = concat(values, axis=self.axis, keys=group_keys,
                                levels=group_levels, names=group_names,
                                sort=False)
            else:

                # GH5610, returns a MI, with the first level being a
                # range index
                keys = list(range(len(values)))
                result = concat(values, axis=self.axis, keys=keys)
        else:
            values = reset_identity(values)
            result = concat(values, axis=self.axis)

        if (isinstance(result, Series) and
                getattr(self, '_selection_name', None) is not None):

            result.name = self._selection_name

        return result 

def intersection(self, other):
        """
        Form the intersection of two Index objects.

        This returns a new Index with elements common to the index and `other`,
        preserving the order of the calling index.

        Parameters
        ----------
        other : Index or array-like

        Returns
        -------
        intersection : Index

        Examples
        --------

        >>> idx1 = pd.Index([1, 2, 3, 4])
        >>> idx2 = pd.Index([3, 4, 5, 6])
        >>> idx1.intersection(idx2)
        Int64Index([3, 4], dtype='int64')

        """
        self._assert_can_do_setop(other)
        other = _ensure_index(other)

        if self.equals(other):
            return self._get_consensus_name(other)

        if not is_dtype_equal(self.dtype, other.dtype):
            this = self.astype('O')
            other = other.astype('O')
            return this.intersection(other)

        if self.is_monotonic and other.is_monotonic:
            try:
                result = self._inner_indexer(self._values, other._values)[0]
                return self._wrap_union_result(other, result)
            except TypeError:
                pass

        try:
            indexer = Index(other._values).get_indexer(self._values)
            indexer = indexer.take((indexer != -1).nonzero()[0])
        except Exception:
            # duplicates
            indexer = algos.unique1d(
                Index(other._values).get_indexer_non_unique(self._values)[0])
            indexer = indexer[indexer != -1]

        taken = other.take(indexer)
        if self.name != other.name:
            taken.name = None
        return taken 

def _concat_objects(self, keys, values, not_indexed_same=False):
        from pandas.core.reshape.concat import concat

        def reset_identity(values):
            # reset the identities of the components
            # of the values to prevent aliasing
            for v in com._not_none(*values):
                ax = v._get_axis(self.axis)
                ax._reset_identity()
            return values

        if not not_indexed_same:
            result = concat(values, axis=self.axis)
            ax = self._selected_obj._get_axis(self.axis)

            if isinstance(result, Series):
                result = result.reindex(ax)
            else:

                # this is a very unfortunate situation
                # we have a multi-index that is NOT lexsorted
                # and we have a result which is duplicated
                # we can't reindex, so we resort to this
                # GH 14776
                if isinstance(ax, MultiIndex) and not ax.is_unique:
                    indexer = algorithms.unique1d(
                        result.index.get_indexer_for(ax.values))
                    result = result.take(indexer, axis=self.axis)
                else:
                    result = result.reindex(ax, axis=self.axis)

        elif self.group_keys:

            values = reset_identity(values)
            if self.as_index:

                # possible MI return case
                group_keys = keys
                group_levels = self.grouper.levels
                group_names = self.grouper.names

                result = concat(values, axis=self.axis, keys=group_keys,
                                levels=group_levels, names=group_names,
                                sort=False)
            else:

                # GH5610, returns a MI, with the first level being a
                # range index
                keys = list(range(len(values)))
                result = concat(values, axis=self.axis, keys=keys)
        else:
            values = reset_identity(values)
            result = concat(values, axis=self.axis)

        if (isinstance(result, Series) and
                getattr(self, '_selection_name', None) is not None):

            result.name = self._selection_name

        return result 

def _concat_objects(self, keys, values, not_indexed_same=False):
        from pandas.core.reshape.concat import concat

        def reset_identity(values):
            # reset the identities of the components
            # of the values to prevent aliasing
            for v in _not_none(*values):
                ax = v._get_axis(self.axis)
                ax._reset_identity()
            return values

        if not not_indexed_same:
            result = concat(values, axis=self.axis)
            ax = self._selected_obj._get_axis(self.axis)

            if isinstance(result, Series):
                result = result.reindex(ax)
            else:

                # this is a very unfortunate situation
                # we have a multi-index that is NOT lexsorted
                # and we have a result which is duplicated
                # we can't reindex, so we resort to this
                # GH 14776
                if isinstance(ax, MultiIndex) and not ax.is_unique:
                    indexer = algorithms.unique1d(
                        result.index.get_indexer_for(ax.values))
                    result = result.take(indexer, axis=self.axis)
                else:
                    result = result.reindex(ax, axis=self.axis)

        elif self.group_keys:

            values = reset_identity(values)
            if self.as_index:

                # possible MI return case
                group_keys = keys
                group_levels = self.grouper.levels
                group_names = self.grouper.names

                result = concat(values, axis=self.axis, keys=group_keys,
                                levels=group_levels, names=group_names)
            else:

                # GH5610, returns a MI, with the first level being a
                # range index
                keys = list(range(len(values)))
                result = concat(values, axis=self.axis, keys=keys)
        else:
            values = reset_identity(values)
            result = concat(values, axis=self.axis)

        if (isinstance(result, Series) and
                getattr(self, '_selection_name', None) is not None):

            result.name = self._selection_name

        return result 

def unique(self):
        """
        Return the ``Categorical`` which ``categories`` and ``codes`` are
        unique. Unused categories are NOT returned.

        - unordered category: values and categories are sorted by appearance
          order.
        - ordered category: values are sorted by appearance order, categories
          keeps existing order.

        Returns
        -------
        unique values : ``Categorical``

        Examples
        --------
        An unordered Categorical will return categories in the
        order of appearance.

        >>> pd.Categorical(list('baabc'))
        [b, a, c]
        Categories (3, object): [b, a, c]

        >>> pd.Categorical(list('baabc'), categories=list('abc'))
        [b, a, c]
        Categories (3, object): [b, a, c]

        An ordered Categorical preserves the category ordering.

        >>> pd.Categorical(list('baabc'),
        ...                categories=list('abc'),
        ...                ordered=True)
        [b, a, c]
        Categories (3, object): [a < b < c]

        See Also
        --------
        unique
        CategoricalIndex.unique
        Series.unique

        """

        # unlike np.unique, unique1d does not sort
        unique_codes = unique1d(self.codes)
        cat = self.copy()

        # keep nan in codes
        cat._codes = unique_codes

        # exclude nan from indexer for categories
        take_codes = unique_codes[unique_codes != -1]
        if self.ordered:
            take_codes = sorted(take_codes)
        return cat.set_categories(cat.categories.take(take_codes)) 

def intersection(self, other):
        """
        Form the intersection of two Index objects.

        This returns a new Index with elements common to the index and `other`,
        preserving the order of the calling index.

        Parameters
        ----------
        other : Index or array-like

        Returns
        -------
        intersection : Index

        Examples
        --------

        >>> idx1 = pd.Index([1, 2, 3, 4])
        >>> idx2 = pd.Index([3, 4, 5, 6])
        >>> idx1.intersection(idx2)
        Int64Index([3, 4], dtype='int64')

        """
        self._assert_can_do_setop(other)
        other = _ensure_index(other)

        if self.equals(other):
            return self._get_consensus_name(other)

        if not is_dtype_equal(self.dtype, other.dtype):
            this = self.astype('O')
            other = other.astype('O')
            return this.intersection(other)

        if self.is_monotonic and other.is_monotonic:
            try:
                result = self._inner_indexer(self._values, other._values)[0]
                return self._wrap_union_result(other, result)
            except TypeError:
                pass

        try:
            indexer = Index(other._values).get_indexer(self._values)
            indexer = indexer.take((indexer != -1).nonzero()[0])
        except:
            # duplicates
            indexer = algos.unique1d(
                Index(other._values).get_indexer_non_unique(self._values)[0])
            indexer = indexer[indexer != -1]

        taken = other.take(indexer)
        if self.name != other.name:
            taken.name = None
        return taken 

def _concat_objects(self, keys, values, not_indexed_same=False):
        from pandas.core.reshape.concat import concat

        def reset_identity(values):
            # reset the identities of the components
            # of the values to prevent aliasing
            for v in _not_none(*values):
                ax = v._get_axis(self.axis)
                ax._reset_identity()
            return values

        if not not_indexed_same:
            result = concat(values, axis=self.axis)
            ax = self._selected_obj._get_axis(self.axis)

            if isinstance(result, Series):
                result = result.reindex(ax)
            else:

                # this is a very unfortunate situation
                # we have a multi-index that is NOT lexsorted
                # and we have a result which is duplicated
                # we can't reindex, so we resort to this
                # GH 14776
                if isinstance(ax, MultiIndex) and not ax.is_unique:
                    indexer = algorithms.unique1d(
                        result.index.get_indexer_for(ax.values))
                    result = result.take(indexer, axis=self.axis)
                else:
                    result = result.reindex(ax, axis=self.axis)

        elif self.group_keys:

            values = reset_identity(values)
            if self.as_index:

                # possible MI return case
                group_keys = keys
                group_levels = self.grouper.levels
                group_names = self.grouper.names

                result = concat(values, axis=self.axis, keys=group_keys,
                                levels=group_levels, names=group_names)
            else:

                # GH5610, returns a MI, with the first level being a
                # range index
                keys = list(range(len(values)))
                result = concat(values, axis=self.axis, keys=keys)
        else:
            values = reset_identity(values)
            result = concat(values, axis=self.axis)

        if (isinstance(result, Series) and
                getattr(self, '_selection_name', None) is not None):

            result.name = self._selection_name

        return result 

def unique(self):
        """
        Return the ``Categorical`` which ``categories`` and ``codes`` are
        unique. Unused categories are NOT returned.

        - unordered category: values and categories are sorted by appearance
          order.
        - ordered category: values are sorted by appearance order, categories
          keeps existing order.

        Returns
        -------
        unique values : ``Categorical``

        Examples
        --------
        An unordered Categorical will return categories in the
        order of appearance.

        >>> pd.Categorical(list('baabc'))
        [b, a, c]
        Categories (3, object): [b, a, c]

        >>> pd.Categorical(list('baabc'), categories=list('abc'))
        [b, a, c]
        Categories (3, object): [b, a, c]

        An ordered Categorical preserves the category ordering.

        >>> pd.Categorical(list('baabc'),
        ...                categories=list('abc'),
        ...                ordered=True)
        [b, a, c]
        Categories (3, object): [a < b < c]

        See Also
        --------
        unique
        CategoricalIndex.unique
        Series.unique

        """

        # unlike np.unique, unique1d does not sort
        unique_codes = unique1d(self.codes)
        cat = self.copy()

        # keep nan in codes
        cat._codes = unique_codes

        # exclude nan from indexer for categories
        take_codes = unique_codes[unique_codes != -1]
        if self.ordered:
            take_codes = sorted(take_codes)
        return cat.set_categories(cat.categories.take(take_codes)) 

def unique(self):
        """
        Return the ``Categorical`` which ``categories`` and ``codes`` are
        unique. Unused categories are NOT returned.

        - unordered category: values and categories are sorted by appearance
          order.
        - ordered category: values are sorted by appearance order, categories
          keeps existing order.

        Returns
        -------
        unique values : ``Categorical``

        Examples
        --------
        An unordered Categorical will return categories in the
        order of appearance.

        >>> pd.Categorical(list('baabc'))
        [b, a, c]
        Categories (3, object): [b, a, c]

        >>> pd.Categorical(list('baabc'), categories=list('abc'))
        [b, a, c]
        Categories (3, object): [b, a, c]

        An ordered Categorical preserves the category ordering.

        >>> pd.Categorical(list('baabc'),
        ...                categories=list('abc'),
        ...                ordered=True)
        [b, a, c]
        Categories (3, object): [a < b < c]

        See Also
        --------
        unique
        CategoricalIndex.unique
        Series.unique

        """

        # unlike np.unique, unique1d does not sort
        unique_codes = unique1d(self.codes)
        cat = self.copy()

        # keep nan in codes
        cat._codes = unique_codes

        # exclude nan from indexer for categories
        take_codes = unique_codes[unique_codes != -1]
        if self.ordered:
            take_codes = np.sort(take_codes)
        return cat.set_categories(cat.categories.take(take_codes))