Python errors.UnsortedIndexError方法代码示例

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import UnsortedIndexError [as 别名]
def test_unsortedindex():
    # GH 11897
    mi = pd.MultiIndex.from_tuples([('z', 'a'), ('x', 'a'), ('y', 'b'),
                                    ('x', 'b'), ('y', 'a'), ('z', 'b')],
                                   names=['one', 'two'])
    df = pd.DataFrame([[i, 10 * i] for i in lrange(6)], index=mi,
                      columns=['one', 'two'])

    # GH 16734: not sorted, but no real slicing
    result = df.loc(axis=0)['z', 'a']
    expected = df.iloc[0]
    tm.assert_series_equal(result, expected)

    with pytest.raises(UnsortedIndexError):
        df.loc(axis=0)['z', slice('a')]
    df.sort_index(inplace=True)
    assert len(df.loc(axis=0)['z', :]) == 2

    with pytest.raises(KeyError):
        df.loc(axis=0)['q', :] 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import UnsortedIndexError [as 别名]
def test_unsortedindex_doc_examples():
    # http://pandas.pydata.org/pandas-docs/stable/advanced.html#sorting-a-multiindex  # noqa
    dfm = DataFrame({'jim': [0, 0, 1, 1],
                     'joe': ['x', 'x', 'z', 'y'],
                     'jolie': np.random.rand(4)})

    dfm = dfm.set_index(['jim', 'joe'])
    with tm.assert_produces_warning(PerformanceWarning):
        dfm.loc[(1, 'z')]

    with pytest.raises(UnsortedIndexError):
        dfm.loc[(0, 'y'):(1, 'z')]

    assert not dfm.index.is_lexsorted()
    assert dfm.index.lexsort_depth == 1

    # sort it
    dfm = dfm.sort_index()
    dfm.loc[(1, 'z')]
    dfm.loc[(0, 'y'):(1, 'z')]

    assert dfm.index.is_lexsorted()
    assert dfm.index.lexsort_depth == 2 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import UnsortedIndexError [as 别名]
def test_unsortedindex(self):
        # GH 11897
        mi = pd.MultiIndex.from_tuples([('z', 'a'), ('x', 'a'), ('y', 'b'),
                                        ('x', 'b'), ('y', 'a'), ('z', 'b')],
                                       names=['one', 'two'])
        df = pd.DataFrame([[i, 10 * i] for i in lrange(6)], index=mi,
                          columns=['one', 'two'])

        # GH 16734: not sorted, but no real slicing
        result = df.loc(axis=0)['z', 'a']
        expected = df.iloc[0]
        tm.assert_series_equal(result, expected)

        with pytest.raises(UnsortedIndexError):
            df.loc(axis=0)['z', slice('a')]
        df.sort_index(inplace=True)
        assert len(df.loc(axis=0)['z', :]) == 2

        with pytest.raises(KeyError):
            df.loc(axis=0)['q', :] 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import UnsortedIndexError [as 别名]
def test_unsortedindex_doc_examples(self):
        # http://pandas.pydata.org/pandas-docs/stable/advanced.html#sorting-a-multiindex  # noqa
        dfm = DataFrame({'jim': [0, 0, 1, 1],
                         'joe': ['x', 'x', 'z', 'y'],
                         'jolie': np.random.rand(4)})

        dfm = dfm.set_index(['jim', 'joe'])
        with tm.assert_produces_warning(PerformanceWarning):
            dfm.loc[(1, 'z')]

        with pytest.raises(UnsortedIndexError):
            dfm.loc[(0, 'y'):(1, 'z')]

        assert not dfm.index.is_lexsorted()
        assert dfm.index.lexsort_depth == 1

        # sort it
        dfm = dfm.sort_index()
        dfm.loc[(1, 'z')]
        dfm.loc[(0, 'y'):(1, 'z')]

        assert dfm.index.is_lexsorted()
        assert dfm.index.lexsort_depth == 2 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import UnsortedIndexError [as 别名]
def _partial_tup_index(self, tup, side='left'):
        if len(tup) > self.lexsort_depth:
            raise UnsortedIndexError(
                'Key length (%d) was greater than MultiIndex'
                ' lexsort depth (%d)' %
                (len(tup), self.lexsort_depth))

        n = len(tup)
        start, end = 0, len(self)
        zipped = zip(tup, self.levels, self.codes)
        for k, (lab, lev, labs) in enumerate(zipped):
            section = labs[start:end]

            if lab not in lev:
                if not lev.is_type_compatible(lib.infer_dtype([lab],
                                                              skipna=False)):
                    raise TypeError('Level type mismatch: %s' % lab)

                # short circuit
                loc = lev.searchsorted(lab, side=side)
                if side == 'right' and loc >= 0:
                    loc -= 1
                return start + section.searchsorted(loc, side=side)

            idx = lev.get_loc(lab)
            if k < n - 1:
                end = start + section.searchsorted(idx, side='right')
                start = start + section.searchsorted(idx, side='left')
            else:
                return start + section.searchsorted(idx, side=side) 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import UnsortedIndexError [as 别名]
def _partial_tup_index(self, tup, side='left'):
        if len(tup) > self.lexsort_depth:
            raise UnsortedIndexError(
                'Key length (%d) was greater than MultiIndex'
                ' lexsort depth (%d)' %
                (len(tup), self.lexsort_depth))

        n = len(tup)
        start, end = 0, len(self)
        zipped = zip(tup, self.levels, self.labels)
        for k, (lab, lev, labs) in enumerate(zipped):
            section = labs[start:end]

            if lab not in lev:
                if not lev.is_type_compatible(lib.infer_dtype([lab])):
                    raise TypeError('Level type mismatch: %s' % lab)

                # short circuit
                loc = lev.searchsorted(lab, side=side)
                if side == 'right' and loc >= 0:
                    loc -= 1
                return start + section.searchsorted(loc, side=side)

            idx = lev.get_loc(lab)
            if k < n - 1:
                end = start + section.searchsorted(idx, side='right')
                start = start + section.searchsorted(idx, side='left')
            else:
                return start + section.searchsorted(idx, side=side) 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import UnsortedIndexError [as 别名]
def test_per_axis_per_level_doc_examples(self):

        # test index maker
        idx = pd.IndexSlice

        # from indexing.rst / advanced
        index = MultiIndex.from_product([_mklbl('A', 4), _mklbl('B', 2),
                                         _mklbl('C', 4), _mklbl('D', 2)])
        columns = MultiIndex.from_tuples([('a', 'foo'), ('a', 'bar'),
                                          ('b', 'foo'), ('b', 'bah')],
                                         names=['lvl0', 'lvl1'])
        df = DataFrame(np.arange(len(index) * len(columns), dtype='int64')
                       .reshape((len(index), len(columns))),
                       index=index, columns=columns)
        result = df.loc[(slice('A1', 'A3'), slice(None), ['C1', 'C3']), :]
        expected = df.loc[[tuple([a, b, c, d])
                           for a, b, c, d in df.index.values
                           if (a == 'A1' or a == 'A2' or a == 'A3') and (
                               c == 'C1' or c == 'C3')]]
        tm.assert_frame_equal(result, expected)
        result = df.loc[idx['A1':'A3', :, ['C1', 'C3']], :]
        tm.assert_frame_equal(result, expected)

        result = df.loc[(slice(None), slice(None), ['C1', 'C3']), :]
        expected = df.loc[[tuple([a, b, c, d])
                           for a, b, c, d in df.index.values
                           if (c == 'C1' or c == 'C3')]]
        tm.assert_frame_equal(result, expected)
        result = df.loc[idx[:, :, ['C1', 'C3']], :]
        tm.assert_frame_equal(result, expected)

        # not sorted
        with pytest.raises(UnsortedIndexError):
            df.loc['A1', ('a', slice('foo'))]

        # GH 16734: not sorted, but no real slicing
        tm.assert_frame_equal(df.loc['A1', (slice(None), 'foo')],
                              df.loc['A1'].iloc[:, [0, 2]])

        df = df.sort_index(axis=1)

        # slicing
        df.loc['A1', (slice(None), 'foo')]
        df.loc[(slice(None), slice(None), ['C1', 'C3']), (slice(None), 'foo')]

        # setitem
        df.loc(axis=0)[:, :, ['C1', 'C3']] = -10 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import UnsortedIndexError [as 别名]
def test_per_axis_per_level_doc_examples(self):

        # test index maker
        idx = pd.IndexSlice

        # from indexing.rst / advanced
        index = MultiIndex.from_product([_mklbl('A', 4), _mklbl('B', 2),
                                         _mklbl('C', 4), _mklbl('D', 2)])
        columns = MultiIndex.from_tuples([('a', 'foo'), ('a', 'bar'),
                                          ('b', 'foo'), ('b', 'bah')],
                                         names=['lvl0', 'lvl1'])
        df = DataFrame(np.arange(len(index) * len(columns), dtype='int64')
                       .reshape((len(index), len(columns))),
                       index=index, columns=columns)
        result = df.loc[(slice('A1', 'A3'), slice(None), ['C1', 'C3']), :]
        expected = df.loc[[tuple([a, b, c, d])
                           for a, b, c, d in df.index.values
                           if (a == 'A1' or a == 'A2' or a == 'A3') and (
                               c == 'C1' or c == 'C3')]]
        tm.assert_frame_equal(result, expected)
        result = df.loc[idx['A1':'A3', :, ['C1', 'C3']], :]
        tm.assert_frame_equal(result, expected)

        result = df.loc[(slice(None), slice(None), ['C1', 'C3']), :]
        expected = df.loc[[tuple([a, b, c, d])
                           for a, b, c, d in df.index.values
                           if (c == 'C1' or c == 'C3')]]
        tm.assert_frame_equal(result, expected)
        result = df.loc[idx[:, :, ['C1', 'C3']], :]
        tm.assert_frame_equal(result, expected)

        # not sorted
        def f():
            df.loc['A1', ('a', slice('foo'))]

        pytest.raises(UnsortedIndexError, f)

        # GH 16734: not sorted, but no real slicing
        tm.assert_frame_equal(df.loc['A1', (slice(None), 'foo')],
                              df.loc['A1'].iloc[:, [0, 2]])

        df = df.sort_index(axis=1)

        # slicing
        df.loc['A1', (slice(None), 'foo')]
        df.loc[(slice(None), slice(None), ['C1', 'C3']), (slice(None), 'foo')]

        # setitem
        df.loc(axis=0)[:, :, ['C1', 'C3']] = -10