Python pandas.CategoricalIndex方法代码示例

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_get_indexer_consistency(self):
        # See GH 16819
        for name, index in self.indices.items():
            if isinstance(index, IntervalIndex):
                continue

            if index.is_unique or isinstance(index, CategoricalIndex):
                indexer = index.get_indexer(index[0:2])
                assert isinstance(indexer, np.ndarray)
                assert indexer.dtype == np.intp
            else:
                e = "Reindexing only valid with uniquely valued Index objects"
                with pytest.raises(InvalidIndexError, match=e):
                    index.get_indexer(index[0:2])

            indexer, _ = index.get_indexer_non_unique(index[0:2])
            assert isinstance(indexer, np.ndarray)
            assert indexer.dtype == np.intp 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_numpy_argsort(self):
        for k, ind in self.indices.items():
            result = np.argsort(ind)
            expected = ind.argsort()
            tm.assert_numpy_array_equal(result, expected)

            # these are the only two types that perform
            # pandas compatibility input validation - the
            # rest already perform separate (or no) such
            # validation via their 'values' attribute as
            # defined in pandas.core.indexes/base.py - they
            # cannot be changed at the moment due to
            # backwards compatibility concerns
            if isinstance(type(ind), (CategoricalIndex, RangeIndex)):
                msg = "the 'axis' parameter is not supported"
                with pytest.raises(ValueError, match=msg):
                    np.argsort(ind, axis=1)

                msg = "the 'kind' parameter is not supported"
                with pytest.raises(ValueError, match=msg):
                    np.argsort(ind, kind='mergesort')

                msg = "the 'order' parameter is not supported"
                with pytest.raises(ValueError, match=msg):
                    np.argsort(ind, order=('a', 'b')) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_astype_category(self, copy, name, ordered):
        # GH 18630
        index = self.create_index()
        if name:
            index = index.rename(name)

        # standard categories
        dtype = CategoricalDtype(ordered=ordered)
        result = index.astype(dtype, copy=copy)
        expected = CategoricalIndex(index.values, name=name, ordered=ordered)
        tm.assert_index_equal(result, expected)

        # non-standard categories
        dtype = CategoricalDtype(index.unique().tolist()[:-1], ordered)
        result = index.astype(dtype, copy=copy)
        expected = CategoricalIndex(index.values, name=name, dtype=dtype)
        tm.assert_index_equal(result, expected)

        if ordered is False:
            # dtype='category' defaults to ordered=False, so only test once
            result = index.astype('category', copy=copy)
            expected = CategoricalIndex(index.values, name=name)
            tm.assert_index_equal(result, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_construction_with_dtype(self):

        # specify dtype
        ci = self.create_index(categories=list('abc'))

        result = Index(np.array(ci), dtype='category')
        tm.assert_index_equal(result, ci, exact=True)

        result = Index(np.array(ci).tolist(), dtype='category')
        tm.assert_index_equal(result, ci, exact=True)

        # these are generally only equal when the categories are reordered
        ci = self.create_index()

        result = Index(
            np.array(ci), dtype='category').reorder_categories(ci.categories)
        tm.assert_index_equal(result, ci, exact=True)

        # make sure indexes are handled
        expected = CategoricalIndex([0, 1, 2], categories=[0, 1, 2],
                                    ordered=True)
        idx = Index(range(3))
        result = CategoricalIndex(idx, categories=idx, ordered=True)
        tm.assert_index_equal(result, expected, exact=True) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_contains(self):

        ci = self.create_index(categories=list('cabdef'))

        assert 'a' in ci
        assert 'z' not in ci
        assert 'e' not in ci
        assert np.nan not in ci

        # assert codes NOT in index
        assert 0 not in ci
        assert 1 not in ci

        ci = CategoricalIndex(
            list('aabbca') + [np.nan], categories=list('cabdef'))
        assert np.nan in ci 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_delete(self):

        ci = self.create_index()
        categories = ci.categories

        result = ci.delete(0)
        expected = CategoricalIndex(list('abbca'), categories=categories)
        tm.assert_index_equal(result, expected, exact=True)

        result = ci.delete(-1)
        expected = CategoricalIndex(list('aabbc'), categories=categories)
        tm.assert_index_equal(result, expected, exact=True)

        with pytest.raises((IndexError, ValueError)):
            # Either depending on NumPy version
            ci.delete(10) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_astype(self):

        ci = self.create_index()
        result = ci.astype(object)
        tm.assert_index_equal(result, Index(np.array(ci)))

        # this IS equal, but not the same class
        assert result.equals(ci)
        assert isinstance(result, Index)
        assert not isinstance(result, CategoricalIndex)

        # interval
        ii = IntervalIndex.from_arrays(left=[-0.001, 2.0],
                                       right=[2, 4],
                                       closed='right')

        ci = CategoricalIndex(Categorical.from_codes(
            [0, 1, -1], categories=ii, ordered=True))

        result = ci.astype('interval')
        expected = ii.take([0, 1, -1])
        tm.assert_index_equal(result, expected)

        result = IntervalIndex(result.values)
        tm.assert_index_equal(result, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_repr_roundtrip(self):

        ci = CategoricalIndex(['a', 'b'], categories=['a', 'b'], ordered=True)
        str(ci)
        tm.assert_index_equal(eval(repr(ci)), ci, exact=True)

        # formatting
        if PY3:
            str(ci)
        else:
            compat.text_type(ci)

        # long format
        # this is not reprable
        ci = CategoricalIndex(np.random.randint(0, 5, size=100))
        if PY3:
            str(ci)
        else:
            compat.text_type(ci) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_isin(self):

        ci = CategoricalIndex(
            list('aabca') + [np.nan], categories=['c', 'a', 'b'])
        tm.assert_numpy_array_equal(
            ci.isin(['c']),
            np.array([False, False, False, True, False, False]))
        tm.assert_numpy_array_equal(
            ci.isin(['c', 'a', 'b']), np.array([True] * 5 + [False]))
        tm.assert_numpy_array_equal(
            ci.isin(['c', 'a', 'b', np.nan]), np.array([True] * 6))

        # mismatched categorical -> coerced to ndarray so doesn't matter
        result = ci.isin(ci.set_categories(list('abcdefghi')))
        expected = np.array([True] * 6)
        tm.assert_numpy_array_equal(result, expected)

        result = ci.isin(ci.set_categories(list('defghi')))
        expected = np.array([False] * 5 + [True])
        tm.assert_numpy_array_equal(result, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_categorical_preserves_tz(self):
        # GH#18664 retain tz when going DTI-->Categorical-->DTI
        # TODO: parametrize over DatetimeIndex/DatetimeArray
        #  once CategoricalIndex(DTA) works

        dti = pd.DatetimeIndex(
            [pd.NaT, '2015-01-01', '1999-04-06 15:14:13', '2015-01-01'],
            tz='US/Eastern')

        ci = pd.CategoricalIndex(dti)
        carr = pd.Categorical(dti)
        cser = pd.Series(ci)

        for obj in [ci, carr, cser]:
            result = pd.DatetimeIndex(obj)
            tm.assert_index_equal(result, dti) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_map_dictlike(idx, mapper):

    if isinstance(idx, (pd.CategoricalIndex, pd.IntervalIndex)):
        pytest.skip("skipping tests for {}".format(type(idx)))

    identity = mapper(idx.values, idx)

    # we don't infer to UInt64 for a dict
    if isinstance(idx, pd.UInt64Index) and isinstance(identity, dict):
        expected = idx.astype('int64')
    else:
        expected = idx

    result = idx.map(identity)
    tm.assert_index_equal(result, expected)

    # empty mappable
    expected = pd.Index([np.nan] * len(idx))
    result = idx.map(mapper(expected, idx))
    tm.assert_index_equal(result, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_numpy_argsort(idx):
    result = np.argsort(idx)
    expected = idx.argsort()
    tm.assert_numpy_array_equal(result, expected)

    # these are the only two types that perform
    # pandas compatibility input validation - the
    # rest already perform separate (or no) such
    # validation via their 'values' attribute as
    # defined in pandas.core.indexes/base.py - they
    # cannot be changed at the moment due to
    # backwards compatibility concerns
    if isinstance(type(idx), (CategoricalIndex, RangeIndex)):
        msg = "the 'axis' parameter is not supported"
        with pytest.raises(ValueError, match=msg):
            np.argsort(idx, axis=1)

        msg = "the 'kind' parameter is not supported"
        with pytest.raises(ValueError, match=msg):
            np.argsort(idx, kind='mergesort')

        msg = "the 'order' parameter is not supported"
        with pytest.raises(ValueError, match=msg):
            np.argsort(idx, order=('a', 'b')) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_from_arrays_index_series_categorical():
    # GH13743
    idx1 = pd.CategoricalIndex(list("abcaab"), categories=list("bac"),
                               ordered=False)
    idx2 = pd.CategoricalIndex(list("abcaab"), categories=list("bac"),
                               ordered=True)

    result = pd.MultiIndex.from_arrays([idx1, idx2])
    tm.assert_index_equal(result.get_level_values(0), idx1)
    tm.assert_index_equal(result.get_level_values(1), idx2)

    result2 = pd.MultiIndex.from_arrays([pd.Series(idx1), pd.Series(idx2)])
    tm.assert_index_equal(result2.get_level_values(0), idx1)
    tm.assert_index_equal(result2.get_level_values(1), idx2)

    result3 = pd.MultiIndex.from_arrays([idx1.values, idx2.values])
    tm.assert_index_equal(result3.get_level_values(0), idx1)
    tm.assert_index_equal(result3.get_level_values(1), idx2) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_dataframe_dummies_preserve_categorical_dtype(self, dtype):
        # GH13854
        for ordered in [False, True]:
            cat = pd.Categorical(list("xy"), categories=list("xyz"),
                                 ordered=ordered)
            result = get_dummies(cat, dtype=dtype)

            data = np.array([[1, 0, 0], [0, 1, 0]],
                            dtype=self.effective_dtype(dtype))
            cols = pd.CategoricalIndex(cat.categories,
                                       categories=cat.categories,
                                       ordered=ordered)
            expected = DataFrame(data, columns=cols,
                                 dtype=self.effective_dtype(dtype))

            tm.assert_frame_equal(result, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import CategoricalIndex [as 别名]
def test_preserve_categorical_dtype(self):
        # GH13854
        for ordered in [False, True]:
            cidx = pd.CategoricalIndex(list("xyz"), ordered=ordered)
            midx = pd.MultiIndex(levels=[['a'], cidx],
                                 codes=[[0, 0], [0, 1]])
            df = DataFrame([[10, 11]], index=midx)

            expected = DataFrame([[1.0, 0.0, 0.0], [0.0, 1.0, 0.0]],
                                 index=midx, columns=cidx)

            from pandas.core.reshape.reshape import make_axis_dummies
            result = make_axis_dummies(df)
            tm.assert_frame_equal(result, expected)

            result = make_axis_dummies(df, transform=lambda x: x)
            tm.assert_frame_equal(result, expected)