Python pandas.util.testing.assert_index_equal() Examples

def test_tdi_round(self):
        td = pd.timedelta_range(start='16801 days', periods=5, freq='30Min')
        elt = td[1]

        expected_rng = TimedeltaIndex([Timedelta('16801 days 00:00:00'),
                                       Timedelta('16801 days 00:00:00'),
                                       Timedelta('16801 days 01:00:00'),
                                       Timedelta('16801 days 02:00:00'),
                                       Timedelta('16801 days 02:00:00')])
        expected_elt = expected_rng[1]

        tm.assert_index_equal(td.round(freq='H'), expected_rng)
        assert elt.round(freq='H') == expected_elt

        msg = pd._libs.tslibs.frequencies.INVALID_FREQ_ERR_MSG
        with pytest.raises(ValueError, match=msg):
            td.round(freq='foo')
        with pytest.raises(ValueError, match=msg):
            elt.round(freq='foo')

        msg = "<MonthEnd> is a non-fixed frequency"
        with pytest.raises(ValueError, match=msg):
            td.round(freq='M')
        with pytest.raises(ValueError, match=msg):
            elt.round(freq='M') 

def test_take(self):
        def assert_take_ok(mgr, axis, indexer):
            mat = mgr.as_array()
            taken = mgr.take(indexer, axis)
            tm.assert_numpy_array_equal(np.take(mat, indexer, axis),
                                        taken.as_array(), check_dtype=False)
            tm.assert_index_equal(mgr.axes[axis].take(indexer),
                                  taken.axes[axis])

        for mgr in self.MANAGERS:
            for ax in range(mgr.ndim):
                # take/fancy indexer
                assert_take_ok(mgr, ax, [])
                assert_take_ok(mgr, ax, [0, 0, 0])
                assert_take_ok(mgr, ax, lrange(mgr.shape[ax]))

                if mgr.shape[ax] >= 3:
                    assert_take_ok(mgr, ax, [0, 1, 2])
                    assert_take_ok(mgr, ax, [-1, -2, -3]) 

def test_constructor_dict_mixed(self):
        data = {k: v.values for k, v in self.panel.iteritems()}
        result = Panel(data)
        exp_major = Index(np.arange(len(self.panel.major_axis)))
        tm.assert_index_equal(result.major_axis, exp_major)

        result = Panel(data, items=self.panel.items,
                       major_axis=self.panel.major_axis,
                       minor_axis=self.panel.minor_axis)
        assert_panel_equal(result, self.panel)

        data['ItemC'] = self.panel['ItemC']
        result = Panel(data)
        assert_panel_equal(result, self.panel)

        # corner, blow up
        data['ItemB'] = data['ItemB'][:-1]
        pytest.raises(Exception, Panel, data)

        data['ItemB'] = self.panel['ItemB'].values[:, :-1]
        pytest.raises(Exception, Panel, data) 

def assert_frame_equal(self, left, right, *args, **kwargs):
        # TODO(EA): select_dtypes
        tm.assert_index_equal(
            left.columns, right.columns,
            exact=kwargs.get('check_column_type', 'equiv'),
            check_names=kwargs.get('check_names', True),
            check_exact=kwargs.get('check_exact', False),
            check_categorical=kwargs.get('check_categorical', True),
            obj='{obj}.columns'.format(obj=kwargs.get('obj', 'DataFrame')))

        decimals = (left.dtypes == 'decimal').index

        for col in decimals:
            self.assert_series_equal(left[col], right[col],
                                     *args, **kwargs)

        left = left.drop(columns=decimals)
        right = right.drop(columns=decimals)
        tm.assert_frame_equal(left, right, *args, **kwargs) 

def test_getitem(self):

        r = self.frame.rolling(window=5)
        tm.assert_index_equal(r._selected_obj.columns, self.frame.columns)

        r = self.frame.rolling(window=5)[1]
        assert r._selected_obj.name == self.frame.columns[1]

        # technically this is allowed
        r = self.frame.rolling(window=5)[1, 3]
        tm.assert_index_equal(r._selected_obj.columns,
                              self.frame.columns[[1, 3]])

        r = self.frame.rolling(window=5)[[1, 3]]
        tm.assert_index_equal(r._selected_obj.columns,
                              self.frame.columns[[1, 3]]) 

def test_agg_consistency(self):

        df = DataFrame({'A': range(5), 'B': range(0, 10, 2)})
        r = df.rolling(window=3)

        result = r.agg([np.sum, np.mean]).columns
        expected = pd.MultiIndex.from_product([list('AB'), ['sum', 'mean']])
        tm.assert_index_equal(result, expected)

        result = r['A'].agg([np.sum, np.mean]).columns
        expected = Index(['sum', 'mean'])
        tm.assert_index_equal(result, expected)

        result = r.agg({'A': [np.sum, np.mean]}).columns
        expected = pd.MultiIndex.from_tuples([('A', 'sum'), ('A', 'mean')])
        tm.assert_index_equal(result, expected) 

def test_pairwise_with_self(self, f):

        # DataFrame with itself, pairwise=True
        # note that we may construct the 1st level of the MI
        # in a non-motononic way, so compare accordingly
        results = []
        for i, df in enumerate(self.df1s):
            result = f(df)
            tm.assert_index_equal(result.index.levels[0],
                                  df.index,
                                  check_names=False)
            tm.assert_numpy_array_equal(safe_sort(result.index.levels[1]),
                                        safe_sort(df.columns.unique()))
            tm.assert_index_equal(result.columns, df.columns)
            results.append(df)

        for i, result in enumerate(results):
            if i > 0:
                self.compare(result, results[0]) 

def test_axis_dummies(self):
        from pandas.core.reshape.reshape import make_axis_dummies

        minor_dummies = make_axis_dummies(self.panel, 'minor').astype(np.uint8)
        assert len(minor_dummies.columns) == len(self.panel.index.levels[1])

        major_dummies = make_axis_dummies(self.panel, 'major').astype(np.uint8)
        assert len(major_dummies.columns) == len(self.panel.index.levels[0])

        mapping = {'A': 'one', 'B': 'one', 'C': 'two', 'D': 'two'}

        transformed = make_axis_dummies(self.panel, 'minor',
                                        transform=mapping.get).astype(np.uint8)
        assert len(transformed.columns) == 2
        tm.assert_index_equal(transformed.columns, Index(['one', 'two']))

        # TODO: test correctness 

def test_no_pairwise_with_other(self, f):

        # DataFrame with another DataFrame, pairwise=False
        results = [f(df, self.df2) if df.columns.is_unique else None
                   for df in self.df1s]
        for (df, result) in zip(self.df1s, results):
            if result is not None:
                with catch_warnings(record=True):
                    warnings.simplefilter("ignore", RuntimeWarning)
                    # we can have int and str columns
                    expected_index = df.index.union(self.df2.index)
                    expected_columns = df.columns.union(self.df2.columns)
                tm.assert_index_equal(result.index, expected_index)
                tm.assert_index_equal(result.columns, expected_columns)
            else:
                with pytest.raises(ValueError,
                                   match="'arg1' columns are not unique"):
                    f(df, self.df2)
                with pytest.raises(ValueError,
                                   match="'arg2' columns are not unique"):
                    f(self.df2, df) 

def assert_frame_equal(self, left, right, *args, **kwargs):
        tm.assert_index_equal(
            left.columns, right.columns,
            exact=kwargs.get('check_column_type', 'equiv'),
            check_names=kwargs.get('check_names', True),
            check_exact=kwargs.get('check_exact', False),
            check_categorical=kwargs.get('check_categorical', True),
            obj='{obj}.columns'.format(obj=kwargs.get('obj', 'DataFrame')))

        jsons = (left.dtypes == 'json').index

        for col in jsons:
            self.assert_series_equal(left[col], right[col],
                                     *args, **kwargs)

        left = left.drop(columns=jsons)
        right = right.drop(columns=jsons)
        tm.assert_frame_equal(left, right, *args, **kwargs) 

def test_dropna(self):
        sp = SparseSeries([0, 0, 0, nan, nan, 5, 6], fill_value=0)

        sp_valid = sp.dropna()

        expected = sp.to_dense().dropna()
        expected = expected[expected != 0]
        exp_arr = pd.SparseArray(expected.values, fill_value=0, kind='block')
        tm.assert_sp_array_equal(sp_valid.values, exp_arr)
        tm.assert_index_equal(sp_valid.index, expected.index)
        assert len(sp_valid.sp_values) == 2

        result = self.bseries.dropna()
        expected = self.bseries.to_dense().dropna()
        assert not isinstance(result, SparseSeries)
        tm.assert_series_equal(result, expected) 

def test_astype_index(self, all_data, dropna):
        # as an int/uint index to Index

        all_data = all_data[:10]
        if dropna:
            other = all_data[~all_data.isna()]
        else:
            other = all_data

        dtype = all_data.dtype
        idx = pd.Index(np.array(other))
        assert isinstance(idx, ABCIndexClass)

        result = idx.astype(dtype)
        expected = idx.astype(object).astype(dtype)
        tm.assert_index_equal(result, expected) 

def test_take(self):
        data = np.arange(100, dtype='i8') * 24 * 3600 * 10**9
        np.random.shuffle(data)

        idx = self.index_cls._simple_new(data, freq='D')
        arr = self.array_cls(idx)

        takers = [1, 4, 94]
        result = arr.take(takers)
        expected = idx.take(takers)

        tm.assert_index_equal(self.index_cls(result), expected)

        takers = np.array([1, 4, 94])
        result = arr.take(takers)
        expected = idx.take(takers)

        tm.assert_index_equal(self.index_cls(result), expected) 

def test_nan_handling(self):

        # Nans are represented as -1 in codes
        c = Categorical(["a", "b", np.nan, "a"])
        tm.assert_index_equal(c.categories, Index(["a", "b"]))
        tm.assert_numpy_array_equal(c._codes, np.array([0, 1, -1, 0],
                                                       dtype=np.int8))
        c[1] = np.nan
        tm.assert_index_equal(c.categories, Index(["a", "b"]))
        tm.assert_numpy_array_equal(c._codes, np.array([0, -1, -1, 0],
                                                       dtype=np.int8))

        # Adding nan to categories should make assigned nan point to the
        # category!
        c = Categorical(["a", "b", np.nan, "a"])
        tm.assert_index_equal(c.categories, Index(["a", "b"]))
        tm.assert_numpy_array_equal(c._codes, np.array([0, 1, -1, 0],
                                                       dtype=np.int8)) 

def test_categories_assigments(self):
        s = Categorical(["a", "b", "c", "a"])
        exp = np.array([1, 2, 3, 1], dtype=np.int64)
        s.categories = [1, 2, 3]
        tm.assert_numpy_array_equal(s.__array__(), exp)
        tm.assert_index_equal(s.categories, Index([1, 2, 3]))

        # lengthen
        with pytest.raises(ValueError):
            s.categories = [1, 2, 3, 4]

        # shorten
        with pytest.raises(ValueError):
            s.categories = [1, 2]

    # Combinations of sorted/unique: 

def test_ordered_api(self):
        # GH 9347
        cat1 = Categorical(list('acb'), ordered=False)
        tm.assert_index_equal(cat1.categories, Index(['a', 'b', 'c']))
        assert not cat1.ordered

        cat2 = Categorical(list('acb'), categories=list('bca'), ordered=False)
        tm.assert_index_equal(cat2.categories, Index(['b', 'c', 'a']))
        assert not cat2.ordered

        cat3 = Categorical(list('acb'), ordered=True)
        tm.assert_index_equal(cat3.categories, Index(['a', 'b', 'c']))
        assert cat3.ordered

        cat4 = Categorical(list('acb'), categories=list('bca'), ordered=True)
        tm.assert_index_equal(cat4.categories, Index(['b', 'c', 'a']))
        assert cat4.ordered 

def test_unique_index_series(self):
        c = Categorical([3, 1, 2, 2, 1], categories=[3, 2, 1])
        # Categorical.unique sorts categories by appearance order
        # if ordered=False
        exp = Categorical([3, 1, 2], categories=[3, 1, 2])
        tm.assert_categorical_equal(c.unique(), exp)

        tm.assert_index_equal(Index(c).unique(), Index(exp))
        tm.assert_categorical_equal(Series(c).unique(), exp)

        c = Categorical([1, 1, 2, 2], categories=[3, 2, 1])
        exp = Categorical([1, 2], categories=[1, 2])
        tm.assert_categorical_equal(c.unique(), exp)
        tm.assert_index_equal(Index(c).unique(), Index(exp))
        tm.assert_categorical_equal(Series(c).unique(), exp)

        c = Categorical([3, 1, 2, 2, 1], categories=[3, 2, 1], ordered=True)
        # Categorical.unique keeps categories order if ordered=True
        exp = Categorical([3, 1, 2], categories=[3, 2, 1], ordered=True)
        tm.assert_categorical_equal(c.unique(), exp)

        tm.assert_index_equal(Index(c).unique(), Index(exp))
        tm.assert_categorical_equal(Series(c).unique(), exp) 

def test_difference_freq(self, sort):
        # GH14323: Difference of TimedeltaIndex should not preserve frequency

        index = timedelta_range("0 days", "5 days", freq="D")

        other = timedelta_range("1 days", "4 days", freq="D")
        expected = TimedeltaIndex(["0 days", "5 days"], freq=None)
        idx_diff = index.difference(other, sort)
        tm.assert_index_equal(idx_diff, expected)
        tm.assert_attr_equal('freq', idx_diff, expected)

        other = timedelta_range("2 days", "5 days", freq="D")
        idx_diff = index.difference(other, sort)
        expected = TimedeltaIndex(["0 days", "1 days"], freq=None)
        tm.assert_index_equal(idx_diff, expected)
        tm.assert_attr_equal('freq', idx_diff, expected) 

def test_difference_sort(self, sort):

        index = pd.TimedeltaIndex(["5 days", "3 days", "2 days", "4 days",
                                   "1 days", "0 days"])

        other = timedelta_range("1 days", "4 days", freq="D")
        idx_diff = index.difference(other, sort)

        expected = TimedeltaIndex(["5 days", "0 days"], freq=None)

        if sort is None:
            expected = expected.sort_values()

        tm.assert_index_equal(idx_diff, expected)
        tm.assert_attr_equal('freq', idx_diff, expected)

        other = timedelta_range("2 days", "5 days", freq="D")
        idx_diff = index.difference(other, sort)
        expected = TimedeltaIndex(["1 days", "0 days"], freq=None)

        if sort is None:
            expected = expected.sort_values()

        tm.assert_index_equal(idx_diff, expected)
        tm.assert_attr_equal('freq', idx_diff, expected) 

def test_take(self):
        # GH 10295
        idx1 = timedelta_range('1 day', '31 day', freq='D', name='idx')

        for idx in [idx1]:
            result = idx.take([0])
            assert result == Timedelta('1 day')

            result = idx.take([-1])
            assert result == Timedelta('31 day')

            result = idx.take([0, 1, 2])
            expected = timedelta_range('1 day', '3 day', freq='D',
                                       name='idx')
            tm.assert_index_equal(result, expected)
            assert result.freq == expected.freq

            result = idx.take([0, 2, 4])
            expected = timedelta_range('1 day', '5 day', freq='2D',
                                       name='idx')
            tm.assert_index_equal(result, expected)
            assert result.freq == expected.freq

            result = idx.take([7, 4, 1])
            expected = timedelta_range('8 day', '2 day', freq='-3D',
                                       name='idx')
            tm.assert_index_equal(result, expected)
            assert result.freq == expected.freq

            result = idx.take([3, 2, 5])
            expected = TimedeltaIndex(['4 day', '3 day', '6 day'], name='idx')
            tm.assert_index_equal(result, expected)
            assert result.freq is None

            result = idx.take([-3, 2, 5])
            expected = TimedeltaIndex(['29 day', '3 day', '6 day'], name='idx')
            tm.assert_index_equal(result, expected)
            assert result.freq is None 

def test_take2(self):
        tds = ['1day 02:00:00', '1 day 04:00:00', '1 day 10:00:00']
        idx = timedelta_range(start='1d', end='2d', freq='H', name='idx')
        expected = TimedeltaIndex(tds, freq=None, name='idx')

        taken1 = idx.take([2, 4, 10])
        taken2 = idx[[2, 4, 10]]

        for taken in [taken1, taken2]:
            tm.assert_index_equal(taken, expected)
            assert isinstance(taken, TimedeltaIndex)
            assert taken.freq is None
            assert taken.name == expected.name 

def test_float64_ns_rounded(self):
        # GH#23539 without specifying a unit, floats are regarded as nanos,
        #  and fractional portions are truncated
        tdi = TimedeltaIndex([2.3, 9.7])
        expected = TimedeltaIndex([2, 9])
        tm.assert_index_equal(tdi, expected)

        # integral floats are non-lossy
        tdi = TimedeltaIndex([2.0, 9.0])
        expected = TimedeltaIndex([2, 9])
        tm.assert_index_equal(tdi, expected)

        # NaNs get converted to NaT
        tdi = TimedeltaIndex([2.0, np.nan])
        expected = TimedeltaIndex([pd.Timedelta(nanoseconds=2), pd.NaT])
        tm.assert_index_equal(tdi, expected) 

def test_constructor_from_index_series_timedelta(self):
        idx = timedelta_range('1 days', freq='D', periods=3)
        result = Categorical(idx)
        tm.assert_index_equal(result.categories, idx)

        result = Categorical(Series(idx))
        tm.assert_index_equal(result.categories, idx) 

def test_no_flex(self, f):

        # DataFrame methods (which do not call _flex_binary_moment())

        results = [f(df) for df in self.df1s]
        for (df, result) in zip(self.df1s, results):
            tm.assert_index_equal(result.index, df.columns)
            tm.assert_index_equal(result.columns, df.columns)
        for i, result in enumerate(results):
            if i > 0:
                self.compare(result, results[0]) 

def test_fillna_timedelta(self):
        # GH 11343
        idx = pd.TimedeltaIndex(['1 day', pd.NaT, '3 day'])

        exp = pd.TimedeltaIndex(['1 day', '2 day', '3 day'])
        tm.assert_index_equal(idx.fillna(pd.Timedelta('2 day')), exp)

        exp = pd.TimedeltaIndex(['1 day', '3 hour', '3 day'])
        idx.fillna(pd.Timedelta('3 hour'))

        exp = pd.Index(
            [pd.Timedelta('1 day'), 'x', pd.Timedelta('3 day')], dtype=object)
        tm.assert_index_equal(idx.fillna('x'), exp) 

def test_constructor_imaginary(self):
        values = [1, 2, 3 + 1j]
        c1 = Categorical(values)
        tm.assert_index_equal(c1.categories, Index(values))
        tm.assert_numpy_array_equal(np.array(c1), np.array(values)) 

def test_pickle(self):

        rng = timedelta_range('1 days', periods=10)
        rng_p = tm.round_trip_pickle(rng)
        tm.assert_index_equal(rng, rng_p) 

def test_union(self):

        i1 = timedelta_range('1day', periods=5)
        i2 = timedelta_range('3day', periods=5)
        result = i1.union(i2)
        expected = timedelta_range('1day', periods=7)
        tm.assert_index_equal(result, expected)

        i1 = Int64Index(np.arange(0, 20, 2))
        i2 = timedelta_range(start='1 day', periods=10, freq='D')
        i1.union(i2)  # Works
        i2.union(i1)  # Fails with "AttributeError: can't set attribute" 

def test_union_coverage(self):

        idx = TimedeltaIndex(['3d', '1d', '2d'])
        ordered = TimedeltaIndex(idx.sort_values(), freq='infer')
        result = ordered.union(idx)
        tm.assert_index_equal(result, ordered)

        result = ordered[:0].union(ordered)
        tm.assert_index_equal(result, ordered)
        assert result.freq == ordered.freq 

def test_does_not_convert_mixed_integer(self):
        df = tm.makeCustomDataframe(10, 10,
                                    data_gen_f=lambda *args, **kwargs: randn(),
                                    r_idx_type='i', c_idx_type='td')
        str(df)

        cols = df.columns.join(df.index, how='outer')
        joined = cols.join(df.columns)
        assert cols.dtype == np.dtype('O')
        assert cols.dtype == joined.dtype
        tm.assert_index_equal(cols, joined)