Python pandas.util.testing.assert_raises_regex() Examples

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):
                    # 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:
                tm.assert_raises_regex(
                    ValueError, "'arg1' columns are not unique", f, df,
                    self.df2)
                tm.assert_raises_regex(
                    ValueError, "'arg2' columns are not unique", f,
                    self.df2, df) 

def test_errors(self):
        # not enough params
        msg = ('Of the four parameters: start, end, periods, and freq, '
               'exactly three must be specified')
        with tm.assert_raises_regex(ValueError, msg):
            timedelta_range(start='0 days')

        with tm.assert_raises_regex(ValueError, msg):
            timedelta_range(end='5 days')

        with tm.assert_raises_regex(ValueError, msg):
            timedelta_range(periods=2)

        with tm.assert_raises_regex(ValueError, msg):
            timedelta_range()

        # too many params
        with tm.assert_raises_regex(ValueError, msg):
            timedelta_range(start='0 days', end='5 days', periods=10, freq='H') 

def test_take_invalid_kwargs(self):
        idx = timedelta_range('1 day', '31 day', freq='D', name='idx')
        indices = [1, 6, 5, 9, 10, 13, 15, 3]

        msg = r"take\(\) got an unexpected keyword argument 'foo'"
        tm.assert_raises_regex(TypeError, msg, idx.take,
                               indices, foo=2)

        msg = "the 'out' parameter is not supported"
        tm.assert_raises_regex(ValueError, msg, idx.take,
                               indices, out=indices)

        msg = "the 'mode' parameter is not supported"
        tm.assert_raises_regex(ValueError, msg, idx.take,
                               indices, mode='clip')

    # TODO: This method came from test_timedelta; de-dup with version above 

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_ERROR
        with tm.assert_raises_regex(ValueError, msg):
            td.round(freq='foo')
        with tm.assert_raises_regex(ValueError, msg):
            elt.round(freq='foo')

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

def test_numpy_round(self):
        with catch_warnings(record=True):
            values = [[[-3.2, 2.2], [0, -4.8213], [3.123, 123.12],
                       [-1566.213, 88.88], [-12, 94.5]],
                      [[-5.82, 3.5], [6.21, -73.272], [-9.087, 23.12],
                       [272.212, -99.99], [23, -76.5]]]
            evalues = [[[float(np.around(i)) for i in j] for j in k]
                       for k in values]
            p = Panel(values, items=['Item1', 'Item2'],
                      major_axis=date_range('1/1/2000', periods=5),
                      minor_axis=['A', 'B'])
            expected = Panel(evalues, items=['Item1', 'Item2'],
                             major_axis=date_range('1/1/2000', periods=5),
                             minor_axis=['A', 'B'])
            result = np.round(p)
            assert_panel_equal(expected, result)

            msg = "the 'out' parameter is not supported"
            tm.assert_raises_regex(ValueError, msg, np.round, p, out=p) 

def test_freq_setter_errors(self):
        # GH 20678
        idx = TimedeltaIndex(['0 days', '2 days', '4 days'])

        # setting with an incompatible freq
        msg = ('Inferred frequency 2D from passed values does not conform to '
               'passed frequency 5D')
        with tm.assert_raises_regex(ValueError, msg):
            idx.freq = '5D'

        # setting with a non-fixed frequency
        msg = '<2 \* BusinessDays> is a non-fixed frequency'
        with tm.assert_raises_regex(ValueError, msg):
            idx.freq = '2B'

        # setting with non-freq string
        with tm.assert_raises_regex(ValueError, 'Invalid frequency'):
            idx.freq = 'foo' 

def test_astype(self):
        res = self.arr.astype('f8')
        res.sp_values[:3] = 27
        assert not (self.arr.sp_values[:3] == 27).any()

        msg = "unable to coerce current fill_value nan to int64 dtype"
        with tm.assert_raises_regex(ValueError, msg):
            self.arr.astype('i8')

        arr = SparseArray([0, np.nan, 0, 1])
        with tm.assert_raises_regex(ValueError, msg):
            arr.astype('i8')

        arr = SparseArray([0, np.nan, 0, 1], fill_value=0)
        msg = 'Cannot convert non-finite values \\(NA or inf\\) to integer'
        with tm.assert_raises_regex(ValueError, msg):
            arr.astype('i8') 

def test_numpy_all(self, data, pos, neg):
        # GH 17570
        out = np.all(SparseArray(data))
        assert out

        out = np.all(SparseArray(data, fill_value=pos))
        assert out

        data[1] = neg
        out = np.all(SparseArray(data))
        assert not out

        out = np.all(SparseArray(data, fill_value=pos))
        assert not out

        msg = "the 'out' parameter is not supported"
        tm.assert_raises_regex(ValueError, msg, np.all,
                               SparseArray(data), out=out) 

def test_set_value(self):
        with catch_warnings(record=True):
            for item in self.panel.items:
                for mjr in self.panel.major_axis[::2]:
                    for mnr in self.panel.minor_axis:
                        self.panel.set_value(item, mjr, mnr, 1.)
                        tm.assert_almost_equal(self.panel[item][mnr][mjr], 1.)

            # resize
            res = self.panel.set_value('ItemE', 'foo', 'bar', 1.5)
            assert isinstance(res, Panel)
            assert res is not self.panel
            assert res.get_value('ItemE', 'foo', 'bar') == 1.5

            res3 = self.panel.set_value('ItemE', 'foobar', 'baz', 5)
            assert is_float_dtype(res3['ItemE'].values)

            msg = ("There must be an argument for each "
                   "axis plus the value provided")
            with tm.assert_raises_regex(TypeError, msg):
                self.panel.set_value('a') 

def test_numpy_any(self, data, pos, neg):
        # GH 17570
        out = np.any(SparseArray(data))
        assert out

        out = np.any(SparseArray(data, fill_value=pos))
        assert out

        data[1] = neg
        out = np.any(SparseArray(data))
        assert not out

        out = np.any(SparseArray(data, fill_value=pos))
        assert not out

        msg = "the 'out' parameter is not supported"
        tm.assert_raises_regex(ValueError, msg, np.any,
                               SparseArray(data), out=out) 

def test_numpy_sum(self):
        data = np.arange(10).astype(float)
        out = np.sum(SparseArray(data))
        assert out == 45.0

        data[5] = np.nan
        out = np.sum(SparseArray(data, fill_value=2))
        assert out == 40.0

        out = np.sum(SparseArray(data, fill_value=np.nan))
        assert out == 40.0

        msg = "the 'dtype' parameter is not supported"
        tm.assert_raises_regex(ValueError, msg, np.sum,
                               SparseArray(data), dtype=np.int64)

        msg = "the 'out' parameter is not supported"
        tm.assert_raises_regex(ValueError, msg, np.sum,
                               SparseArray(data), out=out) 

def test_metadata_immutable(self):
        levels, labels = self.index.levels, self.index.labels
        # shouldn't be able to set at either the top level or base level
        mutable_regex = re.compile('does not support mutable operations')
        with tm.assert_raises_regex(TypeError, mutable_regex):
            levels[0] = levels[0]
        with tm.assert_raises_regex(TypeError, mutable_regex):
            levels[0][0] = levels[0][0]
        # ditto for labels
        with tm.assert_raises_regex(TypeError, mutable_regex):
            labels[0] = labels[0]
        with tm.assert_raises_regex(TypeError, mutable_regex):
            labels[0][0] = labels[0][0]
        # and for names
        names = self.index.names
        with tm.assert_raises_regex(TypeError, mutable_regex):
            names[0] = names[0] 

def test_numpy_compat(self, method):
        # see gh-12811
        e = rwindow.EWM(Series([2, 4, 6]), alpha=0.5)

        msg = "numpy operations are not valid with window objects"

        tm.assert_raises_regex(UnsupportedFunctionCall, msg,
                               getattr(e, method), 1, 2, 3)
        tm.assert_raises_regex(UnsupportedFunctionCall, msg,
                               getattr(e, method), dtype=np.float64)


# gh-12373 : rolling functions error on float32 data
# make sure rolling functions works for different dtypes
#
# NOTE that these are yielded tests and so _create_data
# is explicitly called.
#
# further note that we are only checking rolling for fully dtype
# compliance (though both expanding and ewm inherit) 

def test_cumsum(self):
        non_null_data = np.array([1, 2, 3, 4, 5], dtype=float)
        non_null_expected = SparseArray(non_null_data.cumsum())

        null_data = np.array([1, 2, np.nan, 4, 5], dtype=float)
        null_expected = SparseArray(np.array([1.0, 3.0, np.nan, 7.0, 12.0]))

        for data, expected in [
            (null_data, null_expected),
            (non_null_data, non_null_expected)
        ]:
            out = SparseArray(data).cumsum()
            tm.assert_sp_array_equal(out, expected)

            out = SparseArray(data, fill_value=np.nan).cumsum()
            tm.assert_sp_array_equal(out, expected)

            out = SparseArray(data, fill_value=2).cumsum()
            tm.assert_sp_array_equal(out, expected)

            axis = 1  # SparseArray currently 1-D, so only axis = 0 is valid.
            msg = "axis\\(={axis}\\) out of bounds".format(axis=axis)
            with tm.assert_raises_regex(ValueError, msg):
                SparseArray(data).cumsum(axis=axis) 

def test_unbounded_slice_raises(self):
        def assert_unbounded_slice_error(slc):
            tm.assert_raises_regex(ValueError, "unbounded slice",
                                   lambda: BlockPlacement(slc))

        assert_unbounded_slice_error(slice(None, None))
        assert_unbounded_slice_error(slice(10, None))
        assert_unbounded_slice_error(slice(None, None, -1))
        assert_unbounded_slice_error(slice(None, 10, -1))

        # These are "unbounded" because negative index will change depending on
        # container shape.
        assert_unbounded_slice_error(slice(-1, None))
        assert_unbounded_slice_error(slice(None, -1))
        assert_unbounded_slice_error(slice(-1, -1))
        assert_unbounded_slice_error(slice(-1, None, -1))
        assert_unbounded_slice_error(slice(None, -1, -1))
        assert_unbounded_slice_error(slice(-1, -1, -1)) 

def test_constructor_ndarray(self):
        # no index or columns
        sp = SparseDataFrame(self.frame.values)

        # 1d
        sp = SparseDataFrame(self.data['A'], index=self.dates, columns=['A'])
        tm.assert_sp_frame_equal(sp, self.frame.reindex(columns=['A']))

        # raise on level argument
        pytest.raises(TypeError, self.frame.reindex, columns=['A'],
                      level=1)

        # wrong length index / columns
        with tm.assert_raises_regex(ValueError, "^Index length"):
            SparseDataFrame(self.frame.values, index=self.frame.index[:-1])

        with tm.assert_raises_regex(ValueError, "^Column length"):
            SparseDataFrame(self.frame.values, columns=self.frame.columns[:-1])

    # GH 9272 

def test_constructor_mismatched_label_levels(self):
        labels = [np.array([1]), np.array([2]), np.array([3])]
        levels = ["a"]
        tm.assert_raises_regex(ValueError, "Length of levels and labels "
                                           "must be the same", MultiIndex,
                               levels=levels, labels=labels)
        length_error = re.compile('>= length of level')
        label_error = re.compile(r'Unequal label lengths: \[4, 2\]')

        # important to check that it's looking at the right thing.
        with tm.assert_raises_regex(ValueError, length_error):
            MultiIndex(levels=[['a'], ['b']],
                       labels=[[0, 1, 2, 3], [0, 3, 4, 1]])

        with tm.assert_raises_regex(ValueError, label_error):
            MultiIndex(levels=[['a'], ['b']], labels=[[0, 0, 0, 0], [0, 0]])

        # external API
        with tm.assert_raises_regex(ValueError, length_error):
            self.index.copy().set_levels([['a'], ['b']])

        with tm.assert_raises_regex(ValueError, label_error):
            self.index.copy().set_labels([[0, 0, 0, 0], [0, 0]]) 

def test_constructor_nonhashable_names(self):
        # GH 20527
        levels = [[1, 2], [u'one', u'two']]
        labels = [[0, 0, 1, 1], [0, 1, 0, 1]]
        names = ((['foo'], ['bar']))
        message = "MultiIndex.name must be a hashable type"
        tm.assert_raises_regex(TypeError, message,
                               MultiIndex, levels=levels,
                               labels=labels, names=names)

        # With .rename()
        mi = MultiIndex(levels=[[1, 2], [u'one', u'two']],
                        labels=[[0, 0, 1, 1], [0, 1, 0, 1]],
                        names=('foo', 'bar'))
        renamed = [['foor'], ['barr']]
        tm.assert_raises_regex(TypeError, message, mi.rename, names=renamed)
        # With .set_names()
        tm.assert_raises_regex(TypeError, message, mi.set_names, names=renamed) 

def test_numpy_cumsum(self):
        result = np.cumsum(self.bseries)
        expected = SparseSeries(self.bseries.to_dense().cumsum())
        tm.assert_sp_series_equal(result, expected)

        result = np.cumsum(self.zbseries)
        expected = self.zbseries.to_dense().cumsum()
        tm.assert_series_equal(result, expected)

        msg = "the 'dtype' parameter is not supported"
        tm.assert_raises_regex(ValueError, msg, np.cumsum,
                               self.bseries, dtype=np.int64)

        msg = "the 'out' parameter is not supported"
        tm.assert_raises_regex(ValueError, msg, np.cumsum,
                               self.zbseries, out=result) 

def test_from_arrays_empty(self):
        # 0 levels
        with tm.assert_raises_regex(
                ValueError, "Must pass non-zero number of levels/labels"):
            MultiIndex.from_arrays(arrays=[])

        # 1 level
        result = MultiIndex.from_arrays(arrays=[[]], names=['A'])
        assert isinstance(result, MultiIndex)
        expected = Index([], name='A')
        tm.assert_index_equal(result.levels[0], expected)

        # N levels
        for N in [2, 3]:
            arrays = [[]] * N
            names = list('ABC')[:N]
            result = MultiIndex.from_arrays(arrays=arrays, names=names)
            expected = MultiIndex(levels=[[]] * N, labels=[[]] * N,
                                  names=names)
            tm.assert_index_equal(result, expected) 

def test_from_arrays_different_lengths(self):
        # see gh-13599
        idx1 = [1, 2, 3]
        idx2 = ['a', 'b']
        tm.assert_raises_regex(ValueError, '^all arrays must '
                                           'be same length$',
                               MultiIndex.from_arrays, [idx1, idx2])

        idx1 = []
        idx2 = ['a', 'b']
        tm.assert_raises_regex(ValueError, '^all arrays must '
                                           'be same length$',
                               MultiIndex.from_arrays, [idx1, idx2])

        idx1 = [1, 2, 3]
        idx2 = []
        tm.assert_raises_regex(ValueError, '^all arrays must '
                                           'be same length$',
                               MultiIndex.from_arrays, [idx1, idx2]) 

def test_from_product_iterator(self):
        # GH 18434
        first = ['foo', 'bar', 'buz']
        second = ['a', 'b', 'c']
        names = ['first', 'second']
        tuples = [('foo', 'a'), ('foo', 'b'), ('foo', 'c'), ('bar', 'a'),
                  ('bar', 'b'), ('bar', 'c'), ('buz', 'a'), ('buz', 'b'),
                  ('buz', 'c')]
        expected = MultiIndex.from_tuples(tuples, names=names)

        # iterator as input
        result = MultiIndex.from_product(iter([first, second]), names=names)
        tm.assert_index_equal(result, expected)

        # Invalid non-iterable input
        with tm.assert_raises_regex(
                TypeError, "Input must be a list / sequence of iterables."):
            MultiIndex.from_product(0) 

def test_names(self):

        # names are assigned in setup
        names = self.index_names
        level_names = [level.name for level in self.index.levels]
        assert names == level_names

        # setting bad names on existing
        index = self.index
        tm.assert_raises_regex(ValueError, "^Length of names",
                               setattr, index, "names",
                               list(index.names) + ["third"])
        tm.assert_raises_regex(ValueError, "^Length of names",
                               setattr, index, "names", [])

        # initializing with bad names (should always be equivalent)
        major_axis, minor_axis = self.index.levels
        major_labels, minor_labels = self.index.labels
        tm.assert_raises_regex(ValueError, "^Length of names", MultiIndex,
                               levels=[major_axis, minor_axis],
                               labels=[major_labels, minor_labels],
                               names=['first'])
        tm.assert_raises_regex(ValueError, "^Length of names", MultiIndex,
                               levels=[major_axis, minor_axis],
                               labels=[major_labels, minor_labels],
                               names=['first', 'second', 'third'])

        # names are assigned
        index.names = ["a", "b"]
        ind_names = list(index.names)
        level_names = [level.name for level in index.levels]
        assert ind_names == level_names 

def test_get_loc(self):
        idx = pd.to_timedelta(['0 days', '1 days', '2 days'])

        for method in [None, 'pad', 'backfill', 'nearest']:
            assert idx.get_loc(idx[1], method) == 1
            assert idx.get_loc(idx[1].to_pytimedelta(), method) == 1
            assert idx.get_loc(str(idx[1]), method) == 1

        assert idx.get_loc(idx[1], 'pad',
                           tolerance=Timedelta(0)) == 1
        assert idx.get_loc(idx[1], 'pad',
                           tolerance=np.timedelta64(0, 's')) == 1
        assert idx.get_loc(idx[1], 'pad',
                           tolerance=timedelta(0)) == 1

        with tm.assert_raises_regex(ValueError,
                                    'unit abbreviation w/o a number'):
            idx.get_loc(idx[1], method='nearest', tolerance='foo')

        with pytest.raises(
                ValueError,
                match='tolerance size must match'):
            idx.get_loc(idx[1], method='nearest',
                        tolerance=[Timedelta(0).to_timedelta64(),
                                   Timedelta(0).to_timedelta64()])

        for method, loc in [('pad', 1), ('backfill', 2), ('nearest', 1)]:
            assert idx.get_loc('1 day 1 hour', method) == loc

        # GH 16909
        assert idx.get_loc(idx[1].to_timedelta64()) == 1

        # GH 16896
        assert idx.get_loc('0 days') == 0 

def test_take_fill_value(self):
        # GH 12631
        idx = TimedeltaIndex(['1 days', '2 days', '3 days'],
                             name='xxx')
        result = idx.take(np.array([1, 0, -1]))
        expected = TimedeltaIndex(['2 days', '1 days', '3 days'],
                                  name='xxx')
        tm.assert_index_equal(result, expected)

        # fill_value
        result = idx.take(np.array([1, 0, -1]), fill_value=True)
        expected = TimedeltaIndex(['2 days', '1 days', 'NaT'],
                                  name='xxx')
        tm.assert_index_equal(result, expected)

        # allow_fill=False
        result = idx.take(np.array([1, 0, -1]), allow_fill=False,
                          fill_value=True)
        expected = TimedeltaIndex(['2 days', '1 days', '3 days'],
                                  name='xxx')
        tm.assert_index_equal(result, expected)

        msg = ('When allow_fill=True and fill_value is not None, '
               'all indices must be >= -1')
        with tm.assert_raises_regex(ValueError, msg):
            idx.take(np.array([1, 0, -2]), fill_value=True)
        with tm.assert_raises_regex(ValueError, msg):
            idx.take(np.array([1, 0, -5]), fill_value=True)

        with pytest.raises(IndexError):
            idx.take(np.array([1, -5])) 

def test_check_integrity(self):

        # Too many indices than specified in self.length
        msg = "Too many indices"

        with tm.assert_raises_regex(ValueError, msg):
            IntIndex(length=1, indices=[1, 2, 3])

        # No index can be negative.
        msg = "No index can be less than zero"

        with tm.assert_raises_regex(ValueError, msg):
            IntIndex(length=5, indices=[1, -2, 3])

        # No index can be negative.
        msg = "No index can be less than zero"

        with tm.assert_raises_regex(ValueError, msg):
            IntIndex(length=5, indices=[1, -2, 3])

        # All indices must be less than the length.
        msg = "All indices must be less than the length"

        with tm.assert_raises_regex(ValueError, msg):
            IntIndex(length=5, indices=[1, 2, 5])

        with tm.assert_raises_regex(ValueError, msg):
            IntIndex(length=5, indices=[1, 2, 6])

        # Indices must be strictly ascending.
        msg = "Indices must be strictly increasing"

        with tm.assert_raises_regex(ValueError, msg):
            IntIndex(length=5, indices=[1, 3, 2])

        with tm.assert_raises_regex(ValueError, msg):
            IntIndex(length=5, indices=[1, 3, 3]) 

def test_validate_ndim():
    values = np.array([1.0, 2.0])
    placement = slice(2)
    msg = "Wrong number of dimensions. values.ndim != ndim \[1 != 2\]"

    with tm.assert_raises_regex(ValueError, msg):
        make_block(values, placement, ndim=2) 

def test_fails_on_no_datetime_index(self):
        index_names = ('Int64Index', 'Index', 'Float64Index', 'MultiIndex')
        index_funcs = (tm.makeIntIndex,
                       tm.makeUnicodeIndex, tm.makeFloatIndex,
                       lambda m: tm.makeCustomIndex(m, 2))
        n = 2
        for name, func in zip(index_names, index_funcs):
            index = func(n)
            df = DataFrame({'a': np.random.randn(n)}, index=index)
            with tm.assert_raises_regex(TypeError,
                                        "Only valid with "
                                        "DatetimeIndex, TimedeltaIndex "
                                        "or PeriodIndex, but got an "
                                        "instance of %r" % name):
                df.groupby(TimeGrouper('D')) 

def test_numpy_compat(self):
        # see gh-12811
        s = Series([1, 2, 3, 4, 5], index=date_range(
            '20130101', periods=5, freq='s'))
        r = s.resample('2s')

        msg = "numpy operations are not valid with resample"

        for func in ('min', 'max', 'sum', 'prod',
                     'mean', 'var', 'std'):
            tm.assert_raises_regex(UnsupportedFunctionCall, msg,
                                   getattr(r, func),
                                   func, 1, 2, 3)
            tm.assert_raises_regex(UnsupportedFunctionCall, msg,
                                   getattr(r, func), axis=1) 

def test_numpy_cumsum(self):
        non_null_data = np.array([1, 2, 3, 4, 5], dtype=float)
        non_null_expected = SparseArray(non_null_data.cumsum())

        null_data = np.array([1, 2, np.nan, 4, 5], dtype=float)
        null_expected = SparseArray(np.array([1.0, 3.0, np.nan, 7.0, 12.0]))

        for data, expected in [
            (null_data, null_expected),
            (non_null_data, non_null_expected)
        ]:
            out = np.cumsum(SparseArray(data))
            tm.assert_sp_array_equal(out, expected)

            out = np.cumsum(SparseArray(data, fill_value=np.nan))
            tm.assert_sp_array_equal(out, expected)

            out = np.cumsum(SparseArray(data, fill_value=2))
            tm.assert_sp_array_equal(out, expected)

            msg = "the 'dtype' parameter is not supported"
            tm.assert_raises_regex(ValueError, msg, np.cumsum,
                                   SparseArray(data), dtype=np.int64)

            msg = "the 'out' parameter is not supported"
            tm.assert_raises_regex(ValueError, msg, np.cumsum,
                                   SparseArray(data), out=out)