Python pandas.util.testing.assert_almost_equal() Examples

def check_pow(self, lhs, arith1, rhs):
        ex = 'lhs {0} rhs'.format(arith1)
        expected = self.get_expected_pow_result(lhs, rhs)
        result = pd.eval(ex, engine=self.engine, parser=self.parser)

        if (is_scalar(lhs) and is_scalar(rhs) and
                _is_py3_complex_incompat(result, expected)):
            pytest.raises(AssertionError, tm.assert_numpy_array_equal,
                          result, expected)
        else:
            tm.assert_almost_equal(result, expected)

            ex = '(lhs {0} rhs) {0} rhs'.format(arith1)
            result = pd.eval(ex, engine=self.engine, parser=self.parser)
            expected = self.get_expected_pow_result(
                self.get_expected_pow_result(lhs, rhs), rhs)
            tm.assert_almost_equal(result, expected) 

def check_compound_invert_op(self, lhs, cmp1, rhs):
        skip_these = 'in', 'not in'
        ex = '~(lhs {0} rhs)'.format(cmp1)

        if is_scalar(rhs) and cmp1 in skip_these:
            pytest.raises(TypeError, pd.eval, ex, engine=self.engine,
                          parser=self.parser, local_dict={'lhs': lhs,
                                                          'rhs': rhs})
        else:
            # compound
            if is_scalar(lhs) and is_scalar(rhs):
                lhs, rhs = map(lambda x: np.array([x]), (lhs, rhs))
            expected = _eval_single_bin(lhs, cmp1, rhs, self.engine)
            if is_scalar(expected):
                expected = not expected
            else:
                expected = ~expected
            result = pd.eval(ex, engine=self.engine, parser=self.parser)
            tm.assert_almost_equal(expected, result)

            # make sure the other engines work the same as this one
            for engine in self.current_engines:
                ev = pd.eval(ex, engine=self.engine, parser=self.parser)
                tm.assert_almost_equal(ev, result) 

def check_chained_cmp_op(self, lhs, cmp1, mid, cmp2, rhs):

        def check_operands(left, right, cmp_op):
            return _eval_single_bin(left, cmp_op, right, self.engine)

        lhs_new = check_operands(lhs, mid, cmp1)
        rhs_new = check_operands(mid, rhs, cmp2)

        if lhs_new is not None and rhs_new is not None:
            ex1 = 'lhs {0} mid {1} rhs'.format(cmp1, cmp2)
            ex2 = 'lhs {0} mid and mid {1} rhs'.format(cmp1, cmp2)
            ex3 = '(lhs {0} mid) & (mid {1} rhs)'.format(cmp1, cmp2)
            expected = _eval_single_bin(lhs_new, '&', rhs_new, self.engine)

            for ex in (ex1, ex2, ex3):
                result = pd.eval(ex, engine=self.engine,
                                 parser=self.parser)

                tm.assert_almost_equal(result, expected) 

def test_errorbar_asymmetrical(self):

        np.random.seed(0)
        err = np.random.rand(3, 2, 5)

        # each column is [0, 1, 2, 3, 4], [3, 4, 5, 6, 7]...
        df = DataFrame(np.arange(15).reshape(3, 5)).T

        ax = df.plot(yerr=err, xerr=err / 2)

        yerr_0_0 = ax.collections[1].get_paths()[0].vertices[:, 1]
        expected_0_0 = err[0, :, 0] * np.array([-1, 1])
        tm.assert_almost_equal(yerr_0_0, expected_0_0)

        with pytest.raises(ValueError):
            df.plot(yerr=err.T)

        tm.close()

    # This XPASSES when tested with mpl == 3.0.1 

def test_slice_consolidate_invalidate_item_cache(self):

        # this is chained assignment, but will 'work'
        with option_context('chained_assignment', None):

            # #3970
            df = DataFrame({"aa": compat.lrange(5), "bb": [2.2] * 5})

            # Creates a second float block
            df["cc"] = 0.0

            # caches a reference to the 'bb' series
            df["bb"]

            # repr machinery triggers consolidation
            repr(df)

            # Assignment to wrong series
            df['bb'].iloc[0] = 0.17
            df._clear_item_cache()
            tm.assert_almost_equal(df['bb'][0], 0.17) 

def test_frame_getitem_setitem_boolean(
            self, multiindex_dataframe_random_data):
        frame = multiindex_dataframe_random_data
        df = frame.T.copy()
        values = df.values

        result = df[df > 0]
        expected = df.where(df > 0)
        tm.assert_frame_equal(result, expected)

        df[df > 0] = 5
        values[values > 0] = 5
        tm.assert_almost_equal(df.values, values)

        df[df == 5] = 0
        values[values == 5] = 0
        tm.assert_almost_equal(df.values, values)

        # a df that needs alignment first
        df[df[:-1] < 0] = 2
        np.putmask(values[:-1], values[:-1] < 0, 2)
        tm.assert_almost_equal(df.values, values)

        with pytest.raises(TypeError, match='boolean values only'):
            df[df * 0] = 2 

def check_values(self, f, func, values=False):

        if f is None:
            return
        axes = f.axes
        indicies = itertools.product(*axes)

        for i in indicies:
            result = getattr(f, func)[i]

            # check against values
            if values:
                expected = f.values[i]
            else:
                expected = f
                for a in reversed(i):
                    expected = expected.__getitem__(a)

            tm.assert_almost_equal(result, expected) 

def test_nanvar_ddof(self):
        n = 5
        samples = self.prng.uniform(size=(10000, n + 1))
        samples[:, -1] = np.nan  # Force use of our own algorithm.

        variance_0 = nanops.nanvar(samples, axis=1, skipna=True, ddof=0).mean()
        variance_1 = nanops.nanvar(samples, axis=1, skipna=True, ddof=1).mean()
        variance_2 = nanops.nanvar(samples, axis=1, skipna=True, ddof=2).mean()

        # The unbiased estimate.
        var = 1.0 / 12
        tm.assert_almost_equal(variance_1, var,
                               check_less_precise=2)

        # The underestimated variance.
        tm.assert_almost_equal(variance_0, (n - 1.0) / n * var,
                               check_less_precise=2)

        # The overestimated variance.
        tm.assert_almost_equal(variance_2, (n - 1.0) / (n - 2.0) * var,
                               check_less_precise=2) 

def test_set_value(self):
        for item in self.panel.items:
            for mjr in self.panel.major_axis[::2]:
                for mnr in self.panel.minor_axis:
                    with tm.assert_produces_warning(FutureWarning,
                                                    check_stacklevel=False):
                        self.panel.set_value(item, mjr, mnr, 1.)
                    tm.assert_almost_equal(self.panel[item][mnr][mjr], 1.)

        # resize
        with catch_warnings():
            simplefilter("ignore", FutureWarning)
            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 pytest.raises(TypeError, match=msg):
                self.panel.set_value('a') 

def test_constructor_cast(self):
        zero_filled = self.panel.fillna(0)

        casted = Panel(zero_filled._data, dtype=int)
        casted2 = Panel(zero_filled.values, dtype=int)

        exp_values = zero_filled.values.astype(int)
        assert_almost_equal(casted.values, exp_values)
        assert_almost_equal(casted2.values, exp_values)

        casted = Panel(zero_filled._data, dtype=np.int32)
        casted2 = Panel(zero_filled.values, dtype=np.int32)

        exp_values = zero_filled.values.astype(np.int32)
        assert_almost_equal(casted.values, exp_values)
        assert_almost_equal(casted2.values, exp_values)

        # can't cast
        data = [[['foo', 'bar', 'baz']]]
        pytest.raises(ValueError, Panel, data, dtype=float) 

def test_apply(frame):
    applied = frame.apply(np.sqrt)
    assert isinstance(applied, SparseDataFrame)
    tm.assert_almost_equal(applied.values, np.sqrt(frame.values))

    # agg / broadcast
    with tm.assert_produces_warning(FutureWarning):
        broadcasted = frame.apply(np.sum, broadcast=True)
    assert isinstance(broadcasted, SparseDataFrame)

    with tm.assert_produces_warning(FutureWarning):
        exp = frame.to_dense().apply(np.sum, broadcast=True)
    tm.assert_frame_equal(broadcasted.to_dense(), exp)

    applied = frame.apply(np.sum)
    tm.assert_series_equal(applied,
                           frame.to_dense().apply(nanops.nansum).to_sparse()) 

def test_tdi_total_seconds(self):
        # GH#10939
        # test index
        rng = timedelta_range('1 days, 10:11:12.100123456', periods=2,
                              freq='s')
        expt = [1 * 86400 + 10 * 3600 + 11 * 60 + 12 + 100123456. / 1e9,
                1 * 86400 + 10 * 3600 + 11 * 60 + 13 + 100123456. / 1e9]
        tm.assert_almost_equal(rng.total_seconds(), Index(expt))

        # test Series
        ser = Series(rng)
        s_expt = Series(expt, index=[0, 1])
        tm.assert_series_equal(ser.dt.total_seconds(), s_expt)

        # with nat
        ser[1] = np.nan
        s_expt = Series([1 * 86400 + 10 * 3600 + 11 * 60 +
                         12 + 100123456. / 1e9, np.nan], index=[0, 1])
        tm.assert_series_equal(ser.dt.total_seconds(), s_expt)

        # with both nat
        ser = Series([np.nan, np.nan], dtype='timedelta64[ns]')
        tm.assert_series_equal(ser.dt.total_seconds(),
                               Series([np.nan, np.nan], index=[0, 1])) 

def _check_data(self, xp, rs):
        """
        Check each axes has identical lines

        Parameters
        ----------
        xp : matplotlib Axes object
        rs : matplotlib Axes object
        """
        xp_lines = xp.get_lines()
        rs_lines = rs.get_lines()

        def check_line(xpl, rsl):
            xpdata = xpl.get_xydata()
            rsdata = rsl.get_xydata()
            tm.assert_almost_equal(xpdata, rsdata)

        assert len(xp_lines) == len(rs_lines)
        [check_line(xpl, rsl) for xpl, rsl in zip(xp_lines, rs_lines)]
        tm.close() 

def test_nans_skipna(self):
        samples = np.hstack([self.samples, np.nan])
        skew = nanops.nanskew(samples, skipna=True)
        tm.assert_almost_equal(skew, self.actual_skew) 

def test_axis(self):
        samples = np.vstack([self.samples,
                             np.nan * np.ones(len(self.samples))])
        skew = nanops.nanskew(samples, axis=1)
        tm.assert_almost_equal(skew, np.array([self.actual_skew, np.nan])) 

def test_binary_functions(self):
        df = DataFrame({'a': np.random.randn(10),
                        'b': np.random.randn(10)})
        a = df.a
        b = df.b
        for fn in self.binary_fns:
            expr = "{0}(a, b)".format(fn)
            got = self.eval(expr)
            with np.errstate(all='ignore'):
                expect = getattr(np, fn)(a, b)
            tm.assert_almost_equal(got, expect, check_names=False) 

def check_alignment(self, result, nlhs, ghs, op):
        try:
            nlhs, ghs = nlhs.align(ghs)
        except (ValueError, TypeError, AttributeError):
            # ValueError: series frame or frame series align
            # TypeError, AttributeError: series or frame with scalar align
            pass
        else:
            expected = eval('nlhs {0} ghs'.format(op))
            tm.assert_almost_equal(result, expected) 

def check_modulus(self, lhs, arith1, rhs):
        ex = 'lhs {0} rhs'.format(arith1)
        result = pd.eval(ex, engine=self.engine, parser=self.parser)

        expected = lhs % rhs
        tm.assert_almost_equal(result, expected)

        expected = _eval_single_bin(expected, arith1, rhs, self.engine)
        tm.assert_almost_equal(result, expected) 

def test_axis(self):
        samples = np.vstack([self.samples,
                             np.nan * np.ones(len(self.samples))])
        kurt = nanops.nankurt(samples, axis=1)
        tm.assert_almost_equal(kurt, np.array([self.actual_kurt, np.nan])) 

def test_tab_completion_with_categorical(self):
        # test the tab completion display
        ok_for_cat = ['name', 'index', 'categorical', 'categories', 'codes',
                      'ordered', 'set_categories', 'add_categories',
                      'remove_categories', 'rename_categories',
                      'reorder_categories', 'remove_unused_categories',
                      'as_ordered', 'as_unordered']

        def get_dir(s):
            results = [r for r in s.cat.__dir__() if not r.startswith('_')]
            return list(sorted(set(results)))

        s = Series(list('aabbcde')).astype('category')
        results = get_dir(s)
        tm.assert_almost_equal(results, list(sorted(set(ok_for_cat)))) 

def test_string_index_alias_tz_aware(self, tz):
        rng = date_range('1/1/2000', periods=10, tz=tz)
        ser = Series(np.random.randn(len(rng)), index=rng)

        result = ser['1/3/2000']
        tm.assert_almost_equal(result, ser[2])

    # TODO: De-duplicate with test below 

def check_modulus(self, lhs, arith1, rhs):
        ex = 'lhs {0} rhs'.format(arith1)
        result = pd.eval(ex, engine=self.engine, parser=self.parser)
        expected = lhs % rhs

        tm.assert_almost_equal(result, expected)
        expected = self.ne.evaluate('expected {0} rhs'.format(arith1))
        if isinstance(result, (DataFrame, Series)):
            tm.assert_almost_equal(result.values, expected)
        else:
            tm.assert_almost_equal(result, expected.item()) 

def check_binary_arith_op(self, lhs, arith1, rhs):
        ex = 'lhs {0} rhs'.format(arith1)
        result = pd.eval(ex, engine=self.engine, parser=self.parser)
        expected = _eval_single_bin(lhs, arith1, rhs, self.engine)

        tm.assert_almost_equal(result, expected)
        ex = 'lhs {0} rhs {0} rhs'.format(arith1)
        result = pd.eval(ex, engine=self.engine, parser=self.parser)
        nlhs = _eval_single_bin(lhs, arith1, rhs,
                                self.engine)
        self.check_alignment(result, nlhs, rhs, arith1) 

def test_getitem_setitem_integers():
    # caused bug without test
    s = Series([1, 2, 3], ['a', 'b', 'c'])

    assert s.iloc[0] == s['a']
    s.iloc[0] = 5
    tm.assert_almost_equal(s['a'], 5) 

def check(self, namespace, expected, ignored=None):
        # see which names are in the namespace, minus optional
        # ignored ones
        # compare vs the expected

        result = sorted(f for f in dir(namespace) if not f.startswith('_'))
        if ignored is not None:
            result = sorted(list(set(result) - set(ignored)))

        expected = sorted(expected)
        tm.assert_almost_equal(result, expected) 

def test_conversion_float(self):
        decimals = 9

        rs = self.dtc.convert(
            Timestamp('2012-1-1 01:02:03', tz='UTC'), None, None)
        xp = converter.dates.date2num(Timestamp('2012-1-1 01:02:03', tz='UTC'))
        tm.assert_almost_equal(rs, xp, decimals)

        rs = self.dtc.convert(
            Timestamp('2012-1-1 09:02:03', tz='Asia/Hong_Kong'), None, None)
        tm.assert_almost_equal(rs, xp, decimals)

        rs = self.dtc.convert(datetime(2012, 1, 1, 1, 2, 3), None, None)
        tm.assert_almost_equal(rs, xp, decimals) 

def test_corr(self, datetime_series):
        import scipy.stats as stats

        # full overlap
        tm.assert_almost_equal(datetime_series.corr(datetime_series), 1)

        # partial overlap
        tm.assert_almost_equal(datetime_series[:15].corr(datetime_series[5:]),
                               1)

        assert isna(datetime_series[:15].corr(datetime_series[5:],
                    min_periods=12))

        ts1 = datetime_series[:15].reindex(datetime_series.index)
        ts2 = datetime_series[5:].reindex(datetime_series.index)
        assert isna(ts1.corr(ts2, min_periods=12))

        # No overlap
        assert np.isnan(datetime_series[::2].corr(datetime_series[1::2]))

        # all NA
        cp = datetime_series[:10].copy()
        cp[:] = np.nan
        assert isna(cp.corr(cp))

        A = tm.makeTimeSeries()
        B = tm.makeTimeSeries()
        result = A.corr(B)
        expected, _ = stats.pearsonr(A, B)
        tm.assert_almost_equal(result, expected) 

def test_bar_log(self):
        expected = np.array([1e-1, 1e0, 1e1, 1e2, 1e3, 1e4])

        _, ax = self.plt.subplots()
        ax = Series([200, 500]).plot.bar(log=True, ax=ax)
        tm.assert_numpy_array_equal(ax.yaxis.get_ticklocs(), expected)
        tm.close()

        _, ax = self.plt.subplots()
        ax = Series([200, 500]).plot.barh(log=True, ax=ax)
        tm.assert_numpy_array_equal(ax.xaxis.get_ticklocs(), expected)
        tm.close()

        # GH 9905
        expected = np.array([1e-5, 1e-4, 1e-3, 1e-2, 1e-1, 1e0, 1e1])

        _, ax = self.plt.subplots()
        ax = Series([0.1, 0.01, 0.001]).plot(log=True, kind='bar', ax=ax)
        ymin = 0.0007943282347242822
        ymax = 0.12589254117941673
        res = ax.get_ylim()
        tm.assert_almost_equal(res[0], ymin)
        tm.assert_almost_equal(res[1], ymax)
        tm.assert_numpy_array_equal(ax.yaxis.get_ticklocs(), expected)
        tm.close()

        _, ax = self.plt.subplots()
        ax = Series([0.1, 0.01, 0.001]).plot(log=True, kind='barh', ax=ax)
        res = ax.get_xlim()
        tm.assert_almost_equal(res[0], ymin)
        tm.assert_almost_equal(res[1], ymax)
        tm.assert_numpy_array_equal(ax.xaxis.get_ticklocs(), expected) 

def test_at_and_iat_set(self):
        def _check(f, func, values=False):

            if f is not None:
                indicies = self.generate_indices(f, values)
                for i in indicies:
                    getattr(f, func)[i] = 1
                    expected = self.get_value(f, i, values)
                    tm.assert_almost_equal(expected, 1)

        for t in self._objs:

            d = getattr(self, t)

            # iat
            for f in [d['ints'], d['uints']]:
                _check(f, 'iat', values=True)

            for f in [d['labels'], d['ts'], d['floats']]:
                if f is not None:
                    pytest.raises(ValueError, _check, f, 'iat')

            # at
            for f in [d['ints'], d['uints'], d['labels'],
                      d['ts'], d['floats']]:
                _check(f, 'at') 

def check_reduce(self, s, op_name, skipna):
        result = getattr(s, op_name)(skipna=skipna)
        expected = getattr(s.astype('float64'), op_name)(skipna=skipna)
        tm.assert_almost_equal(result, expected)