Python pandas.compat.range() Examples

def test_index_groupby(self):
        int_idx = Index(range(6))
        float_idx = Index(np.arange(0, 0.6, 0.1))
        obj_idx = Index('A B C D E F'.split())
        dt_idx = pd.date_range('2013-01-01', freq='M', periods=6)

        for idx in [int_idx, float_idx, obj_idx, dt_idx]:
            to_groupby = np.array([1, 2, np.nan, np.nan, 2, 1])
            tm.assert_dict_equal(idx.groupby(to_groupby),
                                 {1.0: idx[[0, 5]], 2.0: idx[[1, 4]]})

            to_groupby = Index([datetime(2011, 11, 1),
                                datetime(2011, 12, 1),
                                pd.NaT,
                                pd.NaT,
                                datetime(2011, 12, 1),
                                datetime(2011, 11, 1)],
                               tz='UTC').values

            ex_keys = [Timestamp('2011-11-01'), Timestamp('2011-12-01')]
            expected = {ex_keys[0]: idx[[0, 5]],
                        ex_keys[1]: idx[[1, 4]]}
            tm.assert_dict_equal(idx.groupby(to_groupby), expected) 

def test_to_xarray_index_types(self, index):
        from xarray import DataArray

        index = getattr(tm, 'make{}'.format(index))
        s = Series(range(6), index=index(6))
        s.index.name = 'foo'
        result = s.to_xarray()
        repr(result)
        assert len(result) == 6
        assert len(result.coords) == 1
        assert_almost_equal(list(result.coords.keys()), ['foo'])
        assert isinstance(result, DataArray)

        # idempotency
        assert_series_equal(result.to_series(), s,
                            check_index_type=False,
                            check_categorical=True) 

def test_expanding_axis(self, axis_frame):
        # see gh-23372.
        df = DataFrame(np.ones((10, 20)))
        axis = df._get_axis_number(axis_frame)

        if axis == 0:
            expected = DataFrame({
                i: [np.nan] * 2 + [float(j) for j in range(3, 11)]
                for i in range(20)
            })
        else:
            # axis == 1
            expected = DataFrame([
                [np.nan] * 2 + [float(i) for i in range(3, 21)]
            ] * 10)

        result = df.expanding(3, axis=axis_frame).sum()
        tm.assert_frame_equal(result, expected) 

def test_cmov_window_special_linear_range(self, win_types_special):
        # GH 8238
        kwds = {
            'kaiser': {'beta': 1.},
            'gaussian': {'std': 1.},
            'general_gaussian': {'power': 2., 'width': 2.},
            'slepian': {'width': 0.5}}

        vals = np.array(range(10), dtype=np.float)
        xp = vals.copy()
        xp[:2] = np.nan
        xp[-2:] = np.nan
        xp = Series(xp)

        rs = Series(vals).rolling(
            5, win_type=win_types_special, center=True).mean(
            **kwds[win_types_special])
        tm.assert_series_equal(xp, rs) 

def test_corr_sanity(self):
        # GH 3155
        df = DataFrame(np.array(
            [[0.87024726, 0.18505595], [0.64355431, 0.3091617],
             [0.92372966, 0.50552513], [0.00203756, 0.04520709],
             [0.84780328, 0.33394331], [0.78369152, 0.63919667]]))

        res = df[0].rolling(5, center=True).corr(df[1])
        assert all(np.abs(np.nan_to_num(x)) <= 1 for x in res)

        # and some fuzzing
        for _ in range(10):
            df = DataFrame(np.random.rand(30, 2))
            res = df[0].rolling(5, center=True).corr(df[1])
            try:
                assert all(np.abs(np.nan_to_num(x)) <= 1 for x in res)
            except AssertionError:
                print(res) 

def test_get_numeric_data(self):

        n = 4
        kwargs = {self._typ._AXIS_NAMES[i]: list(range(n))
                  for i in range(self._ndim)}

        # get the numeric data
        o = self._construct(n, **kwargs)
        result = o._get_numeric_data()
        self._compare(result, o)

        # non-inclusion
        result = o._get_bool_data()
        expected = self._construct(n, value='empty', **kwargs)
        self._compare(result, expected)

        # get the bool data
        arr = np.array([True, True, False, True])
        o = self._construct(n, value=arr, **kwargs)
        result = o._get_numeric_data()
        self._compare(result, o)

        # _get_numeric_data is includes _get_bool_data, so can't test for
        # non-inclusion 

def test_rolling_axis(self, axis_frame):
        # see gh-23372.
        df = DataFrame(np.ones((10, 20)))
        axis = df._get_axis_number(axis_frame)

        if axis == 0:
            expected = DataFrame({
                i: [np.nan] * 2 + [3.0] * 8
                for i in range(20)
            })
        else:
            # axis == 1
            expected = DataFrame([
                [np.nan] * 2 + [3.0] * 18
            ] * 10)

        result = df.rolling(3, axis=axis_frame).sum()
        tm.assert_frame_equal(result, expected) 

def test_to_xarray(self):
        from xarray import DataArray

        s = Series([])
        s.index.name = 'foo'
        result = s.to_xarray()
        assert len(result) == 0
        assert len(result.coords) == 1
        assert_almost_equal(list(result.coords.keys()), ['foo'])
        assert isinstance(result, DataArray)

        s = Series(range(6))
        s.index.name = 'foo'
        s.index = pd.MultiIndex.from_product([['a', 'b'], range(3)],
                                             names=['one', 'two'])
        result = s.to_xarray()
        assert len(result) == 2
        assert_almost_equal(list(result.coords.keys()), ['one', 'two'])
        assert isinstance(result, DataArray)
        assert_series_equal(result.to_series(), s) 

def test_pandas_dtypes(self, col):
        # GH 15785
        df = DataFrame({'klass': range(5),
                        'col': col,
                        'attr1': [1, 0, 0, 0, 0],
                        'attr2': col})
        expected_value = pd.concat([pd.Series([1, 0, 0, 0, 0]), col],
                                   ignore_index=True)
        result = melt(df, id_vars=['klass', 'col'], var_name='attribute',
                      value_name='value')
        expected = DataFrame({0: list(range(5)) * 2,
                              1: pd.concat([col] * 2, ignore_index=True),
                              2: ['attr1'] * 5 + ['attr2'] * 5,
                              3: expected_value})
        expected.columns = ['klass', 'col', 'attribute', 'value']
        tm.assert_frame_equal(result, expected) 

def test_cache_updating():
    # 5216
    # make sure that we don't try to set a dead cache
    a = np.random.rand(10, 3)
    df = DataFrame(a, columns=['x', 'y', 'z'])
    tuples = [(i, j) for i in range(5) for j in range(2)]
    index = MultiIndex.from_tuples(tuples)
    df.index = index

    # setting via chained assignment
    # but actually works, since everything is a view
    df.loc[0]['z'].iloc[0] = 1.
    result = df.loc[(0, 0), 'z']
    assert result == 1

    # correct setting
    df.loc[(0, 0), 'z'] = 2
    result = df.loc[(0, 0), 'z']
    assert result == 2 

def apply(self, other):
        if self._use_relativedelta:
            other = as_datetime(other)

        if len(self.kwds) > 0:
            tzinfo = getattr(other, 'tzinfo', None)
            if tzinfo is not None and self._use_relativedelta:
                # perform calculation in UTC
                other = other.replace(tzinfo=None)

            if self.n > 0:
                for i in range(self.n):
                    other = other + self._offset
            else:
                for i in range(-self.n):
                    other = other - self._offset

            if tzinfo is not None and self._use_relativedelta:
                # bring tz back from UTC calculation
                other = conversion.localize_pydatetime(other, tzinfo)

            return as_timestamp(other)
        else:
            return other + timedelta(self.n) 

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_rolling_functions_window_non_shrinkage(self, f):
        # GH 7764
        s = Series(range(4))
        s_expected = Series(np.nan, index=s.index)
        df = DataFrame([[1, 5], [3, 2], [3, 9], [-1, 0]], columns=['A', 'B'])
        df_expected = DataFrame(np.nan, index=df.index, columns=df.columns)

        try:
            s_result = f(s)
            tm.assert_series_equal(s_result, s_expected)

            df_result = f(df)
            tm.assert_frame_equal(df_result, df_expected)
        except (ImportError):

            # scipy needed for rolling_window
            pytest.skip("scipy not available") 

def test_expanding_corr_pairwise_diff_length(self):
        # GH 7512
        df1 = DataFrame([[1, 2], [3, 2], [3, 4]],
                        columns=['A', 'B'],
                        index=Index(range(3), name='bar'))
        df1a = DataFrame([[1, 2], [3, 4]],
                         index=Index([0, 2], name='bar'),
                         columns=['A', 'B'])
        df2 = DataFrame([[5, 6], [None, None], [2, 1]],
                        columns=['X', 'Y'],
                        index=Index(range(3), name='bar'))
        df2a = DataFrame([[5, 6], [2, 1]],
                         index=Index([0, 2], name='bar'),
                         columns=['X', 'Y'])
        result1 = df1.expanding().corr(df2, pairwise=True).loc[2]
        result2 = df1.expanding().corr(df2a, pairwise=True).loc[2]
        result3 = df1a.expanding().corr(df2, pairwise=True).loc[2]
        result4 = df1a.expanding().corr(df2a, pairwise=True).loc[2]
        expected = DataFrame([[-1.0, -1.0], [-1.0, -1.0]],
                             columns=['A', 'B'],
                             index=Index(['X', 'Y']))
        tm.assert_frame_equal(result1, expected)
        tm.assert_frame_equal(result2, expected)
        tm.assert_frame_equal(result3, expected)
        tm.assert_frame_equal(result4, expected) 

def test_rolling_max_gh6297(self):
        """Replicate result expected in GH #6297"""

        indices = [datetime(1975, 1, i) for i in range(1, 6)]
        # So that we can have 2 datapoints on one of the days
        indices.append(datetime(1975, 1, 3, 6, 0))
        series = Series(range(1, 7), index=indices)
        # Use floats instead of ints as values
        series = series.map(lambda x: float(x))
        # Sort chronologically
        series = series.sort_index()

        expected = Series([1.0, 2.0, 6.0, 4.0, 5.0],
                          index=[datetime(1975, 1, i, 0) for i in range(1, 6)])
        x = series.resample('D').max().rolling(window=1).max()
        tm.assert_series_equal(expected, x) 

def test_rolling_min_resample(self):

        indices = [datetime(1975, 1, i) for i in range(1, 6)]
        # So that we can have 3 datapoints on last day (4, 10, and 20)
        indices.append(datetime(1975, 1, 5, 1))
        indices.append(datetime(1975, 1, 5, 2))
        series = Series(list(range(0, 5)) + [10, 20], index=indices)
        # Use floats instead of ints as values
        series = series.map(lambda x: float(x))
        # Sort chronologically
        series = series.sort_index()

        # Default how should be min
        expected = Series([0.0, 1.0, 2.0, 3.0, 4.0],
                          index=[datetime(1975, 1, i, 0) for i in range(1, 6)])
        r = series.resample('D').min().rolling(window=1)
        tm.assert_series_equal(expected, r.min()) 

def test_rolling_median_resample(self):

        indices = [datetime(1975, 1, i) for i in range(1, 6)]
        # So that we can have 3 datapoints on last day (4, 10, and 20)
        indices.append(datetime(1975, 1, 5, 1))
        indices.append(datetime(1975, 1, 5, 2))
        series = Series(list(range(0, 5)) + [10, 20], index=indices)
        # Use floats instead of ints as values
        series = series.map(lambda x: float(x))
        # Sort chronologically
        series = series.sort_index()

        # Default how should be median
        expected = Series([0.0, 1.0, 2.0, 3.0, 10],
                          index=[datetime(1975, 1, i, 0) for i in range(1, 6)])
        x = series.resample('D').median().rolling(window=1).median()
        tm.assert_series_equal(expected, x) 

def test_rangeindex_fallback_coercion_bug():
    # GH 12893
    foo = pd.DataFrame(np.arange(100).reshape((10, 10)))
    bar = pd.DataFrame(np.arange(100).reshape((10, 10)))
    df = pd.concat({'foo': foo.stack(), 'bar': bar.stack()}, axis=1)
    df.index.names = ['fizz', 'buzz']

    str(df)
    expected = pd.DataFrame({'bar': np.arange(100),
                             'foo': np.arange(100)},
                            index=pd.MultiIndex.from_product(
                                [range(10), range(10)],
                                names=['fizz', 'buzz']))
    tm.assert_frame_equal(df, expected, check_like=True)

    result = df.index.get_level_values('fizz')
    expected = pd.Int64Index(np.arange(10), name='fizz').repeat(10)
    tm.assert_index_equal(result, expected)

    result = df.index.get_level_values('buzz')
    expected = pd.Int64Index(np.tile(np.arange(10), 10), name='buzz')
    tm.assert_index_equal(result, expected) 

def test_monotonic_on(self):

        # on/index must be monotonic
        df = DataFrame({'A': pd.date_range('20130101',
                                           periods=5,
                                           freq='s'),
                        'B': range(5)})

        assert df.A.is_monotonic
        df.rolling('2s', on='A').sum()

        df = df.set_index('A')
        assert df.index.is_monotonic
        df.rolling('2s').sum()

        # non-monotonic
        df.index = reversed(df.index.tolist())
        assert not df.index.is_monotonic

        with pytest.raises(ValueError):
            df.rolling('2s').sum()

        df = df.reset_index()
        with pytest.raises(ValueError):
            df.rolling('2s', on='A').sum() 

def _check_tick(self, base_delta, code):
        b = Timestamp(datetime.now())
        for i in range(1, 5):
            inc = base_delta * i
            index = _dti([b + inc * j for j in range(3)])
            if i > 1:
                exp_freq = '%d%s' % (i, code)
            else:
                exp_freq = code
            assert frequencies.infer_freq(index) == exp_freq

        index = _dti([b + base_delta * 7] + [b + base_delta * j for j in range(
            3)])
        assert frequencies.infer_freq(index) is None

        index = _dti([b + base_delta * j for j in range(3)] + [b + base_delta *
                                                               7])

        assert frequencies.infer_freq(index) is None 

def test_large_multiindex_error():
    # GH12527
    df_below_1000000 = pd.DataFrame(
        1, index=pd.MultiIndex.from_product([[1, 2], range(499999)]),
        columns=['dest'])
    with pytest.raises(KeyError):
        df_below_1000000.loc[(-1, 0), 'dest']
    with pytest.raises(KeyError):
        df_below_1000000.loc[(3, 0), 'dest']
    df_above_1000000 = pd.DataFrame(
        1, index=pd.MultiIndex.from_product([[1, 2], range(500001)]),
        columns=['dest'])
    with pytest.raises(KeyError):
        df_above_1000000.loc[(-1, 0), 'dest']
    with pytest.raises(KeyError):
        df_above_1000000.loc[(3, 0), 'dest'] 

def test_labels_dtypes():

    # GH 8456
    i = MultiIndex.from_tuples([('A', 1), ('A', 2)])
    assert i.codes[0].dtype == 'int8'
    assert i.codes[1].dtype == 'int8'

    i = MultiIndex.from_product([['a'], range(40)])
    assert i.codes[1].dtype == 'int8'
    i = MultiIndex.from_product([['a'], range(400)])
    assert i.codes[1].dtype == 'int16'
    i = MultiIndex.from_product([['a'], range(40000)])
    assert i.codes[1].dtype == 'int32'

    i = pd.MultiIndex.from_product([['a'], range(1000)])
    assert (i.codes[0] >= 0).all()
    assert (i.codes[1] >= 0).all() 

def test_onOffset(self, offset_types):
        dt = self.expecteds[offset_types.__name__]
        offset_s = self._get_offset(offset_types)
        assert offset_s.onOffset(dt)

        # when normalize=True, onOffset checks time is 00:00:00
        if issubclass(offset_types, Tick):
            # normalize=True disallowed for Tick subclasses GH#21427
            return
        offset_n = self._get_offset(offset_types, normalize=True)
        assert not offset_n.onOffset(dt)

        if offset_types in (BusinessHour, CustomBusinessHour):
            # In default BusinessHour (9:00-17:00), normalized time
            # cannot be in business hour range
            return
        date = datetime(dt.year, dt.month, dt.day)
        assert offset_n.onOffset(date) 

def test_pie_df_nan(self):
        df = DataFrame(np.random.rand(4, 4))
        for i in range(4):
            df.iloc[i, i] = np.nan
        fig, axes = self.plt.subplots(ncols=4)
        df.plot.pie(subplots=True, ax=axes, legend=True)

        base_expected = ['0', '1', '2', '3']
        for i, ax in enumerate(axes):
            expected = list(base_expected)  # force copy
            expected[i] = ''
            result = [x.get_text() for x in ax.texts]
            assert result == expected
            # legend labels
            # NaN's not included in legend with subplots
            # see https://github.com/pandas-dev/pandas/issues/8390
            assert ([x.get_text() for x in ax.get_legend().get_texts()] ==
                    base_expected[:i] + base_expected[i + 1:]) 

def test_set_labels_deprecated():
    # GH23752
    ind = pd.MultiIndex.from_tuples([(0, i) for i in range(130)])
    new_labels = range(129, -1, -1)
    expected = pd.MultiIndex.from_tuples(
        [(0, i) for i in new_labels])

    # [w/o mutation]
    with tm.assert_produces_warning(FutureWarning):
        result = ind.set_labels(labels=new_labels, level=1)
    assert result.equals(expected)

    # [w/ mutation]
    result = ind.copy()
    with tm.assert_produces_warning(FutureWarning):
        result.set_labels(labels=new_labels, level=1, inplace=True)
    assert result.equals(expected) 

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) 

def test_rolling_functions_window_non_shrinkage_binary(self):

        # corr/cov return a MI DataFrame
        df = DataFrame([[1, 5], [3, 2], [3, 9], [-1, 0]],
                       columns=Index(['A', 'B'], name='foo'),
                       index=Index(range(4), name='bar'))
        df_expected = DataFrame(
            columns=Index(['A', 'B'], name='foo'),
            index=pd.MultiIndex.from_product([df.index, df.columns],
                                             names=['bar', 'foo']),
            dtype='float64')
        functions = [lambda x: (x.rolling(window=10, min_periods=5)
                                .cov(x, pairwise=True)),
                     lambda x: (x.rolling(window=10, min_periods=5)
                                .corr(x, pairwise=True))]
        for f in functions:
            df_result = f(df)
            tm.assert_frame_equal(df_result, df_expected) 

def test_errorbar_scatter(self):
        df = DataFrame(
            np.random.randn(5, 2), index=range(5), columns=['x', 'y'])
        df_err = DataFrame(np.random.randn(5, 2) / 5,
                           index=range(5), columns=['x', 'y'])

        ax = _check_plot_works(df.plot.scatter, x='x', y='y')
        self._check_has_errorbars(ax, xerr=0, yerr=0)
        ax = _check_plot_works(df.plot.scatter, x='x', y='y', xerr=df_err)
        self._check_has_errorbars(ax, xerr=1, yerr=0)

        ax = _check_plot_works(df.plot.scatter, x='x', y='y', yerr=df_err)
        self._check_has_errorbars(ax, xerr=0, yerr=1)
        ax = _check_plot_works(df.plot.scatter, x='x', y='y', xerr=df_err,
                               yerr=df_err)
        self._check_has_errorbars(ax, xerr=1, yerr=1)

        def _check_errorbar_color(containers, expected, has_err='has_xerr'):
            lines = []
            errs = [c.lines
                    for c in ax.containers if getattr(c, has_err, False)][0]
            for el in errs:
                if is_list_like(el):
                    lines.extend(el)
                else:
                    lines.append(el)
            err_lines = [x for x in lines if x in ax.collections]
            self._check_colors(
                err_lines, linecolors=np.array([expected] * len(err_lines)))

        # GH 8081
        df = DataFrame(
            np.random.randn(10, 5), columns=['a', 'b', 'c', 'd', 'e'])
        ax = df.plot.scatter(x='a', y='b', xerr='d', yerr='e', c='red')
        self._check_has_errorbars(ax, xerr=1, yerr=1)
        _check_errorbar_color(ax.containers, 'red', has_err='has_xerr')
        _check_errorbar_color(ax.containers, 'red', has_err='has_yerr')

        ax = df.plot.scatter(x='a', y='b', yerr='e', color='green')
        self._check_has_errorbars(ax, xerr=0, yerr=1)
        _check_errorbar_color(ax.containers, 'green', has_err='has_yerr') 

def test_pivot_integer_columns(self):
        # caused by upstream bug in unstack

        d = date.min
        data = list(product(['foo', 'bar'], ['A', 'B', 'C'], ['x1', 'x2'],
                            [d + timedelta(i)
                             for i in range(20)], [1.0]))
        df = DataFrame(data)
        table = df.pivot_table(values=4, index=[0, 1, 3], columns=[2])

        df2 = df.rename(columns=str)
        table2 = df2.pivot_table(
            values='4', index=['0', '1', '3'], columns=['2'])

        tm.assert_frame_equal(table, table2, check_names=False) 

def test_monthly(self):
        rng = date_range('1/1/2000', '12/31/2004', freq='M')
        ts = Series(np.random.randn(len(rng)), index=rng)

        annual = pivot_table(pd.DataFrame(ts), index=ts.index.year,
                             columns=ts.index.month)
        annual.columns = annual.columns.droplevel(0)

        month = ts.index.month
        for i in range(1, 13):
            subset = ts[month == i]
            subset.index = subset.index.year
            result = annual[i].dropna()
            tm.assert_series_equal(result, subset, check_names=False)
            assert result.name == i