Python pandas.compat.lrange() Examples

def test_droplevel_list():
    index = MultiIndex(
        levels=[Index(lrange(4)), Index(lrange(4)), Index(lrange(4))],
        codes=[np.array([0, 0, 1, 2, 2, 2, 3, 3]), np.array(
            [0, 1, 0, 0, 0, 1, 0, 1]), np.array([1, 0, 1, 1, 0, 0, 1, 0])],
        names=['one', 'two', 'three'])

    dropped = index[:2].droplevel(['three', 'one'])
    expected = index[:2].droplevel(2).droplevel(0)
    assert dropped.equals(expected)

    dropped = index[:2].droplevel([])
    expected = index[:2]
    assert dropped.equals(expected)

    with pytest.raises(ValueError):
        index[:2].droplevel(['one', 'two', 'three'])

    with pytest.raises(KeyError):
        index[:2].droplevel(['one', 'four']) 

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_pad(self):
        old = Index([1, 5, 10])
        new = Index(lrange(12))

        filler = libalgos.pad["int64_t"](old.values, new.values)

        expect_filler = np.array([-1, 0, 0, 0, 0, 1,
                                  1, 1, 1, 1, 2, 2], dtype=np.int64)
        tm.assert_numpy_array_equal(filler, expect_filler)

        # corner case
        old = Index([5, 10])
        new = Index(lrange(5))
        filler = libalgos.pad["int64_t"](old.values, new.values)
        expect_filler = np.array([-1, -1, -1, -1, -1], dtype=np.int64)
        tm.assert_numpy_array_equal(filler, expect_filler) 

def test_backfill(self):
        old = Index([1, 5, 10])
        new = Index(lrange(12))

        filler = libalgos.backfill["int64_t"](old.values, new.values)

        expect_filler = np.array([0, 0, 1, 1, 1, 1,
                                  2, 2, 2, 2, 2, -1], dtype=np.int64)
        tm.assert_numpy_array_equal(filler, expect_filler)

        # corner case
        old = Index([1, 4])
        new = Index(lrange(5, 10))
        filler = libalgos.backfill["int64_t"](old.values, new.values)

        expect_filler = np.array([-1, -1, -1, -1, -1], dtype=np.int64)
        tm.assert_numpy_array_equal(filler, expect_filler) 

def __call__(self):
        'Return the locations of the ticks.'
        # axis calls Locator.set_axis inside set_m<xxxx>_formatter
        _check_implicitly_registered()

        vi = tuple(self.axis.get_view_interval())
        if vi != self.plot_obj.view_interval:
            self.plot_obj.date_axis_info = None
        self.plot_obj.view_interval = vi
        vmin, vmax = vi
        if vmax < vmin:
            vmin, vmax = vmax, vmin
        if self.isdynamic:
            locs = self._get_default_locs(vmin, vmax)
        else:  # pragma: no cover
            base = self.base
            (d, m) = divmod(vmin, base)
            vmin = (d + 1) * base
            locs = lrange(vmin, vmax + 1, base)
        return locs 

def test_argsort(self, datetime_series):
        self._check_accum_op('argsort', datetime_series, check_dtype=False)
        argsorted = datetime_series.argsort()
        assert issubclass(argsorted.dtype.type, np.integer)

        # GH 2967 (introduced bug in 0.11-dev I think)
        s = Series([Timestamp('201301%02d' % (i + 1)) for i in range(5)])
        assert s.dtype == 'datetime64[ns]'
        shifted = s.shift(-1)
        assert shifted.dtype == 'datetime64[ns]'
        assert isna(shifted[4])

        result = s.argsort()
        expected = Series(lrange(5), dtype='int64')
        assert_series_equal(result, expected)

        result = shifted.argsort()
        expected = Series(lrange(4) + [-1], dtype='int64')
        assert_series_equal(result, expected) 

def test_getitem_setitem_slice_bug():
    s = Series(lrange(10), lrange(10))
    result = s[-12:]
    assert_series_equal(result, s)

    result = s[-7:]
    assert_series_equal(result, s[3:])

    result = s[:-12]
    assert_series_equal(result, s[:0])

    s = Series(lrange(10), lrange(10))
    s[-12:] = 0
    assert (s == 0).all()

    s[:-12] = 5
    assert (s == 0).all() 

def test_truncate():
    major_axis = Index(lrange(4))
    minor_axis = Index(lrange(2))

    major_codes = np.array([0, 0, 1, 2, 3, 3])
    minor_codes = np.array([0, 1, 0, 1, 0, 1])

    index = MultiIndex(levels=[major_axis, minor_axis],
                       codes=[major_codes, minor_codes])

    result = index.truncate(before=1)
    assert 'foo' not in result.levels[0]
    assert 1 in result.levels[0]

    result = index.truncate(after=1)
    assert 2 not in result.levels[0]
    assert 1 in result.levels[0]

    result = index.truncate(before=1, after=2)
    assert len(result.levels[0]) == 2

    # after < before
    pytest.raises(ValueError, index.truncate, 3, 1) 

def test_unsortedindex():
    # GH 11897
    mi = pd.MultiIndex.from_tuples([('z', 'a'), ('x', 'a'), ('y', 'b'),
                                    ('x', 'b'), ('y', 'a'), ('z', 'b')],
                                   names=['one', 'two'])
    df = pd.DataFrame([[i, 10 * i] for i in lrange(6)], index=mi,
                      columns=['one', 'two'])

    # GH 16734: not sorted, but no real slicing
    result = df.loc(axis=0)['z', 'a']
    expected = df.iloc[0]
    tm.assert_series_equal(result, expected)

    with pytest.raises(UnsortedIndexError):
        df.loc(axis=0)['z', slice('a')]
    df.sort_index(inplace=True)
    assert len(df.loc(axis=0)['z', :]) == 2

    with pytest.raises(KeyError):
        df.loc(axis=0)['q', :] 

def test_consistency():
    # need to construct an overflow
    major_axis = lrange(70000)
    minor_axis = lrange(10)

    major_codes = np.arange(70000)
    minor_codes = np.repeat(lrange(10), 7000)

    # the fact that is works means it's consistent
    index = MultiIndex(levels=[major_axis, minor_axis],
                       codes=[major_codes, minor_codes])

    # inconsistent
    major_codes = np.array([0, 0, 1, 1, 1, 2, 2, 3, 3])
    minor_codes = np.array([0, 1, 0, 1, 1, 0, 1, 0, 1])
    index = MultiIndex(levels=[major_axis, minor_axis],
                       codes=[major_codes, minor_codes])

    assert index.is_unique is False 

def test_iloc():
    s = Series(np.random.randn(10), index=lrange(0, 20, 2))

    for i in range(len(s)):
        result = s.iloc[i]
        exp = s[s.index[i]]
        assert_almost_equal(result, exp)

    # pass a slice
    result = s.iloc[slice(1, 3)]
    expected = s.loc[2:4]
    assert_series_equal(result, expected)

    # test slice is a view
    result[:] = 0
    assert (s[1:3] == 0).all()

    # list of integers
    result = s.iloc[[0, 2, 3, 4, 5]]
    expected = s.reindex(s.index[[0, 2, 3, 4, 5]])
    assert_series_equal(result, expected) 

def test_series_append_aware_naive(self):
        rng1 = date_range('1/1/2011 01:00', periods=1, freq='H')
        rng2 = date_range('1/1/2011 02:00', periods=1, freq='H',
                          tz='US/Eastern')
        ser1 = Series(np.random.randn(len(rng1)), index=rng1)
        ser2 = Series(np.random.randn(len(rng2)), index=rng2)
        ts_result = ser1.append(ser2)

        expected = ser1.index.astype(object).append(ser2.index.astype(object))
        assert ts_result.index.equals(expected)

        # mixed
        rng1 = date_range('1/1/2011 01:00', periods=1, freq='H')
        rng2 = lrange(100)
        ser1 = Series(np.random.randn(len(rng1)), index=rng1)
        ser2 = Series(np.random.randn(len(rng2)), index=rng2)
        ts_result = ser1.append(ser2)

        expected = ser1.index.astype(object).append(ser2.index)
        assert ts_result.index.equals(expected) 

def test_bar_edge(self):
        df = DataFrame({'A': [3] * 5, 'B': lrange(5)}, index=lrange(5))

        self._check_bar_alignment(df, kind='bar', stacked=True, align='edge')
        self._check_bar_alignment(df, kind='bar', stacked=True, width=0.9,
                                  align='edge')
        self._check_bar_alignment(df, kind='barh', stacked=True, align='edge')
        self._check_bar_alignment(df, kind='barh', stacked=True, width=0.9,
                                  align='edge')

        self._check_bar_alignment(df, kind='bar', stacked=False, align='edge')
        self._check_bar_alignment(df, kind='bar', stacked=False, width=0.9,
                                  align='edge')
        self._check_bar_alignment(df, kind='barh', stacked=False, align='edge')
        self._check_bar_alignment(df, kind='barh', stacked=False, width=0.9,
                                  align='edge')

        self._check_bar_alignment(df, kind='bar', subplots=True, align='edge')
        self._check_bar_alignment(df, kind='bar', subplots=True, width=0.9,
                                  align='edge')
        self._check_bar_alignment(df, kind='barh', subplots=True, align='edge')
        self._check_bar_alignment(df, kind='barh', subplots=True, width=0.9,
                                  align='edge') 

def test_name_printing(self):
        # Test small Series.
        s = Series([0, 1, 2])

        s.name = "test"
        assert "Name: test" in repr(s)

        s.name = None
        assert "Name:" not in repr(s)

        # Test big Series (diff code path).
        s = Series(lrange(0, 1000))

        s.name = "test"
        assert "Name: test" in repr(s)

        s.name = None
        assert "Name:" not in repr(s)

        s = Series(index=date_range('20010101', '20020101'), name='test')
        assert "Name: test" in repr(s) 

def test_astype_datetime(self):
        s = Series(iNaT, dtype='M8[ns]', index=lrange(5))

        s = s.astype('O')
        assert s.dtype == np.object_

        s = Series([datetime(2001, 1, 2, 0, 0)])

        s = s.astype('O')
        assert s.dtype == np.object_

        s = Series([datetime(2001, 1, 2, 0, 0) for i in range(3)])

        s[1] = np.nan
        assert s.dtype == 'M8[ns]'

        s = s.astype('O')
        assert s.dtype == np.object_ 

def test_frame_setitem_ix(self, multiindex_dataframe_random_data):
        frame = multiindex_dataframe_random_data
        frame.loc[('bar', 'two'), 'B'] = 5
        assert frame.loc[('bar', 'two'), 'B'] == 5

        # with integer labels
        df = frame.copy()
        df.columns = lrange(3)
        df.loc[('bar', 'two'), 1] = 7
        assert df.loc[('bar', 'two'), 1] == 7

        with catch_warnings(record=True):
            simplefilter("ignore", DeprecationWarning)
            df = frame.copy()
            df.columns = lrange(3)
            df.ix[('bar', 'two'), 1] = 7
        assert df.loc[('bar', 'two'), 1] == 7 

def test_loc_getitem_setitem_integer_slice_keyerrors():
    s = Series(np.random.randn(10), index=lrange(0, 20, 2))

    # this is OK
    cp = s.copy()
    cp.iloc[4:10] = 0
    assert (cp.iloc[4:10] == 0).all()

    # so is this
    cp = s.copy()
    cp.iloc[3:11] = 0
    assert (cp.iloc[3:11] == 0).values.all()

    result = s.iloc[2:6]
    result2 = s.loc[3:11]
    expected = s.reindex([4, 6, 8, 10])

    assert_series_equal(result, expected)
    assert_series_equal(result2, expected)

    # non-monotonic, raise KeyError
    s2 = s.iloc[lrange(5) + lrange(5, 10)[::-1]]
    with pytest.raises(KeyError, match=r"^3L?$"):
        s2.loc[3:11]
    with pytest.raises(KeyError, match=r"^3L?$"):
        s2.loc[3:11] = 0 

def test_getitem_unordered_dup():
    obj = Series(lrange(5), index=['c', 'a', 'a', 'b', 'b'])
    assert is_scalar(obj['c'])
    assert obj['c'] == 0 

def test_basic_getitem_with_labels(test_data):
    indices = test_data.ts.index[[5, 10, 15]]

    result = test_data.ts[indices]
    expected = test_data.ts.reindex(indices)
    assert_series_equal(result, expected)

    result = test_data.ts[indices[0]:indices[2]]
    expected = test_data.ts.loc[indices[0]:indices[2]]
    assert_series_equal(result, expected)

    # integer indexes, be careful
    s = Series(np.random.randn(10), index=lrange(0, 20, 2))
    inds = [0, 2, 5, 7, 8]
    arr_inds = np.array([0, 2, 5, 7, 8])
    with tm.assert_produces_warning(FutureWarning,
                                    check_stacklevel=False):
        result = s[inds]
    expected = s.reindex(inds)
    assert_series_equal(result, expected)

    with tm.assert_produces_warning(FutureWarning,
                                    check_stacklevel=False):
        result = s[arr_inds]
    expected = s.reindex(arr_inds)
    assert_series_equal(result, expected)

    # GH12089
    # with tz for values
    s = Series(pd.date_range("2011-01-01", periods=3, tz="US/Eastern"),
               index=['a', 'b', 'c'])
    expected = Timestamp('2011-01-01', tz='US/Eastern')
    result = s.loc['a']
    assert result == expected
    result = s.iloc[0]
    assert result == expected
    result = s['a']
    assert result == expected 

def test_map_type_inference(self):
        s = Series(lrange(3))
        s2 = s.map(lambda x: np.where(x == 0, 0, 1))
        assert issubclass(s2.dtype.type, np.integer) 

def test_first_last_nth_dtypes(df_mixed_floats):

    df = df_mixed_floats.copy()
    df['E'] = True
    df['F'] = 1

    # tests for first / last / nth
    grouped = df.groupby('A')
    first = grouped.first()
    expected = df.loc[[1, 0], ['B', 'C', 'D', 'E', 'F']]
    expected.index = Index(['bar', 'foo'], name='A')
    expected = expected.sort_index()
    assert_frame_equal(first, expected)

    last = grouped.last()
    expected = df.loc[[5, 7], ['B', 'C', 'D', 'E', 'F']]
    expected.index = Index(['bar', 'foo'], name='A')
    expected = expected.sort_index()
    assert_frame_equal(last, expected)

    nth = grouped.nth(1)
    expected = df.loc[[3, 2], ['B', 'C', 'D', 'E', 'F']]
    expected.index = Index(['bar', 'foo'], name='A')
    expected = expected.sort_index()
    assert_frame_equal(nth, expected)

    # GH 2763, first/last shifting dtypes
    idx = lrange(10)
    idx.append(9)
    s = Series(data=lrange(11), index=idx, name='IntCol')
    assert s.dtype == 'int64'
    f = s.groupby(level=0).first()
    assert f.dtype == 'int64' 

def test_apply_chunk_view():
    # Low level tinkering could be unsafe, make sure not
    df = DataFrame({'key': [1, 1, 1, 2, 2, 2, 3, 3, 3],
                    'value': compat.lrange(9)})

    result = df.groupby('key', group_keys=False).apply(lambda x: x[:2])
    expected = df.take([0, 1, 3, 4, 6, 7])
    tm.assert_frame_equal(result, expected) 

def test_groupby_count_dateparseerror(self):
        dr = date_range(start='1/1/2012', freq='5min', periods=10)

        # BAD Example, datetimes first
        s = Series(np.arange(10), index=[dr, lrange(10)])
        grouped = s.groupby(lambda x: x[1] % 2 == 0)
        result = grouped.count()

        s = Series(np.arange(10), index=[lrange(10), dr])
        grouped = s.groupby(lambda x: x[0] % 2 == 0)
        expected = grouped.count()

        assert_series_equal(result, expected) 

def _get_xticks(self, convert_period=False):
        index = self.data.index
        is_datetype = index.inferred_type in ('datetime', 'date',
                                              'datetime64', 'time')

        if self.use_index:
            if convert_period and isinstance(index, ABCPeriodIndex):
                self.data = self.data.reindex(index=index.sort_values())
                x = self.data.index.to_timestamp()._mpl_repr()
            elif index.is_numeric():
                """
                Matplotlib supports numeric values or datetime objects as
                xaxis values. Taking LBYL approach here, by the time
                matplotlib raises exception when using non numeric/datetime
                values for xaxis, several actions are already taken by plt.
                """
                x = index._mpl_repr()
            elif is_datetype:
                self.data = self.data[notna(self.data.index)]
                self.data = self.data.sort_index()
                x = self.data.index._mpl_repr()
            else:
                self._need_to_set_index = True
                x = lrange(len(index))
        else:
            x = lrange(len(index))

        return x 

def test_set_index_makes_timeseries(self):
        idx = tm.makeDateIndex(10)

        s = Series(lrange(10))
        s.index = idx
        assert s.index.is_all_dates 

def test_loc_non_unique_memory_error(self):

        # GH 4280
        # non_unique index with a large selection triggers a memory error

        columns = list('ABCDEFG')

        def gen_test(l, l2):
            return pd.concat([
                DataFrame(np.random.randn(l, len(columns)),
                          index=lrange(l), columns=columns),
                DataFrame(np.ones((l2, len(columns))),
                          index=[0] * l2, columns=columns)])

        def gen_expected(df, mask):
            len_mask = len(mask)
            return pd.concat([df.take([0]),
                              DataFrame(np.ones((len_mask, len(columns))),
                                        index=[0] * len_mask,
                                        columns=columns),
                              df.take(mask[1:])])

        df = gen_test(900, 100)
        assert df.index.is_unique is False

        mask = np.arange(100)
        result = df.loc[mask]
        expected = gen_expected(df, mask)
        tm.assert_frame_equal(result, expected)

        df = gen_test(900000, 100000)
        assert df.index.is_unique is False

        mask = np.arange(100000)
        result = df.loc[mask]
        expected = gen_expected(df, mask)
        tm.assert_frame_equal(result, expected) 

def generate_indices(self, f, values=False):
        """ generate the indices
        if values is True , use the axis values
        is False, use the range
        """

        axes = f.axes
        if values:
            axes = [lrange(len(a)) for a in axes]

        return itertools.product(*axes) 

def test_apply_no_name_column_conflict():
    df = DataFrame({'name': [1, 1, 1, 1, 1, 1, 2, 2, 2, 2],
                    'name2': [0, 0, 0, 1, 1, 1, 0, 0, 1, 1],
                    'value': compat.lrange(10)[::-1]})

    # it works! #2605
    grouped = df.groupby(['name', 'name2'])
    grouped.apply(lambda x: x.sort_values('value', inplace=True)) 

def test_xs_integer_key():
    # see gh-2107
    dates = lrange(20111201, 20111205)
    ids = 'abcde'
    index = MultiIndex.from_tuples(
        [x for x in cart_product(dates, ids)],
        names=['date', 'secid'])
    df = DataFrame(
        np.random.randn(len(index), 3), index, ['X', 'Y', 'Z'])

    result = df.xs(20111201, level='date')
    expected = df.loc[20111201, :]
    tm.assert_frame_equal(result, expected) 

def test_setitem_ambiguous_keyerror():
    s = Series(lrange(10), index=lrange(0, 20, 2))

    # equivalent of an append
    s2 = s.copy()
    s2[1] = 5
    expected = s.append(Series([5], index=[1]))
    assert_series_equal(s2, expected)

    s2 = s.copy()
    s2.loc[1] = 5
    expected = s.append(Series([5], index=[1]))
    assert_series_equal(s2, expected)