Python pandas.interval_range() Examples

def test_interval_index(self):
        # GH 19977
        index = pd.interval_range(start=0, periods=3)
        df = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
                          index=index,
                          columns=['A', 'B', 'C'])

        expected = 1
        result = df.loc[0.5, 'A']
        assert_almost_equal(result, expected)

        index = pd.interval_range(start=0, periods=3, closed='both')
        df = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
                          index=index,
                          columns=['A', 'B', 'C'])

        index_exp = pd.interval_range(start=0, periods=2,
                                      freq=1, closed='both')
        expected = pd.Series([1, 4], index=index_exp, name='A')
        result = df.loc[1, 'A']
        assert_series_equal(result, expected) 

def test_interval_index(self):
        # GH 19977
        index = pd.interval_range(start=0, periods=3)
        df = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
                          index=index,
                          columns=['A', 'B', 'C'])

        expected = 1
        result = df.loc[0.5, 'A']
        assert_almost_equal(result, expected)

        index = pd.interval_range(start=0, periods=3, closed='both')
        df = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
                          index=index,
                          columns=['A', 'B', 'C'])

        index_exp = pd.interval_range(start=0, periods=2,
                                      freq=1, closed='both')
        expected = pd.Series([1, 4], index=index_exp, name='A')
        result = df.loc[1, 'A']
        assert_series_equal(result, expected) 

def test_interval_array_equal(kwargs):
    arr = interval_range(**kwargs).values
    assert_interval_array_equal(arr, arr) 

def test_cython_agg_empty_buckets_nanops(observed):
    # GH-18869 can't call nanops on empty groups, so hardcode expected
    # for these
    df = pd.DataFrame([11, 12, 13], columns=['a'])
    grps = range(0, 25, 5)
    # add / sum
    result = df.groupby(pd.cut(df['a'], grps),
                        observed=observed)._cython_agg_general('add')
    intervals = pd.interval_range(0, 20, freq=5)
    expected = pd.DataFrame(
        {"a": [0, 0, 36, 0]},
        index=pd.CategoricalIndex(intervals, name='a', ordered=True))
    if observed:
        expected = expected[expected.a != 0]

    tm.assert_frame_equal(result, expected)

    # prod
    result = df.groupby(pd.cut(df['a'], grps),
                        observed=observed)._cython_agg_general('prod')
    expected = pd.DataFrame(
        {"a": [1, 1, 1716, 1]},
        index=pd.CategoricalIndex(intervals, name='a', ordered=True))
    if observed:
        expected = expected[expected.a != 1]

    tm.assert_frame_equal(result, expected) 

def test_construction_from_timedelta(self, closed):
        # combinations of start/end/periods without freq
        start, end = Timedelta('1 day'), Timedelta('6 days')
        breaks = timedelta_range(start=start, end=end)
        expected = IntervalIndex.from_breaks(breaks, name='foo', closed=closed)

        result = interval_range(start=start, end=end, name='foo',
                                closed=closed)
        tm.assert_index_equal(result, expected)

        result = interval_range(start=start, periods=5, name='foo',
                                closed=closed)
        tm.assert_index_equal(result, expected)

        result = interval_range(end=end, periods=5, name='foo',
                                closed=closed)
        tm.assert_index_equal(result, expected)

        # combinations of start/end/periods with fixed freq
        freq = '2D'
        start, end = Timedelta('1 day'), Timedelta('7 days')
        breaks = timedelta_range(start=start, end=end, freq=freq)
        expected = IntervalIndex.from_breaks(breaks, name='foo', closed=closed)

        result = interval_range(start=start, end=end, freq=freq, name='foo',
                                closed=closed)
        tm.assert_index_equal(result, expected)

        result = interval_range(start=start, periods=3, freq=freq, name='foo',
                                closed=closed)
        tm.assert_index_equal(result, expected)

        result = interval_range(end=end, periods=3, freq=freq, name='foo',
                                closed=closed)
        tm.assert_index_equal(result, expected)

        # output truncates early if freq causes end to be skipped.
        end = Timedelta('7 days 1 hour')
        result = interval_range(start=start, end=end, freq=freq, name='foo',
                                closed=closed)
        tm.assert_index_equal(result, expected) 

def test_construction_from_numeric(self, closed):
        # combinations of start/end/periods without freq
        expected = IntervalIndex.from_breaks(
            np.arange(0, 6), name='foo', closed=closed)

        result = interval_range(start=0, end=5, name='foo', closed=closed)
        tm.assert_index_equal(result, expected)

        result = interval_range(start=0, periods=5, name='foo', closed=closed)
        tm.assert_index_equal(result, expected)

        result = interval_range(end=5, periods=5, name='foo', closed=closed)
        tm.assert_index_equal(result, expected)

        # combinations of start/end/periods with freq
        expected = IntervalIndex.from_tuples([(0, 2), (2, 4), (4, 6)],
                                             name='foo', closed=closed)

        result = interval_range(start=0, end=6, freq=2, name='foo',
                                closed=closed)
        tm.assert_index_equal(result, expected)

        result = interval_range(start=0, periods=3, freq=2, name='foo',
                                closed=closed)
        tm.assert_index_equal(result, expected)

        result = interval_range(end=6, periods=3, freq=2, name='foo',
                                closed=closed)
        tm.assert_index_equal(result, expected)

        # output truncates early if freq causes end to be skipped.
        expected = IntervalIndex.from_tuples([(0.0, 1.5), (1.5, 3.0)],
                                             name='foo', closed=closed)
        result = interval_range(start=0, end=4, freq=1.5, name='foo',
                                closed=closed)
        tm.assert_index_equal(result, expected) 

def histogram_plot(nx, ny, x, source, xlo=None, xhi=None, nsub=5, output_backend=DEFAULT_BACKEND):
    if not present(source, x): return None
    xlo, xhi = source[x].min() if xlo is None else xlo, source[x].max() if xhi is None else xhi
    bins = pd.interval_range(start=xlo, end=xhi, periods=nsub * (xhi - xlo), closed='left')
    c = [palettes.Inferno[int(xhi - xlo + 1)][int(b.left - xlo)] for b in bins]
    hrz_categorized = pd.cut(source[x], bins)
    counts = hrz_categorized.groupby(hrz_categorized).count()
    f = figure(output_backend=output_backend, plot_width=nx, plot_height=ny, x_range=Range1d(start=xlo, end=xhi),
               x_axis_label=x)
    f.quad(left=counts.index.categories.left, right=counts.index.categories.right, top=counts, bottom=0,
           color=c, fill_alpha=0.2)
    f.toolbar_location = None
    f.yaxis.visible = False
    return f 

def test_interval_array_equal_start_mismatch():
    kwargs = dict(periods=4)
    arr1 = interval_range(start=0, **kwargs).values
    arr2 = interval_range(start=1, **kwargs).values

    msg = """\
IntervalArray.left are different

IntervalArray.left values are different \\(100.0 %\\)
\\[left\\]:  Int64Index\\(\\[0, 1, 2, 3\\], dtype='int64'\\)
\\[right\\]: Int64Index\\(\\[1, 2, 3, 4\\], dtype='int64'\\)"""

    with pytest.raises(AssertionError, match=msg):
        assert_interval_array_equal(arr1, arr2) 

def test_interval_array_equal_periods_mismatch():
    kwargs = dict(start=0)
    arr1 = interval_range(periods=5, **kwargs).values
    arr2 = interval_range(periods=6, **kwargs).values

    msg = """\
IntervalArray.left are different

IntervalArray.left length are different
\\[left\\]:  5, Int64Index\\(\\[0, 1, 2, 3, 4\\], dtype='int64'\\)
\\[right\\]: 6, Int64Index\\(\\[0, 1, 2, 3, 4, 5\\], dtype='int64'\\)"""

    with pytest.raises(AssertionError, match=msg):
        assert_interval_array_equal(arr1, arr2) 

def test_interval_array_equal_closed_mismatch():
    kwargs = dict(start=0, periods=5)
    arr1 = interval_range(closed="left", **kwargs).values
    arr2 = interval_range(closed="right", **kwargs).values

    msg = """\
IntervalArray are different

Attribute "closed" are different
\\[left\\]:  left
\\[right\\]: right"""

    with pytest.raises(AssertionError, match=msg):
        assert_interval_array_equal(arr1, arr2) 

def test_interval_array_equal(kwargs):
    arr = interval_range(**kwargs).values
    assert_interval_array_equal(arr, arr) 

def test_cython_agg_empty_buckets_nanops(observed):
    # GH-18869 can't call nanops on empty groups, so hardcode expected
    # for these
    df = pd.DataFrame([11, 12, 13], columns=['a'])
    grps = range(0, 25, 5)
    # add / sum
    result = df.groupby(pd.cut(df['a'], grps),
                        observed=observed)._cython_agg_general('add')
    intervals = pd.interval_range(0, 20, freq=5)
    expected = pd.DataFrame(
        {"a": [0, 0, 36, 0]},
        index=pd.CategoricalIndex(intervals, name='a', ordered=True))
    if observed:
        expected = expected[expected.a != 0]

    tm.assert_frame_equal(result, expected)

    # prod
    result = df.groupby(pd.cut(df['a'], grps),
                        observed=observed)._cython_agg_general('prod')
    expected = pd.DataFrame(
        {"a": [1, 1, 1716, 1]},
        index=pd.CategoricalIndex(intervals, name='a', ordered=True))
    if observed:
        expected = expected[expected.a != 1]

    tm.assert_frame_equal(result, expected) 

def test_cython_agg_empty_buckets_nanops(observed):
    # GH-18869 can't call nanops on empty groups, so hardcode expected
    # for these
    df = pd.DataFrame([11, 12, 13], columns=['a'])
    grps = range(0, 25, 5)
    # add / sum
    result = df.groupby(pd.cut(df['a'], grps),
                        observed=observed)._cython_agg_general('add')
    intervals = pd.interval_range(0, 20, freq=5)
    expected = pd.DataFrame(
        {"a": [0, 0, 36, 0]},
        index=pd.CategoricalIndex(intervals, name='a', ordered=True))
    if observed:
        expected = expected[expected.a != 0]

    tm.assert_frame_equal(result, expected)

    # prod
    result = df.groupby(pd.cut(df['a'], grps),
                        observed=observed)._cython_agg_general('prod')
    expected = pd.DataFrame(
        {"a": [1, 1, 1716, 1]},
        index=pd.CategoricalIndex(intervals, name='a', ordered=True))
    if observed:
        expected = expected[expected.a != 1]

    tm.assert_frame_equal(result, expected) 

def test_cython_agg_empty_buckets_nanops(observed):
    # GH-18869 can't call nanops on empty groups, so hardcode expected
    # for these
    df = pd.DataFrame([11, 12, 13], columns=['a'])
    grps = range(0, 25, 5)
    # add / sum
    result = df.groupby(pd.cut(df['a'], grps),
                        observed=observed)._cython_agg_general('add')
    intervals = pd.interval_range(0, 20, freq=5)
    expected = pd.DataFrame(
        {"a": [0, 0, 36, 0]},
        index=pd.CategoricalIndex(intervals, name='a', ordered=True))
    if observed:
        expected = expected[expected.a != 0]

    tm.assert_frame_equal(result, expected)

    # prod
    result = df.groupby(pd.cut(df['a'], grps),
                        observed=observed)._cython_agg_general('prod')
    expected = pd.DataFrame(
        {"a": [1, 1, 1716, 1]},
        index=pd.CategoricalIndex(intervals, name='a', ordered=True))
    if observed:
        expected = expected[expected.a != 1]

    tm.assert_frame_equal(result, expected) 

def bin_spikes(spikes, binsize, interval_indices=False):
    """
    Wrapper for bincount2D which is intended to take in a TimeSeries object of spike times
    and cluster identities and spit out spike counts in bins of a specified width binsize, also in
    another TimeSeries object. Can either return a TS object with each row labeled with the
    corresponding interval or the value of the left edge of the bin.

    :param spikes: Spike times and cluster identities of sorted spikes
    :type spikes: TimeSeries object with \'clusters\' column and timestamps
    :param binsize: Width of the non-overlapping bins in which to bin spikes
    :type binsize: float
    :param interval_indices: Whether to use intervals as the time stamps for binned spikes, rather
        than the left edge value of the bins, defaults to False
    :type interval_indices: bool, optional
    :return: Object with 2D array of shape T x N, for T timesteps and N clusters, and the
        associated time stamps.
    :rtype: TimeSeries object
    """
    if type(spikes) is not core.TimeSeries:
        raise TypeError('Input spikes need to be in TimeSeries object format')

    if not hasattr(spikes, 'clusters'):
        raise AttributeError('Input spikes need to have a clusters attribute. Make sure you set '
                             'columns=(\'clusters\',)) when constructing spikes.')

    rates, tbins, clusters = bincount2D(spikes.times, spikes.clusters, binsize)
    if interval_indices:
        intervals = pd.interval_range(tbins[0], tbins[-1], freq=binsize, closed='left')
        return core.TimeSeries(times=intervals, values=rates.T[:-1], columns=clusters)
    else:
        return core.TimeSeries(times=tbins, values=rates.T, columns=clusters) 

def test_interval_array_equal_start_mismatch():
    kwargs = dict(periods=4)
    arr1 = interval_range(start=0, **kwargs).values
    arr2 = interval_range(start=1, **kwargs).values

    msg = """\
IntervalArray.left are different

IntervalArray.left values are different \\(100.0 %\\)
\\[left\\]:  Int64Index\\(\\[0, 1, 2, 3\\], dtype='int64'\\)
\\[right\\]: Int64Index\\(\\[1, 2, 3, 4\\], dtype='int64'\\)"""

    with pytest.raises(AssertionError, match=msg):
        assert_interval_array_equal(arr1, arr2) 

def test_interval_array_equal_periods_mismatch():
    kwargs = dict(start=0)
    arr1 = interval_range(periods=5, **kwargs).values
    arr2 = interval_range(periods=6, **kwargs).values

    msg = """\
IntervalArray.left are different

IntervalArray.left length are different
\\[left\\]:  5, Int64Index\\(\\[0, 1, 2, 3, 4\\], dtype='int64'\\)
\\[right\\]: 6, Int64Index\\(\\[0, 1, 2, 3, 4, 5\\], dtype='int64'\\)"""

    with pytest.raises(AssertionError, match=msg):
        assert_interval_array_equal(arr1, arr2) 

def test_interval_array_equal_closed_mismatch():
    kwargs = dict(start=0, periods=5)
    arr1 = interval_range(closed="left", **kwargs).values
    arr2 = interval_range(closed="right", **kwargs).values

    msg = """\
IntervalArray are different

Attribute "closed" are different
\\[left\\]:  left
\\[right\\]: right"""

    with pytest.raises(AssertionError, match=msg):
        assert_interval_array_equal(arr1, arr2) 

def test_constructor_coverage(self):
        # float value for periods
        expected = pd.interval_range(start=0, periods=10)
        result = pd.interval_range(start=0, periods=10.5)
        tm.assert_index_equal(result, expected)

        # equivalent timestamp-like start/end
        start, end = Timestamp('2017-01-01'), Timestamp('2017-01-15')
        expected = pd.interval_range(start=start, end=end)

        result = pd.interval_range(start=start.to_pydatetime(),
                                   end=end.to_pydatetime())
        tm.assert_index_equal(result, expected)

        result = pd.interval_range(start=start.tz_localize('UTC'),
                                   end=end.tz_localize('UTC'))
        tm.assert_index_equal(result, expected)

        result = pd.interval_range(start=start.asm8, end=end.asm8)
        tm.assert_index_equal(result, expected)

        # equivalent freq with timestamp
        equiv_freq = ['D', Day(), Timedelta(days=1), timedelta(days=1),
                      DateOffset(days=1)]
        for freq in equiv_freq:
            result = pd.interval_range(start=start, end=end, freq=freq)
            tm.assert_index_equal(result, expected)

        # equivalent timedelta-like start/end
        start, end = Timedelta(days=1), Timedelta(days=10)
        expected = pd.interval_range(start=start, end=end)

        result = pd.interval_range(start=start.to_pytimedelta(),
                                   end=end.to_pytimedelta())
        tm.assert_index_equal(result, expected)

        result = pd.interval_range(start=start.asm8, end=end.asm8)
        tm.assert_index_equal(result, expected)

        # equivalent freq with timedelta
        equiv_freq = ['D', Day(), Timedelta(days=1), timedelta(days=1)]
        for freq in equiv_freq:
            result = pd.interval_range(start=start, end=end, freq=freq)
            tm.assert_index_equal(result, expected)