Python pandas._libs.tslib.Timestamp() Examples

def test_usecols_with_parse_dates(all_parsers, usecols):
    # see gh-9755
    data = """a,b,c,d,e
0,1,20140101,0900,4
0,1,20140102,1000,4"""
    parser = all_parsers
    parse_dates = [[1, 2]]

    cols = {
        "a": [0, 0],
        "c_d": [
            Timestamp("2014-01-01 09:00:00"),
            Timestamp("2014-01-02 10:00:00")
        ]
    }
    expected = DataFrame(cols, columns=["c_d", "a"])
    result = parser.read_csv(StringIO(data), usecols=usecols,
                             parse_dates=parse_dates)
    tm.assert_frame_equal(result, expected) 

def _wrap_results(result, dtype):
    """ wrap our results if needed """

    if is_datetime64_dtype(dtype):
        if not isinstance(result, np.ndarray):
            result = tslib.Timestamp(result)
        else:
            result = result.view(dtype)
    elif is_timedelta64_dtype(dtype):
        if not isinstance(result, np.ndarray):

            # raise if we have a timedelta64[ns] which is too large
            if np.fabs(result) > _int64_max:
                raise ValueError("overflow in timedelta operation")

            result = tslib.Timedelta(result, unit='ns')
        else:
            result = result.astype('i8').view(dtype)

    return result 

def test_usecols_with_parse_dates_and_full_names(self):
        # See gh-9755
        s = """0,1,20140101,0900,4
        0,1,20140102,1000,4"""
        parse_dates = [[1, 2]]
        names = list('abcde')

        cols = {
            'a': [0, 0],
            'c_d': [
                Timestamp('2014-01-01 09:00:00'),
                Timestamp('2014-01-02 10:00:00')
            ]
        }
        expected = DataFrame(cols, columns=['c_d', 'a'])

        df = self.read_csv(StringIO(s), names=names,
                           usecols=[0, 2, 3],
                           parse_dates=parse_dates)
        tm.assert_frame_equal(df, expected)

        df = self.read_csv(StringIO(s), names=names,
                           usecols=[3, 0, 2],
                           parse_dates=parse_dates)
        tm.assert_frame_equal(df, expected) 

def test_converters(self):
        data = """A,B,C,D
a,1,2,01/01/2009
b,3,4,01/02/2009
c,4,5,01/03/2009
"""
        result = self.read_csv(StringIO(data), converters={'D': parse_date})
        result2 = self.read_csv(StringIO(data), converters={3: parse_date})

        expected = self.read_csv(StringIO(data))
        expected['D'] = expected['D'].map(parse_date)

        assert isinstance(result['D'][0], (datetime, Timestamp))
        tm.assert_frame_equal(result, expected)
        tm.assert_frame_equal(result2, expected)

        # produce integer
        converter = lambda x: int(x.split('/')[2])
        result = self.read_csv(StringIO(data), converters={'D': converter})
        expected = self.read_csv(StringIO(data))
        expected['D'] = expected['D'].map(converter)
        tm.assert_frame_equal(result, expected) 

def test_last_week_of_month_on_offset():
    # GH#19036, GH#18977 _adjust_dst was incorrect for LastWeekOfMonth
    offset = LastWeekOfMonth(n=4, weekday=6)
    ts = Timestamp('1917-05-27 20:55:27.084284178+0200',
                   tz='Europe/Warsaw')
    slow = (ts + offset) - offset == ts
    fast = offset.onOffset(ts)
    assert fast == slow

    # negative n
    offset = LastWeekOfMonth(n=-4, weekday=5)
    ts = Timestamp('2005-08-27 05:01:42.799392561-0500',
                   tz='America/Rainy_River')
    slow = (ts + offset) - offset == ts
    fast = offset.onOffset(ts)
    assert fast == slow 

def test_datetime_units(self):
        val = datetime.datetime(2013, 8, 17, 21, 17, 12, 215504)
        stamp = Timestamp(val)

        roundtrip = ujson.decode(ujson.encode(val, date_unit='s'))
        assert roundtrip == stamp.value // 10**9

        roundtrip = ujson.decode(ujson.encode(val, date_unit='ms'))
        assert roundtrip == stamp.value // 10**6

        roundtrip = ujson.decode(ujson.encode(val, date_unit='us'))
        assert roundtrip == stamp.value // 10**3

        roundtrip = ujson.decode(ujson.encode(val, date_unit='ns'))
        assert roundtrip == stamp.value

        msg = "Invalid value 'foo' for option 'date_unit'"
        with pytest.raises(ValueError, match=msg):
            ujson.encode(val, date_unit='foo') 

def test_datetime_units(self):
        from pandas._libs.tslib import Timestamp

        val = datetime.datetime(2013, 8, 17, 21, 17, 12, 215504)
        stamp = Timestamp(val)

        roundtrip = ujson.decode(ujson.encode(val, date_unit='s'))
        assert roundtrip == stamp.value // 10**9

        roundtrip = ujson.decode(ujson.encode(val, date_unit='ms'))
        assert roundtrip == stamp.value // 10**6

        roundtrip = ujson.decode(ujson.encode(val, date_unit='us'))
        assert roundtrip == stamp.value // 10**3

        roundtrip = ujson.decode(ujson.encode(val, date_unit='ns'))
        assert roundtrip == stamp.value

        pytest.raises(ValueError, ujson.encode, val, date_unit='foo') 

def test_nat_parse(self):
        # See gh-3062
        df = DataFrame(dict({
            'A': np.asarray(lrange(10), dtype='float64'),
            'B': pd.Timestamp('20010101')}))
        df.iloc[3:6, :] = np.nan

        with tm.ensure_clean('__nat_parse_.csv') as path:
            df.to_csv(path)
            result = self.read_csv(path, index_col=0, parse_dates=['B'])
            tm.assert_frame_equal(result, df)

            expected = Series(dict(A='float64', B='datetime64[ns]'))
            tm.assert_series_equal(expected, result.dtypes)

            # test with NaT for the nan_rep
            # we don't have a method to specify the Datetime na_rep
            # (it defaults to '')
            df.to_csv(path)
            result = self.read_csv(path, index_col=0, parse_dates=['B'])
            tm.assert_frame_equal(result, df) 

def test_usecols_with_parse_dates_and_names(all_parsers, usecols, names):
    # see gh-9755
    s = """0,1,20140101,0900,4
0,1,20140102,1000,4"""
    parse_dates = [[1, 2]]
    parser = all_parsers

    cols = {
        "a": [0, 0],
        "c_d": [
            Timestamp("2014-01-01 09:00:00"),
            Timestamp("2014-01-02 10:00:00")
        ]
    }
    expected = DataFrame(cols, columns=["c_d", "a"])

    result = parser.read_csv(StringIO(s), names=names,
                             parse_dates=parse_dates,
                             usecols=usecols)
    tm.assert_frame_equal(result, expected) 

def test_usecols_with_parse_dates3(all_parsers):
    # see gh-14792
    parser = all_parsers
    data = """a,b,c,d,e,f,g,h,i,j
2016/09/21,1,1,2,3,4,5,6,7,8"""

    usecols = list("abcdefghij")
    parse_dates = [0]

    cols = {"a": Timestamp("2016-09-21"),
            "b": [1], "c": [1], "d": [2],
            "e": [3], "f": [4], "g": [5],
            "h": [6], "i": [7], "j": [8]}
    expected = DataFrame(cols, columns=usecols)

    result = parser.read_csv(StringIO(data), usecols=usecols,
                             parse_dates=parse_dates)
    tm.assert_frame_equal(result, expected) 

def test_usecols_with_parse_dates2(all_parsers):
    # see gh-13604
    parser = all_parsers
    data = """2008-02-07 09:40,1032.43
2008-02-07 09:50,1042.54
2008-02-07 10:00,1051.65"""

    names = ["date", "values"]
    usecols = names[:]
    parse_dates = [0]

    index = Index([Timestamp("2008-02-07 09:40"),
                   Timestamp("2008-02-07 09:50"),
                   Timestamp("2008-02-07 10:00")],
                  name="date")
    cols = {"values": [1032.43, 1042.54, 1051.65]}
    expected = DataFrame(cols, index=index)

    result = parser.read_csv(StringIO(data), parse_dates=parse_dates,
                             index_col=0, usecols=usecols,
                             header=None, names=names)
    tm.assert_frame_equal(result, expected) 

def take_invalid_kwargs(self):
        vals = [['A', 'B'],
                [pd.Timestamp('2011-01-01'), pd.Timestamp('2011-01-02')]]
        idx = pd.MultiIndex.from_product(vals, names=['str', 'dt'])
        indices = [1, 2]

        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') 

def test_union_sort_other_incomparable(self):
        # https://github.com/pandas-dev/pandas/issues/24959
        idx = pd.Index([1, pd.Timestamp('2000')])
        # default (sort=None)
        with tm.assert_produces_warning(RuntimeWarning):
            result = idx.union(idx[:1])

        tm.assert_index_equal(result, idx)

        # sort=None
        with tm.assert_produces_warning(RuntimeWarning):
            result = idx.union(idx[:1], sort=None)
        tm.assert_index_equal(result, idx)

        # sort=False
        result = idx.union(idx[:1], sort=False)
        tm.assert_index_equal(result, idx) 

def test_difference_incomparable(self, opname):
        a = pd.Index([3, pd.Timestamp('2000'), 1])
        b = pd.Index([2, pd.Timestamp('1999'), 1])
        op = operator.methodcaller(opname, b)

        # sort=None, the default
        result = op(a)
        expected = pd.Index([3, pd.Timestamp('2000'), 2, pd.Timestamp('1999')])
        if opname == 'difference':
            expected = expected[:2]
        tm.assert_index_equal(result, expected)

        # sort=False
        op = operator.methodcaller(opname, b, sort=False)
        result = op(a)
        tm.assert_index_equal(result, expected) 

def test_difference_incomparable(self, opname):
        a = pd.Index([3, pd.Timestamp('2000'), 1])
        b = pd.Index([2, pd.Timestamp('1999'), 1])
        op = operator.methodcaller(opname, b)

        # sort=None, the default
        result = op(a)
        expected = pd.Index([3, pd.Timestamp('2000'), 2, pd.Timestamp('1999')])
        if opname == 'difference':
            expected = expected[:2]
        tm.assert_index_equal(result, expected)

        # sort=False
        op = operator.methodcaller(opname, b, sort=False)
        result = op(a)
        tm.assert_index_equal(result, expected) 

def test_union_sort_other_incomparable(self):
        # https://github.com/pandas-dev/pandas/issues/24959
        idx = pd.Index([1, pd.Timestamp('2000')])
        # default (sort=None)
        with tm.assert_produces_warning(RuntimeWarning):
            result = idx.union(idx[:1])

        tm.assert_index_equal(result, idx)

        # sort=None
        with tm.assert_produces_warning(RuntimeWarning):
            result = idx.union(idx[:1], sort=None)
        tm.assert_index_equal(result, idx)

        # sort=False
        result = idx.union(idx[:1], sort=False)
        tm.assert_index_equal(result, idx) 

def _to_primitive(arr, string_max_len=None, forced_dtype=None):
    if arr.dtype.hasobject:
        if len(arr) > 0 and isinstance(arr[0], Timestamp):
            return np.array([t.value for t in arr], dtype=DTN64_DTYPE)

        if forced_dtype is not None:
            casted_arr = arr.astype(dtype=forced_dtype, copy=False)
        elif string_max_len is not None:
            casted_arr = np.array(arr.astype('U{:d}'.format(string_max_len)))
        else:
            casted_arr = np.array(list(arr))

        # Pick any unwanted data conversions (e.g. np.NaN to 'nan')
        if np.array_equal(arr, casted_arr):
            return casted_arr
    return arr 

def test_vectorized_offset_addition(self, klass, assert_func):
        s = klass([Timestamp('2000-01-15 00:15:00', tz='US/Central'),
                   Timestamp('2000-02-15', tz='US/Central')], name='a')
        result = s + SemiMonthBegin()
        result2 = SemiMonthBegin() + s
        exp = klass([Timestamp('2000-02-01 00:15:00', tz='US/Central'),
                     Timestamp('2000-03-01', tz='US/Central')], name='a')
        assert_func(result, exp)
        assert_func(result2, exp)

        s = klass([Timestamp('2000-01-01 00:15:00', tz='US/Central'),
                   Timestamp('2000-02-01', tz='US/Central')], name='a')
        result = s + SemiMonthBegin()
        result2 = SemiMonthBegin() + s
        exp = klass([Timestamp('2000-01-15 00:15:00', tz='US/Central'),
                     Timestamp('2000-02-15', tz='US/Central')], name='a')
        assert_func(result, exp)
        assert_func(result2, exp) 

def test_apply_nanoseconds(self):
        tests = []

        tests.append((BusinessHour(),
                      {Timestamp('2014-07-04 15:00') + Nano(5): Timestamp(
                          '2014-07-04 16:00') + Nano(5),
                       Timestamp('2014-07-04 16:00') + Nano(5): Timestamp(
                           '2014-07-07 09:00') + Nano(5),
                       Timestamp('2014-07-04 16:00') - Nano(5): Timestamp(
                           '2014-07-04 17:00') - Nano(5)}))

        tests.append((BusinessHour(-1),
                      {Timestamp('2014-07-04 15:00') + Nano(5): Timestamp(
                          '2014-07-04 14:00') + Nano(5),
                       Timestamp('2014-07-04 10:00') + Nano(5): Timestamp(
                           '2014-07-04 09:00') + Nano(5),
                       Timestamp('2014-07-04 10:00') - Nano(5): Timestamp(
                           '2014-07-03 17:00') - Nano(5), }))

        for offset, cases in tests:
            for base, expected in compat.iteritems(cases):
                assert_offset_equal(offset, base, expected) 

def test_vectorized_offset_addition(self, klass, assert_func):
        s = klass([Timestamp('2000-01-15 00:15:00', tz='US/Central'),
                   Timestamp('2000-02-15', tz='US/Central')], name='a')

        result = s + SemiMonthEnd()
        result2 = SemiMonthEnd() + s
        exp = klass([Timestamp('2000-01-31 00:15:00', tz='US/Central'),
                     Timestamp('2000-02-29', tz='US/Central')], name='a')
        assert_func(result, exp)
        assert_func(result2, exp)

        s = klass([Timestamp('2000-01-01 00:15:00', tz='US/Central'),
                   Timestamp('2000-02-01', tz='US/Central')], name='a')
        result = s + SemiMonthEnd()
        result2 = SemiMonthEnd() + s
        exp = klass([Timestamp('2000-01-15 00:15:00', tz='US/Central'),
                     Timestamp('2000-02-15', tz='US/Central')], name='a')
        assert_func(result, exp)
        assert_func(result2, exp) 

def test_asof_datetime_partial(self):
        index = pd.date_range('2010-01-01', periods=2, freq='m')
        expected = Timestamp('2010-02-28')
        result = index.asof('2010-02')
        assert result == expected
        assert not isinstance(result, Index) 

def _dict_compat(d):
    """
    Helper function to convert datetimelike-keyed dicts to Timestamp-keyed dict

    Parameters
    ----------
    d: dict like object

    Returns
    -------
    dict

    """
    return dict((_maybe_box_datetimelike(key), value)
                for key, value in iteritems(d)) 

def test_multiple_date_col_timestamp_parse(self):
        data = """05/31/2012,15:30:00.029,1306.25,1,E,0,,1306.25
05/31/2012,15:30:00.029,1306.25,8,E,0,,1306.25"""
        result = self.read_csv(StringIO(data), sep=',', header=None,
                               parse_dates=[[0, 1]], date_parser=Timestamp)

        ex_val = Timestamp('05/31/2012 15:30:00.029')
        assert result['0_1'][0] == ex_val 

def test_read_csv_no_index_name(self):
        df = self.read_csv(self.csv2, index_col=0, parse_dates=True)
        df2 = self.read_table(self.csv2, sep=',', index_col=0,
                              parse_dates=True)
        tm.assert_index_equal(df.columns,
                              pd.Index(['A', 'B', 'C', 'D', 'E']))
        assert isinstance(df.index[0], (datetime, np.datetime64, Timestamp))
        assert df.loc[:, ['A', 'B', 'C', 'D']].values.dtype == np.float64
        tm.assert_frame_equal(df, df2) 

def test_read_csv_dataframe(self):
        df = self.read_csv(self.csv1, index_col=0, parse_dates=True)
        df2 = self.read_table(self.csv1, sep=',', index_col=0,
                              parse_dates=True)
        tm.assert_index_equal(df.columns, pd.Index(['A', 'B', 'C', 'D']))
        assert df.index.name == 'index'
        assert isinstance(
            df.index[0], (datetime, np.datetime64, Timestamp))
        assert df.values.dtype == np.float64
        tm.assert_frame_equal(df, df2) 

def test_weekofmonth_onoffset():
    # GH#18864
    # Make sure that nanoseconds don't trip up onOffset (and with it apply)
    offset = WeekOfMonth(n=2, week=2, weekday=0)
    ts = Timestamp('1916-05-15 01:14:49.583410462+0422', tz='Asia/Qyzylorda')
    fast = offset.onOffset(ts)
    slow = (ts + offset) - offset == ts
    assert fast == slow

    # negative n
    offset = WeekOfMonth(n=-3, week=1, weekday=0)
    ts = Timestamp('1980-12-08 03:38:52.878321185+0500', tz='Asia/Oral')
    fast = offset.onOffset(ts)
    slow = (ts + offset) - offset == ts
    assert fast == slow 

def test_weeks_onoffset():
    # GH#18510 Week with weekday = None, normalize = False should always
    # be onOffset
    offset = Week(n=2, weekday=None)
    ts = Timestamp('1862-01-13 09:03:34.873477378+0210', tz='Africa/Lusaka')
    fast = offset.onOffset(ts)
    slow = (ts + offset) - offset == ts
    assert fast == slow

    # negative n
    offset = Week(n=2, weekday=None)
    ts = Timestamp('1856-10-24 16:18:36.556360110-0717', tz='Pacific/Easter')
    fast = offset.onOffset(ts)
    slow = (ts + offset) - offset == ts
    assert fast == slow 

def test_fallback_singular(self):
        # in the case of singular offsets, we don't necessarily know which utc
        # offset the new Timestamp will wind up in (the tz for 1 month may be
        # different from 1 second) so we don't specify an expected_utc_offset
        for tz, utc_offsets in self.timezone_utc_offsets.items():
            hrs_pre = utc_offsets['utc_offset_standard']
            self._test_all_offsets(n=1, tstart=self._make_timestamp(
                self.ts_pre_fallback, hrs_pre, tz), expected_utc_offset=None) 

def _make_timestamp(self, string, hrs_offset, tz):
        if hrs_offset >= 0:
            offset_string = '{hrs:02d}00'.format(hrs=hrs_offset)
        else:
            offset_string = '-{hrs:02d}00'.format(hrs=-1 * hrs_offset)
        return Timestamp(string + offset_string).tz_convert(tz) 

def get_utc_offset_hours(ts):
    # take a Timestamp and compute total hours of utc offset
    o = ts.utcoffset()
    return (o.days * 24 * 3600 + o.seconds) / 3600.0