Python pandas.to_timedelta() Examples

def test_apply_to_timedelta(self):
        timedelta_NaT = pd.to_timedelta('NaT')

        list_of_valid_strings = ['00:00:01', '00:00:02']
        a = pd.to_timedelta(list_of_valid_strings)
        b = Series(list_of_valid_strings).apply(pd.to_timedelta)
        # Can't compare until apply on a Series gives the correct dtype
        # assert_series_equal(a, b)

        list_of_strings = ['00:00:01', np.nan, pd.NaT, timedelta_NaT]

        # TODO: unused?
        a = pd.to_timedelta(list_of_strings)  # noqa
        b = Series(list_of_strings).apply(pd.to_timedelta)  # noqa
        # Can't compare until apply on a Series gives the correct dtype
        # assert_series_equal(a, b) 

def test_mode_dropna(self, dropna, expected):

        df = DataFrame({"A": [12, 12, 19, 11],
                        "B": [10, 10, np.nan, 3],
                        "C": [1, np.nan, np.nan, np.nan],
                        "D": [np.nan, np.nan, 'a', np.nan],
                        "E": Categorical([np.nan, np.nan, 'a', np.nan]),
                        "F": to_datetime(['NaT', '2000-1-2', 'NaT', 'NaT']),
                        "G": to_timedelta(['1 days', 'nan', 'nan', 'nan']),
                        "H": [8, 8, 9, 9],
                        "I": [9, 9, 8, 8],
                        "J": [1, 1, np.nan, np.nan],
                        "K": Categorical(['a', np.nan, 'a', np.nan]),
                        "L": to_datetime(['2000-1-2', '2000-1-2',
                                          'NaT', 'NaT']),
                        "M": to_timedelta(['1 days', 'nan',
                                           '1 days', 'nan']),
                        "N": np.arange(4, dtype='int64')})

        result = df[sorted(list(expected.keys()))].mode(dropna=dropna)
        expected = DataFrame(expected)
        tm.assert_frame_equal(result, expected) 

def get_orbit_url_file(
    granuleName, inventory="poeorb.txt", url="https://s1qc.asf.alaska.edu/aux_poeorb"
):
    """Find and construct orbit URL from directory listing."""
    sat = granuleName[:3]
    date = granuleName[17:25]
    print(f"finding precise orbit for {sat}, {date}")
    df = pd.read_csv(inventory, header=None, names=["orbit"])
    dfSat = df[df.orbit.str.startswith(sat)].copy()
    dayBefore = pd.to_datetime(date) - pd.to_timedelta(1, unit="d")
    dayBeforeStr = dayBefore.strftime("%Y%m%d")
    dfSat.loc[:, "startTime"] = dfSat.orbit.str[42:50]
    match = dfSat.loc[dfSat.startTime == dayBeforeStr, "orbit"].values[0]
    orbitUrl = f"{url}/{match}"

    return orbitUrl 

def test_cummax_timedelta64(self):
        s = pd.Series(pd.to_timedelta(['NaT',
                                       '2 min',
                                       'NaT',
                                       '1 min',
                                       'NaT',
                                       '3 min', ]))

        expected = pd.Series(pd.to_timedelta(['NaT',
                                              '2 min',
                                              'NaT',
                                              '2 min',
                                              'NaT',
                                              '3 min', ]))
        result = s.cummax(skipna=True)
        tm.assert_series_equal(expected, result)

        expected = pd.Series(pd.to_timedelta(['NaT',
                                              '2 min',
                                              '2 min',
                                              '2 min',
                                              '2 min',
                                              '3 min', ]))
        result = s.cummax(skipna=False)
        tm.assert_series_equal(expected, result) 

def test_cummin_timedelta64(self):
        s = pd.Series(pd.to_timedelta(['NaT',
                                       '2 min',
                                       'NaT',
                                       '1 min',
                                       'NaT',
                                       '3 min', ]))

        expected = pd.Series(pd.to_timedelta(['NaT',
                                              '2 min',
                                              'NaT',
                                              '1 min',
                                              'NaT',
                                              '1 min', ]))
        result = s.cummin(skipna=True)
        tm.assert_series_equal(expected, result)

        expected = pd.Series(pd.to_timedelta(['NaT',
                                              '2 min',
                                              '2 min',
                                              '1 min',
                                              '1 min',
                                              '1 min', ]))
        result = s.cummin(skipna=False)
        tm.assert_series_equal(expected, result) 

def test_constructor_dict_timedelta_index(self):
        # GH #12169 : Resample category data with timedelta index
        # construct Series from dict as data and TimedeltaIndex as index
        # will result NaN in result Series data
        expected = self.series_klass(
            data=['A', 'B', 'C'],
            index=pd.to_timedelta([0, 10, 20], unit='s')
        )

        result = self.series_klass(
            data={pd.to_timedelta(0, unit='s'): 'A',
                  pd.to_timedelta(10, unit='s'): 'B',
                  pd.to_timedelta(20, unit='s'): 'C'},
            index=pd.to_timedelta([0, 10, 20], unit='s')
        )
        self._assert_series_equal(result, expected) 

def test_sum_nanops_timedelta(self):
        # prod isn't defined on timedeltas
        idx = ['a', 'b', 'c']
        df = pd.DataFrame({"a": [0, 0],
                           "b": [0, np.nan],
                           "c": [np.nan, np.nan]})

        df2 = df.apply(pd.to_timedelta)

        # 0 by default
        result = df2.sum()
        expected = pd.Series([0, 0, 0], dtype='m8[ns]', index=idx)
        tm.assert_series_equal(result, expected)

        # min_count=0
        result = df2.sum(min_count=0)
        tm.assert_series_equal(result, expected)

        # min_count=1
        result = df2.sum(min_count=1)
        expected = pd.Series([0, 0, np.nan], dtype='m8[ns]', index=idx)
        tm.assert_series_equal(result, expected) 

def test_interp_timedelta64(self):
        # GH 6424
        df = Series([1, np.nan, 3],
                    index=pd.to_timedelta([1, 2, 3]))
        result = df.interpolate(method='time')
        expected = Series([1., 2., 3.],
                          index=pd.to_timedelta([1, 2, 3]))
        assert_series_equal(result, expected)

        # test for non uniform spacing
        df = Series([1, np.nan, 3],
                    index=pd.to_timedelta([1, 2, 4]))
        result = df.interpolate(method='time')
        expected = Series([1., 1.666667, 3.],
                          index=pd.to_timedelta([1, 2, 4]))
        assert_series_equal(result, expected) 

def test_tdi_add_timestamp_nat_masking(self):
        # GH#17991 checking for overflow-masking with NaT
        tdinat = pd.to_timedelta(['24658 days 11:15:00', 'NaT'])

        tsneg = Timestamp('1950-01-01')
        ts_neg_variants = [tsneg,
                           tsneg.to_pydatetime(),
                           tsneg.to_datetime64().astype('datetime64[ns]'),
                           tsneg.to_datetime64().astype('datetime64[D]')]

        tspos = Timestamp('1980-01-01')
        ts_pos_variants = [tspos,
                           tspos.to_pydatetime(),
                           tspos.to_datetime64().astype('datetime64[ns]'),
                           tspos.to_datetime64().astype('datetime64[D]')]

        for variant in ts_neg_variants + ts_pos_variants:
            res = tdinat + variant
            assert res[1] is pd.NaT 

def test_get_indexer(self):
        idx = pd.to_timedelta(['0 days', '1 days', '2 days'])
        tm.assert_numpy_array_equal(idx.get_indexer(idx),
                                    np.array([0, 1, 2], dtype=np.intp))

        target = pd.to_timedelta(['-1 hour', '12 hours', '1 day 1 hour'])
        tm.assert_numpy_array_equal(idx.get_indexer(target, 'pad'),
                                    np.array([-1, 0, 1], dtype=np.intp))
        tm.assert_numpy_array_equal(idx.get_indexer(target, 'backfill'),
                                    np.array([0, 1, 2], dtype=np.intp))
        tm.assert_numpy_array_equal(idx.get_indexer(target, 'nearest'),
                                    np.array([0, 1, 1], dtype=np.intp))

        res = idx.get_indexer(target, 'nearest',
                              tolerance=Timedelta('1 hour'))
        tm.assert_numpy_array_equal(res, np.array([0, -1, 1], dtype=np.intp)) 

def inverse_transform(self, X, copy=None):
        Q = []

        for track in X:
            
            new_mocap = self.org_mocap_.clone()
            time_index = pd.to_timedelta([f for f in range(track.shape[0])], unit='s')

            new_df =  pd.DataFrame(data=track, index=time_index, columns=self.org_mocap_.values.columns)
            
            new_mocap.values = new_df
            

            Q.append(new_mocap)

        return Q 

def test_to_timedelta_on_missing_values(self):
        # GH5438
        timedelta_NaT = np.timedelta64('NaT')

        actual = pd.to_timedelta(Series(['00:00:01', np.nan]))
        expected = Series([np.timedelta64(1000000000, 'ns'),
                           timedelta_NaT], dtype='<m8[ns]')
        assert_series_equal(actual, expected)

        actual = pd.to_timedelta(Series(['00:00:01', pd.NaT]))
        assert_series_equal(actual, expected)

        actual = pd.to_timedelta(np.nan)
        assert actual.value == timedelta_NaT.astype('int64')

        actual = pd.to_timedelta(pd.NaT)
        assert actual.value == timedelta_NaT.astype('int64') 

def test_none(self):
        delta_1d = pd.to_timedelta(1, unit='D')
        delta_0d = pd.to_timedelta(0, unit='D')
        delta_1s = pd.to_timedelta(1, unit='s')
        delta_500ms = pd.to_timedelta(500, unit='ms')

        drepr = lambda x: x._repr_base()
        assert drepr(delta_1d) == "1 days"
        assert drepr(-delta_1d) == "-1 days"
        assert drepr(delta_0d) == "0 days"
        assert drepr(delta_1s) == "0 days 00:00:01"
        assert drepr(delta_500ms) == "0 days 00:00:00.500000"
        assert drepr(delta_1d + delta_1s) == "1 days 00:00:01"
        assert drepr(-delta_1d + delta_1s) == "-1 days +00:00:01"
        assert drepr(delta_1d + delta_500ms) == "1 days 00:00:00.500000"
        assert drepr(-delta_1d + delta_500ms) == "-1 days +00:00:00.500000" 

def test_sub_day(self):
        delta_1d = pd.to_timedelta(1, unit='D')
        delta_0d = pd.to_timedelta(0, unit='D')
        delta_1s = pd.to_timedelta(1, unit='s')
        delta_500ms = pd.to_timedelta(500, unit='ms')

        drepr = lambda x: x._repr_base(format='sub_day')
        assert drepr(delta_1d) == "1 days"
        assert drepr(-delta_1d) == "-1 days"
        assert drepr(delta_0d) == "00:00:00"
        assert drepr(delta_1s) == "00:00:01"
        assert drepr(delta_500ms) == "00:00:00.500000"
        assert drepr(delta_1d + delta_1s) == "1 days 00:00:01"
        assert drepr(-delta_1d + delta_1s) == "-1 days +00:00:01"
        assert drepr(delta_1d + delta_500ms) == "1 days 00:00:00.500000"
        assert drepr(-delta_1d + delta_500ms) == "-1 days +00:00:00.500000" 

def _wrap_result(self, result, block=None, obj=None):
        """
        Wrap a single result.
        """

        if obj is None:
            obj = self._selected_obj
        index = obj.index

        if isinstance(result, np.ndarray):

            # coerce if necessary
            if block is not None:
                if is_timedelta64_dtype(block.values.dtype):
                    from pandas import to_timedelta
                    result = to_timedelta(
                        result.ravel(), unit='ns').values.reshape(result.shape)

            if result.ndim == 1:
                from pandas import Series
                return Series(result, index, name=obj.name)

            return type(obj)(result, index=index, columns=block.columns)
        return result 

def test_to_timedelta_on_missing_values(self):
        # GH5438
        timedelta_NaT = np.timedelta64('NaT')

        actual = pd.to_timedelta(Series(['00:00:01', np.nan]))
        expected = Series([np.timedelta64(1000000000, 'ns'),
                           timedelta_NaT], dtype='<m8[ns]')
        assert_series_equal(actual, expected)

        actual = pd.to_timedelta(Series(['00:00:01', pd.NaT]))
        assert_series_equal(actual, expected)

        actual = pd.to_timedelta(np.nan)
        assert actual.value == timedelta_NaT.astype('int64')

        actual = pd.to_timedelta(pd.NaT)
        assert actual.value == timedelta_NaT.astype('int64') 

def setup_method(self, datapath):
        self.dirpath = datapath("io", "sas", "data")
        self.data = []
        self.test_ix = [list(range(1, 16)), [16]]
        for j in 1, 2:
            fname = os.path.join(
                self.dirpath, "test_sas7bdat_{j}.csv".format(j=j))
            df = pd.read_csv(fname)
            epoch = pd.datetime(1960, 1, 1)
            t1 = pd.to_timedelta(df["Column4"], unit='d')
            df["Column4"] = epoch + t1
            t2 = pd.to_timedelta(df["Column12"], unit='d')
            df["Column12"] = epoch + t2
            for k in range(df.shape[1]):
                col = df.iloc[:, k]
                if col.dtype == np.int64:
                    df.iloc[:, k] = df.iloc[:, k].astype(np.float64)
                elif col.dtype == np.dtype('O'):
                    if PY2:
                        f = lambda x: (x.decode('utf-8') if
                                       isinstance(x, str) else x)
                        df.iloc[:, k] = df.iloc[:, k].apply(f)
            self.data.append(df) 

def test_timedeltaindex_add_timestamp_nat_masking(self):
        # GH17991 checking for overflow-masking with NaT
        tdinat = pd.to_timedelta(['24658 days 11:15:00', 'NaT'])

        tsneg = Timestamp('1950-01-01')
        ts_neg_variants = [tsneg,
                           tsneg.to_pydatetime(),
                           tsneg.to_datetime64().astype('datetime64[ns]'),
                           tsneg.to_datetime64().astype('datetime64[D]')]

        tspos = Timestamp('1980-01-01')
        ts_pos_variants = [tspos,
                           tspos.to_pydatetime(),
                           tspos.to_datetime64().astype('datetime64[ns]'),
                           tspos.to_datetime64().astype('datetime64[D]')]

        for variant in ts_neg_variants + ts_pos_variants:
            res = tdinat + variant
            assert res[1] is pd.NaT 

def test_timedelta64_dtype_array_returned(self):
        # GH 9431
        expected = np.array([31200, 45678, 10000], dtype='m8[ns]')

        td_index = pd.to_timedelta([31200, 45678, 31200, 10000, 45678])
        result = algos.unique(td_index)
        tm.assert_numpy_array_equal(result, expected)
        assert result.dtype == expected.dtype

        s = Series(td_index)
        result = algos.unique(s)
        tm.assert_numpy_array_equal(result, expected)
        assert result.dtype == expected.dtype

        arr = s.values
        result = algos.unique(arr)
        tm.assert_numpy_array_equal(result, expected)
        assert result.dtype == expected.dtype 

def test_get_indexer(self):
        idx = pd.to_timedelta(['0 days', '1 days', '2 days'])
        tm.assert_numpy_array_equal(idx.get_indexer(idx),
                                    np.array([0, 1, 2], dtype=np.intp))

        target = pd.to_timedelta(['-1 hour', '12 hours', '1 day 1 hour'])
        tm.assert_numpy_array_equal(idx.get_indexer(target, 'pad'),
                                    np.array([-1, 0, 1], dtype=np.intp))
        tm.assert_numpy_array_equal(idx.get_indexer(target, 'backfill'),
                                    np.array([0, 1, 2], dtype=np.intp))
        tm.assert_numpy_array_equal(idx.get_indexer(target, 'nearest'),
                                    np.array([0, 1, 1], dtype=np.intp))

        res = idx.get_indexer(target, 'nearest',
                              tolerance=Timedelta('1 hour'))
        tm.assert_numpy_array_equal(res, np.array([0, -1, 1], dtype=np.intp)) 

def test_time():
    assert time_slice.time == pd.to_timedelta(t, 's') 

def test_timedelta_range(self):

        expected = to_timedelta(np.arange(5), unit='D')
        result = timedelta_range('0 days', periods=5, freq='D')
        tm.assert_index_equal(result, expected)

        expected = to_timedelta(np.arange(11), unit='D')
        result = timedelta_range('0 days', '10 days', freq='D')
        tm.assert_index_equal(result, expected)

        expected = to_timedelta(np.arange(5), unit='D') + Second(2) + Day()
        result = timedelta_range('1 days, 00:00:02', '5 days, 00:00:02',
                                 freq='D')
        tm.assert_index_equal(result, expected)

        expected = to_timedelta([1, 3, 5, 7, 9], unit='D') + Second(2)
        result = timedelta_range('1 days, 00:00:02', periods=5, freq='2D')
        tm.assert_index_equal(result, expected)

        expected = to_timedelta(np.arange(50), unit='T') * 30
        result = timedelta_range('0 days', freq='30T', periods=50)
        tm.assert_index_equal(result, expected)

        # GH 11776
        arr = np.arange(10).reshape(2, 5)
        df = pd.DataFrame(np.arange(10).reshape(2, 5))
        for arg in (arr, df):
            with tm.assert_raises_regex(TypeError, "1-d array"):
                to_timedelta(arg)
            for errors in ['ignore', 'raise', 'coerce']:
                with tm.assert_raises_regex(TypeError, "1-d array"):
                    to_timedelta(arg, errors=errors)

        # issue10583
        df = pd.DataFrame(np.random.normal(size=(10, 4)))
        df.index = pd.timedelta_range(start='0s', periods=10, freq='s')
        expected = df.loc[pd.Timedelta('0s'):, :]
        result = df.loc['0s':, :]
        tm.assert_frame_equal(expected, result) 

def test_duration():
    assert time_slice.duration == pd.to_timedelta(d, 's') 

def test_categorical_coerces_timedelta(all_parsers):
    parser = all_parsers
    dtype = {"b": CategoricalDtype(pd.to_timedelta(["1H", "2H", "3H"]))}

    data = "b\n1H\n2H\n3H"
    expected = DataFrame({"b": Categorical(dtype["b"].categories)})

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

def test_synthesize_fails_if_too_long():
    time = pd.to_timedelta(21 * 60, unit='s')
    with pytest.raises(SynthesizeError):
        res = synthesize(([audio.timings['beats'][5]], [time])) 

def get_orbit_url(granuleName, url="https://s1qc.asf.alaska.edu/aux_poeorb"):
    """Retrieve precise orbit file for a specific Sentinel-1 granule.

    Precise orbits available ~3 weeks after aquisition.

    Parameters
    ----------
    granuleName : str
        ASF granule name, e.g.:
        S1B_IW_SLC__1SDV_20171117T015310_20171117T015337_008315_00EB6C_40CA
    url : str
        website with simple list of orbit file links

    Returns
    -------
    orbitUrl :  str
        url pointing to matched orbit file

    """
    sat = granuleName[:3]
    date = granuleName[17:25]
    print(f"retrieving precise orbit URL for {sat}, {date}")
    r = requests.get(url)
    webpage = html.fromstring(r.content)
    orbits = webpage.xpath("//a/@href")
    df = pd.DataFrame(dict(orbit=orbits))
    dfSat = df[df.orbit.str.startswith(sat)].copy()
    dayBefore = pd.to_datetime(date) - pd.to_timedelta(1, unit="d")
    dayBeforeStr = dayBefore.strftime("%Y%m%d")
    dfSat.loc[:, "startTime"] = dfSat.orbit.str[42:50]
    match = dfSat.loc[dfSat.startTime == dayBeforeStr, "orbit"].values[0]
    orbitUrl = f"{url}/{match}"

    return orbitUrl 

def to_timedelta(obj, numbers_as=None):
    """Convert an object to a python datetime object.

    Args:
        obj: Can be a string with time information, a number, a
            numpy.timedelta64 or a pandas.Timedelta object.
        numbers_as: A string that indicates how numbers should be
            interpreted. Allowed values are *weeks*, *days*, *hours*,
            *minutes*, *seconds*, *milliseconds* and *microseconds.

    Returns:
        A python datetime object.

    Examples:

    .. code-block:: python

        # A timedelta object with 200 seconds
        t = to_timedelta("200 seconds")

        # A timedelta object with 24 days
        t = to_timedelta(24, numbers_as="days")
    """

    if numbers_as is None:
        numbers_as = "seconds"

    if isinstance(obj, timedelta):
        return obj
    elif isinstance(obj, Number):
        return timedelta(**{numbers_as: int(obj)})
    else:
        return pd.to_timedelta(obj).to_pytimedelta() 

def _to_DataFrame(self):
        '''Returns all of the channels parsed from the file as a pandas DataFrame'''

        import pandas as pd
        time_index = pd.to_timedelta([f[0] for f in self._motions], unit='s')
        frames = [f[1] for f in self._motions]
        channels = np.asarray([[channel[2] for channel in frame] for frame in frames])
        column_names = ['%s_%s'%(c[0], c[1]) for c in self._motion_channels]

        return pd.DataFrame(data=channels, index=time_index, columns=column_names) 

def test_timedelta(self):
        converter = lambda x: pd.to_timedelta(x, unit='ms')

        s = Series([timedelta(23), timedelta(seconds=5)])
        assert s.dtype == 'timedelta64[ns]'

        result = pd.read_json(s.to_json(), typ='series').apply(converter)
        assert_series_equal(result, s)

        s = Series([timedelta(23), timedelta(seconds=5)],
                   index=pd.Index([0, 1]))
        assert s.dtype == 'timedelta64[ns]'
        result = pd.read_json(s.to_json(), typ='series').apply(converter)
        assert_series_equal(result, s)

        frame = DataFrame([timedelta(23), timedelta(seconds=5)])
        assert frame[0].dtype == 'timedelta64[ns]'
        assert_frame_equal(frame, pd.read_json(frame.to_json())
                           .apply(converter))

        frame = DataFrame({'a': [timedelta(days=23), timedelta(seconds=5)],
                           'b': [1, 2],
                           'c': pd.date_range(start='20130101', periods=2)})

        result = pd.read_json(frame.to_json(date_unit='ns'))
        result['a'] = pd.to_timedelta(result.a, unit='ns')
        result['c'] = pd.to_datetime(result.c)
        assert_frame_equal(frame, result) 

def test_all(self):
        delta_1d = pd.to_timedelta(1, unit='D')
        delta_0d = pd.to_timedelta(0, unit='D')
        delta_1ns = pd.to_timedelta(1, unit='ns')

        drepr = lambda x: x._repr_base(format='all')
        assert drepr(delta_1d) == "1 days 00:00:00.000000000"
        assert drepr(-delta_1d) == "-1 days +00:00:00.000000000"
        assert drepr(delta_0d) == "0 days 00:00:00.000000000"
        assert drepr(delta_1ns) == "0 days 00:00:00.000000001"
        assert drepr(-delta_1d + delta_1ns) == "-1 days +00:00:00.000000001"