Python pandas.DateOffset方法代码示例

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def setup(self):
        """Runs before every method to create a clean testing setup"""
        # Load a test instrument
        self.testInst = pysat.Instrument()
        self.testInst.data = pds.DataFrame({'Kp': np.arange(0, 4, 1.0/3.0),
                                            'ap_nan': np.full(shape=12, \
                                                            fill_value=np.nan),
                                            'ap_inf': np.full(shape=12, \
                                                            fill_value=np.inf)},
                                           index=[pysat.datetime(2009, 1, 1)
                                                  + pds.DateOffset(hours=3*i)
                                                  for i in range(12)])
        self.testInst.meta = pysat.Meta()
        self.testInst.meta.__setitem__('Kp', {self.testInst.meta.fill_label:
                                              np.nan})
        self.testInst.meta.__setitem__('ap_nan', {self.testInst.meta.fill_label:
                                                  np.nan})
        self.testInst.meta.__setitem__('ap_inv', {self.testInst.meta.fill_label:
                                                  np.inf})

        # Load a test Metadata
        self.testMeta = pysat.Meta() 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def test_calc_f107a_high_rate(self):
        """ Test the calc_f107a routine with sub-daily data"""
        self.testInst.data = pds.DataFrame({'f107': np.linspace(70, 200,
                                                                3840)},
                                           index=[pysat.datetime(2009, 1, 1)
                                                  + pds.DateOffset(hours=i)
                                                  for i in range(3840)])
        sw_f107.calc_f107a(self.testInst, f107_name='f107', f107a_name='f107a')

        # Assert that new data and metadata exist
        assert 'f107a' in self.testInst.data.columns
        assert 'f107a' in self.testInst.meta.keys()

        # Assert the values are finite and realistic means
        assert np.all(np.isfinite(self.testInst['f107a']))
        assert self.testInst['f107a'].min() > self.testInst['f107'].min()
        assert self.testInst['f107a'].max() < self.testInst['f107'].max()

        # Assert the same mean value is used for a day
        assert len(np.unique(self.testInst['f107a'][:24])) == 1 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def test_calc_f107a_daily_missing(self):
        """ Test the calc_f107a routine with some daily data missing"""

        self.testInst.data = pds.DataFrame({'f107': np.linspace(70, 200, 160)},
                                           index=[pysat.datetime(2009, 1, 1)
                                                  + pds.DateOffset(days=2*i+1)
                                                  for i in range(160)])
        sw_f107.calc_f107a(self.testInst, f107_name='f107', f107a_name='f107a')

        # Assert that new data and metadata exist
        assert 'f107a' in self.testInst.data.columns
        assert 'f107a' in self.testInst.meta.keys()

        # Assert the finite values have realistic means
        assert(np.nanmin(self.testInst['f107a'])
               > np.nanmin(self.testInst['f107']))
        assert(np.nanmax(self.testInst['f107a'])
               < np.nanmax(self.testInst['f107']))

        # Assert the expected number of fill values
        assert(len(self.testInst['f107a'][np.isnan(self.testInst['f107a'])])
               == 40) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def setup(self):
        """Runs before every method to create a clean testing setup."""
        info = {'index': 'mlt'}
        self.testInst = pysat.Instrument('pysat', 'testing',
                                         clean_level='clean',
                                         orbit_info=info)
        times = [[pysat.datetime(2008, 12, 31, 4),
                  pysat.datetime(2008, 12, 31, 5, 37)],
                 [pysat.datetime(2009, 1, 1),
                  pysat.datetime(2009, 1, 1, 1, 37)]
                 ]
        for seconds in np.arange(38):
            day = pysat.datetime(2009, 1, 2) + \
                pds.DateOffset(days=int(seconds))
            times.append([day, day +
                          pds.DateOffset(hours=1, minutes=37,
                                         seconds=int(seconds)) -
                          pds.DateOffset(seconds=20)])

        self.testInst.custom.add(filter_data2, 'modify', times=times) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def test_single_adding_custom_function_wrong_times(self):
        """Only the data at the correct time should be accepted, otherwise it
        returns nan
        """
        def custom1(inst):
            new_index = inst.index+pds.DateOffset(milliseconds=500)
            d = pds.Series(2.0 * inst['mlt'], index=new_index)
            d.name = 'doubleMLT'
            print(new_index)
            return d

        self.add(custom1, 'add')
        self.testInst.load(2009, 1)
        ans = (self.testInst['doubleMLT'].isnull()).all()
        if self.testInst.pandas_format:
            assert ans
        else:
            print("Warning! Xarray doesn't enforce the same times on all " +
                  "parameters in dataset.") 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def _apply_loffset(self, result):
        """
        If loffset is set, offset the result index.

        This is NOT an idempotent routine, it will be applied
        exactly once to the result.

        Parameters
        ----------
        result : Series or DataFrame
            the result of resample
        """

        needs_offset = (
            isinstance(self.loffset, (DateOffset, timedelta,
                                      np.timedelta64)) and
            isinstance(result.index, DatetimeIndex) and
            len(result.index) > 0
        )

        if needs_offset:
            result.index = result.index + self.loffset

        self.loffset = None
        return result 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def test_dt64_with_offset_array(klass, assert_func):
    # GH#10699
    # array of offsets
    box = Series if klass is Series else pd.Index
    with tm.assert_produces_warning(PerformanceWarning):
        s = klass([Timestamp('2000-1-1'), Timestamp('2000-2-1')])
        result = s + box([pd.offsets.DateOffset(years=1),
                          pd.offsets.MonthEnd()])
        exp = klass([Timestamp('2001-1-1'), Timestamp('2000-2-29')])
        assert_func(result, exp)

        # same offset
        result = s + box([pd.offsets.DateOffset(years=1),
                          pd.offsets.DateOffset(years=1)])
        exp = klass([Timestamp('2001-1-1'), Timestamp('2001-2-1')])
        assert_func(result, exp) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def test_select_has_data():
    algo = algos.SelectHasData(min_count=3, lookback=pd.DateOffset(days=3))

    s = bt.Strategy('s')

    dts = pd.date_range('2010-01-01', periods=10)
    data = pd.DataFrame(index=dts, columns=['c1', 'c2'], data=100.)
    data['c1'].ix[dts[0]] = np.nan
    data['c1'].ix[dts[1]] = np.nan

    s.setup(data)
    s.update(dts[2])

    assert algo(s)
    selected = s.temp['selected']
    assert len(selected) == 1
    assert 'c2' in selected 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def test_select_has_data_preselected():
    algo = algos.SelectHasData(min_count=3, lookback=pd.DateOffset(days=3))

    s = bt.Strategy('s')

    dts = pd.date_range('2010-01-01', periods=3)
    data = pd.DataFrame(index=dts, columns=['c1', 'c2'], data=100.)
    data['c1'].ix[dts[0]] = np.nan
    data['c1'].ix[dts[1]] = np.nan

    s.setup(data)
    s.update(dts[2])
    s.temp['selected'] = ['c1']

    assert algo(s)
    selected = s.temp['selected']
    assert len(selected) == 0 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def test_weigh_erc(mock_erc):
    algo = algos.WeighERC(lookback=pd.DateOffset(days=5))

    mock_erc.return_value = pd.Series({'c1': 0.3, 'c2': 0.7})

    s = bt.Strategy('s')

    dts = pd.date_range('2010-01-01', periods=5)
    data = pd.DataFrame(index=dts, columns=['c1', 'c2'], data=100.)

    s.setup(data)
    s.update(dts[4])
    s.temp['selected'] = ['c1', 'c2']

    assert algo(s)
    assert mock_erc.called
    rets = mock_erc.call_args[0][0]
    assert len(rets) == 4
    assert 'c1' in rets
    assert 'c2' in rets

    weights = s.temp['weights']
    assert len(weights) == 2
    assert weights['c1'] == 0.3
    assert weights['c2'] == 0.7 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def test_weigh_mean_var(mock_mv):
    algo = algos.WeighMeanVar(lookback=pd.DateOffset(days=5))

    mock_mv.return_value = pd.Series({'c1': 0.3, 'c2': 0.7})

    s = bt.Strategy('s')

    dts = pd.date_range('2010-01-01', periods=5)
    data = pd.DataFrame(index=dts, columns=['c1', 'c2'], data=100.)

    s.setup(data)
    s.update(dts[4])
    s.temp['selected'] = ['c1', 'c2']

    assert algo(s)
    assert mock_mv.called
    rets = mock_mv.call_args[0][0]
    assert len(rets) == 4
    assert 'c1' in rets
    assert 'c2' in rets

    weights = s.temp['weights']
    assert len(weights) == 2
    assert weights['c1'] == 0.3
    assert weights['c2'] == 0.7 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def test_select_momentum():
    algo = algos.SelectMomentum(n=1, lookback=pd.DateOffset(days=3))

    s = bt.Strategy('s')

    dts = pd.date_range('2010-01-01', periods=3)
    data = pd.DataFrame(index=dts, columns=['c1', 'c2'], data=100.)
    data['c1'].ix[dts[2]] = 105
    data['c2'].ix[dts[2]] = 95

    s.setup(data)
    s.update(dts[2])
    s.temp['selected'] = ['c1', 'c2']

    assert algo(s)
    actual = s.temp['selected']
    assert len(actual) == 1
    assert 'c1' in actual 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def apply_time_offset(time, years=0, months=0, days=0, hours=0):
    """Apply a specified offset to the given time array.

    This is useful for GFDL model output of instantaneous values.  For example,
    3 hourly data postprocessed to netCDF files spanning 1 year each will
    actually have time values that are offset by 3 hours, such that the first
    value is for 1 Jan 03:00 and the last value is 1 Jan 00:00 of the
    subsequent year.  This causes problems in xarray, e.g. when trying to group
    by month.  It is resolved by manually subtracting off those three hours,
    such that the dates span from 1 Jan 00:00 to 31 Dec 21:00 as desired.

    Parameters
    ----------
    time : xarray.DataArray representing a timeseries
    years, months, days, hours : int, optional
        The number of years, months, days, and hours, respectively, to offset
        the time array by.  Positive values move the times later.

    Returns
    -------
    pandas.DatetimeIndex

    Examples
    --------
    Case of a length-1 input time array:

    >>> times = xr.DataArray(datetime.datetime(1899, 12, 31, 21))
    >>> apply_time_offset(times)
    Timestamp('1900-01-01 00:00:00')

    Case of input time array with length greater than one:

    >>> times = xr.DataArray([datetime.datetime(1899, 12, 31, 21),
    ...                       datetime.datetime(1899, 1, 31, 21)])
    >>> apply_time_offset(times) # doctest: +NORMALIZE_WHITESPACE
    DatetimeIndex(['1900-01-01', '1899-02-01'], dtype='datetime64[ns]',
                  freq=None)
    """
    return (pd.to_datetime(time.values) +
            pd.DateOffset(years=years, months=months, days=days, hours=hours)) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def test_apply_time_offset():
    start = datetime.datetime(1900, 5, 10)
    years, months, days, hours = -2, 1, 7, 3
    # test lengths 0, 1, and >1 of input time array
    for periods in range(3):
        times = pd.date_range(start=start, freq='M', periods=periods)
        times = pd.to_datetime(times.values)  # Workaround for pandas bug
        actual = apply_time_offset(xr.DataArray(times), years=years,
                                   months=months, days=days, hours=hours)
        desired = (times + pd.DateOffset(
            years=years, months=months, days=days, hours=hours
        ))
        assert actual.identical(desired) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DateOffset [as 别名]
def get_dataset(src, name, distribution):
    df = src[src.airport == name].copy()
    del df['airport']
    df['date'] = pd.to_datetime(df.date)
    # timedelta here instead of pd.DateOffset to avoid pandas bug < 0.18 (Pandas issue #11925)
    df['left'] = df.date - datetime.timedelta(days=0.5)
    df['right'] = df.date + datetime.timedelta(days=0.5)
    df = df.set_index(['date'])
    df.sort_index(inplace=True)
    if distribution == 'Smoothed':
        window, order = 51, 3
        for key in STATISTICS:
            df[key] = savgol_filter(df[key], window, order)

    return ColumnDataSource(data=df)