def test_julian2date():
"""
Test julian2date.
"""
year, month, day, hour, minute, second, ms = julian2date(
2457533.9306828701)
assert type(year) == int
assert year == 2016
assert month == 5
assert day == 25
assert hour == 10
assert minute == 20
assert second == 10
assert ms == 999976
year, month, day, hour, minute, second, ms = julian2date(2454515.40972)
assert year == 2008
assert month == 2
assert day == 18
assert hour == 21
assert minute == 49
assert second == 59
assert ms == 807989
def test_julian2date_array():
"""
Test julian2date.
"""
year, month, day, hour, minute, second, micro = julian2date(
np.array([2457533.9306828701, 2457533.9306828701]))
nptest.assert_almost_equal(year, np.array([2016, 2016]))
nptest.assert_almost_equal(month, np.array([5, 5]))
nptest.assert_almost_equal(day, np.array([25, 25]))
nptest.assert_almost_equal(hour, np.array([10, 10]))
nptest.assert_almost_equal(minute, np.array([20, 20]))
nptest.assert_almost_equal(second, np.array([10, 10]))
nptest.assert_almost_equal(micro, np.array([999976, 999976]))
def test_julian2date_single_array():
"""
Test julian2date single array.
"""
year, month, day, hour, minute, second, micro = julian2date(
np.array([2457533.9306828701]))
assert type(year) == np.ndarray
assert year == 2016
assert month == 5
assert day == 25
assert hour == 10
assert minute == 20
assert second == 10
assert micro == 999976
def julian2doy(j, consider_nonleap_years=True):
"""
Calendar date from julian date.
Works only for years past 1582!
Parameters
----------
j : numpy.ndarray or double
Julian days.
consider_nonleap_years : boolean, optional
Flag if all dates are interpreted as leap years (False) or not (True).
Returns
-------
doy : numpy.ndarray or int32
Day of year.
"""
return julian2date(j, return_doy=True, doy_leap_year=not consider_nonleap_years)[-1]
def julian2datetimeindex(j, tz=pytz.UTC):
"""
Converting Julian days to datetimeindex.
Parameters
----------
j : numpy.ndarray or int32
Julian days.
tz : instance of pytz, optional
Time zone. Default: UTC
Returns
-------
datetime : pandas.DatetimeIndex
Datetime index.
"""
year, month, day, hour, minute, second, microsecond = julian2date(j)
return pd.DatetimeIndex([datetime(y, m, d, h, mi, s, ms, tz)
for y, m, d, h, mi, s, ms in
zip(year, month, day, hour, minute,
second, microsecond)])
def calc_climatology(Ser,
moving_avg_orig=5,
moving_avg_clim=30,
median=False,
timespan=None,
fill=np.nan,
wraparound=False,
respect_leap_years=False,
interpolate_leapday=False,
fillna=True,
min_obs_orig=1,
min_obs_clim=1):
'''
Calculates the climatology of a data set.
Parameters
----------
Ser : pandas.Series (index must be a DateTimeIndex or julian date)
moving_avg_orig : float, optional
The size of the moving_average window [days] that will be applied on the
input Series (gap filling, short-term rainfall correction)
Default: 5
moving_avg_clim : float, optional
The size of the moving_average window [days] that will be applied on the
calculated climatology (long-term event correction)
Default: 35
median : boolean, optional
if set to True, the climatology will be based on the median conditions
timespan : [timespan_from, timespan_to], datetime.datetime(y,m,d), optional
Set this to calculate the climatology based on a subset of the input
Series
fill : float or int, optional
Fill value to use for days on which no climatology exists
wraparound : boolean, optional
If set then the climatology is wrapped around at the edges before
doing the second running average (long-term event correction)
respect_leap_years : boolean, optional
If set then leap years will be respected during the calculation of
the climatology
Default: False
fillna: boolean, optional
If set, then the moving average used for the calculation of the
climatology will be filled at the nan-values
min_obs_orig: int
Minimum observations required to give a valid output in the first
moving average applied on the input series
min_obs_clim: int
Minimum observations required to give a valid output in the second
moving average applied on the calculated climatology
Returns
-------
climatology : pandas.Series
Series containing the calculated climatology
Always has 366 values behaving like a leap year
'''
if timespan is not None:
Ser = Ser.truncate(before=timespan[0], after=timespan[1])
Ser = moving_average(Ser, window_size=moving_avg_orig, fillna=fillna, min_obs=min_obs_orig)
Ser = pd.DataFrame(Ser)
if type(Ser.index) == pd.DatetimeIndex:
year, month, day = (np.asarray(Ser.index.year),
np.asarray(Ser.index.month),
np.asarray(Ser.index.day))
else:
year, month, day = julian2date(Ser.index.values)[0:3]
if respect_leap_years:
doys = doy(month, day, year)
else:
doys = doy(month, day)
Ser['doy'] = doys
if median:
clim = Ser.groupby('doy').median()
else:
clim = Ser.groupby('doy').mean()
clim_ser = pd.Series(clim.values.flatten(),
index=clim.index.values)
if wraparound:
index_old = clim_ser.index.copy()
left_mirror = clim_ser.iloc[-moving_avg_clim:]
right_mirror = clim_ser.iloc[:moving_avg_clim]
# Shift index to start at 366 - index at -moving_avg_clim
# to run over a whole year while keeping gaps the same size
right_mirror.index = right_mirror.index + 366 * 2
clim_ser.index = clim_ser.index + 366
clim_ser = pd.concat([left_mirror,
clim_ser,
right_mirror])
clim_ser = moving_average(clim_ser, window_size=moving_avg_clim, fillna=fillna, min_obs=min_obs_clim)
clim_ser = clim_ser.iloc[moving_avg_clim:-moving_avg_clim]
clim_ser.index = index_old
else:
clim_ser = moving_average(clim_ser, window_size=moving_avg_clim, fillna=fillna, min_obs=min_obs_clim)
clim_ser = clim_ser.reindex(np.arange(366) + 1)
if interpolate_leapday and not respect_leap_years:
clim_ser[60] = np.mean((clim_ser[59], clim_ser[61]))
elif interpolate_leapday and respect_leap_years:
clim_ser[366] = np.mean((clim_ser[365], clim_ser[1]))
clim_ser = clim_ser.fillna(fill)
return clim_ser
def calc_anomaly(Ser,
window_size=35,
climatology=None,
respect_leap_years=True,
return_clim=False):
'''
Calculates the anomaly of a time series (Pandas series).
Both, climatology based, or moving-average based anomalies can be
calculated
Parameters
----------
Ser : pandas.Series (index must be a DateTimeIndex)
window_size : float, optional
The window-size [days] of the moving-average window to calculate the
anomaly reference (only used if climatology is not provided)
Default: 35 (days)
climatology : pandas.Series (index: 1-366), optional
if provided, anomalies will be based on the climatology
timespan : [timespan_from, timespan_to], datetime.datetime(y,m,d), optional
If set, only a subset
respect_leap_years : boolean, optional
If set then leap years will be respected during matching of the climatology
to the time series
return_clim : boolean, optional
if set to true the return argument will be a DataFrame which
also contains the climatology time series.
Only has an effect if climatology is used.
Returns
-------
anomaly : pandas.Series
Series containing the calculated anomalies
'''
if climatology is not None:
if type(Ser.index) == pd.DatetimeIndex:
year, month, day = (np.asarray(Ser.index.year),
np.asarray(Ser.index.month),
np.asarray(Ser.index.day))
else:
year, month, day = julian2date(Ser.index.values)[0:3]
if respect_leap_years:
doys = doy(month, day, year)
else:
doys = doy(month, day)
df = pd.DataFrame()
df['absolute'] = Ser
df['doy'] = doys
clim = pd.DataFrame({'climatology': climatology})
df = df.join(clim, on='doy', how='left')
anomaly = df['absolute'] - df['climatology']
anomaly.index = df.index
if return_clim:
anomaly = pd.DataFrame({'anomaly': anomaly})
anomaly['climatology'] = df['climatology']
else:
reference = moving_average(Ser, window_size=window_size)
anomaly = Ser - reference
return anomaly
def calc_climatology(Ser,
moving_avg_orig=5,
moving_avg_clim=35,
moving_avg_month_clim=3,
median=False,
timespan=None,
fill=np.nan,
wraparound=True,
respect_leap_years=False,
interpolate_leapday=False,
fillna=True,
min_obs_orig=1,
min_obs_clim=1,
unit="day"):
"""
Calculates the climatology of a data set.
Parameters
----------
Ser : pandas.Series (index must be a DateTimeIndex or julian date)
moving_avg_orig : float, optional
The size of the moving_average window [days] that will be applied on the
input Series (gap filling, short-term rainfall correction)
Default: 5
moving_avg_clim : float, optional
The size of the moving_average window in days that will be applied on the
calculated climatology (long-term event correction)
Default: 35
moving_avg_month_clim: : float, optional
Same as for 'moving_avg_clim', but applied to monthly climatologies. In case
unit='month', this value overrides 'moving_avg_clim'
Default: 3
median : boolean, optional
if set to True, the climatology will be based on the median conditions
timespan : [timespan_from, timespan_to], datetime.datetime(y,m,d), optional
Set this to calculate the climatology based on a subset of the input
Series
fill : float or int, optional
Fill value to use for days on which no climatology exists
wraparound : boolean, optional
If set then the climatology is wrapped around at the edges before
doing the second running average (long-term event correction)
respect_leap_years : boolean, optional
If set then leap years will be respected during the calculation of
the climatology. Only valid with 'unit' value set to 'day'.
Default: False
interpolate_leapday: boolean, optional
<description>. Only valid with 'unit' value set to 'day'.
Default: False
fillna: boolean, optional
If set, then the moving average used for the calculation of the
climatology will be filled at the nan-values
min_obs_orig: int
Minimum observations required to give a valid output in the first
moving average applied on the input series
min_obs_clim: int
Minimum observations required to give a valid output in the second
moving average applied on the calculated climatology
unit: str, optional
Unit of the year to apply the climatology calculation to. Currently,
supported options are 'day', 'month'.
Default: 'day'
Returns
-------
climatology : pandas.Series
Series containing the calculated climatology
Always has 366 values behaving like a leap year
"""
if unit != "day":
respect_leap_years, interpolate_leapday = False, False
if unit == "month":
moving_avg_clim = moving_avg_month_clim
if timespan is not None:
Ser = Ser.truncate(before=timespan[0], after=timespan[1])
Ser = moving_average(Ser,
window_size=moving_avg_orig,
fillna=fillna,
min_obs=min_obs_orig)
Ser = pd.DataFrame(Ser)
if type(Ser.index) == pd.DatetimeIndex:
year, month, day = (np.asarray(Ser.index.year),
np.asarray(Ser.index.month),
np.asarray(Ser.index.day))
else:
year, month, day = julian2date(Ser.index.values)[0:3]
# provide indices for the selected unit
indices, n_idx = _index_units(year,
month,
day,
unit=unit,
respect_leap_years=respect_leap_years)
Ser['unit'] = indices
if median:
clim = Ser.groupby('unit').median()
else:
clim = Ser.groupby('unit').mean()
clim_ser = pd.Series(clim.values.flatten(), index=clim.index.values)
clim_ser = clim_ser.reindex(np.arange(n_idx) + 1)
if wraparound:
index_old = clim_ser.index.copy()
left_mirror = clim_ser.iloc[-moving_avg_clim:]
right_mirror = clim_ser.iloc[:moving_avg_clim]
# Shift index to start at n_idx - index at -moving_avg_clim
# to run over a whole year while keeping gaps the same size
right_mirror.index = right_mirror.index + n_idx * 2
clim_ser.index = clim_ser.index + n_idx
clim_ser = pd.concat([left_mirror, clim_ser, right_mirror])
clim_ser = moving_average(clim_ser,
window_size=moving_avg_clim,
fillna=fillna,
min_obs=min_obs_clim)
clim_ser = clim_ser.iloc[moving_avg_clim:-moving_avg_clim]
clim_ser.index = index_old
else:
clim_ser = moving_average(clim_ser,
window_size=moving_avg_clim,
fillna=fillna,
min_obs=min_obs_clim)
# keep hardcoding as it's only for doys
if interpolate_leapday and not respect_leap_years:
clim_ser[60] = np.mean((clim_ser[59], clim_ser[61]))
elif interpolate_leapday and respect_leap_years:
clim_ser[366] = np.mean((clim_ser[365], clim_ser[1]))
clim_ser = clim_ser.fillna(fill)
return clim_ser
