def date_range(start=None,
end=None,
periods=None,
freq=None,
tz=None,
normalize=False,
name=None,
closed=None,
**kwargs):
'''Creates a fixed frequency Datetime range. Alias for
``ak.Datetime(pd.date_range(args))``. Subject to size limit
imposed by client.maxTransferBytes.
Parameters
----------
start : str or datetime-like, optional
Left bound for generating dates.
end : str or datetime-like, optional
Right bound for generating dates.
periods : int, optional
Number of periods to generate.
freq : str or DateOffset, default 'D'
Frequency strings can have multiples, e.g. '5H'. See
timeseries.offset_aliases for a list of
frequency aliases.
tz : str or tzinfo, optional
Time zone name for returning localized DatetimeIndex, for example
'Asia/Hong_Kong'. By default, the resulting DatetimeIndex is
timezone-naive.
normalize : bool, default False
Normalize start/end dates to midnight before generating date range.
name : str, default None
Name of the resulting DatetimeIndex.
closed : {None, 'left', 'right'}, optional
Make the interval closed with respect to the given frequency to
the 'left', 'right', or both sides (None, the default).
**kwargs
For compatibility. Has no effect on the result.
Returns
-------
rng : DatetimeIndex
Notes
-----
Of the four parameters ``start``, ``end``, ``periods``, and ``freq``,
exactly three must be specified. If ``freq`` is omitted, the resulting
``DatetimeIndex`` will have ``periods`` linearly spaced elements between
``start`` and ``end`` (closed on both sides).
To learn more about the frequency strings, please see `this link
<https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases>`__.
'''
return Datetime(
pd_date_range(start, end, periods, freq, tz, normalize, name, closed,
**kwargs))
def make_fileList(reanalysis, variable, date_range, grid=None):
'''
Generates a list of filepaths for a given reanalysis and variable for a date range.
The code deals with CFSR* spanning two products.
reanalysis - name of reanalysis
variable - my standard variable name
date_range - tuple of dates in format (yyyymmdd, yyyymmdd)
returns - filepath string
'''
from pandas import date_range as pd_date_range
import datetime as dt
filelist = []
for date in pd_date_range(date_range[0], date_range[1], freq='M'):
if (reanalysis == 'CFSR') & (date >= dt.datetime(2011,1,1)):
filelist.append(make_filepath('CFSR2', variable, date, grid=grid))
else:
filelist.append(make_filepath(reanalysis, variable, date, grid=grid))
return filelist
import xarray as xr
import numpy as np
from pandas import date_range as pd_date_range
from cdo import *
cdo = Cdo()
# PET function
exec(open("./src/ai_fao.py").read())
# hydrological time
hydro_time = pd_date_range("1982-01-01", "2016-12-31", freq="D")
hydro_time = hydro_time[~((hydro_time.day == 29) & (hydro_time.month == 2))]
hydro_time2 = pd_date_range("1982-01-01", "2016-12-31", freq="M")
# pet
piscopet = xr.open_dataset(cdo.cat(input="./data/raw/PET/*.nc"))
#piscopet = piscopet.rename({"__xarray_dataarray_variable__":"pet"})
piscopet = piscopet.sel(time=slice("1981-09-01", "2016-08-31"))
piscopet = piscopet.isel(
time=~piscopet.time.dt.strftime('%m-%d').isin("02-29"))
piscopet["time"] = hydro_time
piscopet_anual = piscopet.resample(time="1Y").sum()
piscopet_anual = piscopet_anual.reindex(
longitude=np.arange(piscopet.longitude.values[1],
piscopet.longitude.values[-1], 0.008),
latitude=np.arange(piscopet.latitude.values[1],
piscopet.latitude.values[-1], -0.008),
method="nearest")
# precp
piscop = xr.open_dataset("./data/raw/PISCO/PISCOpd.nc")
piscotx = xr.open_dataset("./data/raw/PISCO/PISCOdtx_v1.1.nc")
piscotn = xr.open_dataset("./data/raw/PISCO/PISCOdtn_v1.1.nc")
# building lat grid
pisco_lat = xr.DataArray(
np.tile(piscotx["latitude"].values, (145, 1)).transpose(),
coords=[piscotx["latitude"].values, piscotx["longitude"].values],
dims=["latitude", "longitude"])
# getting time values as Julian day
"""
# as gridded, not efficient
[np.full((145, 202), i) for i in dates]
np.stack([np.full((145, 202), 1), np.full((145, 202), 2), np.full((145, 202), 3)], axis=2).shape
"""
dates = pd_date_range('1981-01-01', "2016-12-31", freq='D')
dates = np.array([int(i.strftime("%j")) for i in dates])
# computing PET
for year in range(1981, 2017):
dates = pd_date_range(str(year) + '-01-01', str(year) + "-12-31", freq='D')
dates = np.array([int(i.strftime("%j")) for i in dates])
xr.apply_ufunc(hargreaves_samani,
piscotx.tx.loc[str(year) + '-01-01':str(year) + "-12-31"],
piscotn.tn.loc[str(year) + '-01-01':str(year) + "-12-31"],
dates,
pisco_lat,
vectorize=True,