def prepare(self, da, freq, **indexer):
pfreq, anchor = self.split_freq(freq)
null = self.is_null(da, freq, **indexer)
c = null.sum(dim="time")
# Otherwise simply use the start and end dates to find the expected number of days.
if pfreq.endswith("S"):
start_time = c.indexes["time"]
end_time = start_time.shift(1, freq=freq)
else:
end_time = c.indexes["time"]
start_time = end_time.shift(-1, freq=freq)
if indexer:
# Create a full synthetic time series and compare the number of days with the original series.
t0 = str(start_time[0].date())
t1 = str(end_time[-1].date())
if isinstance(c.indexes["time"], xr.CFTimeIndex):
cal = da.time.encoding.get("calendar")
t = xr.cftime_range(t0, t1, freq="D", calendar=cal)
else:
t = pd.date_range(t0, t1, freq="D")
sda = xr.DataArray(data=np.ones(len(t)), coords={"time": t}, dims=("time",))
st = generic.select_time(sda, **indexer)
count = st.notnull().resample(time=freq).sum(dim="time")
else:
n = (end_time - start_time).days
count = xr.DataArray(n.values, coords={"time": c.time}, dims="time")
return null, count
def is_null(da, freq, **indexer):
# Compute the number of days in the time series during each period at the given frequency.
selected = generic.select_time(da, **indexer)
if selected.time.size == 0:
raise ValueError("No data for selected period.")
return selected.isnull().resample(time=freq)
def is_null(da, freq, **indexer):
"""Return a boolean array indicating which values are null."""
selected = generic.select_time(da, **indexer)
if selected.time.size == 0:
raise ValueError("No data for selected period.")
null = selected.isnull()
if freq:
return null.resample(time=freq)
return null
def prepare(self, da, freq, src_timestep, **indexer):
"""Prepare arrays to be fed to the `is_missing` function.
Parameters
----------
da : xr.DataArray
Input data.
freq : str
Resampling frequency defining the periods defined in
http://pandas.pydata.org/pandas-docs/stable/timeseries.html#resampling.
src_timestep : {"D", "H"}
Expected input frequency.
**indexer : {dim: indexer, }, optional
Time attribute and values over which to subset the array. For example, use season='DJF' to select winter
values, month=1 to select January, or month=[6,7,8] to select summer months. If not indexer is given,
all values are considered.
Returns
-------
xr.DataArray, xr.DataArray
Boolean array indicating which values are null, array of expected number of valid values.
Notes
-----
If `freq=None` and an indexer is given, then missing values during period at the start or end of array won't be
flagged.
"""
# This function can probably be made simpler once CFPeriodIndex is implemented.
null = self.is_null(da, freq, **indexer)
pfreq, anchor = self.split_freq(freq)
c = null.sum(dim="time")
# Otherwise simply use the start and end dates to find the expected number of days.
if pfreq.endswith("S"):
start_time = c.indexes["time"]
end_time = start_time.shift(1, freq=freq)
elif pfreq:
end_time = c.indexes["time"]
start_time = end_time.shift(-1, freq=freq)
else:
i = da.time.to_index()
start_time = i[:1]
end_time = i[-1:]
if indexer:
# Create a full synthetic time series and compare the number of days with the original series.
t = date_range(
start_time[0],
end_time[-1],
freq=src_timestep,
calendar=get_calendar(da),
)
sda = xr.DataArray(data=np.ones(len(t)),
coords={"time": t},
dims=("time", ))
st = generic.select_time(sda, **indexer)
if freq:
count = st.notnull().resample(time=freq).sum(dim="time")
else:
count = st.notnull().sum(dim="time")
else:
delta = end_time - start_time
n = delta.astype(_np_timedelta64[src_timestep])
if freq:
count = xr.DataArray(n.values,
coords={"time": c.time},
dims="time")
else:
count = xr.DataArray(n.values[0] + 1)
return null, count
def compute(da: xr.DataArray, **indexer):
select = select_time(da, **indexer)
return select.mean(dim="time", keep_attrs=True)