ts_pad (pyleoclim.utils.filter.ts_pad)
- pyleoclim.utils.filter.ts_pad(ys, ts, method='reflect', params=(1, 0, 0), reflect_type='odd', padFrac=0.1)[source]
Pad a timeseries based on timeseries model predictions
- Parameters
ys (numpy array) – Evenly-spaced timeseries
ts (numpy array) – Time axis
method (string) – The method to use to pad the series - ARIMA: uses a fitted ARIMA model - reflect (default): Reflects the time series around either end.
params (tuple ARIMA model order parameters (p,d,q), Default corresponds to an AR(1) model) –
reflect_type (string) – {‘even’, ‘odd’}, optional Used in ‘reflect’, and ‘symmetric’. The ‘even’ style is the default with an unaltered reflection around the edge value. For the ‘odd’ style, the extented part of the array is created by subtracting the reflected values from two times the edge value. For more details, see np.lib.pad()
padFrac (float) – padding fraction (scalar) such that padLength = padFrac*length(series)
- Returns
yp (array) – padded timeseries
tp (array) – augmented time axis