rdtools.degradation.degradation_classical_decomposition

rdtools.degradation.degradation_classical_decomposition(energy_normalized, confidence_level=68.2)

Estimate the trend of a timeseries using a classical decomposition approach (moving average) and calculate various statistics, including the result of a Mann-Kendall test and a Monte Carlo-derived confidence interval of slope.

Parameters
  • energy_normalized (pandas.Series) -- Daily or lower frequency time series of normalized system ouput. Must be regular time series.

  • confidence_level (float, default 68.2) -- The size of the confidence interval to return, in percent.

Returns

  • Rd_pct (float) -- Estimated degradation relative to the year 0 system capacity [%/year]

  • Rd_CI (numpy.array) -- The calculated confidence interval bounds.

  • calc_info (dict) -- A dict that contains slope, intercept, root mean square error of regression ('rmse'), standard error of the slope ('slope_stderr'), intercept ('intercept_stderr'), and least squares RegressionResults object ('ols_results'), pandas series for the annual rolling mean ('series'), and Mann-Kendall test trend ('mk_test_trend')