solarforecastarbiter.metrics.deterministic.pearson_correlation_coeff

solarforecastarbiter.metrics.deterministic.pearson_correlation_coeff(obs, fx)[source]

Pearson correlation coefficient (r).

\[r = A / (B * C)\]

where:

\[A = \sum_{i=1}^n (\text{fx}_i - \text{fx}_\text{avg}) * (\text{obs}_i - \text{obs}_\text{avg})\]
\[B = \sqrt{ \sum_{i=1}^n (\text{fx}_i - \text{fx}_\text{avg})^2 }\]
\[C = \sqrt{ \sum_{i=1}^n (\text{obs}_i - \text{obs}_\text{avg})^2 }\]
\[\text{fx}_\text{avg} = 1/n \sum_{i=1} \text{fx}_i\]
\[\text{obs}_\text{avg} = 1/n \sum_{i=1} \text{obs}_i\]
Parameters:
  • obs ((n,) array-like) – Observed values.
  • fx ((n,) array-like) – Forecasted values.
Returns:

r (float) – The correlation coefficient (r [-]) of the observations and forecasts.