focal.focal_correlation

focal.focal_correlation(a1: Array, a2: Array, *, window: int | tuple[int, ...] | list[int] | ndarray[tuple[int, ...], bool] | Window, fraction_accepted: float = 0.7, verbose: bool = False, reduce: bool = False, chunks: int | tuple[int, int] | None = None, p_values: bool = False, out: CorrelationResult | None = None) → CorrelationResult

Focal correlation.

Parameters:

• a1 (Array) – Input arrays to be correlated. They must have the same shape and be two-dimensional.

• a2 (Array) – Input arrays to be correlated. They must have the same shape and be two-dimensional.

• window (int, array-like, or Window, optional) –

  Window applied over the input arrays. It can be:

  • An integer (interpreted as a square window),

  • A sequence of integers (interpreted as a rectangular window),

  • A boolean array,

  • Or a pyspatialstats.windows.Window object.

• fraction_accepted (float, optional) –

  Fraction of valid cells (i.e., not NaN) per window required for the correlation to be computed.

  • 0: include views with at least 1 valid value

  • 1: include only fully valid views

  • Between 0 and 1: minimum fraction of valid values required

  Default is 0.7.

• verbose (bool, optional) – If True, print timing. Default is False.

• reduce (bool, optional) – If True, use each pixel exactly once without overlapping windows. The resulting array will have shape a_shape / window_shape. Default is False.

• p_values (bool, optional) – If True, calculate p-values along with correlation coefficients. Default is False.

• chunks (int or tuple of int, optional) – Shape of chunks to split the array into. If None, the array is not split into chunks, which is the default.

• out (CorrelationResult, optional) – CorrelationResult object to write results to.

Returns:

Dataclass containing correlation coefficients (and optionally p-values).

Return type:

CorrelationResult