pyinterp.TDigestFloat32.quantile

TDigestFloat32.quantile(self, q: float) → numpy.ndarray[dtype=float32]

TDigestFloat32.quantile(self, quantiles: ndarray[dtype=float32, device='cpu']) → numpy.ndarray[dtype=float32]

Overloaded function.

1. quantile(self, q: float) -> numpy.ndarray[dtype=float32]

Calculate quantile using t-digest algorithm.

Parameters:

q – Quantile in range [0, 1]. For example, 0.5 for median, 0.95 for 95th percentile.

Returns:

Estimated quantile value(s).

2. quantile(self, quantiles: ndarray[dtype=float32, device='cpu']) -> numpy.ndarray[dtype=float32]

Calculate multiple quantiles using t-digest algorithm.

Parameters:

quantiles – Array of quantile values in range [0, 1].

Returns:

Matrix of quantile estimates with shape [n_digests x n_quantiles]. If axis reduction was not used (single digest), returns a 1D array.