liger_iris_pipeline.utils.math

Functions

`mad`(x)
`robust_mean`(x[, w, n_sigma])	Calculate robust mean using outlier rejection.
`robust_stddev`(x[, w, n_sigma])	Calculate robust standard deviation using outlier rejection.
`weighted_mean`(x, w)	Computes the weighted mean of a dataset.
`weighted_quantile`(values, weights[, q])
`weighted_stddev`(x, w[, mu])	Calculate the weighted standard deviation of an array.

liger_iris_pipeline.utils.math.robust_mean(x, w=None, n_sigma=4)[source]

Calculate robust mean using outlier rejection.

Parameters: - x: Array of values - w: Array of weights (default: uniform weights) - n_sigma: Number of sigma for outlier rejection

Returns: - Robust mean or NaN if insufficient valid data

liger_iris_pipeline.utils.math.robust_stddev(x, w=None, n_sigma=4)[source]

Calculate robust standard deviation using outlier rejection.

Parameters: - x: Array of values - w: Array of weights (default: uniform weights) - n_sigma: Number of sigma for outlier rejection

Returns: - Robust standard deviation or NaN if insufficient valid data

liger_iris_pipeline.utils.math.weighted_mean(x, w)[source]

Computes the weighted mean of a dataset.

Args:: x (np.ndarray): The input array. w (np.ndarray): The input weights, same shape as x. axis (int): Axis or tuple of axes along which to compute the mean. Default is None.
Returns:: float: The weighted mean.

liger_iris_pipeline.utils.math.weighted_quantile(values: ndarray, weights: ndarray, q: float = 0.5)[source]

liger_iris_pipeline.utils.math.weighted_stddev(x: ndarray, w: ndarray, mu: float | None = None)[source]

Calculate the weighted standard deviation of an array.

Parameters: - x: Array of values - w: Array of weights

Returns: - Weighted standard deviation or NaN if no valid data