poisson outliers

poisson_outliers.py

def poisson_outliers(arr, min_pval=.01, min_size_to_filter=5):
    """
    >>> poisson_outliers([1,1,1,1,1,2,3])
    array([False, False, False, False, False, False, False], dtype=bool)
    >>> poisson_outliers([1,1,1,1,1,2,10])
    array([False, False, False, False, False, False,  True], dtype=bool)
    >>> poisson_outliers([1,1,10])
    array([False, False, False], dtype=bool)
    """
    arr = np.asarray(arr)
    mu = np.median(arr)
    pvals = poisson(mu).sf(arr)
    # outliers have pvalues that are too unlikely given our sample size
    if len(arr) >= min_size_to_filter:
        is_outlier = pvals < min(1.0 / len(arr), min_pval)
    else:
        is_outlier = np.zeros_like(pvals).astype(bool)
    return is_outlier