Function kde_random

Lib/statistics.py:1094–1136

Return a function that makes a random selection from the estimated probability density function created by kde(data, h, kernel). Providing a *seed* allows reproducible selections within a single thread. The seed may be an integer, float, str, or bytes. A StatisticsError will be ra

(data, h, kernel='normal', *, seed=None)

def kde_random(data, h, kernel='normal', *, seed=None):
    """Return a function that makes a random selection from the estimated
    probability density function created by kde(data, h, kernel).

    Providing a *seed* allows reproducible selections within a single
    thread.  The seed may be an integer, float, str, or bytes.

    A StatisticsError will be raised if the *data* sequence is empty.

    Example:

    >>> data = [-2.1, -1.3, -0.4, 1.9, 5.1, 6.2]
    >>> rand = kde_random(data, h=1.5, seed=8675309)
    >>> new_selections = [rand() for i in range(10)]
    >>> [round(x, 1) for x in new_selections]
    [0.7, 6.2, 1.2, 6.9, 7.0, 1.8, 2.5, -0.5, -1.8, 5.6]

    """
    n = len(data)
    if not n:
        raise StatisticsError('Empty data sequence')

    if not isinstance(data[0], (int, float)):
        raise TypeError('Data sequence must contain ints or floats')

    if h <= 0.0:
        raise StatisticsError(f'Bandwidth h must be positive, not {h=!r}')

    kernel_spec = _kernel_specs.get(kernel)
    if kernel_spec is None:
        raise StatisticsError(f'Unknown kernel name: {kernel!r}')
    invcdf = kernel_spec['invcdf']

    prng = _random.Random(seed)
    random = prng.random
    choice = prng.choice

    def rand():
        return choice(data) + h * invcdf(random())

    rand.__doc__ = f'Random KDE selection with {h=!r} and {kernel=!r}'

    return rand


## Quantiles ###############################################################