binnings.py 文件源码

def ideal_bin_count(data, method="default"):
    """A theoretically ideal bin count.

    Parameters
    ----------
    data: array_like or None
        Data to work on. Most methods don't use this.
    method: str
        Name of the method to apply, available values:
          - default (~sturges)
          - sqrt
          - sturges
          - doane
          - rice
        See https://en.wikipedia.org/wiki/Histogram for the description

    Returns
    -------
    int
        Number of bins, always >= 1
    """
    n = data.size
    if n < 1:
        return 1
    if method == "default":
        if n <= 32:
            return 7
        else:
            return ideal_bin_count(data, "sturges")
    elif method == "sqrt":
        return int(np.ceil(np.sqrt(n)))
    elif method == "sturges":
        return int(np.ceil(np.log2(n)) + 1)
    elif method == "doane":
        if n < 3:
            return 1
        from scipy.stats import skew
        sigma = np.sqrt(6 * (n-2) / (n + 1) * (n + 3))
        return int(np.ceil(1 + np.log2(n) + np.log2(1 + np.abs(skew(data)) / sigma)))
    elif method == "rice":
        return int(np.ceil(2 * np.power(n, 1 / 3)))