ecdf.py

class ECDF(object):
    """
    One-dimensional empirical distribution function given a vector of
    observations.

    Parameters
    ----------
    observations : array_like
        An array of observations

    Attributes
    ----------
    observations : array_like
        An array of observations

    """

    def __init__(self, observations):
        self.observations = np.asarray(observations)

    def __call__(self, x):
        """
        Evaluates the ecdf at x

        Parameters
        ----------
        x : scalar(float)
            The x at which the ecdf is evaluated

        Returns
        -------
        scalar(float)
            Fraction of the sample less than x

        """
        return np.mean(self.observations <= x)

    def plot(self, a=None, b=None, *args, **kwargs):
        """
        Plot the ecdf on the interval [a, b].

        Parameters
        ----------
        a : scalar(float), optional(default=None)
            Lower end point of the plot interval
        b : scalar(float), optional(default=None)
            Upper end point of the plot interval

        """

        # === choose reasonable interval if [a, b] not specified === #
        if a is None:
            a = self.observations.min() - self.observations.std()
        if b is None:
            b = self.observations.max() + self.observations.std()

        # === generate plot === #
        x_vals = np.linspace(a, b, num=100)
        f = np.vectorize(self.__call__)
        return (x_vals, f(x_vals))
        #plt.plot(x_vals, f(x_vals), *args, **kwargs)
        #plt.show()