程序包 org.meteoinfo.math.stats.kde

类 KDE

  • public class KDE
extends java.lang.Object

    • 方法概要

      所有方法 静态方法 实例方法 具体方法 
      修饰符和类型 方法 说明
      double logPdf​(Event e)
      Computed the log probability of event e.
      static void main​(java.lang.String... args)  
      static KDE trainAdaptiveKDE​(java.util.List<Event> data, double h0, int K)
      Creates a Kernel Density Estimation for the data using the adaptive bandwidth method.
      static KDE trainAdaptiveKDE​(java.util.List<Event> data, int K)
      Creates a Kernel Density Estimation for the data using the adaptive bandwidth method with the default value of (h0 = 0).
      static KDE trainFixedKDE​(java.util.List<Event> data, double h)
      Creates a Kernel Density Estimation for the data using the fixed bandwidth method.

      • 从类继承的方法 java.lang.Object

        clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

    • 方法详细资料

      • trainFixedKDE

        public static KDE trainFixedKDE​(java.util.List<Event> data,
                                double h)
        Creates a Kernel Density Estimation for the data using the fixed bandwidth method. See: http://www.datalab.uci.edu/papers/kernel_KDD2014.pdf
        参数:
        data - - The observed data
        h - - The fixed bandwidth
        返回:
        A "trained" fixed-KDE model

      • trainAdaptiveKDE

        public static KDE trainAdaptiveKDE​(java.util.List<Event> data,
                                   int K)
        Creates a Kernel Density Estimation for the data using the adaptive bandwidth method with the default value of (h0 = 0). See: http://www.datalab.uci.edu/papers/kernel_KDD2014.pdf
        参数:
        data - - The observed data
        K - - K'th nearest neighbor
        返回:
        A "trained" adaptive-KDE model

      • trainAdaptiveKDE

        public static KDE trainAdaptiveKDE​(java.util.List<Event> data,
                                   double h0,
                                   int K)
        Creates a Kernel Density Estimation for the data using the adaptive bandwidth method. See: http://www.datalab.uci.edu/papers/kernel_KDD2014.pdf
        参数:
        data - - The observed data
        h0 - - h0 value (default 1)
        K - - K'th nearest neighbor
        返回:
        A "trained" adaptive-KDE model

      • logPdf

        public double logPdf​(Event e)
        Computed the log probability of event e. The computation is done by using the kd tree. See: http://www.datalab.uci.edu/papers/kernel_KDD2014.pdf
        参数:
        e -
        返回:
        Log probability for event e

      • main

        public static void main​(java.lang.String... args)
                 throws java.lang.Exception
        抛出:
        java.lang.Exception