spark 朴素贝叶斯
训练代码(scala)
import org.apache.spark.mllib.classification.{NaiveBayes,NaiveBayesModel}
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.{SparkContext,SparkConf}
object NaiveBayes {
def main(args: Array[String]): Unit = {
val conf = new SparkConf()
.setMaster("local")
.setAppName("NaiveBayes")
val sc = new SparkContext(conf)
val path = "../data/sample_football_weather.txt"
val data = sc.textFile(path)
val parsedData =data.map {
line =>
val parts =line.split(',')
LabeledPoint(parts(0).toDouble,Vectors.dense(parts(1).split(' ').map(_.toDouble)))
}
//样本划分train和test数据样本60%用于train
val splits = parsedData.randomSplit(Array(0.6,0.4),seed = 11L)
val training =splits(0)
val test =splits(1)
//获得训练模型,第一个参数为数据,第二个参数为平滑参数,默认为1,可改变
val model =NaiveBayes.train(training,lambda = 1.0)
//对测试样本进行测试
//对模型进行准确度分析
val predictionAndLabel= test.map(p => (model.predict(p.features),p.label))
val accuracy =1.0 *predictionAndLabel.filter(x => x._1 == x._2).count() / test.count()
//打印一个预测值
println("NaiveBayes精度----->" + accuracy)
//我们这里特地打印一个预测值:假如一天是 晴天(0)凉(2)高(0)高(1) 踢球与否
println("假如一天是 晴天(0)凉(2)高(0)高(1) 踢球与否:" + model.predict(Vectors.dense(0.0,2.0,0.0,1.0)))
//保存model
val ModelPath = "../model/NaiveBayes_model.obj"
model.save(sc,ModelPath)
//val testmodel = NaiveBayesModel.load(sc,ModelPath)
}
}
NaiveBayes
类的分布估计调整为
aaarticlea/png;base64,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" alt="" />
多项式模型下的参数估计调整为:
aaarticlea/png;base64,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" alt="" />
伯努力模型下参数估计调整为:
aaarticlea/png;base64,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" alt="" />
拉普拉斯平滑
也就是代码中的NaiveBayes.train(training,lambda = 1.0)
spark 朴素贝叶斯的更多相关文章
- Spark朴素贝叶斯(naiveBayes)
朴素贝叶斯(Naïve Bayes) 介绍 Byesian算法是统计学的分类方法,它是一种利用概率统计知识进行分类的算法.在许多场合,朴素贝叶斯分类算法可以与决策树和神经网络分类算法想媲美,该算法能运 ...
- 贝叶斯、朴素贝叶斯及调用spark官网 mllib NavieBayes示例
贝叶斯法则 机器学习的任务:在给定训练数据A时,确定假设空间B中的最佳假设. 最佳假设:一种方法是把它定义为在给定数据A以及B中不同假设的先验概率的有关知识下的最可能假设 贝叶斯理论提供了 ...
- 朴素贝叶斯算法原理及Spark MLlib实例(Scala/Java/Python)
朴素贝叶斯 算法介绍: 朴素贝叶斯法是基于贝叶斯定理与特征条件独立假设的分类方法. 朴素贝叶斯的思想基础是这样的:对于给出的待分类项,求解在此项出现的条件下各个类别出现的概率,在没有其它可用信息下,我 ...
- spark 机器学习 朴素贝叶斯 实现(二)
已知10月份10-22日网球场地,会员打球情况通过朴素贝叶斯算法,预测23,24号是否适合打网球.结果,日期,天气 温度 风速结果(0否,1是)天气(0晴天,1阴天,2下雨)温度(0热,1舒适,2冷) ...
- 朴素贝叶斯算法源码分析及代码实战【python sklearn/spark ML】
一.简介 贝叶斯定理是关于随机事件A和事件B的条件概率的一个定理.通常在事件A发生的前提下事件B发生的概率,与在事件B发生的前提下事件A发生的概率是不一致的.然而,这两者之间有确定的关系,贝叶斯定理就 ...
- 【Spark机器学习速成宝典】模型篇04朴素贝叶斯【Naive Bayes】(Python版)
目录 朴素贝叶斯原理 朴素贝叶斯代码(Spark Python) 朴素贝叶斯原理 详见博文:http://www.cnblogs.com/itmorn/p/7905975.html 返回目录 朴素贝叶 ...
- spark(1.1) mllib 源码分析(三)-朴素贝叶斯
原创文章,转载请注明: 转载自http://www.cnblogs.com/tovin/p/4042467.html 本文主要以mllib 1.1版本为基础,分析朴素贝叶斯的基本原理与源码 一.基本原 ...
- spark 机器学习 朴素贝叶斯 原理(一)
朴素贝叶斯算法仍然是流行的挖掘算法之一,该算法是有监督的学习算法,解决的是分类问题,如客户是否流失.是否值得投资.信用等级评定等多分类问题.该算法的优点在于简单易懂.学习效率高.在某些领域的分类问题中 ...
- 数据算法 --hadoop/spark数据处理技巧 --(13.朴素贝叶斯 14.情感分析)
十三.朴素贝叶斯 朴素贝叶斯是一个线性分类器.处理数值数据时,最好使用聚类技术(eg:K均值)和k-近邻方法,不过对于名字.符号.电子邮件和文本的分类,则最好使用概率方法,朴素贝叶斯就可以.在某些情况 ...
随机推荐
- 2014.04.16,读书,读书笔记-《Matlab R2014a完全自学一本通》-第17章 图形用户界面
界面对象分三类: 用户控件对象(uicontrol) 下拉式菜单对象(uimenu) 内容式菜单对象(uicontextmenu) 创建用户界面: 1.命令行方式 采用uicontrol来创建控件对象 ...
- NDK历史版本
https://developer.android.google.cn/ndk/downloads/older_releases.html https://developer.android.goog ...
- iOS 权限判断 跳转对应设置界面
相机权限 1.1 使用说明 在合适的地方导入#import <AVFoundation/AVFoundation.h> 使用AVAuthorizationStatus类获取当前权限状态 在 ...
- hdoj--1201--18岁生日(模拟)
18岁生日 Time Limit: 2000/1000 MS (Java/Others) Memory Limit: 65536/32768 K (Java/Others) Total Subm ...
- 17.UNP第一章 简介
获取时间的客户端代码: //客户端程序 #include "unp.h" int main(int argc, char **argv) { int sockfd, n; ]; s ...
- docker compose的使用--在线安装未完成
Compose 是一个用户定义和运行多个容器的 Docker 应用程序.在 Compose 中你可以使用 YAML 文件来配置你的应用服务.然后,只需要一个简单的命令,就可以创建并启动你配置的所有服务 ...
- MSSQL执行大脚本文件时,提示“内存不足”的解决办法
导出了一个脚本文件,将近900M,回来往sql studio一丢,报了个内存不足,然后就有了此文.. 问题描述: 当客户服务器不允许直接备份时,往往通过导出数据库脚本的方式来部署-还原数据库, 但是当 ...
- MacOS系统下简单安装以及配置MongoDB数据库(一)
最近写了一个用node来操作MongoDB完成增.删.改.查.排序.分页功能的示例,并且已经放在了服务器上地址:http://39.105.32.180:3333. 项目一共四部分: 1.MacOS下 ...
- jQuery应用实例2:简单动画
效果: 代码: <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www ...
- deploy sql clr
1, create strong signed key file 2, create asymmetric key