java推荐算法_基于内容的推荐算法实现

Job1.java

package com.oracle.moviecf;

import java.io.IOException;

import java.util.ArrayList;

import java.util.List;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Job;

import org.apache.hadoop.mapreduce.Mapper;

import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

/**

* 与Job2共同完成：

* 用户对电影的评价矩阵 × 电影特征建模矩阵 = 用户对某种特征的偏好权重

* (矩阵的相乘)

* */

public class Job1 {

public static class Map extends Mapper {

@Override

protected void map(LongWritable key, Text value, Context context)

throws IOException, InterruptedException {

String line = value.toString();

String split[];

String val;

String mvID;

String userID;

if(line.startsWith("u")) {

split = line.split("\t");

userID = split[0];

for(int i = 1; i < split.length; i++) {

val = split[i].substring(split[i].indexOf("_")+1);

mvID = split[i].substring(0, split[i].indexOf("_"));

context.write(new Text(mvID), new Text(userID+"_"+val));

}

}

if(line.startsWith("m")) {

split = line.split("\t");

for(int i = 1; i < split.length; i++) {

context.write(new Text(split[0]), new Text(split[i]));

}

}

}

}

public static class Reduce extends Reducer {

@Override

protected void reduce(Text key, Iterable values, Context context)

throws IOException, InterruptedException {

List list_user_val = new ArrayList<>();

List list_tag_val = new ArrayList<>();

for(Text i: values) {

if(i.toString().startsWith("u")) {

list_user_val.add(i.toString());

}else {

list_tag_val.add(i.toString());

}

}

String userID;

double userVal;

String tagID;

double tagVal;

for(String i: list_user_val) {

userID = i.substring(0, i.indexOf("_"));

userVal = Double.parseDouble(i.substring(i.indexOf("_")+1));

for(String j: list_tag_val) {

tagID = j.substring(0, j.indexOf("_"));

tagVal = Double.parseDouble(j.substring(j.indexOf(