mapreduce代码部分

计算推荐结果

recommend部分代码

Test.java

package my;

import java.util.HashMap;
import java.util.Map;
import java.util.regex.Pattern;

public class Test {
  
    public   Map<String, String> path;
    public static final Pattern DELIMITER = Pattern.compile("[,\t]");
    public Test()
    {
          path = new HashMap<String, String>();
          path.put("Step1Input", "hdfs://localhost:9000/user/hadoop/recommend");
          path.put("Step1Output", path.get("Step1Input") + "/step1");
          path.put("Step2Input", path.get("Step1Output"));
          path.put("Step2Output", path.get("Step1Input") + "/step2");
          path.put("Step3Input1", path.get("Step1Output"));
          path.put("Step3Output1", path.get("Step1Input") + "/step3_1");
          path.put("Step3Input2", path.get("Step2Output"));
          path.put("Step3Output2", path.get("Step1Input") + "/step3_2");
          path.put("Step4Input1", path.get("Step3Output1"));
          path.put("Step4Input2", path.get("Step3Output2"));
          path.put("Step4Output", path.get("Step1Input") + "/step4");
    }
    
      
    public Map<String, String> getPath() {
        return path;
    }

public void setPath(Map<String, String> path) {
        this.path = path;
    }

}

Cooccurrence.java

package my;

public class Cooccurrence {
    private int itemID1;
    private int itemID2;
    private int num;

public Cooccurrence(int itemID1, int itemID2, int num) {
        super();
        this.itemID1 = itemID1;
        this.itemID2 = itemID2;
        this.num = num;
    }

public int getItemID1() {
        return itemID1;
    }

public void setItemID1(int itemID1) {
        this.itemID1 = itemID1;
    }

public int getItemID2() {
        return itemID2;
    }

public void setItemID2(int itemID2) {
        this.itemID2 = itemID2;
    }

public int getNum() {
        return num;
    }

public void setNum(int num) {
        this.num = num;
    }
}

MultiTask2.java

package my;
 
import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.regex.Pattern;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob;
import org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class MultiTask2 {
    
      public static final Pattern DELIMITER = Pattern.compile("[\t,]");
    public static class Step1Mapper extends  Mapper<Object, Text, IntWritable, Text> {
        private final static IntWritable k = new IntWritable();
        private final static Text v = new Text();
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String[] tokens = DELIMITER.split(value.toString()); 
            int userID = Integer.parseInt(tokens[0]);
            String itemID = tokens[1];
            String pref = tokens[2];
            k.set(userID);
            v.set(itemID + ":" + pref);//133 24 5----->133 24:5 
            context.write(k, v);
        }
    }
 
    public static class Step1Reducer extends Reducer<IntWritable, Text, IntWritable, Text>{

private final static Text v = new Text();
        public void reduce(IntWritable key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
            StringBuilder sb = new StringBuilder();
          for (Text val : values) {
              sb.append("," + val.toString());
          }
          v.set(sb.toString().replaceFirst(",", ""));//133 24:5,57:3,41:4
          context.write(key, v);
        }
      }

public static class Step2Mapper extends Mapper<LongWritable, Text, Text, IntWritable> {
        private final static Text k = new Text();
        private final static IntWritable v = new IntWritable(1);
        public void map(LongWritable key, Text values, Context context) throws IOException, InterruptedException {
            String[] tokens = Test.DELIMITER.split(values.toString());
            for (int i = 1; i < tokens.length; i++) {
                String itemID = tokens[i].split(":")[0];
                for (int j = 1; j < tokens.length; j++) {
                    String itemID2 = tokens[j].split(":")[0];
                    k.set(itemID + ":" + itemID2);
                    context.write(k, v);
                }
            }
        }
    }

public static class Step2Reducer extends Reducer<Text,IntWritable,Text,IntWritable> {
        private IntWritable result = new IntWritable();
     
        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
          int sum = 0;
          for (IntWritable val : values) {
            sum += val.get();
          }
          result.set(sum);
          context.write(key, result);
        }
      }

public static class Step3Mapper1 extends Mapper<LongWritable, Text, IntWritable, Text> {
        private final static IntWritable k = new IntWritable();
        private final static Text v = new Text();

@Override
        public void map(LongWritable key, Text values, Context context) throws IOException, InterruptedException {
            String[] tokens = DELIMITER.split(values.toString());
            for (int i = 1; i < tokens.length; i++) {
                String[] vector = tokens[i].split(":");
                int itemID = Integer.parseInt(vector[0]);
                String pref = vector[1];
                k.set(itemID);
                v.set(tokens[0] + ":" + pref);
                context.write(k,v);
            }
        }
    }
    
    public static class Step3Mapper2 extends Mapper<LongWritable, Text, Text, IntWritable> {
        private final static Text k = new Text();
        private final static IntWritable v = new IntWritable();

@Override
        public void map(LongWritable key, Text values, Context context) throws IOException, InterruptedException {
            String[] tokens = DELIMITER.split(values.toString());
            k.set(tokens[0]);
            v.set(Integer.parseInt(tokens[1]));
            context.write(k,v);
        }
    }
    
    
    public static class Step4Mapper extends Mapper<LongWritable, Text, IntWritable, Text> {
        private final static IntWritable k = new IntWritable();
        private final static Text v = new Text();
        private final static Map<Integer, List<Cooccurrence>> cooccurrenceMatrix = new HashMap<Integer, List<Cooccurrence>>();
        public void map(LongWritable key, Text values,Context context) throws IOException, InterruptedException {
            String[] tokens = DELIMITER.split(values.toString());

String[] v1 = tokens[0].split(":");
            String[] v2 = tokens[1].split(":");

if (v1.length > 1) {// cooccurrence
                int itemID1 = Integer.parseInt(v1[0]);
                int itemID2 = Integer.parseInt(v1[1]);
                int num = Integer.parseInt(tokens[1]);

List list = null;
                if (!cooccurrenceMatrix.containsKey(itemID1)) {
                    list = new ArrayList();
                } else {
                    list = cooccurrenceMatrix.get(itemID1);
                }
                list.add(new Cooccurrence(itemID1, itemID2, num));
                cooccurrenceMatrix.put(itemID1, list);
            }

if (v2.length > 1) {// userVector
                int itemID = Integer.parseInt(tokens[0]);
                int userID = Integer.parseInt(v2[0]);
                double pref = Double.parseDouble(v2[1]);
                k.set(userID);
    
               for (Cooccurrence co : cooccurrenceMatrix.get(itemID)) {
                    v.set(co.getItemID2() + "," + pref * co.getNum());
                    //System.out.println("score:"+co.getItemID2() + "," + pref * co.getNum());
                    context.write(k, v);
                }
        }
    }
    }

public static class Step4Reducer extends Reducer<IntWritable, Text, IntWritable, Text> {
        private Text v = new Text();

public void reduce(IntWritable key, Iterable<Text> values, Context context) throws IOException, InterruptedException  {
            Map<String, Double> result = new HashMap<String, Double>();

for(Text vale : values){
                    String[] str = vale.toString().split(",");
                   if (result.containsKey(str[0]))
                         result.put( str[0], result.get(str[0]) + Double.parseDouble(str[1]) );
                    else {
                          result.put(str[0], Double.parseDouble(str[1]));
                         }
                 }

for (String val : result.keySet()) {
                           String itemID = (String) val;
                           double score = result.get(itemID);
                           v.set(itemID + "," + score);    
                           context.write(key, v);
                        }
        }
    }
    
    
    
    
    public static void main(String[] args)throws Exception {
           
    Test test=new Test();
    String input1 = test.getPath().get("Step1Input");
    String output1 = test.getPath().get("Step1Output");
    Configuration conf = new Configuration();
    Job job1 = new Job(conf, "job1");
    job1.setJarByClass(MultiTask2.class);
    job1.setMapperClass(Step1Mapper.class);
    job1.setCombinerClass(Step1Reducer.class);
    job1.setReducerClass(Step1Reducer.class);
    job1.setOutputKeyClass(IntWritable.class);
    job1.setOutputValueClass(Text.class);
    FileInputFormat.addInputPath(job1, new Path(input1));
    FileOutputFormat.setOutputPath(job1, new Path(output1));
    job1.waitForCompletion(true);
    ControlledJob ctrljob1=new  ControlledJob(conf);
    ctrljob1.setJob(job1);
    
    
    
     String input2 = test.getPath().get("Step2Input");
    String output2 = test.getPath().get("Step2Output");
    Job job2 = new Job(conf, "job2");
    job2.setJarByClass(MultiTask2.class);
    job2.setMapperClass(Step2Mapper.class);
    job2.setCombinerClass(Step2Reducer.class);
    job2.setReducerClass(Step2Reducer.class);
    job2.setOutputKeyClass(Text.class);
    job2.setOutputValueClass(IntWritable.class);  
    FileInputFormat.addInputPath(job2, new Path(input2));
    FileOutputFormat.setOutputPath(job2, new Path(output2));
    job2.waitForCompletion(true);
    ControlledJob ctrljob2=new ControlledJob(conf);
    ctrljob2.setJob(job2);
    ctrljob2.addDependingJob(ctrljob1);
    
    
     String input31 = test.getPath().get("Step3Input1");
    String output31 = test.getPath().get("Step3Output1");
    Job job31 = new Job(conf, "job31");
    job31.setMapperClass(Step3Mapper1.class);
    job31.setOutputKeyClass(IntWritable.class);
    job31.setOutputValueClass(Text.class);
    FileInputFormat.addInputPath(job31, new Path(input31));
    FileOutputFormat.setOutputPath(job31, new Path(output31));
    job31.waitForCompletion(true);

ControlledJob ctrljob31=new ControlledJob(conf);
    ctrljob31.setJob(job31);
    ctrljob31.addDependingJob(ctrljob2);
    
       String input32 = test.getPath().get("Step3Input2");
    String output32 = test.getPath().get("Step3Output2");
    Job job32 = new Job(conf, "job32");
    job32.setMapperClass(Step3Mapper2.class);
    job32.setOutputKeyClass(Text.class);
    job32.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job32, new Path(input32));
    FileOutputFormat.setOutputPath(job32, new Path(output32));
    job32.waitForCompletion(true);
    ControlledJob ctrljob32=new ControlledJob(conf);
    ctrljob32.setJob(job32);
    ctrljob32.addDependingJob(ctrljob31);
    
    String input41 = test.getPath().get("Step4Input1");
    String input42 = test.getPath().get("Step4Input2");
    String output4 = test.getPath().get("Step4Output");
    Job job4 = new Job(conf, "job4");
    job4.setJarByClass(MultiTask2.class);
    job4.setMapperClass(Step4Mapper.class);
    job4.setReducerClass(Step4Reducer.class);
    job4.setOutputKeyClass(IntWritable.class);
    job4.setOutputValueClass(Text.class);
    FileInputFormat.setInputPaths(job4, new Path(input41), new Path(input42));
    FileOutputFormat.setOutputPath(job4, new Path(output4));
    job4.waitForCompletion(true);
    ControlledJob ctrljob4=new ControlledJob(conf);
    ctrljob4.setJob(job4);
    ctrljob4.addDependingJob(ctrljob32);

JobControl jobCtrl=new JobControl("myctrl");
    jobCtrl.addJob(ctrljob1); 
    jobCtrl.addJob(ctrljob2);
    jobCtrl.addJob(ctrljob31);
    jobCtrl.addJob(ctrljob32);
    jobCtrl.addJob(ctrljob4);
  }
}

level部分代码

levelCount.java

package my;
import java.io.IOException;
import java.util.regex.Pattern;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob;
import org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class count {
    public static final Pattern Delimiter = Pattern.compile("[,\t]");
    public static class countMapper extends  Mapper<Object, Text, IntWritable, Text> {
        private final static IntWritable k = new IntWritable();
        private final static Text v = new Text();
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String[] tokens = Delimiter.split(value.toString()); 
            int userID = Integer.parseInt(tokens[0]);
            int itemID = Integer.parseInt(tokens[1]);
            String pref = tokens[2];
            k.set(itemID);
            v.set(userID + ":" + pref);//133 24 5----->133 24:5 
            context.write(k, v);
        }
    }
    
    public static class countReducer extends Reducer<IntWritable,Text,IntWritable,Text>{
        private static final Text v = new Text();
        public void reduce(IntWritable key,Iterable<Text> values,Context context)throws IOException,InterruptedException{
            int v1 = 0;
            int v2 = 0;
            int v3 = 0;
            int v4 = 0;
            int v5 = 0;
            for (Text val :values) {
                int num = Integer.parseInt((val.toString()).split(":")[1]);
                if (num==1)
                {
                    v1+=1;
                }
                else if(num==2)
                {
                    v2+=1;
                }
                else if(num==3)
                {
                    v3+=1;
                }
                else if (num==4)
                {
                    v4+=1;
                }
                else if(num==5)
                {
                    v5+=5;
                }
            }
            //System.out.println("1:"+v1+",2:"+v2+",3:"+v3+",4:"+v4+",5:"+v5);
            v.set("1:"+v1+",2:"+v2+",3:"+v3+",4:"+v4+",5:"+v5);
            context.write(key,v);
        }
    }
    public static void main(String[] args) throws Exception{
        Configuration conf=new Configuration();
        conf.set("fs.defaultFS", "hdfs://localhost:9000");
        conf.set("fs.hdfs.impl", "org.apache.hadoop.hdfs.DistributedFileSystem");
        String[] otherArgs=new String[]{"countNum/","countNum/result"};
        if(otherArgs.length!=2){
            System.err.println("Usage:Merge and duplicate removal<in><out>");
            System.exit(2);
        }
        Job job=Job.getInstance(conf,"Merge and duplicate removal");
        job.setJarByClass(count.class);
        job.setMapperClass(countMapper.class);
        job.setReducerClass(countReducer.class);
        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(Text.class);
        FileInputFormat.addInputPath(job,new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job,new Path(otherArgs[1]));
        boolean result=job.waitForCompletion(true);
        System.out.println(result?"成功":"失败");
    }
}

year部分代码

yearCount.java

package my1;

import java.io.IOException;
import java.util.regex.Pattern;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.log4j.BasicConfigurator;

public class movieCount {
    public static final Pattern Delimiter = Pattern.compile("[|]");
    public static class countMapper extends  Mapper<Object, Text, Text, Text> {
        private final static Text k = new Text();
        private final static Text v = new Text();
        public boolean canParseInt(String str){
            if(str == null){ //验证是否为空
                return false;
            }
            return str.matches("\\d+"); //使用正则表达式判断该字符串是否为数字，第一个\是转义符，\d+表示匹配1个或 //多个连续数字，"+"和"*"类似，"*"表示0个或多个
        }
        public void map(Object key, Text value, Context context) throws IOException,InterruptedException{
            String[] tokens = Delimiter.split(value.toString()); 
            int l = tokens[1].length();
            String year = tokens[1].substring(l-5,l-1);
            k.set(year);//movie year
            v.set(tokens[0]);//movie name
            if (canParseInt(k.toString()))
            {
                context.write(k, v);
            }
        }
    }
    
    public static class countReducer extends Reducer<Text,Text,Text,IntWritable>{
        private static final IntWritable v = new IntWritable();
        public void reduce(Text key,Iterable<Text> values,Context context)throws IOException,InterruptedException{
            int count = 0;
            for(Text val:values) {
                count+=1;
                System.out.println(val.toString());
            }
            v.set(count);
            context.write(key,v);
        }
    }
    public static void main(String[] args) throws Exception{
        Configuration conf=new Configuration();
        conf.set("fs.defaultFS", "hdfs://localhost:9000");
        conf.set("fs.hdfs.impl", "org.apache.hadoop.hdfs.DistributedFileSystem");
        String[] otherArgs=new String[]{"countNum/item","countNum/item/result"};
        if(otherArgs.length!=2){
            System.err.println("Usage:Merge and duplicate removal<in><out>");
            System.exit(2);
        }
        Job job=Job.getInstance(conf,"Merge and duplicate removal");
        job.setJarByClass(movieCount.class);
        job.setMapperClass(countMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        job.setReducerClass(countReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job,new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job,new Path(otherArgs[1]));
        boolean result=job.waitForCompletion(true);
        System.out.println(result?"成功":"失败");
        //BasicConfigurator.configure();
    }
}

job部分代码

jobCount.java

package my2;
import java.io.IOException;
import java.util.regex.Pattern;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.log4j.BasicConfigurator;

public class jobCount {
    public static final Pattern Delimiter = Pattern.compile("[|]");
    public static class countMapper extends  Mapper<Object, Text, Text, Text> {
        private final static Text k = new Text();
        private final static Text v = new Text();
        public boolean canParseInt(String str){
            if(str == null){ //验证是否为空
                return false;
            }
            return str.matches("\\d+"); //使用正则表达式判断该字符串是否为数字，第一个\是转义符，\d+表示匹配1个或 //多个连续数字，"+"和"*"类似，"*"表示0个或多个
        }
        public void map(Object key, Text value, Context context) throws IOException,InterruptedException{
            String[] tokens = Delimiter.split(value.toString()); 
            k.set(tokens[3]);//movie year
            v.set(tokens[0]);//movie name
            context.write(k,v);
        }
    }
    
    public static class countReducer extends Reducer<Text,Text,Text,IntWritable>{
        private static final IntWritable v = new IntWritable();
        public void reduce(Text key,Iterable<Text> values,Context context)throws IOException,InterruptedException{
            int count = 0;
            for(Text val:values) {
                count+=1;
                System.out.println(val.toString());
            }
            v.set(count);
            context.write(key,v);
        }
    }
    public static void main(String[] args) throws Exception{
        Configuration conf=new Configuration();
        conf.set("fs.defaultFS", "hdfs://localhost:9000");
        conf.set("fs.hdfs.impl", "org.apache.hadoop.hdfs.DistributedFileSystem");
        String[] otherArgs=new String[]{"countNum/user","countNum/user/result"};
        if(otherArgs.length!=2){
            System.err.println("Usage:Merge and duplicate removal<in><out>");
            System.exit(2);
        }
        Job job=Job.getInstance(conf,"Merge and duplicate removal");
        job.setJarByClass(jobCount.class);
        job.setMapperClass(countMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        job.setReducerClass(countReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job,new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job,new Path(otherArgs[1]));
        boolean result=job.waitForCompletion(true);
        System.out.println(result?"成功":"失败");
   
    }
}

average部分代码

averageCount.java

package my4;
import java.io.IOException;
import java.util.regex.Pattern;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.DoubleWritable;
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.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.log4j.BasicConfigurator;

public class averageCount {
    public static final Pattern Delimiter = Pattern.compile("[\t,]");
    public static class countMapper extends  Mapper<Object, Text, IntWritable, Text> {
        private final static IntWritable k = new IntWritable();
        private final static Text v = new Text();
        public void map(Object key, Text value, Context context) throws IOException,InterruptedException{
            String[] tokens = Delimiter.split(value.toString()); 
            k.set(Integer.parseInt(tokens[1]));//movie ID
            v.set(tokens[0]+":"+tokens[2]);//user ID + score
            context.write(k,v);
        }
    }
    
    public static class countReducer extends Reducer<IntWritable,Text,IntWritable,DoubleWritable>{
        private static final DoubleWritable v = new DoubleWritable();
        public void reduce(IntWritable key,Iterable<Text> values,Context context)throws IOException,InterruptedException{
            double count = 0;
            double score = 0;
            for(Text val:values) {
                String [] mess = (val.toString()).split(":");
                count+=1;
                score+=Integer.parseInt(mess[1]);
            }
            v.set(score/count);
            context.write(key,v);
        }
    }
    public static void main(String[] args) throws Exception{
        Configuration conf=new Configuration();
        conf.set("fs.defaultFS", "hdfs://localhost:9000");
        conf.set("fs.hdfs.impl", "org.apache.hadoop.hdfs.DistributedFileSystem");
        String[] otherArgs=new String[]{"countNum/average","countNum/average/result"};
        if(otherArgs.length!=2){
            System.err.println("Usage:Merge and duplicate removal<in><out>");
            System.exit(2);
        }
        Job job=Job.getInstance(conf,"Merge and duplicate removal");
        job.setJarByClass(averageCount.class);
        job.setMapperClass(countMapper.class);
        job.setMapOutputKeyClass(IntWritable.class);
        job.setMapOutputValueClass(Text.class);
        job.setReducerClass(countReducer.class);
        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(DoubleWritable.class);
        FileInputFormat.addInputPath(job,new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job,new Path(otherArgs[1]));
        boolean result=job.waitForCompletion(true);
        System.out.println(result?"成功":"失败");
   
    }

}

hot部分代码

hotCount.java

package my4;
import java.io.IOException;
import java.util.regex.Pattern;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.DoubleWritable;
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.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.log4j.BasicConfigurator;

public class averageCount {
    public static final Pattern Delimiter = Pattern.compile("[\t,]");
    public static class countMapper extends  Mapper<Object, Text, IntWritable, Text> {
        private final static IntWritable k = new IntWritable();
        private final static Text v = new Text();
        public void map(Object key, Text value, Context context) throws IOException,InterruptedException{
            String[] tokens = Delimiter.split(value.toString()); 
            k.set(Integer.parseInt(tokens[1]));//movie ID
            v.set(tokens[0]+":"+tokens[2]);//user ID + score
            context.write(k,v);
        }
    }
    
    public static class countReducer extends Reducer<IntWritable,Text,IntWritable,DoubleWritable>{
        private static final DoubleWritable v = new DoubleWritable();
        public void reduce(IntWritable key,Iterable<Text> values,Context context)throws IOException,InterruptedException{
            double count = 0;
            double score = 0;
            for(Text val:values) {
                String [] mess = (val.toString()).split(":");
                count+=1;
                score+=Integer.parseInt(mess[1]);
            }
            v.set(score/count);
            context.write(key,v);
        }
    }
    public static void main(String[] args) throws Exception{
        Configuration conf=new Configuration();
        conf.set("fs.defaultFS", "hdfs://localhost:9000");
        conf.set("fs.hdfs.impl", "org.apache.hadoop.hdfs.DistributedFileSystem");
        String[] otherArgs=new String[]{"countNum/average","countNum/average/result"};
        if(otherArgs.length!=2){
            System.err.println("Usage:Merge and duplicate removal<in><out>");
            System.exit(2);
        }
        Job job=Job.getInstance(conf,"Merge and duplicate removal");
        job.setJarByClass(averageCount.class);
        job.setMapperClass(countMapper.class);
        job.setMapOutputKeyClass(IntWritable.class);
        job.setMapOutputValueClass(Text.class);
        job.setReducerClass(countReducer.class);
        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(DoubleWritable.class);
        FileInputFormat.addInputPath(job,new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job,new Path(otherArgs[1]));
        boolean result=job.waitForCompletion(true);
        System.out.println(result?"成功":"失败");
   
    }

}

smilarity部分代码

similarity.java

package my6;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Pattern;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.IntWritable;
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.Reducer.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import my4.averageCount;
import my4.averageCount.countMapper;
import my4.averageCount.countReducer;

public class similarity {
    public static final Pattern Delimiter = Pattern.compile("[\t,]");
    public static class countMapper extends  Mapper<Object, Text, Text, Text> {
        private final static Text k = new Text();
        private final static Text v = new Text();
        public void map(Object key, Text value, Context context) throws IOException,InterruptedException{
            String[] tokens = Delimiter.split(value.toString()); 
            for (int i = 1;i<=1682;i++)
            {
                int id = Integer.parseInt(tokens[0]);
                if(id!=i)
                {
                    if(id<i)
                    {
                        k.set(tokens[0]+","+i);
                        String val = "";
                        for(int j = 1;j<20;j++)
                        {
                            val+=tokens[j]+",";
                        }
                        val+=tokens[20];
                        v.set(val);
                        context.write(k,v);
                    }
                    else
                    {
                        k.set(i+","+tokens[0]);
                        String val = "";
                        for(int j = 1;j<20;j++)
                        {
                            val+=tokens[j]+",";
                        }
                        val+=tokens[20];
                        v.set(val);
                        context.write(k,v);
                    }
                    //System.out.println(k);
                    //System.out.println(v);
                }
            }
        }
    }
    
    public static class countReducer extends Reducer<Text,Text,Text,DoubleWritable>{
        private static final DoubleWritable v = new DoubleWritable();
        public void reduce(Text key,Iterable<Text> values,Context context)throws IOException,InterruptedException{
            String mes1 = "";
            String mes2 = "";
            int count = 1;
            weight w = new weight();
            for(Text val:values) {
                if (count == 1)
                {
                    mes1+=val.toString();
                }
                if(count ==2)
                {
                    mes2+=val.toString();
                }
                count+=1;
                //System.out.println(val);
                //System.out.println(key);
                //System.out.println(mes1);
                //System.out.println(mes2);
                //System.out.println("-----------------------------------------");
            }
            double sim = 0;
            String [] tokens1 = mes1.split(",");
            String [] tokens2 = mes2.split(",");
            for(int i = 0;i < tokens1.length;i++)
            {
                double num1 = Double.parseDouble(tokens1[i]);
                double num2 = Double.parseDouble(tokens2[i]);
                sim += w.getW(i)*(num1-num2)*(num1-num2);
            }
             v.set(sim);
            context.write(key,v);
            String [] temp = (key.toString()).split(",");
            key.set(temp[1]+","+temp[0]);
            context.write(key,v);
        }
    }
    public static void main(String[] args) throws Exception{

Configuration conf=new Configuration();
        conf.set("fs.defaultFS", "hdfs://localhost:9000");
        conf.set("fs.hdfs.impl", "org.apache.hadoop.hdfs.DistributedFileSystem");
        String[] otherArgs=new String[]{"similarity","similarity/result"};
        if(otherArgs.length!=2){
            System.err.println("Usage:Merge and duplicate removal<in><out>");
            System.exit(2);
        }
        Job job=Job.getInstance(conf,"Merge and duplicate removal");
        job.setJarByClass(similarity.class);
        job.setMapperClass(countMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        job.setReducerClass(countReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(DoubleWritable.class);
        FileInputFormat.addInputPath(job,new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job,new Path(otherArgs[1]));
        boolean result=job.waitForCompletion(true);
        System.out.println(result?"成功":"失败");
   
    }

}

weight.java

package my6;

public class weight {
    public static  double [] weig;
    public weight(){
        weig = new double[20];
        String wei = "0.12765441 0.00169363 0.07760147 0.05145752 0.02151025 0.04790932 0.11253775 0.0441973 0.02463966 0.12589693 0.0128394 0.01377639 0.03906519 0.02689036 0.02870992 0.07683498 0.04182388 0.07760147 0.0322126 0.01514757";
        String [] temp = wei.split(" ");
        for(int i = 0;i < temp.length;i++) {
            weig[i] = Double.parseDouble(temp[i]);
        }
    }
    
    public double getW(int num)
    {
        return weig[num];
    }
}

至此mapreduce处理部分完毕

接下来是可视化和将数据存储进mysql的代码

存储部分

import pandas as pd
import pymysql
import numpy as npjobF = 'job'
hotF = 'hot'
averageF = 'average'
scoreF = 'level'
recommendF = 'recommend'
userF = 'u.user'
movieSF = 'movieS'con = pymysql.connect(host='localhost',port=3306,user='root',passwd='',db='test1',charset = 'utf8',cursorclass=pymysql.cursors.DictCursor,autocommit =True)
cur1 = con.cursor()def insertJ():job = []  # 用来存放用户对电影的评分信息for line in open(jobF):  # 逐行读取work, num = line.split('\t')[0:2]num = int(num)job.append([work, num])# job = np.array(job,dtype=[('work','str'),('num','int')])#job = pd.DataFrame(job, columns=['job', 'num'])cur1.execute("drop table if exists job")cur1.execute("CREATE TABLE job (work VARCHAR(255),num INT(10))")for i in range(len(job)):insert = ("INSERT INTO `job`(work,num) VALUES ('%s','%d')" % (job[i][0],job[i][1]))cur1.execute(insert)con.commit()def insertH():hot = []for line in open(hotF):  # 逐行读取movie, num = line.split('\t')[0:2]movie = int(movie)num = int(num)hot.append([movie, num])# hot = np.array(hot)#hot = pd.DataFrame(hot, columns=['movie', 'assess'])cur1.execute("drop table if exists hot")cur1.execute("CREATE TABLE hot (movieID INT(10),assess INT(10))")for i in range(len(hot)):insert = ("INSERT INTO `hot`(movieID,assess) VALUES ('%s','%d')" % (hot[i][0], hot[i][1]))cur1.execute(insert)con.commit()def insertA():average = []for line in open(averageF):  # 逐行读取movie, score = line.split('\t')[0:2]movie = int(movie)score = float(score[:-1])average.append([movie, score])#average = pd.DataFrame(average, columns=['movie', 'score'])cur1.execute("drop table if exists average")cur1.execute("CREATE TABLE average (movieID INT(10),score FLOAT)")for i in range(len(average)):insert = ("INSERT INTO `average`(movieID,score) VALUES ('%d','%f')" % (average[i][0], average[i][1]))cur1.execute(insert)con.commit()def insertS():scoreM = []for line in open(scoreF):movie, mess = line.split('\t')[0:2]temp = [int(movie), 0, 0, 0, 0, 0]messa = mess.split(',')for i in range(len(messa)):message = messa[i].split(':')temp[int(message[0])] = int(message[1])scoreM.append(temp)# scoreM = np.array(scoreM)#scoreM = pd.DataFrame(scoreM, columns=['movie', '1', '2', '3', '4', '5'])cur1.execute("drop table if exists scoreM")cur1.execute("CREATE TABLE scoreM (movieID INT(10),num1 INT(10),num2 INT(10),num3 INT(10),num4 INT(10),num5 INT(10))")for i in range(len(scoreM)):insert = ("INSERT INTO `scoreM`(movieID,num1,num2,num3,num4,num5) VALUES ('%d','%d','%d','%d','%d','%d')" % (scoreM[i][0],scoreM[i][1], scoreM[i][2], scoreM[i][3], scoreM[i][4], scoreM[i][5]))cur1.execute(insert)con.commit()def insertR():recommend = {}Rec = []for line in open(recommendF):movieID, mess = line.split('\t')[0:2]movieID = int(movieID)recommend.setdefault(movieID, [])messa = mess.split(',')recommend[movieID].append([int(messa[0]),int(float(messa[1]))])for k,v in recommend.items():temp = np.array(v)temp = temp[np.argsort(-temp[:,1])]if (len(temp)>=10):recommend[k] = temp[:10,:]else:length = len(temp)recommend[k] = temp[:length,:]cur1.execute("drop table if exists recommend")cur1.execute("CREATE TABLE recommend (userID INT(10),movieID INT(10),score INT(10))")print(len(recommend))for i in range(len(recommend)):for j in range(len(recommend[i+1])):insert = ("INSERT INTO `recommend`(userID,movieID,score) VALUES ('%d','%d','%d')" % (i + 1, recommend[i + 1][j,0], recommend[i+1][j,1]))cur1.execute(insert)con.commit()def insertUA():UA = {'0-9':0, '10-19':0, '20-29':0, '30-39':0,'40-49':0, '50-59':0, '60-69':0, '70-79':0}age = []cur1.execute("drop table if exists age")cur1.execute("CREATE TABLE age (age VARCHAR(255),num INT(10))")for line in open(userF, encoding='ISO-8859-1'):userID, age = line.split('|')[0:2]age = int(age)if 0<=age<=9:UA['0-9']+=1elif 10<=age<=19:UA['10-19']+=1elif 20<=age<=29:UA['20-29']+=1elif 30<=age<=39:UA['30-39']+=1elif 40<=age<=49:UA['40-49']+=1elif 50<=age<=59:UA['50-59']+=1elif 60<=age<=69:UA['60-69']+=1elif 70<=age<=79:UA['70-79']+=1for k,v in UA.items():insert = ("INSERT INTO `age`(age,num) VALUES ('%s','%d')" % (k, v))cur1.execute(insert)con.commit()def insertMovie():movieS = {}num = 0for line in open(movieSF):movie, sim = line.split('\t')[0:2]sim = float(sim)id1,id2 = movie.split(',')[0:2]id1 = int(id1)id2 = int(id2)movieS.setdefault(id1,[])movieS[id1].append([id2,sim])num+=1print(num)data = []for k,v in movieS.items():temp = np.array(v)temp = temp[np.argsort(-temp[:, 1])]if (len(temp) >= 10):movieS[k] = temp[:10, :]else:length = len(temp)movieS[k] = temp[:length, :]cur1.execute("drop table if exists movieSim")cur1.execute("CREATE TABLE movieSim (movieID1 INT(10),movieID2 INT(10),sim FLOAT)")for k,v in movieS.items():for i in range(len(v)):insert = ("INSERT INTO `movieSim`(movieID1,movieID2,sim) VALUES ('%d','%d','%f')" % (k, movieS[k][i,0], movieS[k][i,1]))cur1.execute(insert)con.commit()#insertS()
#insertA()
#insertJ()
#insertH()
#insertR()
#insertUA()
insertMovie()
cur1.close()
con.close()

可视化部分

import time
import matplotlib.pyplot as plt
from tkinter import END
from tkinter.scrolledtext import ScrolledText
from tkinter import *
from tkinter import ttk
import tkinter as tk
import win32api, win32con
import os
import pymysql
import numpy as np
import pandas as pdmDB = 'test1'
pWD = ''
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
movies = {} #用来存放电影基本信息
for line in open('u.item',encoding='ISO-8859-1'):movieID, movieName = line.split('|')[0:2]movieID = int(movieID)movies[movieID] = movieNamedef similarity():def getMovieS():con = pymysql.connect(host='localhost', port=3306, user='root', passwd=pWD, db=mDB, charset='utf8',cursorclass=pymysql.cursors.DictCursor, autocommit=True)cur = con.cursor()ID = int(user_text.get())user_text.set("")select = 'SELECT movieID2 FROM movieSim WHERE movieID1=%d' % (ID)cur.execute(select)mess = cur.fetchall()cur.close()con.close()top = Toplevel()top.geometry("500x300")top.title('电影'+movies[ID]+'相似影片')scr = ScrolledText(top, width=60, height=20, font=("隶书", 10))scr.pack()for i in range(len(mess)):mes =str(i+1)+'\t'+ movies[mess[i]['movieID2']] +'\n'scr.insert(END, mes)top = tk.Toplevel()  # 生成主窗口top.title("相似影片")  # 窗体名称top.geometry("300x100")  # 指定窗体大小input = Label(top, text="请输影片ID")input.pack()user_text = StringVar()bucket = Entry(top, textvariable=user_text)user_text.set("")bucket.pack()Button(top, text="搜索", command=getMovieS).pack()top.mainloop()def recommend():def getUserR():con = pymysql.connect(host='localhost', port=3306, user='root', passwd=pWD, db=mDB, charset='utf8',cursorclass=pymysql.cursors.DictCursor, autocommit=True)cur = con.cursor()ID = int(user_text.get())user_text.set("")select = 'SELECT movieID FROM recommend WHERE userID=%d' % (ID)cur.execute(select)mess = cur.fetchall()cur.close()con.close()top = Toplevel()top.geometry("500x300")top.title('推荐结果')scr = ScrolledText(top, width=60, height=20, font=("隶书", 10))scr.pack()for i in range(len(mess)):mes = movies[mess[i]['movieID']] +'\n'scr.insert(END, mes)top = tk.Toplevel()  # 生成主窗口top.title("个性化定制")  # 窗体名称top.geometry("300x100")  # 指定窗体大小input = Label(top, text="请输入用户ID")input.pack()user_text = StringVar()bucket = Entry(top, textvariable=user_text)user_text.set("")bucket.pack()Button(top, text="搜索", command=getUserR).pack()top.mainloop()def hot():con = pymysql.connect(host='localhost', port=3306, user='root', passwd=pWD, db=mDB, charset='utf8',cursorclass=pymysql.cursors.DictCursor, autocommit=True)cur = con.cursor()select = 'SELECT * FROM hot'cur.execute(select)mess = cur.fetchall()cur.close()con.close()top = Toplevel()top.geometry("500x300")top.title('热门榜')scr = ScrolledText(top, width=60, height=20, font=("隶书", 10))scr.pack()for i in range(len(mess)):mes = str(i+1) + '\t' +movies[mess[i]['movieID']] + '\n'scr.insert(END, mes)top.mainloop()def average():con = pymysql.connect(host='localhost', port=3306, user='root', passwd=pWD, db=mDB, charset='utf8',cursorclass=pymysql.cursors.DictCursor, autocommit=True)cur = con.cursor()select = 'SELECT * FROM average'cur.execute(select)mess = cur.fetchall()cur.close()con.close()top = Toplevel()top.geometry("500x300")top.title('好评榜')scr = ScrolledText(top, width=60, height=20, font=("隶书", 10))scr.pack()for i in range(len(mess)):mes = str(i+1) + '\t' + movies[mess[i]['movieID']] + '\t' + str(mess[i]['score']) +'\n'scr.insert(END, mes)top.mainloop()def analysis():def scoreAnalysis():ID = int(movie_text.get())con = pymysql.connect(host='localhost', port=3306, user='root', passwd=pWD, db=mDB, charset='utf8',cursorclass=pymysql.cursors.DictCursor, autocommit=True)cur = con.cursor()select = 'SELECT * FROM scoreM WHERE movieID=%d' % (ID)cur.execute(select)mess = cur.fetchall()cur.close()con.close()x = []y = []level = 1for k, v in (mess[0]).items():x.append(level)y.append(v)level += 1plt.bar(x, y)index = np.arange(len(y));for a, b in zip(index, y):  # 柱子上的数字显示plt.text(a, b, '%d' % b, ha='center', va='bottom', fontsize=10);plt.title('电影' + movies[ID] + '评分结果')plt.xlabel('评分')plt.ylabel('人数')plt.show()def ageAnalysis():con = pymysql.connect(host='localhost', port=3306, user='root', passwd=pWD, db=mDB, charset='utf8',cursorclass=pymysql.cursors.DictCursor, autocommit=True)cur = con.cursor()select = 'SELECT * FROM age'cur.execute(select)mess = cur.fetchall()cur.close()con.close()print(mess)x = []y = []for i in range(len(mess)):x.append(mess[i]['age'])y.append(mess[i]['num'])plt.bar(x,y)index = np.arange(len(y));for a, b in zip(index,y):  # 柱子上的数字显示plt.text(a, b, '%d' % b, ha='center', va='bottom', fontsize=10);plt.title('用户年龄分布')plt.xlabel('年龄段')plt.ylabel('人数')plt.show()def jobAnalysis():con = pymysql.connect(host='localhost', port=3306, user='root', passwd=pWD, db=mDB, charset='utf8',cursorclass=pymysql.cursors.DictCursor, autocommit=True)cur = con.cursor()select = 'SELECT * FROM job'cur.execute(select)mess = cur.fetchall()cur.close()con.close()top = Toplevel()top.geometry("500x300")top.title('用户职业分布')scr = ScrolledText(top, width=60, height=20, font=("隶书", 10))scr.pack()for i in range(len(mess)):mes = mess[i]['work'] + '\t' + str(mess[i]['num']) + '\n'scr.insert(END, mes)top.mainloop()'''x = []y = []for i in range(len(mess)):x.append(mess[i]['work'])y.append(mess[i]['num'])plt.bar(x,y)index = np.arange(len(y));for a, b in zip(index,y):  # 柱子上的数字显示plt.text(a, b, '%d' % b, ha='center', va='bottom', fontsize=10);plt.title('用户职业分布')plt.xlabel('职业')plt.ylabel('人数')plt.show()'''def genderAnalysis():plt.rcParams['font.sans-serif'] = ['SimHei']plt.rcParams['axes.unicode_minus'] = Falseu_cols = ['user_id', 'age', 'sex', 'occupation', 'zip_code']users = pd.read_csv('u.user', sep='|', names=u_cols, encoding='latin-1')r_cols = ['user_id', 'movie_id', 'rating', 'unix_timestamp']ratings = pd.read_csv('u.data', sep='\t', names=r_cols, encoding='latin-1')m_cols = ['movie_id', 'title', 'release_date', 'video_release_date', 'imdb_url']movies = pd.read_csv('u.item', sep='|', names=m_cols, usecols=range(5), encoding='latin-1')# 数据集整合movie_ratings = pd.merge(movies, ratings)lens = pd.merge(movie_ratings, users)labels = ['0-9', '10-19', '20-29', '30-39', '40-49', '50-59', '60-69', '70-79']lens['age_group'] = pd.cut(lens.age, range(0, 81, 10), right=False, labels=labels)lens[['age', 'age_group']].drop_duplicates()[:10]lens.groupby('age_group').agg({'rating': [np.size, np.mean]})most_50 = lens.groupby('movie_id').size().sort_values(ascending=False)[:50]lens.set_index('movie_id', inplace=True)by_age = lens.loc[most_50.index].groupby(['title', 'age_group'])lens.reset_index('movie_id', inplace=True)pivoted = lens.pivot_table(index=['movie_id', 'title'],columns=['sex'],values='rating',fill_value=0)pivoted['diff'] = pivoted.M - pivoted.Fpivoted.reset_index('movie_id', inplace=True)disagreements = pivoted[pivoted.movie_id.isin(most_50.index)]['diff']disagreements.sort_values().plot(kind='barh', color='dodgerblue')plt.title('男/女性平均评分\n(差异>0=受男性青睐)', fontsize=14)plt.ylabel('电影', fontsize=14)plt.xlabel('平均评级差', fontsize=14)plt.show()top = Toplevel()top.geometry("500x300")input = Label(top, text="请输入电影ID")input.pack()movie_text = StringVar()bucket = Entry(top, textvariable=movie_text)movie_text.set("")bucket.pack()Button(top, text="电影评分分析", command=scoreAnalysis).pack()Button(top, text="用户年龄分析", command=ageAnalysis).pack()Button(top, text="用户职业分析", command=jobAnalysis).pack()Button(top, text="用户偏好分析", command=genderAnalysis).pack()top.title('电影数据')top.mainloop()if __name__ == "__main__":root = tk.Tk()  # 生成主窗口root.title("电影推荐系统")  # 窗体名称root.geometry("700x250")  # 指定窗体大小Button(root, text="电影推荐", command=recommend).pack()Button(root, text="电影热度榜", command=hot).pack()Button(root, text="电影好评榜", command=average).pack()Button(root, text="电影数据大全", command=analysis).pack()Button(root, text="相似电影", command=similarity).pack()root.mainloop()#con = pymysql.connect(host='localhost', port=3306, user='root', passwd='', db='test1', charset='utf8',cursorclass=pymysql.cursors.DictCursor, autocommit=True)#cur1 = con.cursor()#cur1.close()#con.close()

基于Hadoop的电影推荐系统相关推荐

1. 基于Spark的电影推荐系统（推荐系统~1）

   第四部分-推荐系统-项目介绍 行业背景: 快速:Apache Spark以内存计算为核心 通用 :一站式解决各个问题,ADHOC SQL查询,流计算,数据挖掘,图计算 完整的生态圈 只要掌握Spark ...

2. 基于Spark的电影推荐系统（推荐系统~4）

   第四部分-推荐系统-模型训练 本模块基于第3节 数据加工得到的训练集和测试集数据 做模型训练,最后得到一系列的模型,进而做 预测. 训练多个模型,取其中最好,即取RMSE(均方根误差)值最小的模型 说 ...

3. 基于Spark的电影推荐系统（推荐系统~5）

   第四部分-推荐系统-离线推荐 本模块基于第4节得到的模型,开始为用户做离线推荐,推荐用户最有可能喜爱的5部电影. 说明几点 1.主要分为两个模块.其一是为 单个随机用户 做推荐,其二是为 所有用户做推 ...

4. 基于Spark的电影推荐系统（推荐系统~7）

   第四部分-推荐系统-实时推荐 本模块基于第4节得到的模型,开始为用户做实时推荐,推荐用户最有可能喜爱的5部电影. 说明几点 1.数据来源是 testData 测试集的数据.这里面的用户,可能存在于训练 ...

5. 基于Spark的电影推荐系统（电影网站）

   第一部分-电影网站: 软件架构: SpringBoot+Mybatis+JSP 项目描述:主要实现电影网站的展现 和 用户的所有动作的地方 技术选型: 技术 名称 官网 Spring Boot 容器 ...

6. 电影推荐系统 python简书_基于Spark的电影推荐系统（实战简介）

   ## 写在前面 一直不知道这个专栏该如何开始写,思来想去,还是暂时把自己对这个项目的一些想法 和大家分享 的形式来展现.有什么问题,欢迎大家一起留言讨论. 这个项目的源代码是在https://gith ...

7. 第10课：动手实战基于 CNN 的电影推荐系统

   本文从深度学习卷积神经网络入手,基于 Github 的开源项目来完成 MovieLens 数据集的电影推荐系统. 什么是推荐系统呢? 什么是推荐系统呢?首先我们来看看几个常见的推荐场景. 如果你经常通 ...

8. springboot基于JAVA的电影推荐系统的开发与实现毕业设计源码112306

   目    录 摘要 Abstract 第1章前言 1.1研究背景 1.2研究现状 1.3系统开发目标 第2章技术与原理 2.1  JSP介绍 2.2  JAVA技术 2.3  MySQL数据库 2.4 ...

9. （附源码）springboot基于JAVA的电影推荐系统的开发与实现 毕业设计112306

   目 录 摘 要 4 Abstract 5 第1章 前 言 6 1.1 研究背景 6 1.2 研究现状 6 1.3 系统开发目标 6 第2章 技术与原理 8 2.1 JSP介绍 8 2.2 JAVA技术 ...

最新文章

1. 为EditText输入框加上提示信息
2. python2.7配置tensorflow1.5.0和keras2.1.6
3. mysql自增主键到头了怎么办_自增主键用完了怎么办
4. static 成员小记
5. redhat 6.4 安装ftp
6. 维护100亿个URL
7. 鲁迅散文——狗的驳诘
8. sql时间格式转换yyyymm_XML和实体类之间的转换
9. 每日优鲜小程序基础组件介绍
10. InnerText和InnerXml的区别
11. mybatis 报错 with invalid types () or values 0. Cause: java.lang.NoSuchMethodException:
12. exception类型 java_程序员小白入门，Java如何选择异常类型？
13. 再别极域（亲测有效）
14. 深入剖析RGB、CMYK、HSB、LAB
15. mariadb数据库基本使用
16. 2021年危险化学品生产单位安全生产管理人员复审考试及危险化学品生产单位安全生产管理人员模拟考试题库
17. 遥感物理相关名词解释
18. Django连接MySQL8.0报错django.db.utils.OperationalError: (1045, “Access denied for user ‘16066‘@‘localhos
19. Excel 的基本概念以及 Excel 文件的创建
20. 程序员下班为什么不关电脑？

热门文章

1. 2017全国电赛综合测评四分频电路（一片D触发器74LS74的两种方法，有图有真相，实测波形图）
2. 国产RY8122 18V 2A 500KHz同步降压稳压芯片
3. 【知识星球】视频分类模型和数据集板块汇总介绍
4. Monte Carlo Counterfactual Regret Minimization
5. 按键精灵-UI配置丢失问题解决办法
6. 安卓 蓝牙遥控器键值配对 kl文件
7. ubuntu 14.04 成功迁移根分区到SSD
8. 从零开始做运营 入门版（张亮著）读书知识整理①
9. 计算机芯片英文翻译,芯片的英文翻译,芯片英语怎么说
10. 程序员都会的五大算法之三（贪心算法），恶补恶补恶补！！！