猫眼电影网站各_类型_电影_评分数_分析与可视化

import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;


public class Movie10Mapper extends Mapper<LongWritable,Text,Text, DoubleWritable> {

    @Override
    protected void map(LongWritable key,Text value,Context context) throws IOException,InterruptedException{
        //super.map(key,value,context);
        String line=value.toString();   //[0 芳华 9.1 http://maoyan.com/films/1170264 剧情,爱情,战争 中国大陆 大陆上映 136 2017]
        String[] arr=line.split("\00");
        double mark=0;
        String story=null;
        if (arr.length>4) {
            mark = Double.parseDouble(arr[2]);
            story=arr[4];
            if (story == null ||"".equals(story)){
                return;
            }else if (story.contains(",")){
                story=story.split(",")[0];
            }
            context.write(new Text(story),new DoubleWritable(mark));
        }

        }

    }
}

import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;

public class Movie10Reducer extends Reducer<Text, DoubleWritable,Text,DoubleWritable> {
    @Override
    protected void reduce(Text key, Iterable<DoubleWritable> values, Context context) throws IOException, InterruptedException {
        //super.reduce(key, values, context);
        double sum=0;
        double sc=0;
        double  avg_mark;
        for (DoubleWritable i:values){
            sum+=i.get();
            sc++;
        }
        String str=String.format("%.1f",sum/sc);  //保留一位小数
        avg_mark=Double.parseDouble(str);
        context.write(key,new DoubleWritable(avg_mark));
    }
}

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.io.Writable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.FileOutputStream;
import java.io.IOException;

public class Movie10Runner {
    public static  void  main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf=new Configuration();
        //创建job
        Job job= Job.getInstance(conf,"maoyan");
        //设置输入输出路径
        FileInputFormat.addInputPath(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //设置运行类
        job.setJarByClass(Movie10Runner.class);
        job.setMapperClass(Movie10Mapper.class);
        job.setReducerClass(Movie10Reducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(DoubleWritable.class);
        System.exit(job.waitForCompletion(true)?0:1);

    }
}

import pandas as pd
import matplotlib
import matplotlib.pyplot as plt

matplotlib.rcParams['font.family']='SimHei'   
matplotlib.rcParams['font.sans-serif'] = ['SimHei']

data=pd.read_csv(r"E:\output10\part-r-00000",sep='\t',header=None)
data.columns=['类型','上映电影评分均值']
data.head()

plt.figure(figsize=(12,6))
x=data['类型']
y=data['上映电影评分均值']
plt.bar(x,y,width=0.5,label='分数')
plt.xlabel('电影类型')
plt.ylabel('评分均值')
plt.xticks(rotation=30)
plt.title('上映电影类型的评分均值图表')
plt.legend(fontsize=12)
plt.show()