猫眼电影网站各_类型_电影数据分析与可视化

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class Movie12Mapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    @Override
    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();

        String[] arr=line.split("\00");

        if (arr.length > 4) {
            String type = arr[4];
            int idx = type.indexOf(",");
            if (idx > 0){
                type = type.substring(0, idx);
            }

            context.write(new Text(type), new IntWritable(1));
        }
    }
}

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

import java.io.IOException;

public class Movie12Reducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    @Override
    public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable val : values){
            sum += val.get();
        }
        context.write(key, new IntWritable(sum));

    }
}

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


/**
 * mapreduce的运行类
 */
public class Movie12Runner {
    //    args两个元素，一是输入目录，二是输出目录
//    注意：输出目录原来是不存在的
    public static void main(String[] args) throws Exception{
//        加载配置
        Configuration conf = new Configuration();
//        创建一个Job
        Job job = Job.getInstance(conf, "movie12");
//        设置输入输出路径
        FileInputFormat.addInputPath(job, new Path(args[0]));  // 输入
        FileOutputFormat.setOutputPath(job, new Path(args[1]));  // 输出
//        设置运行类
        job.setJarByClass(Movie12Runner.class);
        job.setMapperClass(Movie12Mapper.class);
        job.setReducerClass(Movie12Reducer.class);

        job.setOutputKeyClass(Text.class);  // 设置输出键的类型
        job.setOutputValueClass(IntWritable.class);  // 设置输出值的类型

        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:\output12\part-r-00000",sep='\t',header=None)
data.columns=['类型','上映电影数量']
data.head()

plt.figure(figsize=(12,8))
plt.pie(data['上映电影数量'],labels=data['类型'],autopct='%1.2f%%')
plt.title("上映电影类型数目占比图")
plt.legend(loc='upper right',bbox_to_anchor=(1.7,1.05),fontsize=10,borderaxespad=0.3)
plt.show()