如何使用值对数据帧进行排序

import pandas as pd

# 创建值对数据帧
data = {'Key': ['A', 'B', 'C', 'D'],
        'Value': [4, 2, 1, 3]}
df = pd.DataFrame(data)

# 按照键进行排序
df_sorted_by_key = df.sort_values('Key')
print("按照键排序:\n", df_sorted_by_key)

# 按照值进行排序
df_sorted_by_value = df.sort_values('Value')
print("按照值排序:\n", df_sorted_by_value)

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;
import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;
import org.apache.hadoop.mapreduce.lib.sort.TotalOrderPartitioner;

public class KeyValueSorting {
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "key value sorting");

        job.setJarByClass(KeyValueSorting.class);
        job.setMapperClass(MyMapper.class);
        job.setReducerClass(MyReducer.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        job.setPartitionerClass(HashPartitioner.class);  // 使用哈希分区
        // 或者使用TotalOrderPartitioner进行全局排序
        // job.setPartitionerClass(TotalOrderPartitioner.class);

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}