Matvey Kryuchkov, [14 Nov 2019 at 22:37:39]:
#!/usr/bin/env python3

import sys
import random

for line in sys.stdin:
    print(random.randint(1, 10**4), line.strip())

#!/usr/bin/env python3

import sys
import random

current_num = random.randint(1, 5)
current_count = 0
current_lines = []
total_count = 0
for line in sys.stdin:
    try:
        rand, id_ = line.strip().split(' ')
        current_count += 1
        if (current_count == current_num):
            for id1 in current_lines:
                print(id1 + ',', end='')
            print(id_)
            current_lines = []
            current_count = 0
            current_num = random.randint(1, 5)
            total_count += 1
        else:
            current_lines.append(id_)

    except ValueError as e:
        continue

    if (total_count > 50):
        break

if (total_count < 50):
    for id1 in current_lines:
        print(id1 + ',', end='')
    print(current_lines[-1])

#!/usr/bin/env bash

OUT_DIR="out"
NUM_REDUCERS=5

hadoop fs -rm -r -skipTrash $OUT_DIR* > /dev/null

yarn jar /opt/cloudera/parcels/CDH/lib/hadoop-mapreduce/hadoop-streaming.jar -D mapreduce.job.reduces=${NUM_REDUCERS} -files mapper.py,reducer.py -mapper mapper.py -reducer reducer.py -input /data/ids_part -output $OUT_DIR > /dev/null

hdfs dfs -cat ${OUT_DIR}/part-00000