# Hadoop Workshop
## [計算每個使用者的總消費金額](https://hackmd.io/@yillkid/r1f7HrFHc/https%3A%2F%2Fhackmd.io%2F%40yillkid%2FHJnI-0QBn)

* mapper.py

import sys

stdInput =[]
for line in sys.stdin:
    line = line.strip() # 去除首尾空格
    stdInput.append(line)

sorted_data = sorted(stdInput, key=lambda x: str(x.split(',')[0]))

for result in sorted_data:
    print(result)

* reducer.py

import sys

stdInput =[]
for line in sys.stdin:
    line = line.strip() # 去除首尾空格
    stdInput.append(line)

output = {}
for entry in stdInput:
    user, value = entry.split(',')
    value = int(value)
    if user in output:
        output[user] += value
    else:
        output[user] = value
for key, value in output.items():
    result  = f"{key},{value}"
    print(result)

cat input.txt | python3 mapper.py | python3 reducer.py


/usr/local/hadoop/bin/hdfs dfs -put input.txt /workshop/

/usr/local/hadoop/bin/hadoop jar '/usr/local/hadoop/share/hadoop/tools/lib/hadoop-streaming-3.3.5.jar' \
-mapper 'python3 mapper.py' \
-file /home/samantha/mapper.py \
-reducer 'python3 reducer.py' \
-file /home/samantha/reducer.py \
-input  hdfs:/workshop/input.txt \
-output hdfs:/workshop/output