1. 用Python编写WordCount程序并提交任务

程序

WordCount

输入

一个包含大量单词的文本文件

输出

文件中每个单词及其出现次数（频数），并按照单词字母顺序排序，每个单词和其频数占一行，单词和频数之间有间隔
  1. 编写map函数，reduce函数
  2. 将其权限作出相应修改
  3. 本机上测试运行代码
  4. 放到HDFS上运行
    1. 将之前爬取的文本文件上传到hdfs上
    2. 用Hadoop Streaming命令提交任务
  5. 查看运行结果
# 创造mapper.py文件

cd / home / hadoop / wc

sudo gedit mapper.py

# map函数
# !/usr/bin/env python
import sys
for i in stdin:
    i = i.strip()
    words = i.split()
    for word in words:
    print
    '%s\t%s' % (word, 1)

# reduce函数
# !/usr/bin/env python
from operator import itemgetter
import sys

current_word = None
current_count = 0
word = None

for i in stdin:
    i = i.strip()
    word, count = i.split('\t', 1)
    try:
    count = int(count)
    except ValueError:
    continue

    if current_word == word:
    current_count += count
    else:
    if current_word:
        print
        '%s\t%s' % (current_word, current_count)
    current_count = count
    current_word = word

if current_word == word:
    print '%s\t%s' % (current_word, current_count)
#!/usr/bin/env python

cd /home/hadoop/wc
sudo gedit reducer.py
#赋予权限

chmod a+x /home/hadoop/mapper.py
echo "foo foo quux labs foo bar quux" | /home/hadoop/wc/mapper.py

echo "foo foo quux labs foo bar quux" | /home/hadoop/wc/mapper.py | sort -k1,1 | /home/hadoop/wc/reducer.p
#上传
cd  /home/hadoop/wc
wget http://www.gutenberg.org/files/5000/5000-8.txt
wget http://www.gutenberg.org/cache/epub/20417/pg20417.txt

#下载
cd /usr/hadoop/wc
hdfs dfs -put /home/hadoop/hadoop/gutenberg/*.txt /user/hadoop/input

2. 用mapreduce 处理气象数据集

编写程序求每日最高最低气温，区间最高最低气温

  1. 气象数据集下载地址为：ftp://ftp.ncdc.noaa.gov/pub/data/noaa
  2. 按学号后三位下载不同年份月份的数据（例如201506110136号同学，就下载2013年以6开头的数据，看具体数据情况稍有变通）
  3. 解压数据集，并保存在文本文件中
  4. 对气象数据格式进行解析
  5. 编写map函数，reduce函数
  6. 将其权限作出相应修改
  7. 本机上测试运行代码
  8. 放到HDFS上运行
    1. 将之前爬取的文本文件上传到hdfs上
    2. 用Hadoop Streaming命令提交任务
  9. 查看运行结果
cd / usr / hadoop

sodu
mkdir
hp

cd / usr / hadoop / hp

wget - D - -accept - regex = REGEX - P
data - r - c
ftp: // ftp.ncdc.noaa.gov / pub / data / noaa / 2010 / 1*

cd / usr / hadoop / hp / data / ftp.ncdc.noaa.gov / pub / data / noaa / 2010

sudo
zcat
1 *.gz > hptext.txt

cd / usr / hadoop / hp

import sys

for line in sys.stdin:
    line = line.strip()

    dtext = line[15:23]

    text = line[87:92]

    print
    '%s\t%s' % (d, t)

from operator import itemggetter

import sys

current_word = None

current_count = 0

word = None

for line in sys.stdin:

    line = line.strip()

    word, count = line.split('\t', 1)

    try:

        count = int(count)

    except ValueError:

        continue

    if current_word == word:

        if current_count > count:
            current_count = count

    else:

        if current_word:
            print
            '%s\t%s' % (current_word, current_count)

        current_count = count

        current_word = word

if current_word == word:
    print
    '%s\t%s' % (current_word, current_count)

chmod
a + x / usr / hadoop / hp / mapper.py

chmod
a + x / usr / hadoop / hp / reducer.py