cd /usr/hadoop sodu mkdir qx cd /usr/hadoop/qx wget -D --accept-regex=REGEX -P data -r -c ftp://ftp.ncdc.noaa.gov/pub/data/noaa/2017/1* cd /usr/hadoop/qx/data/ftp.ncdc.noaa.gov/pub/data/noaa/2017 sudo zcat 1*.gz >qxdata.txt cd /usr/hadoop/qx #!/usr/bin/env python import sys for i in sys.stdin: i = i.strip() d = i[15:23] t = i[87:92] print '%s %s' % (d,t) #!/usr/bin/env python from operator import itemggetter import sys current_word = None current_count = 0 word = None for i in sys.stdin: i = i.strip() word,count = i.split(' ', 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 %s' % (current_word, current_count) current_count = count current_word = word if current_word == word: print '%s %s' % (current_word, current_count) chmod a+x /usr/hadoop/qx/mapper.py chmod a+x /usr/hadoop/qx/reducer.py