cd /usr/hadoopsodu mkdir qxcd /usr/hadoop/qxwget -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/2017sudo zcat 1*.gz >qxdata.txtcd /usr/hadoop/qx#！/usr/bin/env pythonimport sysfor i in sys.stdin:     i = i.strip()     d = i[15:23]     t = i[87:92]     print '%s\t%s' % (d,t) #!/usr/bin/env pythonfrom operator import itemggetterimport syscurrent_word = Nonecurrent_count = 0word = Nonefor i in sys.stdin:     i = i.strip()     word,count = i.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 = wordif current_word == word:     print '%s\t%s' % (current_word, current_count)chmod a+x /usr/hadoop/qx/mapper.pychmod a+x /usr/hadoop/qx/reducer.py