Hadoop入培训.pptVIP

Streaming开发实例 --map脚本内容 #!/usr/bin/python import sys for eachLine in sys.stdin: #从标准输入获取数据 eachLine = eachLine.strip() Seg = eachLine.split(‘|’) #用\t来分割开各个字段 if len(Seg) == 19 and Seg[1] == rpt_cad and Seg[6] != : ad_id = Seg[6] print ‘%s\t%d’ % (ad_id, 1) #将map结果送到标准输出 else: pass 文件名:cat ad_day_pv_map.py Streaming开发实例 --reduce脚本内容 #!/usr/bin/python LastLine = LastCount = 0 import sys for eachLine in sys.stdin: #从标准输入获取数据 eachLine = eachLine.strip() Seg = eachLine.split(‘\t’) #用\t来分割开key和value if len(Seg) ==