Update emailaddr_agg.py

Sotera · Nov 4, 2015 · 6d13b3c · 6d13b3c
1 parent c66f5f4
commit 6d13b3c
Showing 1 changed file with 0 additions and 1 deletion.
diff --git a/spark/emailaddr_agg.py b/spark/emailaddr_agg.py
@@ -97,7 +97,6 @@ def sender_receiver(o):
     sc = SparkContext(conf=conf)
     rdd_raw_emails = sc.textFile(args.input_path_emails).cache()
     rdd_addr_to_emails = rdd_raw_emails.flatMap(email_to_addrs).keyBy(lambda x: x['addr']).groupByKey().map(in_out).cache()
-    #{"recepient": [], "addr": "loraleivp@erols.com", "sender": []}
     #rdd_addr_to_emails.saveAsTextFile(args.output_path_email_address)
 
     rdd_edges = rdd_raw_emails.flatMap(sender_receiver).reduceByKey(lambda a,b: a+b).map(lambda x: (x[0][0], x[0][1], x[1])).cache()