diff --git a/1-1.py b/1-1.py new file mode 100644 index 0000000..f08f1af --- /dev/null +++ b/1-1.py @@ -0,0 +1,11 @@ +from log_analysis_step2 import access_logs + +not200 = access_logs.filter(lambda log: log.response_code != 200) + +endpointCountPairTuple = not200.map(lambda log: (log.endpoint, 1)) + +endpointSum = endpointCountPairTuple.reduceByKey(lambda a, b : a + b) + +topTenErrURLs = endpointSum.takeOrdered(10, lambda s: -1 * s[1]) + +print('Top Ten failed URLs: %s' % topTenErrURLs)