mvrpl / AnaliseLogNASA

AnaliseLogNASA

Versão Spark = 2.4.4

Versão Scala = 2.11.12

BUILD .jar:

scalac -classpath $(find /usr/local/Cellar/apache-spark/2.4.4/libexec/jars -name "*.jar" -type f | paste -sd ":" -) QuestoesLogNASA.scala -d QuestoesLogNASA.jar

EXECUCAO:

spark-submit --class mvrpl.me.QuestoesLogNASA --master "local[*]" QuestoesLogNASA.jar

Resultado:

HOSTS UNICOS: 138010

TOTAL ERROS 404: 20868

TOP 5 URLs 404:
(hoohoo.ncsa.uiuc.edu,251)
(piweba3y.prodigy.com,157)
(jbiagioni.npt.nuwc.navy.mil,132)
(piweba1y.prodigy.com,114)
(www-d4.proxy.aol.com,91)

QTD ERRO 404/DIA:
(1995-09-01,26)
(1995-08-31,551)
(1995-08-30,539)
(1995-08-29,416)
(1995-08-28,406)
(1995-08-27,381)
(1995-08-26,358)
(1995-08-25,419)
(1995-08-24,416)
(1995-08-23,359)
(1995-08-22,264)
(1995-08-21,310)
(1995-08-20,306)
(1995-08-19,213)
(1995-08-18,257)
(1995-08-17,276)
(1995-08-16,253)
(1995-08-15,324)
(1995-08-14,297)
(1995-08-13,220)
(1995-08-12,176)
(1995-08-11,272)
(1995-08-10,303)
(1995-08-09,284)
(1995-08-08,395)
(1995-08-07,524)
(1995-08-06,378)
(1995-08-05,237)
(1995-08-04,349)
(1995-08-03,287)
(1995-08-01,243)
(1995-07-28,105)
(1995-07-27,330)
(1995-07-26,344)
(1995-07-25,471)
(1995-07-24,318)
(1995-07-23,231)
(1995-07-22,190)
(1995-07-21,338)
(1995-07-20,419)
(1995-07-19,646)
(1995-07-18,465)
(1995-07-17,420)
(1995-07-16,238)
(1995-07-15,252)
(1995-07-14,414)
(1995-07-13,531)
(1995-07-12,463)
(1995-07-11,493)
(1995-07-10,379)
(1995-07-09,348)
(1995-07-08,317)
(1995-07-07,578)
(1995-07-06,657)
(1995-07-05,475)
(1995-07-04,369)
(1995-07-03,461)
(1995-07-02,274)
(1995-07-01,303)

TOTAL BYTES: 65524307881