Skip to content

Instantly share code, notes, and snippets.

View alienrobotwizard's full-sized avatar

Esme Mora alienrobotwizard

  • BetterLesson
  • California
View GitHub Profile
java.lang.RuntimeException: java.io.IOException: Invalid localDeleteTime read: 0
at org.apache.cassandra.db.BinaryVerbHandler.doVerb(BinaryVerbHandler.java:54)
at org.apache.cassandra.net.MessageDeliveryTask.run(MessageDeliveryTask.java:50)
at java.util.concurrent.ThreadPoolExecutor$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:619)
Caused by: java.io.IOException: Invalid localDeleteTime read: 0
at org.apache.cassandra.db.SuperColumnSerializer.deserialize(SuperColumn.java:346)
at org.apache.cassandra.db.SuperColumnSerializer.deserialize(SuperColumn.java:298)
at org.apache.cassandra.db.ColumnFamilySerializer.deserializeColumns(ColumnFamilySerializer.java:125)
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.math.BigInteger;
import java.net.URI;
import java.net.URISyntaxException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.List;
2010-10-22 17:58:56,590 WARN transport: [Poundcakes] Transport response handler timed out, action [discovery/zen/fd/masterPing], node [[Spider-Slayer][62863483-6ad6-4531-b3bf-75a34ecd0e96][inet[/10.204.153.212:9300]]]
2010-10-22 18:00:32,544 WARN transport: [Poundcakes] Transport response handler timed out, action [discovery/zen/fd/masterPing], node [[Spider-Slayer][62863483-6ad6-4531-b3bf-75a34ecd0e96][inet[/10.204.153.212:9300]]]
2010-10-22 18:00:32,544 WARN transport: [Poundcakes] Transport response handler timed out, action [discovery/zen/fd/masterPing], node [[Spider-Slayer][62863483-6ad6-4531-b3bf-75a34ecd0e96][inet[/10.204.153.212:9300]]]
#!/usr/bin/env ruby
require 'java'
hector_lib = File.join(ENV['HOME'], "Programming/hector/releases/hector-0.7.0-18")
hector_target = File.join(ENV['HOME'], "Programming/hector/target")
Dir["#{hector_target}/*.jar", "#{hector_lib}/*.jar"].each{|jar| $CLASSPATH << jar}
java_import 'me.prettyprint.cassandra.serializers.StringSerializer'
java_import 'me.prettyprint.hector.api.Cluster'
java_import 'me.prettyprint.hector.api.Keyspace'
module GMLParser
class Graph < Struct.new(
:nodes,
:edges
)
def edge_list
self.edges.map{|e| [e[:source], e[:target], e[:value]]}
end
require 'rubygems'
require 'avro'
require 'wukong'
Time.class_eval do
def self.epoch_microseconds
(Time.now.to_i * 1_000_000)
end
end
bizmarketing4u 49108829 0.094361630 1
BrowneBig570 50190727 0.144720420 1
Megan___Fox 49509322 0.147560500 1
pen2netone 47910899 0.064650595 1
dextradyoung 47502802 0.146222870 2
mbainstitute 41130608 0.864213050 2
mcspartan76 17034645 0.111582670 2
Opereur2u 65572992 0.138023360 2
shaunaconway3 63460580 0.105175970 2
BrianaPitts 69789022 0.163385990 3
cat 200_twitspam_2.json| ruby -ne 'puts ["twitter_user_timeline_request", 15491144, 3, "0", "http://twitter.com/statuses/user_timeline/15491144.json?&page=1&count=200", 20100729, 200, "foobar", $_.strip].join("\t")' | ~/Programming/infochimps-data/social/network/twitter/base/parse/parse_twitter_api_requests.rb --map > 200_twitspam_parsed_2.tsv
4.2.145 [[0,{"latitude":"38.0000","country_code":"US","longitude":"-97.0000"}],[159,{"latitude":"38.0000","country_code":"US","longitude":"-97.0000"}],[160,{"household_income":"41506","percent_hispanic":"17.98","city":"Irving","percent_semi_permanent":"18.61","percent_asian":"14.45","percent_under_18":"20.06","latitude":"32.8791","per_capita_income":"28214","percent_bs_graduate":"16.34","area_code":"623","country_code":"US","zip_code":"75038","percent_below_poverty":"10.61","people_per_household":"2.0","housing_unit_value":"149500","percent_homeownership":"11.27","housing_units":"13305","work_travel_time":"3.1","percent_dual_race":"3.09","percent_pacific":"0.0","percent_white":"50.03","population":"25191","region_code":"TX","percent_hs_graduate":"16.34","percent_non_english":"36.09","percent_foreign":"28.9","percent_black":"23.75","percent_over_65":"1.87","metro_code":"972","longitude":"-96.9898","households":"12466","percent_under_5":"7.3","percent_native":"0.56","percent_female":"48.11"}],[191,{"household_i
#
# Example azkaban job. Assumes you have two MR jobs to be run sequentially.
#
type=command
command=$HADOOP_HOME/bin/hadoop jar $HADOOP_HOME/hadoop-*streaming*.jar -input /path/to/data -output /path/to/outputA -mapper mapperA.py -reducer reducerA.py
command.1=$HADOOP_HOME/bin/hadoop jar $HADOOP_HOME/hadoop-*streaming*.jar -input /path/to/outputA -output /path/to/outputB -mapper mapperB.py -reducer reducerB.py