| import org.apache.http.client.methods.HttpGet | |
| import org.apache.http.impl.client.{BasicResponseHandler, HttpClientBuilder} | |
| import org.apache.spark.mllib.fpm.PrefixSpan | |
| // sequence database | |
| val sequenceDatabase = { | |
| val url = "http://www.philippe-fournier-viger.com/spmf/datasets/SIGN.txt" | |
| val client = HttpClientBuilder.create().build() | |
| val request = new HttpGet(url) | |
| val response = client.execute(request) |
| package com.databricks.spark.jira | |
| import scala.io.Source | |
| import org.apache.spark.rdd.RDD | |
| import org.apache.spark.sql._ | |
| import org.apache.spark.sql.functions._ | |
| import org.apache.spark.sql.sources.{TableScan, BaseRelation, RelationProvider} |
| import pandas as pd | |
| import numpy as np | |
| from sklearn.ensemble import GradientBoostingClassifier | |
| train_loc = 'train.csv' | |
| test_loc = 'test.csv' | |
| TREES = 30 | |
| NODES = 7 |
| ''' | |
| DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE | |
| Version 2, December 2004 | |
| Copyright (C) 2004 Sam Hocevar <sam@hocevar.net> | |
| Everyone is permitted to copy and distribute verbatim or modified | |
| copies of this license document, and changing it is allowed as long | |
| as the name is changed. |
| $ scald.rb --hdfs-local testconv.scala | |
| compiling testconv.scala | |
| scalac -classpath /Users/kraman/.sbt/boot/scala-2.9.3/lib/scala-library.jar:/Users/kraman/.sbt/boot/scala-2.9.3/lib/scala-compiler.jar:/Users/kraman/workspace/scalding/scalding-core/target/scala-2.9.3/scalding-core-assembly-0.11.1.jar:/var/folders/b_/17q0nsss269_2kf855mtg4_c0000gn/T/maven/hadoop-core-1.1.2.jar:/var/folders/b_/17q0nsss269_2kf855mtg4_c0000gn/T/maven/commons-codec-1.8.jar:/var/folders/b_/17q0nsss269_2kf855mtg4_c0000gn/T/maven/commons-configuration-1.9.jar:/var/folders/b_/17q0nsss269_2kf855mtg4_c0000gn/T/maven/jackson-asl-0.9.5.jar:/var/folders/b_/17q0nsss269_2kf855mtg4_c0000gn/T/maven/jackson-mapper-asl-1.9.13.jar:/var/folders/b_/17q0nsss269_2kf855mtg4_c0000gn/T/maven/commons-lang-2.6.jar:/var/folders/b_/17q0nsss269_2kf855mtg4_c0000gn/T/maven/slf4j-log4j12-1.6.6.jar:/var/folders/b_/17q0nsss269_2kf855mtg4_c0000gn/T/maven/log4j-1.2.15.jar:/var/folders/b_/17q0nsss269_2kf855mtg4_c0000gn/T/maven/commons-httpclient-3.1.jar:/var/folders/b |
| /** | |
| git clone https://github.com/twitter/scalding.git | |
| cd scalding | |
| ./sbt scalding-repl/console | |
| */ | |
| import scala.io.Source | |
| val alice = Source.fromURL("http://www.gutenberg.org/files/11/11.txt").getLines | |
| // Add the line numbers, which we might want later | |
| val aliceLineNum = alice.zipWithIndex.toList |
| import scala.collection.JavaConversions._ | |
| import cascading.scheme.Scheme | |
| import cascading.tap.SinkMode | |
| import cascading.tuple.Fields | |
| import com.twitter.scalding.{FixedPathSource, HadoopSchemeInstance, SchemedSource} | |
| import org.apache.hadoop.mapred.{JobConf, OutputCollector, RecordReader} | |
| trait HiveScheme extends SchemedSource { | |
| // cascading-hive Schemes take two arrays as arguments |
| 原文地址：http://in.sdo.com/?p=1707 | |
| 收集和整理了目前互联网上能找到的开源推荐系统，并附上了个人的一些简单点评（未必全面准确），这个列表是目前为止比较全面的了，希望对大家了解掌握推荐系统有帮助（文/陈运文） | |
| SVDFeature | |
| 由上海交大的同学开发，采用C++语言，代码质量很高。去年我们参加KDD竞赛时用过，很好很方便，而且出自咱们国人之手，所以置顶推荐！ | |
| 项目地址： | |
| http://svdfeature.apexlab.org/wiki/Main_Page | |
| SVDFeature包含一个很灵活的Matrix Factorization推荐框架，能方便的实现SVD、SVD++等方法, 是单模型推荐算法中精度最高的一种。SVDFeature代码精炼，可以用相对较少的内存实现较大规模的单机版矩阵分解运算。 | |
| 另外含有Logistic regression的model，可以很方便的用来进行ensemble运算 |
SSHPass is a tiny utility, which allows you to provide the ssh password without using the prompt. This will very helpful for scripting. SSHPass is not good to use in multi-user environment. If you use SSHPass on your development machine, it don't do anything evil.
apt-get install sshpass
