Skip to content
/ spark Public
forked from apache/spark

Spark + Alternating Logistic Regression (GLM)

License

Notifications You must be signed in to change notification settings

haowu80s/spark

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SparkALR

Alternating logistic regression is a collaborative filtering method for the prediction of occurance probability given binary observations (e.g. click-though rate).

Compilation

To compile:

sbt/sbt assembly

Run

To run with 4GB of ram:

./bin/spark-submit --class org.apache.spark.ml.examples.SparkALR \
    ./examples/target/scala-2.10/spark-examples-1.6.2-SNAPSHOT-hadoop2.2.0.jar \
    --executor-memory 4G  --driver-memory 4G

Implementations

Detailed information can be found here.

All the implementations are in the SparkALR.scala except the localTrain method for LogisticRegression() which is in LogisiticRegression.scala.

Sample data is included at data/mllib/SparkALR.data.csv

About

Spark + Alternating Logistic Regression (GLM)

Resources

License

Security policy

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Scala 78.2%
  • Java 9.5%
  • Python 8.3%
  • R 2.7%
  • Shell 0.7%
  • JavaScript 0.3%
  • Other 0.3%