Git Product home page Git Product logo

dist_w2v's Introduction

Asynchronous Training of Word Embeddings for large text corpora

How to use

In the code directory is the script execute_epochs.sh. It handles/sets:

  • calling hadoop streaming
  • number of VCOREs per reducer
  • number of reducers
  • name of the job
  • number of epochs

Additionally, the files mapper.py and reducer.py need to be modified.

In mapper.py one has to set the number of reducers/sampling rate and if required the sub sampling of the actual data.

In the reducer.py the active hadoop namenode has to be set, as well as the path for the models. That path needs to exist (and be word writeable). The correct path vocabulary (in form of a pickled python dict) also needs to be given and depending on the name, also added in execute_epochs.sh.

Before running execute_epochs.sh the KeyPartitioner has to be compiled to byte code:

export CLASSPATH=$(/usr/bin/hadoop classpath)
javac KeyPartitioner.java

The extra partitioner is needed since the default uses the hash of the key modulo the number of reducers to send the data to different reducers. But this will generate collisions and often also result in some reducers getting no data at all. Depending on the configured number of reducers.

dist_w2v's People

Contributors

joshuaghost avatar

Stargazers

Max Idahl avatar Carson Kahn avatar Avishek Anand avatar

Watchers

Jan-Hendrik Zab avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.