Skip to content

mindis/Personalized-Search-Results

BranchesTags
 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

46 Commits

README.md

README.md

 
 

nest_constants.py

nest_constants.py

 
 

nest_similar_prop_initiate.py

nest_similar_prop_initiate.py

 
 

nest_similar_prop_preprocessing.py

nest_similar_prop_preprocessing.py

 
 

nest_similar_prop_spark.py

nest_similar_prop_spark.py

 
 

nest_similar_prop_training.py

nest_similar_prop_training.py

 
 

nest_user_personalization.py

nest_user_personalization.py

 
 

output.txt

output.txt

 
 

recommendation.ipynb

recommendation.ipynb

 
 

ty_test.ipynb

ty_test.ipynb

 
 

Repository files navigation

Personalized-Search-Results

Personalized Search Results using Spark, Mongo, LSH, AWS S3

  • 1+ Billion record are loaded into Spark dataframe from Mongodb
  • Popular items are loaded from user behavioural logs stored in S3
  • Popular items are used to find most similar items from Mongodb database.
  • Similarity is computed using Local Sensitive Hashing concept
  • Code is develoepd using Spark ML framework
  • Code can run on AWS EMR Cluster or Google Cloud Platfor's Dataprocs.

About

Personalized Search Results using Spark, Mongo, LSH

Resources

Readme
Activity

Stars

0 stars

Watchers

1 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 98.8%
  • Python 1.2%