collaborative filtering - Can't get mahout itemsimilarity result with preferences (booleanValue=false) -


I'm trying to make Vichlitta before using Mahaut.

  • 15.910.847 Total number of priorities
  • The problem is that I get some commonalities in output.

    4.047.745 individual users

  • 773.015 different items I built users and distribution prefereces

    The first column separately number of users

    the second column per user preferences that I use 2,221,760 is only a priority, for example.

      2221760 1 688258 2 322497 3 192003 4 122446 5 87033 6 63733 7 49556 8 39090 9 31637 10 25634 11    

    here are my input settings:

      similarityClassname = SIMILARITY_PEARSON_CORRELATION maxSimilaritiesPerItem = 100000 minPrefsPerUser = 0 booleanData = false border = 0.75  column should be consumer user ID of 1, the number of users 0 Should be - 1 column 2  itemprop = "text"> 

    Item Item ID, Number of Items to 0 - 1 You can set the preferences for recording each preference Can not count, which the user has shown some priority for column 3, the strength of priority, like rating

    ID is like row and column numbers in a matrix or table 0,0 , 0 user is 0 item 0, the value is the rating.

    You will have to translate your ID into a major ID, the result of objects.

Comments

Popular posts from this blog

ios - Adding an SKSpriteNode to SKScene from a child SKSpriteNode -

Matlab transpose a table vector -

c# - Textbox not clickable but editable -