-3

I have been working on market basket analysis, by apriori approach in R, data contains 12 variables with 21,00,000 observations, my laptop has 4 GB RAM, my R code is not running for converting data into transactions. Please, help.

mragakshi agarwal
  • 5
  • 2
  • 3
    #Hi! Welcome to SO. Please read - [How to make a great R reproducible example?](https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example), in your case, can you provide us the important piece of code and what the error is? Also, a small sample of your data? – Shique Jun 04 '18 at 07:04
  • Which version of R are you using? 32 or 64 bit? – s__ Jun 04 '18 at 07:14
  • 1
    Do you need all your 21 million observations? Maybe a sample would be sufficient? – FilipW Jun 04 '18 at 07:59

1 Answers1

0

I have worked on apriori algorithm for larger datasets in the past. I faced the similar issue. To solve it temporarily, I used sampling. Later I changed it into few lines of spark implementation which solved my problem permanently.

https://spark.apache.org/docs/1.6.0/mllib-frequent-pattern-mining.html

Aniket Rangrej
  • 192
  • 1
  • 7