Consequent sorting

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

Consequent sorting

reichmaj
r-help Forum

 

I'm using the following code to sort the "right-hand side (rhs, consequent)
of the rules output from the arules packages, which works.  But what I'd
really like is the ability to subset my rules where the rhs = "some item
set"

 

rules_info <-

  data.frame(

    LHS = labels(lhs(rules)),

    RHS = labels(rhs(rules)),          

    quality(rules)

  )

 

rules_info[ order(rules_info$RHS=), ]

 

For example using my code above I'm able to sort as follow's

 

179  {Cereals,Eggs,Tomatoes,Vinegar}    {Bread} 0.1428571  1.0000000
1.1666667     1

184           {Eggs,Milk,Pork,Sugar}    {Bread} 0.1428571  1.0000000
1.1666667     1

189        {Eggs,Milk,Pork,Tomatoes}    {Bread} 0.1428571  1.0000000
1.1666667     1

1                                 {}  {Cereals} 0.2857143  0.2857143
1.0000000     2

8                          {Vinegar}  {Cereals} 0.1428571  1.0000000
3.5000000     1

15                        {Tomatoes}  {Cereals} 0.1428571  0.5000000
1.7500000     1

17                            {Eggs}  {Cereals} 0.2857143  0.3333333
1.1666667     2

 

But what I'd really like to do is just get (say) {Bread} like .

 

                                 LHS        RHS   support confidence
lift count

179  {Cereals,Eggs,Tomatoes,Vinegar}    {Bread} 0.1428571  1.0000000
1.1666667     1

184           {Eggs,Milk,Pork,Sugar}    {Bread} 0.1428571  1.0000000
1.1666667     1

189        {Eggs,Milk,Pork,Tomatoes}    {Bread} 0.1428571  1.0000000
1.1666667     1

 

Jeff Reichman

 


        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Consequent sorting

reichmaj
Never mind.  Working with the arules package notes I was able to figure it
out

rules <- apriori(fp.trans,
                 parameter = list(supp = 0.1, conf = 0.2, target = "rules"),
                 appearance = list(rhs="Sugar", default="lhs"),
                 control = list(verbose=F))
rules.sorted <- sort(rules, by="lift")
inspect(rules.sorted)

-----Original Message-----
From: R-help <[hidden email]> On Behalf Of Jeff Reichman
Sent: Sunday, September 23, 2018 5:18 PM
To: [hidden email]
Subject: [R] Consequent sorting

r-help Forum

 I'm using the following code to sort the "right-hand side (rhs, consequent)
of the rules output from the arules packages, which works.  But what I'd
really like is the ability to subset my rules where the rhs = "some item
set"


rules_info <-
  data.frame(
    LHS = labels(lhs(rules)),
    RHS = labels(rhs(rules)),          
    quality(rules)
  )

rules_info[ order(rules_info$RHS=), ]

For example using my code above I'm able to sort as follow's

179  {Cereals,Eggs,Tomatoes,Vinegar}   {Bread} 0.1428571  1.0000000
1.1666667     1
184           {Eggs,Milk,Pork,Sugar}   {Bread} 0.1428571  1.0000000
1.1666667     1
189        {Eggs,Milk,Pork,Tomatoes}     {Bread} 0.1428571  1.0000000
1.1666667     1
1                                 {}   {Cereals} 0.2857143
0.2857143 1.0000000     2
8                          {Vinegar}   {Cereals} 0.1428571
1.0000000 3.5000000     1
15                        {Tomatoes} {Cereals} 0.1428571
0.5000000 1.7500000     1

But what I'd really like to do is just get (say) {Bread} like .

179  {Cereals,Eggs,Tomatoes,Vinegar}    {Bread} 0.1428571  1.0000000
1.1666667     1
184           {Eggs,Milk,Pork,Sugar}    {Bread} 0.1428571  1.0000000
1.1666667     1
189        {Eggs,Milk,Pork,Tomatoes}    {Bread} 0.1428571  1.0000000
1.1666667     1


Jeff Reichman


______________________________________________
[hidden email] <mailto:[hidden email]>  mailing list -- To
UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.