[R] arules package question- apriori/S4 object export question

[Michael Hahsler]

Hi John,

You can use WRITE (see ? WRITE) to save rules to a file in the
from:

{a,b,c} => {d} 0.1 0.3 2.2

where the numbers after the rule are support, confidence and lift.
There is no csv export since the number of items in the rules varies and 
the data structure can not be converted into a simple table.

Alternatively you can export the rules using PMML (XML) and use a XML 
parser to get the rules.

Best,
Michael

On 01/-10/-28163 01:59 PM, johnistan wrote:
>
> I am new to R( but quickly being awed by the range of this it can accomplish,
> you have one more convert to the useR universe). I have successfully
> implemented the apriori function and are getting great results. My question
> concerns how to export these results. I have read lots about write.csv
> functions and exporting data frames and other standard objects. Im having
> difficulty working with these S4 objects. My object looks as follows.
>
>
>> str(rules)
> Formal class 'rules' [package "arules"] with 4 slots
>    ..@ lhs    :Formal class 'itemMatrix' [package "arules"] with 3 slots
>    .. .. ..@ data       :Formal class 'ngCMatrix' [package "Matrix"] with 5
> slots
>    .. .. .. .. ..@ i       : int [1:2133] 3907 3519 4172 3519 4182 3519 4172
> 4182 4172 4182 ...
>    .. .. .. .. ..@ p       : int [1:790] 0 0 1 2 3 4 5 6 7 8 ...
>    .. .. .. .. ..@ Dim     : int [1:2] 7002 789
>    .. .. .. .. ..@ Dimnames:List of 2
>    .. .. .. .. .. ..$ : NULL
>    .. .. .. .. .. ..$ : NULL
>    .. .. .. .. ..@ factors : list()
>    .. .. ..@ itemInfo   :'data.frame':   7002 obs. of  1 variable:
>    .. .. .. ..$ labels:Class 'AsIs'  chr [1:7002] "0171T_722.52"
> "0171T_724.02" "0172T_724.02" "0197T_185" ...
>    .. .. ..@ itemsetInfo:'data.frame':   0 obs. of  0 variables
>    ..@ rhs    :Formal class 'itemMatrix' [package "arules"] with 3 slots
>    .. .. ..@ data       :Formal class 'ngCMatrix' [package "Matrix"] with 5
> slots
>    .. .. .. .. ..@ i       : int [1:789] 4120 3704 4172 3519 4182 3519 4120
> 4182 4172 4120 ...
>    .. .. .. .. ..@ p       : int [1:790] 0 1 2 3 4 5 6 7 8 9 ...
>    .. .. .. .. ..@ Dim     : int [1:2] 7002 789
>    .. .. .. .. ..@ Dimnames:List of 2
>    .. .. .. .. .. ..$ : NULL
>    .. .. .. .. .. ..$ : NULL
>    .. .. .. .. ..@ factors : list()
>    .. .. ..@ itemInfo   :'data.frame':   7002 obs. of  1 variable:
>    .. .. .. ..$ labels:Class 'AsIs'  chr [1:7002] "0171T_722.52"
> "0171T_724.02" "0172T_724.02" "0197T_185" ...
>    .. .. ..@ itemsetInfo:'data.frame':   0 obs. of  0 variables
>    ..@ quality:'data.frame':     789 obs. of  3 variables:
>    .. ..$ support   : num [1:789] 0.8258 0.0103 0.0102 0.0102 0.0102 ...
>    .. ..$ confidence: num [1:789] 0.826 1 0.987 0.925 0.987 ...
>    .. ..$ lift      : num [1:789] 1 50.8 89.6 89.6 89.6 ...
>    ..@ info   :List of 4
>    .. ..$ data         : symbol lij_trans
>    .. ..$ ntransactions: int 7266
>    .. ..$ support      : num 0.01
>    .. ..$ confidence   : num 0.7
>
> and sample inspect statement:
>
> 95  {93510_411.1,
>       93556_411.1}  =>  {93010_414.9}  0.01279934  1.0000000  1.21100
> 96  {93010_414.9,
>       93510_411.1}  =>  {93556_411.1}  0.01279934  0.9687500 69.00919
> 97  {93010_414.9,
>       93556_411.1}  =>  {93510_411.1}  0.01279934  0.9117647 69.00919
> 98  {93543_413.9,
>       93555_413.9}  =>  {93556_413.9}  0.01541426  1.0000000 60.55000
> 99  {93543_413.9,
>       93556_413.9}  =>  {93555_413.9}  0.01541426  1.0000000 64.87500
> 100 {93555_413.9,
>       93556_413.9}  =>  {93543_413.9}  0.01541426  1.0000000 64.87500
> 101 {93543_413.9,
>       93555_413.9}  =>  {93545_413.9}  0.01541426  1.0000000 60.04959
>
>
>
> What is am most interested in is exporting to a csv or some form of table.
> Where the 1,2 or n transactions on the left are listed in c(1,2,...n) and
> the dependent data point is in c(4 or n+1)(I have limited the max number to
> three) and the support/conf/lift is the next tree columns.
>
> something like:
>
>   93543_413.9 | 93555_413.9 | 93545_413.9 |  0.01541426 |  1.0000000 |
> 60.04959
>
> I have searched around but haven't found anything. Can someone help or
> supply some more promising search terms to direct my dive into
> documentation.
>
>
> Thanks,
>
> John
>
>
>
>
>
>
>
>

-- 
   Michael Hahsler
   email: michael at hahsler.net
   web: http://michael.hahsler.net