library(arules)
ftrmedio <- merged.geotweetsmadcat4sq.dfs[,c(4,6)] %>% as.data.frame() #Se selecciona cat_bajo y user_id_str
ftr.geotweetsmad4sq.medio <- as(split(ftrmedio[,"cat_medio"],ftrmedio[,"user_id_str"]),"transactions") # ftr: frequent travel route Se convierte en transaccion y se eliminan los items dulicados en la transaciones
## Warning in asMethod(object): removing duplicated items in transactions
LIST(ftr.geotweetsmad4sq.medio) %>% head(n=4) #Listado de todas las transacciones sin tomar en cuenta la componente temporal.
## $`7007`
## [1] "Art Museum"                "College Academic Building"
## [3] "Hotel"                     "Office"
## [5] "Park"                      "Plaza"
## [7] "Scenic Lookout"
##
## $`635803`
## [1] "Bank"  "Bar"   "Plaza"
##
## $`731833`
##  [1] "Art Gallery"          "Building"             "Chinese Restaurant"
##  [4] "Convention"           "Coworking Space"      "Farmers Market"
##  [7] "Gym / Fitness Center" "Hotel"                "Multiplex"
## [10] "Music Venue"          "Park"                 "Restaurant"
## [13] "Spanish Restaurant"   "Tapas Restaurant"     "Tech Startup"
## [16] "Turkish Restaurant"
##
## $`732673`
## [1] "Airport"    "Bank"       "Hotel"      "Restaurant"
summary(ftr.geotweetsmad4sq.medio)
## transactions as itemMatrix in sparse format with
##  12382 rows (elements/itemsets/transactions) and
##  413 columns (items) and a density of 0.008856487
##
## most frequent items:
## Train Station         Plaza          Park          Bank         Hotel
##          3759          3746          2417          1846          1615
##       (Other)
##         31907
##
## element (itemset/transaction) length distribution:
## sizes
##    1    2    3    4    5    6    7    8    9   10   11   12   13   14   15
##  384 5369 2550 1432  821  530  368  239  136  118  102   78   60   44   25
##   16   17   18   19   20   21   22   23   24   25   26   27   28   29   30
##   26   16   11    7   10   13    5    6    2    4    1    3    3    2    2
##   31   32   33   34   35   36   46   47   49   75
##    1    3    2    1    1    3    1    1    1    1
##
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.
##   1.000   2.000   3.000   3.658   4.000  75.000
##
## includes extended item information - examples:
##                   labels
## 1      Accessories Store
## 2 Adult Education Center
## 3     Advertising Agency
##
## includes extended transaction information - examples:
##   transactionID
## 1          7007
## 2        635803
## 3        731833
reglas.ftr.mad4sq.medio <- apriori(ftr.geotweetsmad4sq.medio, parameter = list(supp=0.001, conf=0.60,target="rules"))
## Apriori
##
## Parameter specification:
##  confidence minval smax arem  aval originalSupport maxtime support minlen
##         0.6    0.1    1 none FALSE            TRUE       5   0.001      1
##  maxlen target   ext
##      10  rules FALSE
##
## Algorithmic control:
##  filter tree heap memopt load sort verbose
##     0.1 TRUE TRUE  FALSE TRUE    2    TRUE
##
## Absolute minimum support count: 12
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[413 item(s), 12382 transaction(s)] done [0.02s].
## sorting and recoding items ... [218 item(s)] done [0.00s].
## creating transaction tree ... done [0.01s].
## checking subsets of size 1 2 3 4 5 6 done [0.02s].
## writing ... [2287 rule(s)] done [0.00s].
## creating S4 object  ... done [0.01s].
summary(reglas.ftr.mad4sq.medio)
## set of 2287 rules
##
## rule length distribution (lhs + rhs):sizes
##    2    3    4    5    6
##    1  514 1320  434   18
##
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.
##    2.00    4.00    4.00    3.98    4.00    6.00
##
## summary of quality measures:
##     support           confidence          lift
##  Min.   :0.001050   Min.   :0.6000   Min.   : 1.976
##  1st Qu.:0.001131   1st Qu.:0.6500   1st Qu.: 2.267
##  Median :0.001292   Median :0.7143   Median : 2.610
##  Mean   :0.001515   Mean   :0.7322   Mean   : 3.237
##  3rd Qu.:0.001615   3rd Qu.:0.8000   3rd Qu.: 3.202
##  Max.   :0.010176   Max.   :1.0000   Max.   :16.416
##
## mining info:
##                       data ntransactions support confidence
##  ftr.geotweetsmad4sq.medio         12382   0.001        0.6
#Eliminación de reglas redundantes
rules.sorted<- sort(reglas.ftr.mad4sq.medio,by="lift")
subset.matrix <- is.subset(rules.sorted,rules.sorted)
subset.matrix[lower.tri(subset.matrix, diag = T)]=NA
redundant<- colSums(subset.matrix,na.rm=T)>=1

rules.pruned.medio <- rules.sorted[!redundant]
inspect(rules.pruned.medio)