Santander Product Recommendation

https://www.kaggle.com/c/santander-product-recommendation/kernels

Data 살펴보기 > Cleansing

https://www.kaggle.com/apryor6/detailed-cleaning-visualization

우선 엑셀에 데이터를 표로 구성하고, datatype을 정하고, 특징을 정리한다.

d0<- data.table(Month=c(1:7),
                   V1=c(0,0,1,1,1,0,0),
                   V2=c(1,1,0,0,1,1,1),
                   V3=c(0,1,1,1,0,0,0))
# way1
d0.lag1 <- copy(d0)
d0.lag1[, Month:=Month+1]
names(d0.lag1)[2:4] <- str_c(names(d0.lag1)[2:4],"_lag1")
d1 <- merge(d0, d0.lag1, by="Month", all.x=T, roll=Inf)
#d1[is.na(d1)] <- 0

# way2
d0.lag1 <-d0[ , lapply(.SD, function(x) lag(x)), .SDcols=str_subset(names(d0), "V")]
#d0.lag1 <-d0[ , lapply(.SD, lag)][, 2:4]
names(d0.lag1) <- str_c(names(d0.lag1),"_lag1")
d1 <- cbind(d0, d0.lag1)

#cols <- str_c("p",1:3,"_lag1")
#d0[ , P1:=V1-V1_lag1]
#d0[ , ':='(P1=V1-V1_lag1,P2=V2-V2_lag1, P3=V3-V2_lag1)]
for(i in 1:3){
  cols <- c(str_c("V",i), str_c("V",i,"_lag1"))
  d1[, str_c("P", i):=.SD[[1]]-.SD[[2]], .SDcols=cols] 
}

> d0.lag1
   Month V1_lag1 V2_lag1 V3_lag1
1:     2       0       1       0
2:     3       0       1       1
3:     4       1       0       1
4:     5       1       0       1
5:     6       1       1       0
6:     7       0       1       0
7:     8       0       1       0

> d1
   Month V1 V2 V3 V1_lag1 V2_lag1 V3_lag1
1:     1  0  1  0      NA      NA      NA
2:     2  0  1  1       0       1       0
3:     3  1  0  1       0       1       1
4:     4  1  0  1       1       0       1
5:     5  1  1  0       1       0       1
6:     6  0  1  0       1       1       0
7:     7  0  1  0       0       1       0

> d1
   Month V1 V2 V3 V1_lag1 V2_lag1 V3_lag1 P1 P2 P3
1:     1  0  1  0      NA      NA      NA NA NA NA
2:     2  0  1  1       0       1       0  0  0  1
3:     3  1  0  1       0       1       1  1 -1  0
4:     4  1  0  1       1       0       1  0  0  0
5:     5  1  1  0       1       0       1  0  1 -1
6:     6  0  1  0       1       1       0 -1  0  0
7:     7  0  1  0       0       1       0  0  0  0