Geek asks and answers

Subtraction on different rows and columns and grouping

I am very unpleasant to ask two questions in a row, but this is something that I can’t circle around me. So let's say I have a data frame as shown below:

   df
   Row# User    Morning     Evening     Measure Date
   1    1          NA          NA          2/18/11
   2    1          50          115         2/19/11
   3    1          85          128         2/20/11
   4    1          62          NA          2/25/11
   5    1          48          100.8        3/8/11
   6    1          19          71          3/9/11
   7    1          25          98          3/10/11
   8    1          NA          105         3/11/11
   9    2          48          105         2/18/11
   10   2          28          203         2/19/11
   11   2          35          80.99        2/21/11
   12   2          91          78.25        2/22/11

Is it possible for R to take the difference between the previous consecutive day (and only for the previous day, and not the previous result) the evening value of 1 line and the morning value of another line for each user group? Therefore, my desired results would be as follows.

   df
   Row# User    Morning     Evening     Date        Difference
   1       1      NA          NA        2/18/11        NA
   2       1      50          115       2/19/11        NA
   3       1      85          129       2/20/11        30
   4       1      62          NA        2/25/11        NA
   5       1      48          100.8     3/8/11         NA
   6       1      19          71        3/9/11         81.8
   7       1      25          98        3/10/11        46
   8       1      10          105       3/11/11        88
   9       2      48          105       2/18/11        NA
   10      2      28          203       2/19/11        77
   11      2      35          80.99     2/21/11        NA
   12      2      91          78.25     2/22/11        -10.01

, , . , NA , , , , , NA.

google, ( ).

.

df$Difference<-ave((df$Morning,df$Evening),
                    df$User,
                    FUN=function(x){
                        c('NA',diff(df$Evening-df$Morning)),na.rm=T
                   })

, . .

+5
3

. , , . NA, 10 , 2/14/11 2/22/11 .

, .

df$Diff <- c(NA, head(df$Evening, -1) - tail(df$Morning, -1))
df$Diff[which(c(0, diff(as.Date(as.character(df$Measure_Date), 
                 format="%m/%d/%Y"))) != 1)] <- NA

> df

#    Row User Morning Evening Measure_Date   Diff
# 1    1    1      NA      NA      2/18/11     NA
# 2    2    1      50  115.00      2/19/11     NA
# 3    3    1      85  128.00      2/20/11  30.00
# 4    4    1      62      NA      2/25/11     NA
# 5    5    1      48  100.80       3/8/11     NA
# 6    6    1      19   71.00       3/9/11  81.80
# 7    7    1      25   98.00      3/10/11  46.00
# 8    8    1      10  105.00      3/11/11  88.00
# 9    9    2      48  105.00      2/18/11     NA
# 10  10    2      28  203.00      2/19/11  77.00
# 11  11    2      35   80.99      2/21/11     NA
# 12  12    2      91   78.25      2/22/11 -10.01

@user1342086 edit ( , ):

df$Diff[which(diff(df$User) != 0)] <- NA

, "".

+4

(). , User Date.

#if necessary, transform your dates from factor to Date
df$Date <- as.Date(levels(df$Date)[df$Date],format="%m/%d/%y")

df <- within(df, 
  Difference <- ifelse(c(NA,diff(Measure_Date)) == 1 & diff(User) == 0, 
    c(NA,head(Evening,-1)) - Morning, NA
  )
)
+4

plyr, . , (.. ), .

# Your example data, as you should post it for us to use
df <-
structure(list(User = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 
2L, 2L), Morning = c(NA, 50L, 85L, 62L, 48L, 19L, 25L, NA, 48L, 
28L, 35L, 91L), Evening = c(NA, 115, 128, NA, 100.8, 71, 98, 
105, 105, 203, 80.99, 78.25), Measure_Date = structure(c(1L, 
2L, 3L, 5L, 9L, 10L, 6L, 7L, 1L, 2L, 4L, 8L), .Label = c("2/18/11", 
"2/19/11", "2/20/11", "2/21/11", "2/25/11", "3/10/11", "3/11/11", 
"3/14/11", "3/8/11", "3/9/11"), class = "factor")), .Names = c("User", 
"Morning", "Evening", "Measure_Date"), class = "data.frame", row.names = c(NA, 
-12L))

# As already stated by Arun, you need the date as class Date
df$Measure_Date <- as.Date(df$Measure_Date, format='%m/%d/%y')


# Use plyr to procces the dataframe by user
library(package=plyr)
ddply(.data=df, .variables='User',
      .fun=function(x){
        # Complete sequence of dates for each user
        tdf <- data.frame(Measure_Date=seq(from=min(x$Measure_Date),
                                           to=max(x$Measure_Date),
                                           by='1 day'))

        # Merge to fill in NAs for unused dates
        tdf <- merge(tdf, x, all=TRUE)

        # Put desired values side by side
        tdf$Evening <- c(NA, tdf$Evening[-length(tdf$Evening)])

        # Diference
        tdf$Difference  <- tdf$Evening - tdf$Morning

        # Return desired value to original data
        tdf <- tdf[,c('Measure_Date', 'Difference')]
        x <- merge(x, tdf)
        x
      })
+2

More articles:


All Articles