summarize groups into intervals using dplyr

Question

H, I have a data frame like this:

d <- data.frame(v1=seq(0,9.9,0.1),
            v2=rnorm(100),
            v3=rnorm(100))

> head(d)
   v1          v2         v3
1 0.0 -0.01431916 -0.5005415
2 0.1 -1.01575590  1.5307473
3 0.2  1.00081065 -0.1730830
4 0.3 -1.20697918  0.5105118
5 0.4 -2.16698578 -1.0120544
6 0.5  0.33886508  0.4797016

I now want a new data frame that summarizes all values in the intervals 0-0.99, 1-1.99, 2-2.99, 3-3.99,.... by the mean for example

like this

start end mean.v2 mean.v3
    0   1     0.2     0.1
    1   2     0.5     0.4

and so on

thanks

Update I should add that in my real data set the observations in each interval are of different lengths and they don't always start at zero or end at 10

Answer 1

here is one way using cut() as suggested by @akrun:

d %>% mutate( ints = cut(v1 ,breaks = 11)) %>% 
   group_by(ints) %>% 
   summarise( mean.v2 = mean(v2) , mean.v3 = mean(v3) )

Answer 2

Based on @David H"s answer, with 2 options to choose from:

1. Generate intervals with cut() using a vector of breaks
2. Generate intervals with floor() instead of cut()

Create data

set.seed(33)
d <- data.frame(v1=seq(0,9.9,0.1),
            v2=rnorm(100),
            v3=rnorm(100))

Generate intervals with cut() using a vector of breaks

For that simple example you could use breaks <- 0:10 but to be more general let's take the min and max of d$v1 .

breaks <- floor(min(d$v1)):ceiling(max(d$v1))
breaks 
# [1]  0  1  2  3  4  5  6  7  8  9 10

Summarise over intervals 0-0.99, 1-1.99, 2-2.99, 3-3.99,....

d %>% 
    mutate(interval = cut(v1,
                          breaks, 
                          include.lowest = TRUE, 
                          right = FALSE)) %>%
    group_by(interval) %>% 
    summarise( mean.v2 = mean(v2) , mean.v3 = mean(v3))

# Source: local data frame [10 x 3]
# 
#    interval     mean.v2     mean.v3
#      (fctr)       (dbl)       (dbl)
# 1     [0,1) -0.13040624 -0.20781247
# 2     [1,2)  0.26505794  0.51990167
# 3     [2,3)  0.13451628  1.12066174
# 4     [3,4)  0.23451272 -0.14773437
# 5     [4,5)  0.34326922  0.28567969
# 6     [5,6) -0.77059944 -0.16629580
# 7     [6,7) -0.17617190  0.03320797
# 8     [7,8)  0.86550135 -0.24664350
# 9     [8,9) -0.06652047 -0.27798769
# 10   [9,10] -0.10424865  0.24060163

Generate intervals with floor() instead of cut()

Cheat a little bit by subtracting a tiny number 1e-9 from the end of each interval.

d %>% 
    mutate(start = floor(v1), end = start + 1 - 1e-9 ) %>%
    group_by(start, end) %>% 
    summarise_each(funs(mean))

# Source: local data frame [10 x 4]
# Groups: start [?]
# 
#    start   end     mean.v2     mean.v3
#    (dbl) (dbl)       (dbl)       (dbl)
# 1      0     1 -0.13040624 -0.20781247
# 2      1     2  0.26505794  0.51990167
# 3      2     3  0.13451628  1.12066174
# 4      3     4  0.23451272 -0.14773437
# 5      4     5  0.34326922  0.28567969
# 6      5     6 -0.77059944 -0.16629580
# 7      6     7 -0.17617190  0.03320797
# 8      7     8  0.86550135 -0.24664350
# 9      8     9 -0.06652047 -0.27798769
# 10     9    10 -0.10424865  0.24060163

Answer 3

Using the floor() and ceiling() functions. And the ifelse() in cases where the interval is 1 - 1 or 2 - 2 for example.

d<-data.frame(v1=seq(0,9.9,0.1),
              v2=rnorm(100),
              v3=rnorm(100))          

library(dplyr)

d%>%
        mutate(start=floor(v1),
               end=ifelse(ceiling(v1)==start,start+1,ceiling(v1)))%>%
        group_by(start,end)%>%
        summarise(mean.v2=mean(v2),
                  mean.v3=mean(v3))

Source: local data frame [10 x 4]
Groups: start [?]

   start   end      mean.v2     mean.v3
   (dbl) (dbl)        (dbl)       (dbl)
1      0     1  0.135180183 -0.36083298
2      1     2 -0.245567899  0.26827020
3      2     3 -0.051136441  0.14211666
4      3     4  0.252451303  0.38530797
5      4     5  0.007209073  0.30137345
6      5     6 -0.307008690  0.07662942
7      6     7  0.103271270  0.14734865
8      7     8  0.016753997 -0.02559756
9      8     9 -0.199958098 -0.21821830
10     9    10  0.532339512 -0.46509108

The same but including a column named intervals instead of two (start and end):

d%>%
        mutate(start=floor(v1),
               end=ifelse(ceiling(v1)==start,start+1,ceiling(v1)),
               interval=paste(start,"-",end))%>%
        select(-start,-end)%>%
        group_by(interval)%>%
        summarise(mean.v2=mean(v2),
                  mean.v3=mean(v3))

Source: local data frame [10 x 3]

   interval      mean.v2     mean.v3
      (chr)        (dbl)       (dbl)
1     0 - 1  0.135180183 -0.36083298
2     1 - 2 -0.245567899  0.26827020
3     2 - 3 -0.051136441  0.14211666
4     3 - 4  0.252451303  0.38530797
5     4 - 5  0.007209073  0.30137345
6     5 - 6 -0.307008690  0.07662942
7     6 - 7  0.103271270  0.14734865
8     7 - 8  0.016753997 -0.02559756
9     8 - 9 -0.199958098 -0.21821830
10   9 - 10  0.532339512 -0.46509108