## starting httpd help server ... done## Tetrahydrocortisone Pregnanetriol Type
## a1 3.1 11.70 a
## a2 3.0 1.30 a
## a3 1.9 0.10 a
## a4 3.8 0.04 a
## a5 4.1 1.10 a
## a6 1.9 0.40 a## 'data.frame': 27 obs. of 3 variables:
## $ Tetrahydrocortisone: num 3.1 3 1.9 3.8 4.1 1.9 8.3 3.8 3.9 7.8 ...
## $ Pregnanetriol : num 11.7 1.3 0.1 0.04 1.1 0.4 1 0.2 0.6 1.2 ...
## $ Type : Factor w/ 4 levels "a","b","c","u": 1 1 1 1 1 1 2 2 2 2 ...## Type Tetrahydrocortisone Pregnanetriol
## 1 a 2.966667 2.44
## 2 b 8.180000 1.12
## 3 c 19.720000 5.50
## 4 u 14.016667 1.20# method 2
#In order to understand and review it,I disassemble it step by step.
dta<-split(Cushings[,-3], Cushings$Type)
head(dta)## $a
## Tetrahydrocortisone Pregnanetriol
## a1 3.1 11.70
## a2 3.0 1.30
## a3 1.9 0.10
## a4 3.8 0.04
## a5 4.1 1.10
## a6 1.9 0.40
##
## $b
## Tetrahydrocortisone Pregnanetriol
## b1 8.3 1.0
## b2 3.8 0.2
## b3 3.9 0.6
## b4 7.8 1.2
## b5 9.1 0.6
## b6 15.4 3.6
## b7 7.7 1.6
## b8 6.5 0.4
## b9 5.7 0.4
## b10 13.6 1.6
##
## $c
## Tetrahydrocortisone Pregnanetriol
## c1 10.2 6.4
## c2 9.2 7.9
## c3 9.6 3.1
## c4 53.8 2.5
## c5 15.8 7.6
##
## $u
## Tetrahydrocortisone Pregnanetriol
## u1 5.1 0.4
## u2 12.9 5.0
## u3 13.0 0.8
## u4 2.6 0.1
## u5 30.0 0.1
## u6 20.5 0.8##split Cushings by Type, Cushings[,-3] expresses the type that does not display in columns 3
sapply(split(Cushings[,-3], Cushings$Type), function(x) apply(x, 2, mean))## a b c u
## Tetrahydrocortisone 2.966667 8.18 19.72 14.01667
## Pregnanetriol 2.440000 1.12 5.50 1.20000##Then compute the mean With Pregnanetriol and Tetrahydrocortisone by Type. as shown above.
# method 3
##
?do.call
## "do.call" constructs and executes a function call from a name or a function and a list of arguments to be passed to it.
##
do.call("rbind", as.list(
by(Cushings, list(Cushings$Type), function(x) {
y <- subset(x, select = -Type)
apply(y, 2, mean)
}
)))## Tetrahydrocortisone Pregnanetriol
## a 2.966667 2.44
## b 8.180000 1.12
## c 19.720000 5.50
## u 14.016667 1.20## if I delete "apply(y, 2, mean)",then we can see
do.call("rbind", as.list(
by(Cushings, list(Cushings$Type), function(x) {
y <- subset(x, select = -Type) })))## Tetrahydrocortisone Pregnanetriol
## a.a1 3.1 11.70
## a.a2 3.0 1.30
## a.a3 1.9 0.10
## a.a4 3.8 0.04
## a.a5 4.1 1.10
## a.a6 1.9 0.40
## b.b1 8.3 1.00
## b.b2 3.8 0.20
## b.b3 3.9 0.60
## b.b4 7.8 1.20
## b.b5 9.1 0.60
## b.b6 15.4 3.60
## b.b7 7.7 1.60
## b.b8 6.5 0.40
## b.b9 5.7 0.40
## b.b10 13.6 1.60
## c.c1 10.2 6.40
## c.c2 9.2 7.90
## c.c3 9.6 3.10
## c.c4 53.8 2.50
## c.c5 15.8 7.60
## u.u1 5.1 0.40
## u.u2 12.9 5.00
## u.u3 13.0 0.80
## u.u4 2.6 0.10
## u.u5 30.0 0.10
## u.u6 20.5 0.80## if I delete -Type in select , then type will display
do.call("rbind", as.list(
by(Cushings, list(Cushings$Type), function(x) {
y <- subset(x, select = ) })))## Tetrahydrocortisone Pregnanetriol Type
## a.a1 3.1 11.70 a
## a.a2 3.0 1.30 a
## a.a3 1.9 0.10 a
## a.a4 3.8 0.04 a
## a.a5 4.1 1.10 a
## a.a6 1.9 0.40 a
## b.b1 8.3 1.00 b
## b.b2 3.8 0.20 b
## b.b3 3.9 0.60 b
## b.b4 7.8 1.20 b
## b.b5 9.1 0.60 b
## b.b6 15.4 3.60 b
## b.b7 7.7 1.60 b
## b.b8 6.5 0.40 b
## b.b9 5.7 0.40 b
## b.b10 13.6 1.60 b
## c.c1 10.2 6.40 c
## c.c2 9.2 7.90 c
## c.c3 9.6 3.10 c
## c.c4 53.8 2.50 c
## c.c5 15.8 7.60 c
## u.u1 5.1 0.40 u
## u.u2 12.9 5.00 u
## u.u3 13.0 0.80 u
## u.u4 2.6 0.10 u
## u.u5 30.0 0.10 u
## u.u6 20.5 0.80 u##Conclusion:The method 3 use rbind and list Cushings by Type,then use apply compute the mean
# method 4
## Application of dplyr
##Use group_by classfy the Cushings by type.Second,summarize it to compute mean
Cushings %>%
group_by(Type) %>%
summarize( t_m = mean(Tetrahydrocortisone), p_m = mean(Pregnanetriol))## # A tibble: 4 x 3
## Type t_m p_m
## <fct> <dbl> <dbl>
## 1 a 2.97 2.44
## 2 b 8.18 1.12
## 3 c 19.7 5.5
## 4 u 14.0 1.2# method 5
##
##nest() creates a list of data frames containing all the nested variables
#try it to understand
a<-Cushings %>%
nest(-Type)## Warning: All elements of `...` must be named.
## Did you want `data = c(Tetrahydrocortisone, Pregnanetriol)`?## # A tibble: 4 x 2
## Type data
## <fct> <list>
## 1 a <tibble [6 x 2]>
## 2 b <tibble [10 x 2]>
## 3 c <tibble [5 x 2]>
## 4 u <tibble [6 x 2]>#we can see the list by a
#
##mutate add new variable by column
Cushings %>%
nest(-Type) %>%
mutate(avg = map(data, ~ apply(., 2, mean)),
res_1 = map_dbl(avg, "Tetrahydrocortisone"),
res_2 = map_dbl(avg, "Pregnanetriol")) ## Warning: All elements of `...` must be named.
## Did you want `data = c(Tetrahydrocortisone, Pregnanetriol)`?## # A tibble: 4 x 5
## Type data avg res_1 res_2
## <fct> <list> <list> <dbl> <dbl>
## 1 a <tibble [6 x 2]> <dbl [2]> 2.97 2.44
## 2 b <tibble [10 x 2]> <dbl [2]> 8.18 1.12
## 3 c <tibble [5 x 2]> <dbl [2]> 19.7 5.5
## 4 u <tibble [6 x 2]> <dbl [2]> 14.0 1.2