Chapter 9 Group Manipulation
Lander's chapter 11 Group Manipulation
###############################
#chapter 11 group manipulation#
###############################
library(tidyverse)
library(dplyr)
library(plyr)
#notes: pay attention to arguments orders
#in aggregate, aggregate(variable~group, data, function)
#in ddply, ddply(data, .variable, .function)
rm(list = ls())
#tapply, lapply, mapply
#apply must be used on matrix (same type)
#margin 1: operate over the rows; 2: operate over the columns
theMatrix <- matrix(1:9, nrow = 3)
theMatrix## [,1] [,2] [,3]
## [1,] 1 4 7
## [2,] 2 5 8
## [3,] 3 6 9apply(theMatrix, 1, sum)## [1] 12 15 18apply(theMatrix, 2, sum)## [1] 6 15 24rowSums(theMatrix)## [1] 12 15 18colSums(theMatrix)## [1] 6 15 24theMatrix[2,1] <- NA
apply(theMatrix, 1, sum)## [1] 12 NA 18apply(theMatrix, 1, sum, na.rm=T)## [1] 12 13 18rowSums(theMatrix)## [1] 12 NA 18rowSums(theMatrix, na.rm = T)## [1] 12 13 18#example used in my research (can write your own function)
#ties$noofsenders <- apply(ties[ ,11:15], MARGIN = 1,
# FUN = function(x) length(x[!is.na(x)]))
#lapply and sapply
#lapply is used in list; operate on each element
theList <- list(A=matrix(1:9, 3), B=1:5, C=matrix(1:4, 2), D=2)
lapply(theList, sum)## $A
## [1] 45
##
## $B
## [1] 15
##
## $C
## [1] 10
##
## $D
## [1] 2#sapply return the result of lapply as a vector instead
sapply(theList, sum)## A B C D
## 45 15 10 2theNames <- c("Jared", "Deb", "Paul")
lapply(theNames, nchar)## [[1]]
## [1] 5
##
## [[2]]
## [1] 3
##
## [[3]]
## [1] 4#mapply applies a function to each element of multiple lists
firstList <- list(A=matrix(1:16, 4), B=matrix(1:16, 2), C=1:5)
secondList <- list(A=matrix(1:16, 4), B=matrix(1:16, 8), C=15:1)
mapply(identical, firstList, secondList)## A B C
## TRUE FALSE FALSE#aggregate
#check the diamonds data
require(ggplot2)
data("diamonds")
head(diamonds)## # A tibble: 6 x 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.23 Ideal E SI2 61.5 55 326 3.95 3.98 2.43
## 2 0.21 Premium E SI1 59.8 61 326 3.89 3.84 2.31
## 3 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 4 0.290 Premium I VS2 62.4 58 334 4.2 4.23 2.63
## 5 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
## 6 0.24 Very Good J VVS2 62.8 57 336 3.94 3.96 2.48#first part: formula specifying how our data are organized; second: data; third:function
aggregate(price~cut, diamonds, mean)## cut price
## 1 Fair 4358.758
## 2 Good 3928.864
## 3 Very Good 3981.760
## 4 Premium 4584.258
## 5 Ideal 3457.542#aggregate by two variables
aggregate(price~cut+color, diamonds, mean)## cut color price
## 1 Fair D 4291.061
## 2 Good D 3405.382
## 3 Very Good D 3470.467
## 4 Premium D 3631.293
## 5 Ideal D 2629.095
## 6 Fair E 3682.312
## 7 Good E 3423.644
## 8 Very Good E 3214.652
## 9 Premium E 3538.914
## 10 Ideal E 2597.550
## 11 Fair F 3827.003
## 12 Good F 3495.750
## 13 Very Good F 3778.820
## 14 Premium F 4324.890
## 15 Ideal F 3374.939
## 16 Fair G 4239.255
## 17 Good G 4123.482
## 18 Very Good G 3872.754
## 19 Premium G 4500.742
## 20 Ideal G 3720.706
## 21 Fair H 5135.683
## 22 Good H 4276.255
## 23 Very Good H 4535.390
## 24 Premium H 5216.707
## 25 Ideal H 3889.335
## 26 Fair I 4685.446
## 27 Good I 5078.533
## 28 Very Good I 5255.880
## 29 Premium I 5946.181
## 30 Ideal I 4451.970
## 31 Fair J 4975.655
## 32 Good J 4574.173
## 33 Very Good J 5103.513
## 34 Premium J 6294.592
## 35 Ideal J 4918.186#tidyverse
names(diamonds)## [1] "carat" "cut" "color" "clarity" "depth" "table" "price" "x" "y"
## [10] "z"pricestats <- diamonds %>%
group_by(cut)
pricestats## # A tibble: 53,940 x 10
## # Groups: cut [5]
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.23 Ideal E SI2 61.5 55 326 3.95 3.98 2.43
## 2 0.21 Premium E SI1 59.8 61 326 3.89 3.84 2.31
## 3 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 4 0.290 Premium I VS2 62.4 58 334 4.2 4.23 2.63
## 5 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
## 6 0.24 Very Good J VVS2 62.8 57 336 3.94 3.96 2.48
## 7 0.24 Very Good I VVS1 62.3 57 336 3.95 3.98 2.47
## 8 0.26 Very Good H SI1 61.9 55 337 4.07 4.11 2.53
## 9 0.22 Fair E VS2 65.1 61 337 3.87 3.78 2.49
## 10 0.23 Very Good H VS1 59.4 61 338 4 4.05 2.39
## # … with 53,930 more rowspricestats2 <- diamonds %>%
group_by(cut, color)
pricestats2## # A tibble: 53,940 x 10
## # Groups: cut, color [35]
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.23 Ideal E SI2 61.5 55 326 3.95 3.98 2.43
## 2 0.21 Premium E SI1 59.8 61 326 3.89 3.84 2.31
## 3 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 4 0.290 Premium I VS2 62.4 58 334 4.2 4.23 2.63
## 5 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
## 6 0.24 Very Good J VVS2 62.8 57 336 3.94 3.96 2.48
## 7 0.24 Very Good I VVS1 62.3 57 336 3.95 3.98 2.47
## 8 0.26 Very Good H SI1 61.9 55 337 4.07 4.11 2.53
## 9 0.22 Fair E VS2 65.1 61 337 3.87 3.78 2.49
## 10 0.23 Very Good H VS1 59.4 61 338 4 4.05 2.39
## # … with 53,930 more rows#aggregate two variables
aggregate(cbind(price, carat)~cut, diamonds, mean)## cut price carat
## 1 Fair 4358.758 1.0461366
## 2 Good 3928.864 0.8491847
## 3 Very Good 3981.760 0.8063814
## 4 Premium 4584.258 0.8919549
## 5 Ideal 3457.542 0.7028370aggregate(cbind(price, carat)~cut+color, diamonds, mean)## cut color price carat
## 1 Fair D 4291.061 0.9201227
## 2 Good D 3405.382 0.7445166
## 3 Very Good D 3470.467 0.6964243
## 4 Premium D 3631.293 0.7215471
## 5 Ideal D 2629.095 0.5657657
## 6 Fair E 3682.312 0.8566071
## 7 Good E 3423.644 0.7451340
## 8 Very Good E 3214.652 0.6763167
## 9 Premium E 3538.914 0.7177450
## 10 Ideal E 2597.550 0.5784012
## 11 Fair F 3827.003 0.9047115
## 12 Good F 3495.750 0.7759296
## 13 Very Good F 3778.820 0.7409612
## 14 Premium F 4324.890 0.8270356
## 15 Ideal F 3374.939 0.6558285
## 16 Fair G 4239.255 1.0238217
## 17 Good G 4123.482 0.8508955
## 18 Very Good G 3872.754 0.7667986
## 19 Premium G 4500.742 0.8414877
## 20 Ideal G 3720.706 0.7007146
## 21 Fair H 5135.683 1.2191749
## 22 Good H 4276.255 0.9147293
## 23 Very Good H 4535.390 0.9159485
## 24 Premium H 5216.707 1.0164492
## 25 Ideal H 3889.335 0.7995249
## 26 Fair I 4685.446 1.1980571
## 27 Good I 5078.533 1.0572222
## 28 Very Good I 5255.880 1.0469518
## 29 Premium I 5946.181 1.1449370
## 30 Ideal I 4451.970 0.9130291
## 31 Fair J 4975.655 1.3411765
## 32 Good J 4574.173 1.0995440
## 33 Very Good J 5103.513 1.1332153
## 34 Premium J 6294.592 1.2930941
## 35 Ideal J 4918.186 1.0635937