Data Manipulation - Apply Functions

Table of Contents

• Install or Load Libraries

• Download the Data

• apply() Functions

  • Row Level apply()
  • Column Level apply()
  • Using Custom Functions

• tapply() Functions

  • Running by Specific Attribute Levels
  • 2X2 Tables

• lapply()

  • Create a New List

• sapply()

  • Simple Multiplication of Each Elements of A by 10
  • Calculate the Quantiles for Each Variable in the iris Dataset

• aggregate()

  • Compute the mean of all variables by factors

• sweep()

Install or Load Libraries

Download the Data

rm(list=ls())
RawDataset =iris #read.table(file = file.choose())
head(RawDataset)

NewData = subset(RawDataset, select = c("Sepal.Length","Sepal.Width","Petal.Length","Petal.Width"))

ProductDataSet = read.csv(file = file.choose(), header = TRUE)
colnames(ProductDataSet)=c("Product","Color","Price")
head(ProductDataSet)

apply() function

Row-Level apply()

RowApply = apply(X=NewData, MARGIN = 1, FUN = mean)
head(RowApply)

    1     2     3     4     5     6 
2.550 2.375 2.350 2.350 2.550 2.850 

Column-Level apply()

ColumnApply = apply(X=NewData, MARGIN = 2, FUN = mean)
ColumnApply

Sepal.Length  Sepal.Width Petal.Length  Petal.Width 
    5.843333     3.057333     3.758000     1.199333 

Using Custom Functions

ColumnApply = apply(X=NewData, MARGIN = 2, FUN = function(x) sum(x)/length(x))
ColumnApply

Sepal.Length  Sepal.Width Petal.Length  Petal.Width 
    5.843333     3.057333     3.758000     1.199333 

tapply() function

Running by Specific Attribute Levels

with(iris, tapply(X = Sepal.Length,INDEX = Species,FUN = mean))

    setosa versicolor  virginica 
     5.006      5.936      6.588 

2X2 Tables

with(ProductDataSet, tapply(X=Price, INDEX = list(Product,Color), FUN = mean))

                               Black    Blue     Multi       Red White
AWC Logo Cap                      NA      NA  8.759467        NA    NA
HL Road Frame - Red, 44           NA      NA        NA 1332.1078    NA
HL Road Frame - Red, 48           NA      NA        NA 1332.1078    NA
HL Road Frame - Red, 52           NA      NA        NA 1332.1078    NA
HL Road Frame - Red, 56           NA      NA        NA 1332.1078    NA
HL Road Frame - Red, 62           NA      NA        NA 1332.1078    NA
LL Road Frame - Black, 58   313.8061      NA        NA        NA    NA
LL Road Frame - Black, 60   313.8061      NA        NA        NA    NA
LL Road Frame - Black, 62   313.8061      NA        NA        NA    NA
Long-Sleeve Logo Jersey, L        NA      NA 48.708200        NA    NA
Long-Sleeve Logo Jersey, M        NA      NA 48.708200        NA    NA
Long-Sleeve Logo Jersey, S        NA      NA 48.708200        NA    NA
Long-Sleeve Logo Jersey, XL       NA      NA 48.708200        NA    NA
Mountain Bike Socks, L            NA      NA        NA        NA   9.5
Mountain Bike Socks, M            NA      NA        NA        NA   9.5
Sport-100 Helmet, Black      34.0928      NA        NA        NA    NA
Sport-100 Helmet, Blue            NA 34.0928        NA        NA    NA
Sport-100 Helmet, Red             NA      NA        NA   34.0928    NA

lapply() function

lapply() returns a list of the same length as X, each element of which is the result of applying FUN to the corresponding element of X.

Create a New List

x = list(A = 1:2, Beta = exp(-3:3), Logic = c(TRUE,FALSE,FALSE,TRUE))
data = x$A

Simple Multiplication of Each Elements of A by 10

The output is a list() but the unlist() function will tranform the output into a vector.

new = lapply(X=x$A, FUN = function(x) (x*10))
Report = data.frame(Original = unlist(x$A),Transformed = unlist(new))
Report

sapply() function

Simple Multiplication of Each Elements of A by 10

data = iris$Sepal.Length
new = sapply(X= data, FUN = function(x) (x*10))
Report = data.frame(Original = data, Transformed = new)
head(Report)

Simple Multiplication of Each Elements of A by 10

data = iris$Sepal.Length
Report = quantile(x = data)
Report

  0%  25%  50%  75% 100% 
 4.3  5.1  5.8  6.4  7.9 

Calculate the Quantiles for Each Variable in the iris Dataset

data = iris[,1:4]
Report = sapply(X = data, FUN = quantile)
Report

     Sepal.Length Sepal.Width Petal.Length Petal.Width
0%            4.3         2.0         1.00         0.1
25%           5.1         2.8         1.60         0.3
50%           5.8         3.0         4.35         1.3
75%           6.4         3.3         5.10         1.8
100%          7.9         4.4         6.90         2.5

Calculate a specific Quantile (.75) for Each Variable in the iris Dataset

data = iris[,1:4]
Report = sapply(X = data, FUN = quantile, probs = 0.75)
Report

Sepal.Length.75%  Sepal.Width.75% Petal.Length.75%  Petal.Width.75% 
             6.4              3.3              5.1              1.8 

aggregate() function

Using aggregate() with vectors

data = subset(iris,select=c("Sepal.Length","Species"))
Report = as.data.frame(with(data, aggregate(Sepal.Length, by=list(Species), FUN="mean")))
colnames(Report) = c("Species","Mean")
Report

Using aggregate() through formula objects

data = ProductDataSet
Report = with(ProductDataSet, aggregate(Price~Product+Color, data = iris, FUN ="mean"))
colnames(Report) = c("Product","Color","Average Price")
head(Report)

Compute the mean of all variables by factors

Data = iris
Report = with(Data,aggregate(. ~Species, data = iris, FUN ="mean"))
Report

sweep() function

data = matrix(0,ncol =6, nrow = 6)
data

     [,1] [,2] [,3] [,4] [,5] [,6]
[1,]    0    0    0    0    0    0
[2,]    0    0    0    0    0    0
[3,]    0    0    0    0    0    0
[4,]    0    0    0    0    0    0
[5,]    0    0    0    0    0    0
[6,]    0    0    0    0    0    0

Report = sweep(x=data, MARGIN = 1, STATS = 1, FUN = "+")
Report

     [,1] [,2] [,3] [,4] [,5] [,6]
[1,]    1    1    1    1    1    1
[2,]    1    1    1    1    1    1
[3,]    1    1    1    1    1    1
[4,]    1    1    1    1    1    1
[5,]    1    1    1    1    1    1
[6,]    1    1    1    1    1    1