R Notebook

R data structures

#Vectors ___
#Create vectors of data for three medical patients
subject_name <- c("John Doe", "Jane Doe", "Steve Graves")
temperature <- c(98.1, 98.6, 101.4)
flu_status <- c(FALSE, FALSE, TRUE)

#Access the second element in body temperature vector
temperature[2]

[1] 98.6

#Let's try creating other vectors of data with tax advisors
tax_advsior <- c("Zia, Maria, Coleen")
returns_completed <- c(12, 25, 34)

#access the first number of returns completed
returns_completed[1]

[1] 12

#Examples of accessing items in vector
#include items in the range 2 to 3
temperature[2:3]

[1]  98.6 101.4

#exclude item 2 using the minus sign
temperature[-2]

[1]  98.1 101.4

#use a vector to indicate whether to include item
temperature[c(TRUE, TRUE, FALSE)]

[1] 98.1 98.6

#examples of accesing items in vector from tax advisor example
returns_completed[2:3]

[1] 25 34

#exclude item 2 using the minus sign
returns_completed[-3]

[1] 12 25

#use a vector to indicate whether to include the item
returns_completed[c(TRUE, TRUE, FALSE)]

[1] 12 25

Factors-

#add gender factor
gender <- factor(c("MALE", "FEMALE", "MALE"))
gender

[1] MALE   FEMALE MALE  
Levels: FEMALE MALE

#Add blood type factor
blood <- factor (c("O", "AB", "A"),
                 levels = c("A", "B", "AB", "O"))
blood

[1] O  AB A 
Levels: A B AB O

#add order factor
symptoms <- factor(c("SEVERE", "MILD", "MODERATE"),
                   levels =c("MILD", "MODERATE", "SEVERE"),
                   ordered = TRUE)
symptoms

[1] SEVERE   MILD     MODERATE
Levels: MILD < MODERATE < SEVERE

#Check for symptoms greater than moderate
symptoms > "MODERATE"

[1]  TRUE FALSE FALSE

Lists -

#display infromation for a patient
subject_name[1]

[1] "John Doe"

temperature[1]

[1] 98.1

flu_status[1]

[1] FALSE

gender[1]

[1] MALE
Levels: FEMALE MALE

blood[1]

[1] O
Levels: A B AB O

symptoms[1]

[1] SEVERE
Levels: MILD < MODERATE < SEVERE

#create list for a patient
subject1 <- list(fullname = subject_name[1],
                temperature = temperature[1],
                flu_satus = flu_status[1],
                gender = gender[1],
                blood = blood[1],
                symptoms = symptoms[1])

#display the patient
subject1

$fullname
[1] "John Doe"

$temperature
[1] 98.1

$flu_satus
[1] FALSE

$gender
[1] MALE
Levels: FEMALE MALE

$blood
[1] O
Levels: A B AB O

$symptoms
[1] SEVERE
Levels: MILD < MODERATE < SEVERE

Methods for accessing a list

#get a single list value by position (retuns a sub-list)
subject1[2]

$temperature
[1] 98.1

#get a single list by value by postion (returns a numeric vector)
subject1[[2]]

[1] 98.1

#get several list items by specifying a vector of names
subject1[c("temperature", "flu_status")]

$temperature
[1] 98.1

$<NA>
NULL

Data frames

#create a data frame from medical patient data
pt_data <- data.frame(subject_name, temperature, flu_status, gender,
                      blood, symptoms, stringsAsFactors = FALSE)

#display the data frame
pt_data

NA

#accessing a data frame
#get a single colum
pt_data$subject_name

[1] "John Doe"     "Jane Doe"     "Steve Graves"

#get several columns by specifiying a vector of names
pt_data[c("temperature", "flu_status")]

#this is the same as above, extracting temperatue and flu_statues
pt_data[2:3]

#accessing by row and column
pt_data[1,2]

[1] 98.1

#accessing several rows and several columns using vectors
pt_data[c(1,3), c(2,4)]

Leave a row or column blank to extract all rows or columns

#columns 1, all rows
pt_data[,1]

[1] "John Doe"     "Jane Doe"     "Steve Graves"

#row 1, all columns
pt_data[1, ]

#all rows and all columns
pt_data[ , ]

NA

#The following are equivalent
pt_data[c(1,3), c("temperature", "gender")]

NA

pt_data[-2, c(-1, -3, -5, -6)]

NA

#creating a celsius temperature column
pt_data$temp_c <- (pt_data$temperature - 32) * (5/9)

#comparing before and after
pt_data[c("temperature", "temp_c")]

Matrixes

#create a 2X2 matrix
m <- matrix(c(1,2,3,4), nrow = 2)
m

     [,1] [,2]
[1,]    1    3
[2,]    2    4

#equivalent to the above
m <-matrix(c(1,2,3,4), ncol =2)
m

     [,1] [,2]
[1,]    1    3
[2,]    2    4

#create a 2x3 matrix
m <- matrix(c(1,2,3,4,5,6), nrow=2)
m

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

#create a 3x2 matrix
m <- matrix(c(1,2,3,4,5,6), ncol =2)
m

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

#extract values from matrixes
m[1,1]

[1] 1

m[3,2]

[1] 6

#extract rows
m[1,]

[1] 1 4

#extract columns
m[,1]

[1] 1 2 3