#String length
nchar("codiac")

#Combine strings
str_c("patient ", c("a", "b", "c"))

#Sort values in a string
x <- c("carrot", "apple", "banana")
sort(x)

#String length
6

#Combine strings
"patient a" "patient b" "patient c"

#Sort values in a string
"apple" "banana" "carrot"

#Assigning values to variables
n1 = 7
n2 = 3
#Testing operators
cat(n1, "+", n2, "=", n1 + n2, "\n")			# Addition
cat(n1, "-", n2, "=", n1 - n2, "\n")			# Subtraction
cat(n1, "*", n2, "=", n1 * n2, "\n")			# Multiplication
cat(n1, "/", n2, "=", n1 / n2, "\n")			# Division
cat(n1, "/", n2, "=", sprintf("%.2f", n1 / n2), "\n") 	# Print to 2 decimal places
cat(n1, "^", n2, "=", n1 ^ n2, "\n")			# Power/Exponent
cat(n1, "%%", n2, "=", n1 %% n2, "\n")		        # Remainder/Modulo

7 + 3 = 10 
7 - 3 = 4 
7 * 3 = 21 
7 / 3 = 2.333333 
7 / 3 = 2.33 
7 ^ 3 = 343 
7 %% 3 = 1

#This is a single line comment
print("Hello, World!")

"Hello, World!"

#Assign three colors to the "apple" variable
apple <- c('red','green','yellow')

print(apple)

#Get the class of the vector (with and without print statement)
print(class(apple))
class(apple)

"red"  "green"  "yellow"
"character"
"character"

#If the dataset is already loaded into the R directory
read.csv("hospital_data.csv")
read_table("hospital_data.txt")

#To add a new dataset from machine downloads to directory (Mac)
read.csv("/users/username/Downloads/hospital_data.csv")
read_table("/users/username/Downloads/hospital_data.txt")

#To add a new dataset from machine desktop to directory (Windows)
read.csv("C:\\Users\\username\\Desktop\\hospital_data.csv")
read_table("C:\\Users\\username\\Desktop\\hospital_data.txt")

#Note that forward slashes are used on Mac and backwards slashes are used by Windows

#To output a file as a .txt file:
sink("hospital_data.txt")

#To output a file as a .csv file:
sink("hospital_data.csv")

#Create list
mylist <- list("apple", "peach", "plum")

#Access the second element of a list
mylist[2]

#Change the value of the first element of a list
mylist[1] <- "banana"
mylist

#See the number of values in a list
length(mylist)

#Check if item exists in list
"plum" %in% mylist

#Add an item to the list
append(mylist, "orange", after=2)
mylist

#Remove an item at index=3 from a list
mylist <- list("apple", "peach", "plum")
newlist <- mylist[-3]
newlist

#Access the second element of a list
"peach"

#Change the value of the first element of a list
[[1]]
[1] "banana"

[[2]]
[1] "peach"

[[3]]
[1] "plum"

#See the number of values in a list
3

#Check if item exists in list
TRUE

#Add an item to the list
[[1]]
[1] "banana"

[[2]]
[1] "peach"

[[3]]
[1] "orange"

[[4]]
[1] "plum"

#Remove an item from a list
[[1]]
[1] "apple"

[[2]]
[1] "peach"

#Creating array
heart <- matrix(c("left atrium", "left ventricle", 
    "right atrium", "right ventricle"), nrow=2, ncol=2)
heart

#Access element at row=1, column=2
heart[1,2]

#Access entire row 1
heart[1,]

#Access entire column 2
heart[,2]

#Create new row
heart1 <- rbind(heart, c("x", "x"))
heart1

#Create new column
heart2 -< cbind(heart1, c("y", "y", "z"))
heart2

#Creating array
     [,1]           [,2]      
[1,] "left atrium"    "right atrium"   
[2,] "left ventricle" "right ventricle"

#Access element at row=1, column=2
"right atrium"

#Access entire row 1
"left atrium"  "right atrium"

#Access entire column 2
"right atrium" "right ventricle"

#Create new row
     [,1]             [,2]             
[1,] "left atrium"    "right atrium"   
[2,] "left ventricle" "right ventricle"
[3,] "x"              "x"   

#Create new column
     [,1]             [,2]              [,3]
[1,] "left atrium"    "right atrium"    "y" 
[2,] "left ventricle" "right ventricle" "y" 
[3,] "x"              "x"               "z" 

#Creating array
a <- array(c(1:20),dim = c(4,4,2))

#Access element at row=4, column=4, dimension=1
a[4, 4, 1]

#Check if item exists in array
2 %in% a

#Sort increasing
b <- array(c(16:1),dim = c(4,4,1))
sort(b)

#Sort decreasing
c <- array(c(1:16),dim = c(4,4,1))
sort(c, decreasing = TRUE)

#Access element at row=4, column=4, dimension=1
16

#Check if item exists in array
TRUE

#Sort increasing
1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16

#Sort decreasing
16 15 14 13 12 11 10  9  8  7  6  5  4  3  2  1

#Installing a package downloaded locally
install.packages("tidyverse")

#Once the package is installed, you have to load it
library(tidyverse)

#If statement
a <- 2
b <- 1
if (a > b){
print("a is greater than b")}

#Else if statement
x <- 10
y <- 10
if (x > y){
print("x is greater than y")
} else if (x <= y){
print("x is less than or equal to y")
}

#Else statement
d <- 3
if (d > 5){
print("d is greater than 5")
} else if (d == 5){
print("d is equal to 5")
} else {
print("d is less than or equal to 5")
}

#If statement
[1] "a is greater than b"

#Else if statement
[1] "x is less than or equal to y"

#Else statement
[1] "d is less than or equal to 5"

#While loop
i <- 1
while (i < 5){
print(i)
i <- i + 1
}

#While loop with break
j <- 1
while (j < 5){
print(j)
j <- j + 1
if (j == 4){
break
}}

#For loop
fruit <- list("apple", "banana", "peach")
for (x in fruit) {
  print(x)
}

#Nested for loop
adjectives <- list("scrumptious", "overripe", "delicious")
fruit <- list("apple", "banana", "peach")
for (x in adjectives) {
    for (y in fruit) {
      print(paste(x, y))
}}

#While loop
[1] 1
[1] 2
[1] 3
[1] 4

#While loop with break
[1] 1
[1] 2
[1] 3

#For loop
[1] "apple"
[1] "banana"
[1] "peach"

#Nested for loop
[1] "scrumptious apple"
[1] "scrumptious banana"
[1] "scrumptious peach"
[1] "overripe apple"
[1] "overripe banana"
[1] "overripe peach"
[1] "delicious apple"
[1] "delicious banana"
[1] "delicious peach"

# Demonstrate comparison operators

# Assign values to variables
c1 <- 25
c2 <- 50
c3 <- 75
c4 <- 50

# Testing equality
c1 == c3
c2 == c4

# Changing values using assignment operators
c1 <- c1 * 3  # shorthand for c1 = c1 * 3
c4 <- c4 + 1  # shorthand for c4 = c4 + 1

# Testing less than and greater than
c1 < c2
c4 <= c2
c1 > c2
c3 >= c2

# Testing equality
# c1 == c3
[1] FALSE
# c2 == c4
[1] TRUE

# Testing less than and greater than
# c1 < c2
[1] FALSE
# c4 <= c2
[1] FALSE
# c1 > c2
[1] TRUE
# c3 >= c2
[1] TRUE

#Search for substring in a string
y <- c("carrot", "apple", "banana", "carrot")
grep("carrot", y)

#Replace a single value within a string
sub("r”, “R”, y)

#Replace all instances within a string
gsub(“r”, “R”, y)

#Find matches of exact strings
grepl("car", y)

#Search for value in a string
1 4
#Returns the position of the value searched for

#Replace the first instance of a single value within a string
"caRrot" "apple" "banana" "caRrot" 

#Replace all instances within a string
"caRRot" "apple" "banana" "caRRot"

#Find matches of exact strings
TRUE FALSE FALSE TRUE

#Create DataFrame
df <- data.frame(
  id = 1:5,
  gender = c("F", "M", "F", "M", "F"),
  age = c(68, 54, 49, 28, 36)
)

#Display DataFrame
df

 id gender age
1  1      F  68
2  2      M  54
3  3      F  49
4  4      M  28
5  5      F  36

#Print first two lines of DataFrame
head(df, 2)

  id gender age
1  1      F  68
2  2      M  54

# Last two lines of DataFrame
tail(df, 2)

  id gender age
4  4      M  28
5  5      F  36 

#DataFrame size
dim(df)

#First value represents number of rows, second value represents number of columns
[1] 5 3

#DataFrame column names
colnames(df)

[1] "id"     "gender" "age" 

#Describe DataFrame
summary(df)

       id       gender               age    
 Min.   :1   Length:5           Min.   :28  
 1st Qu.:2   Class :character   1st Qu.:36  
 Median :3   Mode  :character   Median :49  
 Mean   :3                      Mean   :47  
 3rd Qu.:4                      3rd Qu.:54  
 Max.   :5                      Max.   :68

#Call by column name
df$age
df[["age"]]

#Get column by column number
df[[3]]

#Call by column name
[1] 68 54 49 28 36
[1] 68 54 49 28 36

#Get column by column number
[1] 68 54 49 28 36

#Print row 2
df[2, ]

  id gender age
2  2      M  54

#Get element in row 2, column 3
df[2,3]

54

#Print out rows 1, 3, & 5
df[c(1, 3, 5), ]

  id gender age
1  1      F  68
3  3      F  49
5  5      F  36

#Print out all rows and only columns 1 (id) and 3 (age)
#Using column names
df[, c("id", "age")]

#Using column numbers
df[, c(1, 3)]

#Using column names:
  id age
1  1  68
2  2  54
3  3  49
4  4  28
5  5  36

#Using column numbers
  id age
1  1  68
2  2  54
3  3  49
4  4  28
5  5  36

#Print all rows where age is greater than 50
df[df$age > 50, ]

  id gender age
1  1      F  68
2  2      M  54

#Print all rows where gender is female ("F")
df[df$gender == "F", ]

  id gender age
1  1      F  68
3  3      F  49
5  5      F  36

#Print all rows where gender is female ("F") and age is between 25-50
df[df$gender == "F" & df$age > 25 & df$age < 50, ]

  id gender age
3  3      F  49
5  5      F  36

#Add a column for height
df$height <- c(62, 60, 61, 63, 64)

#Add a column for weight
df$weight <- c(100, 120, 150, 175, 300)

#Print DataFrame to see changes
df

#Describe DataFrame to see column names and summary
summary(df)

  id gender age height weight
1  1      F  68     62    100
2  2      M  54     60    120
3  3      F  49     61    150
4  4      M  28     63    175
5  5      F  36     64    300

#Describe dataframe to see column names and summary:
       id       gender               age         height       weight   
 Min.   :1   Length:5           Min.   :28   Min.   :60   Min.   :100  
 1st Qu.:2   Class :character   1st Qu.:36   1st Qu.:61   1st Qu.:120  
 Median :3   Mode  :character   Median :49   Median :62   Median :150  
 Mean   :3                      Mean   :47   Mean   :62   Mean   :169  
 3rd Qu.:4                      3rd Qu.:54   3rd Qu.:63   3rd Qu.:175  
 Max.   :5                      Max.   :68   Max.   :64   Max.   :300 

# add a column with calculated BMI
df$bmi <- (df$weight / (df$height^2)) * 703

#Print DataFrame to see changes
df

#Describe DataFrame to see column names and summary
summary(df)

#Updated DataFrame
    id gender age height weight      bmi
1  1      F  68     62    100 18.28824
2  2      M  54     60    120 23.43333
3  3      F  49     61    150 28.33916
4  4      M  28     63    175 30.99647
5  5      F  36     64    300 51.48926

Describe dataframe to see new bmi column and summary:
       id       gender               age         height       weight   
 Min.   :1   Length:5           Min.   :28   Min.   :60   Min.   :100  
 1st Qu.:2   Class :character   1st Qu.:36   1st Qu.:61   1st Qu.:120  
 Median :3   Mode  :character   Median :49   Median :62   Median :150  
 Mean   :3                      Mean   :47   Mean   :62   Mean   :169  
 3rd Qu.:4                      3rd Qu.:54   3rd Qu.:63   3rd Qu.:175  
 Max.   :5                      Max.   :68   Max.   :64   Max.   :300  
      bmi       
 Min.   :18.29  
 1st Qu.:23.43  
 Median :28.34  
 Mean   :30.51  
 3rd Qu.:31.00  
 Max.   :51.49  

#Get counts of males and females in the dataframe
gender_counts <- table(df$gender)
gender_counts

F M 
3 2 

#Sort the dataframe by gender then age, in reverse order for age (oldest to youngest)
df_sorted <- df[order(df$gender, -df$age), ]
df_sorted

  id gender age height weight      bmi
1  1      F  68     62    100 18.28824
3  3      F  49     61    150 28.33916
5  5      F  36     64    300 51.48926
2  2      M  54     60    120 23.43333
4  4      M  28     63    175 30.99647

#Reshape from wide to long format (exclude id column)
long_df <- reshape(df, varying = c("gender", "age", "weight", "height", "bmi"), 
                   v.names = "value", 
                   timevar = "variable", 
                   times = c("gender", "age", "weight", "height", "bmi"), 
                   direction = "long")
long_df

         id variable            value
1.gender  1   gender                F
2.gender  2   gender                M
3.gender  3   gender                F
4.gender  4   gender                M
5.gender  5   gender                F
1.age     1      age               68
2.age     2      age               54
3.age     3      age               49
4.age     4      age               28
5.age     5      age               36
1.weight  1   weight              100
2.weight  2   weight              120
3.weight  3   weight              150
4.weight  4   weight              175
5.weight  5   weight              300
1.height  1   height               62
2.height  2   height               60
3.height  3   height               61
4.height  4   height               63
5.height  5   height               64
1.bmi     1      bmi 18.2882414151925
2.bmi     2      bmi 23.4333333333333
3.bmi     3      bmi 28.3391561408224
4.bmi     4      bmi 30.9964726631393
5.bmi     5      bmi    51.4892578125

#Unstack dataframe to return to wide format based off "id"
wide_df <- reshape(long_df, idvar = "id", timevar = "variable", direction = "wide")
wide_df

         id value.gender value.age value.weight value.height        value.bmi
1.gender  1            F        68          100           62 18.2882414151925
2.gender  2            M        54          120           60 23.4333333333333
3.gender  3            F        49          150           61 28.3391561408224
4.gender  4            M        28          175           63 30.9964726631393
5.gender  5            F        36          300           64    51.4892578125

#Size of dataframe = size(df)
#Set number of rows to nrows and number of columns to ncols
nrows <- nrow(df)
ncols <- ncol(df)

cat("(nrows, ncols) = ", nrows, ncols, "\n")

#Use nested for loop to get information from DataFrame by row and column
for (row in 1:nrows) {
  for (col in 1:ncols) {
    cat("value for row", row, "and col", col, "is", df[row, col], "\n")
  }
}

(nrows, ncols) =  5 6 
value for row 1 and col 1 is 1 
value for row 1 and col 2 is F 
value for row 1 and col 3 is 68 
value for row 1 and col 4 is 62 
value for row 1 and col 5 is 100 
value for row 1 and col 6 is 18.28824 
value for row 2 and col 1 is 2 
value for row 2 and col 2 is M 
value for row 2 and col 3 is 54 
value for row 2 and col 4 is 60 
value for row 2 and col 5 is 120 
value for row 2 and col 6 is 23.43333 
value for row 3 and col 1 is 3 
value for row 3 and col 2 is F 
value for row 3 and col 3 is 49 
value for row 3 and col 4 is 61 
value for row 3 and col 5 is 150 
value for row 3 and col 6 is 28.33916 
value for row 4 and col 1 is 4 
value for row 4 and col 2 is M 
value for row 4 and col 3 is 28 
value for row 4 and col 4 is 63 
value for row 4 and col 5 is 175 
value for row 4 and col 6 is 30.99647 
value for row 5 and col 1 is 5 
value for row 5 and col 2 is F 
value for row 5 and col 3 is 36 
value for row 5 and col 4 is 64 
value for row 5 and col 5 is 300 
value for row 5 and col 6 is 51.48926 

#Load tidyverse and required modulees
install.packages("tidyverse")
library(tidyverse)
library(dplyr)
library(tidyr)

#Create DataFrame
df <- tibble(
  id = 1:5,
  gender = c("F", "M", "F", "M", "F"),
  age = c(68, 54, 49, 28, 36)
  )
df

#A tibble: 5 × 3
     id gender   age
  <int> <chr>  <dbl>
1     1 F         68
2     2 M         54
3     3 F         49
4     4 M         28
5     5 F         36

#DataFrame size:
list(rows = nrow(df), columns = ncol(df))

#DataFrame column names
colnames(df)  

#DataFrame summary
df %>% summary()

#DataFrame size:
$rows
[1] 5

$columns
[1] 3

#DataFrame column names
[1] "id"     "gender" "age" 

#DataFrame summary
       id       gender               age    
 Min.   :1   Length:5           Min.   :28  
 1st Qu.:2   Class :character   1st Qu.:36  
 Median :3   Mode  :character   Median :49  
 Mean   :3                      Mean   :47  
 3rd Qu.:4                      3rd Qu.:54  
 Max.   :5                      Max.   :68  

# Get "age" column
df %>% select(age)

# Get row 2
df %>% slice(2)

# Get element in row 2, column 3
df %>% slice(2) %>% pull(3)

#Get subset (specific rows and all columns)
df %>% slice(c(1, 3, 5))

#Get subset (all rows and specific columns)
df %>% select(id, age)

#Get subset (all rows meeting specified criteria - numbers)
df %>% filter(age > 50)

#Get subset (all rows meeting specified criteria - strings)
df %>% filter(gender == "F")

#Get subset (all rows meeting specified criteria)
df %>% filter(gender == "F", between(age, 25, 50)

#Get "age" column
#A tibble: 5 × 1
    age
  <dbl>
1    68
2    54
3    49
4    28
5    36

#Get row 2
#A tibble: 1 × 3
     id gender   age
  <int> <chr>  <dbl>
1     2 M         54

#Get element in row 2, column 3
[1] 54

#Get subset (specific rows and all columns)
# A tibble: 3 × 3
     id gender   age
  <int> <chr>  <dbl>
1     1 F         68
2     3 F         49
3     5 F         36

#Get subset (all rows and specific columns)
# A tibble: 5 × 2
     id   age
  <int> <dbl>
1     1    68
2     2    54
3     3    49
4     4    28
5     5    36

#Get subset (all rows meeting specified criteria - numbers)
#A tibble: 2 × 3
     id gender   age
  <int> <chr>  <dbl>
1     1 F         68
2     2 M         54

#Get subset (all rows meeting specified criteria - strings)
#A tibble: 3 × 3
     id gender   age
  <int> <chr>  <dbl>
1     1 F         68
2     3 F         49
3     5 F         36

#Get subset (all rows meeting specified criteria)
#A tibble: 2 × 3
     id gender   age
  <int> <chr>  <dbl>
1     3 F         49
2     5 F         36

#New columns with specified values
df <- df %>%
  mutate(
    height = c(62, 60, 61, 63, 64),
    weight = c(100, 120, 150, 175, 300)
  )
df %>% summary()

New column with calculated value
df <- df %>%
  mutate(bmi = (weight / (height^2)) * 703)

#Describe DataFrame
df %>% summary()

#Get counts/frequency
df %>% count(gender)

#New columns with specified values
       id       gender               age         height       weight   
 Min.   :1   Length:5           Min.   :28   Min.   :60   Min.   :100  
 1st Qu.:2   Class :character   1st Qu.:36   1st Qu.:61   1st Qu.:120  
 Median :3   Mode  :character   Median :49   Median :62   Median :150  
 Mean   :3                      Mean   :47   Mean   :62   Mean   :169  
 3rd Qu.:4                      3rd Qu.:54   3rd Qu.:63   3rd Qu.:175  
 Max.   :5                      Max.   :68   Max.   :64   Max.   :300   

#New column with calculated value
       id       gender               age         height       weight   
 Min.   :1   Length:5           Min.   :28   Min.   :60   Min.   :100  
 1st Qu.:2   Class :character   1st Qu.:36   1st Qu.:61   1st Qu.:120  
 Median :3   Mode  :character   Median :49   Median :62   Median :150  
 Mean   :3                      Mean   :47   Mean   :62   Mean   :169  
 3rd Qu.:4                      3rd Qu.:54   3rd Qu.:63   3rd Qu.:175  
 Max.   :5                      Max.   :68   Max.   :64   Max.   :300  
      bmi       
 Min.   :18.29  
 1st Qu.:23.43  
 Median :28.34  
 Mean   :30.51  
 3rd Qu.:31.00  
 Max.   :51.49  

#Get counts/frequency
#A tibble: 2 × 2
  gender     n
  <chr>  <int>
1 F          3
2 M          2

#Transform DataFrame
#Sort the dataframe by gender then age (reverse for age)
df_sorted <- df %>%
  arrange(gender, desc(age))
df_sorted

#Reshape from wide to long format
long_df <- long_df %>%
           mutate(value = as.character(value))
long_df

#Reshape from long to wide format based on "id"
wide_df <- long_df %>%
  pivot_wider(names_from = variable, values_from = value)
wide_df

#Sort the dataframe by gender then age (reverse for age)
#A tibble: 5 × 6
     id gender   age height weight   bmi
  <int> <chr>  <dbl>  <dbl>  <dbl> <dbl>
1     1 F         68     62    100  18.3
2     3 F         49     61    150  28.3
3     5 F         36     64    300  51.5
4     2 M         54     60    120  23.4
5     4 M         28     63    175  31.0

#Reshape from wide to long format
       id variable            value
1.gender  1   gender                F
2.gender  2   gender                M
3.gender  3   gender                F
4.gender  4   gender                M
5.gender  5   gender                F
1.age     1      age               68
2.age     2      age               54
3.age     3      age               49
4.age     4      age               28
5.age     5      age               36
1.weight  1   weight              100
2.weight  2   weight              120
3.weight  3   weight              150
4.weight  4   weight              175
5.weight  5   weight              300
1.height  1   height               62
2.height  2   height               60
3.height  3   height               61
4.height  4   height               63
5.height  5   height               64
1.bmi     1      bmi 18.2882414151925
2.bmi     2      bmi 23.4333333333333
3.bmi     3      bmi 28.3391561408224
4.bmi     4      bmi 30.9964726631393
5.bmi     5      bmi    51.4892578125

#Reshape from long to wide format based on "id"
# A tibble: 5 × 6
     id gender age   weight height bmi             
  <int> <chr>  <chr> <chr>  <chr>  <chr>           
1     1 F      68    100    62     18.2882414151925
2     2 M      54    120    60     23.4333333333333
3     3 F      49    150    61     28.3391561408224
4     4 M      28    175    63     30.9964726631393
5     5 F      36    300    64     51.4892578125 

#Size of DataFrame
nrows <- nrow(df)
ncols <- ncol(df)

cat("(nrows, ncols) = ", nrows, ncols, "\n")

#Nested loop to traverse DataFrame
for (row in 1:nrows) {
  for (col in 1:ncols) {
    value <- df[row, col, drop = TRUE]
    cat("value for row", row, "and col", col, "is", value, "\n")
  }
}

#Size of DataFrame
(nrows, ncols) =  5 6 

#Nested loop to traverse DataFrame
value for row 1 and col 1 is 1 
value for row 1 and col 2 is F 
value for row 1 and col 3 is 68 
value for row 1 and col 4 is 62 
value for row 1 and col 5 is 100 
value for row 1 and col 6 is 18.28824 
value for row 2 and col 1 is 2 
value for row 2 and col 2 is M 
value for row 2 and col 3 is 54 
value for row 2 and col 4 is 60 
value for row 2 and col 5 is 120 
value for row 2 and col 6 is 23.43333 
value for row 3 and col 1 is 3 
value for row 3 and col 2 is F 
value for row 3 and col 3 is 49 
value for row 3 and col 4 is 61 
value for row 3 and col 5 is 150 
value for row 3 and col 6 is 28.33916 
value for row 4 and col 1 is 4 
value for row 4 and col 2 is M 
value for row 4 and col 3 is 28 
value for row 4 and col 4 is 63 
value for row 4 and col 5 is 175 
value for row 4 and col 6 is 30.99647 
value for row 5 and col 1 is 5 
value for row 5 and col 2 is F 
value for row 5 and col 3 is 36 
value for row 5 and col 4 is 64 
value for row 5 and col 5 is 300 
value for row 5 and col 6 is 51.48926