Lesson 1

1+1

16/4

6^8.5

# This is my first calculation in R:

1+1

x <- 1

y <- 2+2

y

print(y)

x+y

silly_name <- 5+3

silly_name

                            # To determine the type of data object you simply ask class().

                            class
                            (silly_name)

                            another_silly_name
                            <-
                            "Hello World"
                            

class
                            (another_silly_name)

# Whenever you do not know what a function does you can ask using "?".

?class()

# To do so you aggregate values with c().

numeric_vector <- c ( 1 , 2 , 3 , 4 , 5 ) 

numeric_vector

                            # A more efficient way to create the same vector would be:

numeric_vector <- c ( 1 : 5 ) 

 numeric_vector

                            # You can create vectors with character strings, too.

character_vector <- c ( "Days" , "Months" , "Year" ) 

character_vector

# As an example, take a look at one of the in-built dataframe of R ("USArrests") that provides crime statistics of US states.

data("USArrests")

print(USArrests)

                            # To access an item in a list, just indicate its place within the vector through [ ].

character_vector <- c("Days", "Months", "Year")

character_vector[2]

# If you are unsure about the location of given information in a list, use the which() function.

which(character_vector == "Months")

# So when you want to access data on "Arkansas" (4th row) on "Murder" (1st column), you would write:

USArrests[4,1]

# If you are interested in all columns for Arkansas just leave the space behind the comma blank.

USArrests[4,]

# Similarly, if you are interested in murder rates for all states just leave the space in front of the comma blank.

USArrests[,1]

                            # To access only the murder rates in the USArrests dataframe, you can call the column name:

USArrests["Murder"]

# Alternatively, to access the data in a column in a dataframe we can also use the $ character:

USArrests$Murder

                            # For instance, to again get the murder rates in Arkansas, you can write:

USArrests$Murder[4]

                            # For instance, we want to create a new dataframe that only has the murder rate data.

murder_rate <- USArrests["Murder"]

# Or we want to exclude murder rates from our dataset. Then we can simply write [,-1] which will eliminate the first column.

other_crimes <- USArrests[,-1]

print(other_crimes)

                            # So if we want to merge the two datasets again, we can do:

full_dataset <- cbind(murder_rate,other_crimes)

print(full_dataset)

# Let's create the following dataset of numbers of claims per year:

year <- c(2008:2017)

claims <- c(32,45,67,98,112,77,67,98,103,88)

disputes <- data.frame(year, claims)

print(disputes)

# We can visualize that data using the plot() function.

plot(disputes)

 # Consult the R documentation to learn how the function can be further customized.

?plot()

plot(disputes$year,disputes$claims, type = "p", xlab="Year", ylab="Claims",
     main = "Claims per Year")

plot(disputes$year,disputes$claims, type = "b", col="blue", xlab="Year", ylab="Claims",
     main = "Claims per Year")

judges <- c("Parker","Parker","Parker","Colbert","Colbert","Colbert","Jones","Jones","Jones","Jones")

# Let's add the judge data to our dataframe and print the data again.

disputes <- cbind(disputes, judges)

print(disputes)

# We can add the name of the judges to the plot with the text() function.

plot(disputes$year,disputes$claims, type = "l", col="blue", xlab="Year", ylab="Claims",
     main = "Claims per Year")

text(disputes$year,disputes$claims, label=disputes$judges)

example <- "Hello World"

new_example <- paste("Hello World", "how is your day")

new_example <- paste("Hello World", "how is your day", sep=", ")

new_example

strsplit(new_example, ",")

strsplit(new_example, ",")[[1]]

# Let's first create a list of numbers from 20 to 29.

number_list <- c(20:29)

print(number_list)

for (element in number_list) { 

print(element*13)
}

length(number_list)

# So we can write: for the ranks from 1 to length of list (here 10), perform a function on each element of that rank.

for (rank in 1:length(number_list)) {print(number_list[rank]*13)}

# This yields the last value of the numbered list i.e. 29.

print(element)

# This yields the last position of the numbered list i.e. 10.

print (rank)

# This is just a sample dataframe with 3 rows and 4 columns:

sample_dataframe <- as.data.frame(matrix(data=1:12, nrow=3, ncol=4, byrow=FALSE))

print(sample_dataframe)

# FOR the rows IN row number 1 to the total number of rows in my sample_dataframe
# PRINT the SUM of each row.

for (row in 1:nrow(sample_dataframe)) {
print(sum(sample_dataframe[row,]))
}

 # To do the same thing for column sums, we just need to (1) adjust for the number of columnes (ncol) and (2) adjust the comma. Note that I also changed "row" to "col" but this is not necessary. But it helps understanding what is being done.

for (col in 1:ncol(sample_dataframe)) {print(sum(sample_dataframe[,col]))
}