#
# Unit 8 - Data frames 
#
# Producing data frames by combining vectors
#



# Two important changes in our work. 

# First change: dimensions of data structure. 

# Vector is a one-dimensional collection 
id <- c(1, 2, 3, 4)
gender <- c(2, 2, 1, 2)
educ <- c(12, 12, 15, 10)
salary <- c(11912.44, 10753.82, 5113.94, 8883.05)

# In R we can store data in 
# two-dimensional collections. 
# data frame is one type of such collections. 
# One way to produce it: 
# The function data.frame() 
employees <- data.frame(id, gender, educ, salary)
print(employees)

# Much of our discussion will be 
# devoted to manipulations in this 
# data structure. 
# Many of these manipulations will 
# be carried out using the library dplyr. 
print(employees)
print(class(employees))

# Note that in principle 
# the combined vectors must have 
# the same length. 
employees <- data.frame(id, 1:99)


# In principle - because 
# in some cases R find 
# suitable solutions. 
employees <- data.frame(id, 1:100)
print(employees)


# Other ways to combine vectors 

# cbind() - combine as columns
employees <- cbind(id, gender, educ, salary)
print(employees)
print(class(employees))
newEmployees <- data.frame(employees)
print(newEmployees)
print(class(newEmployees))


# rbind() - combine as rows
id <- c(1, 2, 3, 4)
gender <- c(2, 2, 1, 2)
educ <- c(12, 12, 15, 10)
salary <- c(11912.44, 10753.82, 5113.94, 8883.05)
employees <- rbind(id, gender, educ, salary)
print(employees)
print(class(employees))
newEmployees <- data.frame(employees)
print(newEmployees)
print(class(newEmployees))


# Second change: source of data. 

# So far the data was provided by us. 
id <- c(1, 2, 3, 4)
gender <- c(2, 2, 1, 2)
educ <- c(12, 12, 15, 10)
salary <- c(11912.44, 10753.82, 5113.94, 8883.05)

# From now on, the data will also 
# be received from an external source, 
# specifically files.