###############################################################
#########                Introduction to R            #########
#####               Prof. Ilaria Benedetti                #####
###############################################################

#  (#) to provide comments in green colour 
 

# --------------------------- first operations with R -----------------------
# R as calculator
2+2

4*13

(8-4)/4

6^2 #  -> control+enter (windows) oppure cmd +enter(mac)



# some function included in R ....  
# square root
sqrt(16)
#absolute value:
abs(-10)
#logaritm base e, natural logarithms,
log(10) 
#logaritm  base 10:
log10(10)





------------------------------------------------------------

# R works with objects 

# the arrow assingns the number to the object called " a " 
a <- 8
print(a) # print function shows the content of the obj 
a

# olternative way to create an object

a = 8 
8 -> a
a

# be carefull with the name !!!! R rewrite objecs with the same name 
a=6 # now object a contains n.6 
a



# Type of data ------------------------------------------------------------

# 1- Logical	(TRUE, FALSE) 	(qualitative data)
# 2- Numeric	(12.3, 5, 999	) (quantitative data)
# 3- Character	'a' , '"good", "TRUE", '23.4'	(qualitative data)

# 1-  Logical	(TRUE, FALSE)
v <- TRUE 
print(class(v)) #  class function  define type of data
v


# 2- Numeric	(12.3, 5, 999	) 
v <- 23.5 # full stop as a decimal separator 
print(class(v))




# 3-  Character: qualitative data (eg. eductional level, type of company, etc....)	

v <- "TRUE" #  please use the "" (quotes) to create charact objects 
print(class(v))




# example 
# 1 - create an object called "height" wich contains the value 180 (cm)
# 2- create an object called "civilstatus" wich contains the value married 



# Ask to R  the nature of the obj 

is.numeric(height)
is.numeric(civilstatus)
is.character(civilstatus)

mode(height)
mode(civilstatus)


# Workspace: environemnt with the create obj  --------------

ls() # all the obj in environment 
rm(a) # remove obj called "a"




# rm(list=ls())


# -------------------------------------------------------------------------------------
# type of object: 
# Vectors
# Matrices
# Factors
# Data Frames


# VECTORS 
#The simplest of these objects is the vector object and there are six data types of these atomic vectors, also termed as six classes of vectors. The other R-Objects are built upon the atomic vectors.

# vector height includes the heights of 4 individuals (in mt.)

height=c(1.87,1.75,1.68,1.9) # 
height  

# order the vector in ascending or descending orde (by default is ascending)
sort(height) 

# descending --> specify: decreasing=T
sort(height,decreasing=T)




# Character  (character, logical values of the vectors )

# create a vector includind the edu level of three individuals 
educational_level<-c("primary edu", "secondary edu", "tertiary edu")
educational_level

mode(educational_level)

# create a logial vector in which the value is equal to TRUE if a student is "in corso", FALSE is a student "is NOT in corso"
incorso<-c(TRUE,FALSE,TRUE,TRUE) #logical
incorso
mode(incorso)


# operations with vectors 

#n. of units included in the vector --> funz: lenght 

length(height) # four units 

# exercise to do 

# In a sample of 10 students, the waiting times at the canteen before being served have been collected
# observed values here: 
# 3 29 0 0 25 60 48 16 25 29

# 1- create the vector 
# 2- ask Rfor the nature 
# 3- how many units? 









# DATAFRAME  --> dataset 

# 1- set your working directory (w.d.)
setwd("~/Desktop/dataset") #set your working directory (your folder in which you stored data)

#change directory Session>Set working Directory 

# vedere working directory 
getwd()


# format of the dataframe 
# CSV 
# excel (eg. xlxs )

# CSV format
library(readr) # load this package!
my_data <- read_csv("wage.csv")

# EXCEL FORMAT 
library(readxl) # load this package!
mydata <- read_excel("wage.xlsx")



# how to see the data????

#show  fist 6 lines 
head(mydata)
#show last 6 lines 
tail(mydata)

#  info: class(), colnames(), rownames(), dim()
class(mydata)

colnames(mydata)
rownames(mydata)

dim(mydata)

# structure of the dataset
str(mydata)

#description of the data
summary(mydata)

# levels of variable Contract 
mydata$contract <-as.factor(mydata$contract) #declare variable as factor 
levels(mydata$contract) #modalities of the variable