## ALL LINES BEGINNING WITH one or more "#" are "comments" and are notes for you, 
## the programmer. They will not be read by R.

### STEP 1: Set PATH ###
## The first thing we need to do is set the path. 
## The path is a line of text that specifies the working directory (folder) that 
## our inputs are held and our outputs will be written.
## The path will be formatted differently in mac/linux compared to Windows.
## Remember, R uses the "<-" operator for assignment, 
## although "=" will work in most cases as well

## To assign the path, use the function setwd() - learn more by typing ?setwd into the console
## Inside the parentheses () we can paste the path text, surrounded by quotes " "
setwd("YOUR PATH GOES HERE")

#In windows, your path will look something like this. You will need to convert backslash "\" to slash "/"
# WINDOWS_PATH_EXAMPLE <- "C:/Program Files/R" 

# With the path set, we can now read the file, which is located in the working directory we have set!
# This line assigns our data's filename to a variable called "FILE_NAME"
FILE_NAME <- "Happiness_2019.csv"

# And this line assigns the data to an R object named "df"
df <- read.csv(FILE_NAME)

## Always check our data to make sure it loaded properly, and to see what we're working with
head(df)

# We can view individual columns by using a $, for example, this will give just the score column
keep_columns <- c("Country.or.region", "Score")
clean_df <- df[keep_columns]

# now lets sort by score, with the highest at the top
clean_df <- clean_df[ order(clean_df$Score, decreasing = TRUE) ,]

# and finally, just report the top 10 - this will keep only the first ten rows
clean_df <- clean_df[1:10 , ]

# This cleans up the old row numbers, which will look a bit weird otherwise
rownames(clean_df) <- NULL

#Finally, we can write this cleaner data to our computer!
write.csv(clean_df, file="top-10-happiness2019.csv")

# Lets also make a simple plot of our happiness data
plot(df$GDP.per.capita, df$Score)

# This graph needs labels and graphical parameters, add them like this:
plot(df$GDP.per.capita, df$Score, xlab = "GDP per capita (relative)", 
     ylab="2019 Happiness Score", main = "2019 Happiness Score vs. GDP",
     col="green", pch = 19
)

# To save as a PDF, we can do the following:
pdf(file="Score-Vs-GDP.pdf")
plot(df$GDP.per.capita, df$Score, xlab = "GDP per capita (relative)", 
     ylab="2019 Happiness Score", main = "2019 Happiness Score vs. GDP",
     col="green", pch = 19
)
dev.off()

#And maybe lets make one for "Social support" as well:
pdf(file="Score-Vs-SocSupp.pdf")
plot(df$Social.support, df$Score, xlab = "Social Support", 
     ylab="2019 Happiness Score", main = "2019 Happiness Score vs. Social Support",
     col="blue", pch = 19
)
dev.off()

# NOTE - the data for the world happiness report comes from the "GALLUP WORLD POLL"
# For methodology and more, visit https://www.gallup.com/178667/gallup-world-poll-work.aspx