# Clean data with R

# Set working directory
setwd("~/Desktop/Test R") # Change the content between quotation marks. It needs to be the path to the folder with your data

mydata <- read.csv2("clean_data.csv")   # read the data in
head(mydata)                    # look at the data

# Clean this dataset
# For example, we want no value > 100
which(mydata > 100)
toohigh <- which(mydata > 100)

# For example, we want no value < 0
which(mydata < 0)
toolow <- which(mydata < 0)

# Second version of my data
mydatav2 <- mydata # copy data
mydatav2[ mydatav2 > 100] <- NA # substitute by "NA" (missing value)

which(mydatav2 > 100)
which(mydata > 100)

mydatav2[ mydatav2 < 0 ] <- NA
which(mydatav2 < 0)
which(mydata < 0)

# variable privilege should not be 50
mydata$privileges
# substitute 50 for NA
mydatav3 <- mydata # copy data set
mydatav3$privileges[ mydatav3$privileges == 50 ] # two cases
# substitute these cases with NA
mydatav3$privileges[ mydatav3$privileges == 50 ] <- NA

which( mydata$privileges == 50 ) # two cases of 50
which( mydatav3$privileges == 50 ) # no case

# column names
head(mydata)
names(mydata)
# rename "rating" to "score"
names(mydata)[1] # return the first entry
names(mydata)[names(mydata) == "rating"] # alternative way to select 1. entry
# rename the first entry
names(mydata)[1] <- "score"
names(mydata) # with new names



# ADDITIONAL CODE THAT COULD BE USEFUL TO YOU (not shown in the video)

# Mean of different variables
# Calculate the mean of several variables in your dataset
# For example the mean of 'complaints' and 'privileges'
variable_names <- c("complaints", "privileges") # store names of variables
MW <- rowSums(mydata[, variable_names]) # compute mean of these two variables for each row and store it in MW
mydata$Mean <- MW # Store the computed mean in mydata as variable ‘Mean’

head(mydata) # check the result


# Recode reverse-coded variables
# Say the variable 'complaints' was reverse coded with the highest value of 111
# Recoding works by subtracting the variable from the highest possible value and adding 1
# highest value - variable + 1

complaints_rev <- 111 - mydata$complaints - 1 # Recode complaints and store it in complaints_rev
mydata$complaints_rev <- complaints_rev # store complaints_rev in the data mydata

head(mydata) # check the result