#set working directory
#read in data set
setwd("C:/Users/micha/OneDrive/Work (Beatty)")
ratings <- read.csv ("UWCRTextMessageDevel_DATA_2018-05-31_1142.csv")

#install packages
install.packages("dplyr")
library("dplyr")

#selecting columns that start with "useful" and "easy
ratings.useful <- dplyr::select(ratings, starts_with("useful"))
ratings.easy  <- dplyr::select(ratings, starts_with("easy"))


### calculating avg useful ratings
useful.means.col <- colMeans(x=ratings.useful, na.rm = TRUE)
vector.useful <- as.vector(useful.means.col,mode='numeric')

#making an empty object
ratings.avg <- NA

#creating a new column for "useful" inside that object
ratings.avg$useful <- vector.useful

### calculating avg easiness
easy.means.col <- colMeans(x=ratings.easy, na.rm = TRUE)
vector.easy <- as.vector(easy.means.col,mode='numeric')

#creating a new column for "easy" inside object
ratings.avg$easy <- vector.easy

#creating a dataframe with all of them together, labeling by text number
text.id <- c(1:236)
ratings.avg <-data.frame(text=text.id, useful=vector.useful, easy=vector.easy)
head(ratings.avg)

#saving dataframe as a csv - for average text ratings
write.csv(ratings.avg, "average text ratings 053118.csv")

#below - extracting all individual useful/easy ratings
flipped <- t(ratings) #tranpose rows and column
head(flipped)
clean = as.data.frame(t(apply(flipped,1, function(x) { return(c(x[!is.na(x)],x[is.na(x)]) )} ))) #shifts all cells to left
write.csv(clean, "all ratings ratings 053118.csv")
head(clean)