Commit 877bdf9c authored by Sarish's avatar Sarish
Browse files

small changes have been made to verify the data cleaning process on reviews

parent 2b66276a

02_code/R/Script 1 - Data cleaning.R

+8 −8
Original line number Diff line number Diff line
@@ -14,7 +14,7 @@ library(wordcloud2) 
library(SnowballC)



#loading of ncessary dataset

load("D:/Hohenheim/SEM 3/ADS/introads_ass2_team18/01_data/raw/gamereviews.RData")

load("C:/Users/akluj/SEM_3/ADS/introads_ass2_team18/01_data/raw/gamereviews.RData")





# Cleaning of the user reviews--------------------------------------------------
@@ -50,8 +50,8 @@ clean.review <- function(review) { 
  return(cleaned.review)

}



# Applying function on each review which gives cleaned review

reviews.clean$review <- sapply(reviews.clean$review, clean.review)

# Applying function on each review which gives cleaned review and created a new column to verify the change

reviews.clean$reviews <- sapply(reviews.clean$review, clean.review)



# Exclude observations with empty spaces

reviews.clean <- reviews.clean[reviews.clean$review != "",]
@@ -66,7 +66,7 @@ reviews.clean <- reviews.clean[reviews.clean$review != "",] 
# Loop through all reviews to check spelling based on US english dictionary



for (i in 1:nrow(reviews.clean)){

  reviews <- reviews.clean$review[i]

  reviews <- reviews.clean$reviews[i]

  

  #extract words

  words <- unlist(strsplit(reviews, " "))
@@ -81,11 +81,11 @@ for (i in 1:nrow(reviews.clean)){ 
  correct_review <- paste(correct_words, collapse = " ")

  

  # update the dataframe

  reviews.clean$review[i] <- correct_review

  reviews.clean$reviews[i] <- correct_review

}



# Transform all upper case chracters in a lower case character

reviews.clean$review <- tolower(reviews.clean$review)

reviews.clean$reviews <- tolower(reviews.clean$reviews)



# Setting a working directory to save dataset

setwd("D:/Hohenheim/SEM 3/ADS/introads_ass2_team18/01_data")
@@ -95,14 +95,14 @@ write.csv(reviews.clean, file = "reviews.clean.csv") 


# word cloud--------------------------------------------------------------------

# combine all reviews into a single text

all.reviews <- paste(reviews.clean$review, collapse = "")

all.reviews <- paste(reviews.clean$reviews, collapse = "")





all.words <- character()

# loop through all reviews

for (i in 1:nrow(reviews.clean)) {

  #split the review into words

  tmp <- unlist(strsplit(reviews.clean$review[i], " "))

  tmp <- unlist(strsplit(reviews.clean$reviews[i], " "))

  # Concatenate the words to the all.words vector

  all.words <- c(all.words, tmp)

}