Billionaires

billionaires.R

# Source: http://www.forbes.com/billionaires/list/#tab:overall
# DateTaken: March 4th, 2014

data_path_original <- '../data/original/'
data_path <- '../data/'


# Load Data
df <- read.csv(paste0(data_path_original,"billionaires.txt"), header = TRUE, sep = "\t", stringsAsFactors=FALSE)
df <- head(df,1645)



# DataCleanup
names(df)[6] <- c("Country")
df$Country <- gsub(pattern= "ChinaRank", replacement="China", x=df$Country)
df$Country <- gsub(pattern= "Czech Republic", replacement="Czech Rep.", x=df$Country)
df$Country <- gsub(pattern= "Vietnam", replacement="Viet Nam", x=df$Country)
df$Country <- gsub(pattern= "United Arab Emirates", replacement="United Arab Emirates", x=df$Country)
df$Country <- gsub(pattern= "Macau", replacement="China", x=df$Country)
df$Country <- gsub(pattern= "Hong Kong", replacement="China", x=df$Country)


df$NetWorth <- gsub(pattern= "[$]", replacement="", x=df$NetWorth)
df$NetWorth <- lapply(strsplit(x = df$NetWorth, " "), FUN = function(x){paste(x[1])})
df$NetWorth <- as.numeric(df$NetWorth)


#Writing data
write.csv2(df, file = paste0(data_path, "Master_dataframe.csv"), row.names = F)