gender_mapping.R

require(arules)
require(arulesViz)
require(reshape2)
require(gender)
require(plyr)
require(dplyr)
require(ggplot2)

transaction.data <- read.csv('fact table; transaction data with first and last customer names')
customer.data    <- read.csv('dim table; Customer information')

customer.transaction.data <-  
  merge(x = customer.data, y = transaction.data, by.x = 'Square.Customer.ID', 
        by.y = 'Customer.ID')

first.names <- as.character(as.vector(customer.data$First.Name))
last.name   <- as.character(as.vector(customer.data$Last.Name))

gender <- gender(first.names, method = "ssa")
gender <- gender[!duplicated(gender), ]

customer.data.wgender <- 
  merge(x = customer.data, y = gender, by.x = 'First.Name', by.y = 'name')

customer.transaction.data.w.gender <- 
  merge(x = customer.data.wgender, y = transaction.data, by.x = 'Square.Customer.ID', 
        by.y = 'Customer.ID')

males   <- subset(customer.data.wgender, gender == "male") 
females <- subset(customer.data.wgender, gender == "female")
  unique.gender.qty <- data.frame(gender = c("Male", "Female"), 
                                  unique.qty = c(nrow(males), nrow(females)))

  ggplot(unique.gender.qty, aes(gender , unique.qty, fill = gender)) + 
  geom_col()