#####################
# Normal Processing #
#####################

# install the gender package if you need to
install.packages('gender')
# NOTE - if asked to install GenderData click 1 for yes.

# load package
library(gender) ;

# Import CSV with list of first names - set path
firstnames <- read.csv("D:\\Dropbox\\Data Mining\\R\\Top 1000 names.csv", stringsAsFactors=FALSE)

# if you have a short list or don't have a CSV to try then you can build your own list - simply uncomment
# firstnames <- c("Elizabeth", "Mary", "Jeff", "John", "Morgan", "Helen", "Tim", "Diane", "Patricia")
values <- as.vector(firstnames[,1])

# Create gender search function
workerFunc <- function(n){
  return
  cbind(n, gender(n, method = "ssa", years = c(1900, 1990))$gender)
}

# Start process and track processing time
Sys.time()
res <- lapply(values, workerFunc)
Sys.time()

# Put final results together in data frame
indx <- sapply(res, length)
results <- as.data.frame(do.call(rbind,lapply(res, `length<-`, max(indx))))
colnames(results) <- c("name", "gender")

# Optional write results to CSV - set path
write.csv(results,"D:/Dropbox/Data Mining/R/Top 1000 names with gender.csv")


#######################
# Parallel Processing #
#######################

# install the gender package
install.packages('gender')
# NOTE - if asked to install GenderData click 1 for yes.
install.packages('parallel') ;
install.packages('doParallel') ;

# load packages
library(gender) ;
library(parallel) ;
library(doParallel) ;

# Detect Cores and Register
cl<-makeCluster(detectCores())
setDefaultCluster(cl)
registerDoParallel(cl, cores=detectCores())
clusterEvalQ(cl, "gender")
clusterExport(cl,"gender")

# Import CSV with list of first names - set path
firstnames <- read.csv("D:\\Dropbox\\Data Mining\\R\\Top 1000 names.csv", stringsAsFactors=FALSE)

# if you have a short list or don't have a CSV to try then you can build your own list - simply uncomment
# firstnames <- c("Elizabeth", "Mary", "Jeff", "John", "Morgan", "Helen", "Tim", "Diane", "Patricia")
values <- as.vector(firstnames[,1])

# Create gender search function
workerFunc <- function(n){
  return
  cbind(n, gender(n, method = "ssa", years = c(1900, 1990))$gender)
}

# Start process and track processing time
Sys.time()
res <- parLapply(cl, values, workerFunc)
Sys.time()

# Stop the cluster and create the result data frame
stopCluster(cl)

# Put final results together in data frame
indx <- sapply(res, length)
results <- as.data.frame(do.call(rbind,lapply(res, `length<-`, max(indx))))
colnames(results) <- c("name", "gender")

# Optional write results to CSV - set path
write.csv(results,"D:/Dropbox/Data Mining/R/Top 1000 names with gender.csv")