kaggle_age_gender_plot.jl

Gadfly.with_theme(:dark) do

	# Subset the data with only rows I need
	gender,age = names(dataset)[3],names(dataset)[2]
	age_with_gender_data = dataset[!,2:3]

	# grouby age and gender and then count
	age_and_gender_counts = combine(
		groupby(
			age_with_gender_data,[gender,age])
		, nrow => :n
	)

	# Sort the results by age
	sort!(age_and_gender_counts,age)

	
	age_gender_plot = plot(
		age_and_gender_counts,
		x=age,
		y=:n,
		color=gender,
		style(bar_spacing=2mm),
		Guide.ylabel("Frequency"),
		Geom.bar
	)
	# draw(SVG("kaggle_age_gender_plot.svg"),age_gender_plot)
end