Yahia yahiaelgamal

## egypt_pop_2006.csv

          
            gov
            population

            
              Alexandria
              4716000

            
              Aswan
              1395000

            
              Asyout
              4123000

            
              Beheira
              5647000

            
              Beni-Suef
              2771000

            
              Cairo
              9102000

            
              Dakahlia
              5818000

            
              Damietta
              1301000

            
              El Wadi Elgedid
              220000

## regex_snippets.R
# removes the table name from hive exporeted dataframe
gsub('.*?\\.(.*)'  , '\\1', 'tablename.columnaname.suffix') # => columnaname.suffix


remove_table_name = function(df) {
  names(df) = gsub('.*?\\.(.*)'  , '\\1', names(df)) # => columnaname.suffix
  df
}

# GTEST of two vectors (range 0, 1)

## sunburst.R
library(ggplot2)
library(dplyr)
library(magrittr)
library(scales)


pop.eg = read.csv('egypt_pop_2006.csv')
sum_total_pop = sum(pop.eg$population)

firstLevel = pop.eg %>% summarize(total_pop=sum(population))

## jolly_plots.R
  library(ggplot2)
library(dplyr)
library(tidyr)

jolly = read.csv('jolly.csv')

jolly  = jolly %>% gather(key, flow, skill, challenge)

# dataframe columns are now [game, level, key, flow]
#     game level    key         flow    up

## perf_sub_two.csv

          
            tx_merchant_clean
            month_number
            year(Post_date)
            key
            value

            
              A/D POLICE(FINES DEPT)
              1
              2014
              Sum
              946460

            
              A/D POLICE(FINES DEPT)
              2
              2014
              Sum
              645740

            
              A/D POLICE(FINES DEPT)
              3
              2014
              Sum
              830610

            
              A/D POLICE(FINES DEPT)
              4
              2014
              Sum
              422565

            
              A/D POLICE(FINES DEPT)
              9
              2013
              Sum
              671820

            
              A/D POLICE(FINES DEPT)
              10
              2013
              Sum
              200645

            
              A/D POLICE(FINES DEPT)
              11
              2013
              Sum
              323660

            
              A/D POLICE(FINES DEPT)
              12
              2013
              Sum
              457225.55

            
              ACE
              1
              2014
              Sum
              410792.24

## march.html
<html>
<style>
.group{
  width: 100%;
  margin: 20px auto 20px auto;

  vertical-align: middle;
}
.btn{
  background: white;

## vis_tut.R
library(ggplot2)
# 1- gentle qplot

#qplot(x, y, data=, color=, shape=, size=, alpha=, geom=, method=, formula=, facets=, xlim=, ylim= xlab=, ylab=, main=, sub=)

# normal
plot(iris$Sepal.Length, iris$Petal.Length,  col=iris$Specie)
qplot(Sepal.Length, Petal.Length, data=iris, color=Species)

#

## boys_and_girls
library(ggplot2)
# boy 1, girl 0
b = sapply(1:100, function(x){
  births = lapply(1:num_sim, function(x){rbinom(10, 1, 0.5)})
  num_boys = length(births)
  num_girls = sum(sapply(births, function(birth){match(1, birth) - 1} ))

  num_boys / num_girls
})

## Penny's game simulation
# returns % of losses of the first player
play = function(first, second, num_sim=200){
  games = lapply(1:num_sim, function(x){rbinom(1000, 1, 0.5)})
  games = sapply(games, function(x) {do.call(paste0, as.list(x))})

  #first = paste(paste0, as.list(first))
  #second = paste(paste0, as.list(second))

  first_m = sapply(games, function(game){ regexpr(first, game)})
  first_m[first_m == -1] = Inf

## cluster_visual
require('ggplot2')
require("LICORS") #library that implements kmeans++

plotClusters = function(df, cluster, name){
  num_centers = length(cluster$centers)
  gr = ggplot(df, aes(x=X, y=Y))
  before_cluster = gr + geom_point(size=3, alpha=0.7) + labs(title='Before Clustering'); before_cluster

  after_cluster= gr + geom_point(aes(col=factor(cluster$cluster)), size=3, alpha=0.7) + guides(colour=F)
  after_cluster = after_cluster + scale_color_hue(l=50)
	gov	population
	Alexandria	4716000
	Aswan	1395000
	Asyout	4123000
	Beheira	5647000
	Beni-Suef	2771000
	Cairo	9102000
	Dakahlia	5818000
	Damietta	1301000
	El Wadi Elgedid	220000
	# removes the table name from hive exporeted dataframe
	gsub('.?\\.(.)' , '\\1', 'tablename.columnaname.suffix') # => columnaname.suffix


	remove_table_name = function(df) {
	names(df) = gsub('.?\\.(.)' , '\\1', names(df)) # => columnaname.suffix
	df
	}

	# GTEST of two vectors (range 0, 1)
	library(ggplot2)
	library(dplyr)
	library(magrittr)
	library(scales)


	pop.eg = read.csv('egypt_pop_2006.csv')
	sum_total_pop = sum(pop.eg$population)

	firstLevel = pop.eg %>% summarize(total_pop=sum(population))
	library(ggplot2)
	library(dplyr)
	library(tidyr)

	jolly = read.csv('jolly.csv')

	jolly = jolly %>% gather(key, flow, skill, challenge)

	# dataframe columns are now [game, level, key, flow]
	# game level key flow up
tx_merchant_clean	month_number	year(Post_date)	key	value
A/D POLICE(FINES DEPT)	1	2014	Sum	946460
A/D POLICE(FINES DEPT)	2	2014	Sum	645740
A/D POLICE(FINES DEPT)	3	2014	Sum	830610
A/D POLICE(FINES DEPT)	4	2014	Sum	422565
A/D POLICE(FINES DEPT)	9	2013	Sum	671820
A/D POLICE(FINES DEPT)	10	2013	Sum	200645
A/D POLICE(FINES DEPT)	11	2013	Sum	323660
A/D POLICE(FINES DEPT)	12	2013	Sum	457225.55
ACE	1	2014	Sum	410792.24
	<html>
	<style>
	.group{
	width: 100%;
	margin: 20px auto 20px auto;

	vertical-align: middle;
	}
	.btn{
	background: white;
	library(ggplot2)
	# 1- gentle qplot

	#qplot(x, y, data=, color=, shape=, size=, alpha=, geom=, method=, formula=, facets=, xlim=, ylim= xlab=, ylab=, main=, sub=)

	# normal
	plot(iris$Sepal.Length, iris$Petal.Length, col=iris$Specie)
	qplot(Sepal.Length, Petal.Length, data=iris, color=Species)

	#
	library(ggplot2)
	# boy 1, girl 0
	b = sapply(1:100, function(x){
	births = lapply(1:num_sim, function(x){rbinom(10, 1, 0.5)})
	num_boys = length(births)
	num_girls = sum(sapply(births, function(birth){match(1, birth) - 1} ))

	num_boys / num_girls
	})
	# returns % of losses of the first player
	play = function(first, second, num_sim=200){
	games = lapply(1:num_sim, function(x){rbinom(1000, 1, 0.5)})
	games = sapply(games, function(x) {do.call(paste0, as.list(x))})

	#first = paste(paste0, as.list(first))
	#second = paste(paste0, as.list(second))

	first_m = sapply(games, function(game){ regexpr(first, game)})
	first_m[first_m == -1] = Inf
	require('ggplot2')
	require("LICORS") #library that implements kmeans++

	plotClusters = function(df, cluster, name){
	num_centers = length(cluster$centers)
	gr = ggplot(df, aes(x=X, y=Y))
	before_cluster = gr + geom_point(size=3, alpha=0.7) + labs(title='Before Clustering'); before_cluster

	after_cluster= gr + geom_point(aes(col=factor(cluster$cluster)), size=3, alpha=0.7) + guides(colour=F)
	after_cluster = after_cluster + scale_color_hue(l=50)