Piotr Sobczyk psobczyk

## scraping_ncn.R
library(httr)
library(XML)

#this is copied from my browser - thus Mozilla and Mac OS
headers <- ('{"Host":"www.ncn.gov.pl","User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.11; rv:54.0) Gecko/20100101 Firefox/54.0","Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8","Accept-Language":"en-US,en;q=0.5","Accept-Encoding":"gzip, deflate, br","Content-Type":"application/x-www-form-urlencoded","Content-Length":"156","Referer":"https://www.ncn.gov.pl/statystyki/","Cookie":"has_js=1; __utma=198221488.1697332473.1495532703.1495532703.1495532703.1; __utmc=198221488; __utmz=198221488.1495532703.1.1.utmcsr=google|utmccn=(organic)|utmcmd=organic|utmctr=(not%20provided)","Connection":"keep-alive","Upgrade-Insecure-Requests":"1"}')
body <- list(zestawienie = "kwota", podzial = "wojewodztwo", 'zakres'='rok',
						 konkursid = '', 'panelid'= '', typid = '', rokid= '1',
						 wojewodztwoid= '', plecid = '', tytulid=  '', rodzajejednostekid = '1')

granty <- vector(mode = "list", 6)

## plot_ncn_grants.R
library(dplyr)
library(ggplot2)
library(ggthemes)

top_percent <- granty %>%
	group_by(rok) %>%
	mutate(procent = kwota/sum(kwota)) %>%
	arrange(desc(procent)) %>%
	top_n(7, procent) %>%
	mutate(pozycja = row_number(),

## analiza_wynikow_polmaraton_wroclaw_2017.R

library(XML)
library(dplyr)
library(tidyr)
library(ggplot2)
library(ggthemes)

url_address <- 'wyniki.txt' #tabela sciagnieta ze strony http://wyniki.datasport.pl/results2200/
doc.html = htmlTreeParse(url_address, useInternal = TRUE, encoding = "UTF-8")

## plot_obesity.R
# data can be downloaded from http://ghdx.healthdata.org/gbd-2015
obesity <- read.csv("IHME_GBD_2015_OBESITY_PREVALENCE_1980_2015_1/IHME_GBD_2015_OBESITY_PREVALENCE_1980_2015_Y2017M06D12.CSV")


obesity %>%
	filter(location_name %in% c("United States", "Poland", "Sweden"),
				 metric == "Percent",
				 sex == "Both",
				 age_group_name %in% c('15 to 19', '20 to 24',
				 											'30 to 34', '35 to 39',

## plot_temperature_hdi.R

library(rvest)
library(ggplot2)
library(ggthemes)
library(highcharter)

avg_temp <- read_html('https://en.wikipedia.org/wiki/List_of_countries_by_average_yearly_temperature')
avg_temp <- html_table(avg_temp, fill = T)[[2]]

gdp <- read_html('https://en.wikipedia.org/wiki/List_of_countries_by_GDP_(PPP)_per_capita')

## scraping_timeanddata.R
library(rvest)
library(dplyr)

main_page <- read_html('https://www.timeanddate.com/holidays/')

all_countries <- main_page %>%
  html_nodes(xpath = '//div[@class="row"]//li//a') %>%
  html_attr(name = 'href')

holidays <- NULL

## knock_off_fixtures.csv
match;group.x;position.x;group.y;position.y
49;A;1;B;2
50;C;1;D;2
51;B;1;A;2
52;D;1;C;2
53;E;1;F;2
54;G;1;H;2
55;F;1;E;2
56;H;1;G;2
57;;49;;50

## Sheet 1-Table 1.csv
Województwo;Ogółem;Mężczyźni;Kobiety;PIS;PO;Nowoczesna;Kukiz;SLD;PSL
MAZOWIECKIE;5 349 114;2 559 241;2 789 873;41.7;20.2;7.2;8.1;2.8;4.9
ŚLĄSKIE;4 570 849;2 204 972;2 365 877;37.4;20.0;6.1;10.1;4.3;1.8
WIELKOPOLSKIE;3 475 323;1 690 930;1 784 393;34.3;27.4;6.6;6.7;4.4;5.0
MAŁOPOLSKIE;3 372 618;1 636 707;1 735 911;50.1;12.0;4.3;6.8;3.0;1.7
DOLNOŚLĄSKIE;2 904 207;1 396 318;1 507 889;32.0;26.9;8.4;10.3;7.0;3.3
ŁÓDZKIE;2 493 603;1 188 118;1 305 485;36.4;19.1;6.6;6.9;5.6;3.7
POMORSKIE;2 307 710;1 124 377;1 183 333;30.1;28.5;9.9;5.5;4.1;3.0
LUBELSKIE;2 139 726;1 037 052;1 102 674;45.3;13.2;4.6;7.2;3.2;8.0
PODKARPACKIE;2 127 657;1 041 779;1 085 878;53.5;14.3;3.2;8.5;2.3;4.7

## parliament_seats.R

require(dplyr)
require(rvest)
require(ggplot2)
require(ggthemes)

url <- "https://en.wikipedia.org/wiki/List_of_legislatures_by_number_of_members"
html_downloaded <- read_html(url)

tables<- url %>% read_html %>%

## wedding_vignette.R
library(png)

#' Print Table Vignette
#'
#' @param out_dir
#' @param img
#' @param name
#' @param file_name
#' @param two_sided
#'
	library(httr)
	library(XML)

	#this is copied from my browser - thus Mozilla and Mac OS
	headers <- ('{"Host":"www.ncn.gov.pl","User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.11; rv:54.0) Gecko/20100101 Firefox/54.0","Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,/;q=0.8","Accept-Language":"en-US,en;q=0.5","Accept-Encoding":"gzip, deflate, br","Content-Type":"application/x-www-form-urlencoded","Content-Length":"156","Referer":"https://www.ncn.gov.pl/statystyki/","Cookie":"has_js=1; __utma=198221488.1697332473.1495532703.1495532703.1495532703.1; __utmc=198221488; __utmz=198221488.1495532703.1.1.utmcsr=google\|utmccn=(organic)\|utmcmd=organic\|utmctr=(not%20provided)","Connection":"keep-alive","Upgrade-Insecure-Requests":"1"}')
	body <- list(zestawienie = "kwota", podzial = "wojewodztwo", 'zakres'='rok',
	konkursid = '', 'panelid'= '', typid = '', rokid= '1',
	wojewodztwoid= '', plecid = '', tytulid= '', rodzajejednostekid = '1')

	granty <- vector(mode = "list", 6)
	library(dplyr)
	library(ggplot2)
	library(ggthemes)

	top_percent <- granty %>%
	group_by(rok) %>%
	mutate(procent = kwota/sum(kwota)) %>%
	arrange(desc(procent)) %>%
	top_n(7, procent) %>%
	mutate(pozycja = row_number(),

	library(XML)
	library(dplyr)
	library(tidyr)
	library(ggplot2)
	library(ggthemes)

	url_address <- 'wyniki.txt' #tabela sciagnieta ze strony http://wyniki.datasport.pl/results2200/
	doc.html = htmlTreeParse(url_address, useInternal = TRUE, encoding = "UTF-8")
	# data can be downloaded from http://ghdx.healthdata.org/gbd-2015
	obesity <- read.csv("IHME_GBD_2015_OBESITY_PREVALENCE_1980_2015_1/IHME_GBD_2015_OBESITY_PREVALENCE_1980_2015_Y2017M06D12.CSV")


	obesity %>%
	filter(location_name %in% c("United States", "Poland", "Sweden"),
	metric == "Percent",
	sex == "Both",
	age_group_name %in% c('15 to 19', '20 to 24',
	'30 to 34', '35 to 39',

	library(rvest)
	library(ggplot2)
	library(ggthemes)
	library(highcharter)

	avg_temp <- read_html('https://en.wikipedia.org/wiki/List_of_countries_by_average_yearly_temperature')
	avg_temp <- html_table(avg_temp, fill = T)[[2]]

	gdp <- read_html('https://en.wikipedia.org/wiki/List_of_countries_by_GDP_(PPP)_per_capita')
	library(rvest)
	library(dplyr)

	main_page <- read_html('https://www.timeanddate.com/holidays/')

	all_countries <- main_page %>%
	html_nodes(xpath = '//div[@class="row"]//li//a') %>%
	html_attr(name = 'href')

	holidays <- NULL
	match;group.x;position.x;group.y;position.y
	49;A;1;B;2
	50;C;1;D;2
	51;B;1;A;2
	52;D;1;C;2
	53;E;1;F;2
	54;G;1;H;2
	55;F;1;E;2
	56;H;1;G;2
	57;;49;;50
	Województwo;Ogółem;Mężczyźni;Kobiety;PIS;PO;Nowoczesna;Kukiz;SLD;PSL
	MAZOWIECKIE;5 349 114;2 559 241;2 789 873;41.7;20.2;7.2;8.1;2.8;4.9
	ŚLĄSKIE;4 570 849;2 204 972;2 365 877;37.4;20.0;6.1;10.1;4.3;1.8
	WIELKOPOLSKIE;3 475 323;1 690 930;1 784 393;34.3;27.4;6.6;6.7;4.4;5.0
	MAŁOPOLSKIE;3 372 618;1 636 707;1 735 911;50.1;12.0;4.3;6.8;3.0;1.7
	DOLNOŚLĄSKIE;2 904 207;1 396 318;1 507 889;32.0;26.9;8.4;10.3;7.0;3.3
	ŁÓDZKIE;2 493 603;1 188 118;1 305 485;36.4;19.1;6.6;6.9;5.6;3.7
	POMORSKIE;2 307 710;1 124 377;1 183 333;30.1;28.5;9.9;5.5;4.1;3.0
	LUBELSKIE;2 139 726;1 037 052;1 102 674;45.3;13.2;4.6;7.2;3.2;8.0
	PODKARPACKIE;2 127 657;1 041 779;1 085 878;53.5;14.3;3.2;8.5;2.3;4.7

	require(dplyr)
	require(rvest)
	require(ggplot2)
	require(ggthemes)

	url <- "https://en.wikipedia.org/wiki/List_of_legislatures_by_number_of_members"
	html_downloaded <- read_html(url)

	tables<- url %>% read_html %>%
	library(png)

	#' Print Table Vignette
	#'
	#' @param out_dir
	#' @param img
	#' @param name
	#' @param file_name
	#' @param two_sided
	#'