Imanol-Mikel Barba Sabariego / DDS · Commits

Commit a35b1822f74f45fef93d064c174e56344bbae169

Authored by Imanol-Mikel Barba Sabariego
2 parents 3d78700e eb9b2537

Merge branch 'master' of https://gitlab.imanolbarba.net/imanol/DDS

Inline Side-by-side
Showing 3 changed files with 73 additions and 27 deletions
ISO27001effectiveness/Main.R 0 → 100644
  View file @a35b182
  1 +source("./R/Util.R")
  2 +LoadLibraries()
  3 +source("./R/ISOSurvey_Parser.R")
  4 +
  5 +Cert_PerCountry <- ParseExcelFileRaw("./data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", 1)
  6 +Sites_PerCountry <- ParseExcelFileRaw("./data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", 2)
  7 +Cert_PerSector <- ParseExcelFileRaw("./data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", 3)
  8 +
  9 +Cert_PerCountry <- ProccesISOSurveyByCountryRaw(Cert_PerCountry, c("X2010", "X2011", "X2012", "X2013", "X2014", "X2015"))
  10 +Sites_PerCountry <- ProccesISOSurveyByCountryRaw(Sites_PerCountry, c("X2010", "X2011", "X2012", "X2013", "X2014", "X2015"))
  11 +#Cert_PerSector <- ProccesISOSurveyRaw(Cert_PerSector, c("X2010", "X2011", "X2012", "X2013", "X2014", "X2015"))
... ...
ISO27001effectiveness/R/ISOSurvey_Parser.R
  View file @a35b182
... ... @@ -3,25 +3,6 @@
3 3 #------------------------------------------------------------------------------------------------------
4 4  
5 5  
6   -
7   -#-----------------------------Library tests / install--------------------------------------------------
8   -
9   -
10   -#' Install and load required libraries
11   -#'
12   -#' This function checks if every required library is installed to be loaded, if not they will be installed and then loaded.
13   -#' Libraries installed:
14   -#' xlsx to parse excel files like ISO survey source format
15   -LoadParserLibraries <- function(){
16   - if (!require("xlsx"))
17   - {
18   - install.packages("xlsx")
19   - if (!require("xlsx")) stop("Error while loading package [xlsx]")
20   - }
21   -}
22   -
23   -#-----------------------------Read from file-----------------------------------------------------------
24   -
25 6 #' Get data frame from an excel file
26 7 #'
27 8 #' Check if the file exists and then parse it into a data.frame
... ... @@ -29,27 +10,51 @@ LoadParserLibraries &lt;- function(){
29 10 #' @param sheet index of sheet to parse
30 11 #'
31 12 #' @return data.frame
  13 +#'
  14 +#' @examples
  15 +#' Cert_PerCountry <- ParseExcelFileRaw("./data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", 1)
  16 +#' Sites_PerCountry <- ParseExcelFileRaw("./data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", 2)
  17 +#' Cert_PerSector <- ParseExcelFileRaw("./data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", 3)
32 18 ParseExcelFileRaw <- function(file, sheet){
33 19  
34 20 if (!file.exists(file)) {
35 21 stop(paste("Error, file [", file, "] not found"))
36 22 }
37 23  
38   - dataset <- read.xlsx2(file, sheet, header = TRUE)
  24 + dataset <- read.xlsx2(file, sheet,colClasses = c("character","numeric","numeric","numeric","numeric","numeric","numeric","numeric","numeric","numeric","numeric"), header = TRUE, as.data.frame = TRUE)
39 25  
40 26 dataset
41 27 }
42 28  
  29 +
  30 +
43 31 #' Process raw data from ISO survey
44 32 #'
45   -#' ...
  33 +#' Proccess the raw data from ISO survey to replace NAs, normalizate country names and filter years
46 34 #' @param dataset.raw raw data from ISO Survey excel file
  35 +#' @param years List of years to return, c("X2006", "X2010", ...)
47 36 #'
48 37 #' @return data.frame
49   -ProccesISOSurveyRaw <- function(dataset.raw){
50   -#Complete
51   -}
  38 +#'
  39 +#' @examples
  40 +#'
  41 +#' Cert_PerCountry <- ProccesISOSurveyRaw(Cert_PerCountry, c("X2010", "X2011", "X2012", "X2013", "X2014", "X2015"))
  42 +#' Sites_PerCountry <- ProccesISOSurveyRaw(Sites_PerCountry, c("X2010", "X2011", "X2012", "X2013", "X2014", "X2015"))
  43 +#' Cert_PerSector <- ProccesISOSurveyRaw(Cert_PerSector, c("X2010", "X2011", "X2012", "X2013", "X2014", "X2015"))
  44 +ProccesISOSurveyByCountryRaw <- function(dataset.raw, years){
  45 +
  46 + #NAs to 0s
  47 + dataset <- dataset.raw
  48 + dataset[is.na(dataset)] <- 0
52 49  
53   -#ISO_survey_certificates_countries <- read.xlsx2(paste(getwd(), "/Data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", sep = ""), 1)
54   -#ISO_survey_sites_countries <- read.xlsx2(paste(getwd(), "/Data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", sep = ""), 2)
55   -#ISO_survey_certificates_sector <- read.xlsx2(paste(getwd(), "/Data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", sep = ""), 3)
  50 + #Translate country names to 2 letter code
  51 + CountryNames <- GetCountryAbrev()
  52 +
  53 + dataset <- merge(x = dataset, y = CountryNames, by = "Country", all.x = TRUE)
  54 +
  55 + vars <- names(dataset)
  56 + years_checked <- intersect(vars, years)
  57 + dataset <- dataset[,c(c("Country", "country_short"), years_checked)]
  58 +
  59 + dataset
  60 +}
... ...
ISO27001effectiveness/R/Util.R 0 → 100644
  View file @a35b182
  1 +#-----------------------------Util functions--------------------------------------------------
  2 +
  3 +
  4 +#' Install and load required libraries
  5 +#'
  6 +#' This function checks if every required library is installed to be loaded, if not they will be installed and then loaded.
  7 +#' Libraries installed:
  8 +#' xlsx to parse excel files like ISO survey source format
  9 +LoadParserLibraries <- function(){
  10 + if (!require("xlsx"))
  11 + {
  12 + install.packages("xlsx")
  13 + if (!require("xlsx")) stop("Error while loading package [xlsx]")
  14 + }
  15 +}
  16 +
  17 +#' Return the 2 letter code of a country relation
  18 +#'
  19 +#' Relation of country names included in the ISO Survey input file with 2 letter code
  20 +#' included on the hackmaggedon input files
  21 +#'
  22 +#' @return data.frame
  23 +GetCountryAbrev <- function(){
  24 + Country <- c("Afghanistan", "Albania", "Algeria", "American Samoa", "Andorra", "Angola", "Anguilla", "Antarctica", "Antigua and Barbuda", "Argentina", "Armenia", "Aruba", "Australia", "Austria", "Azerbaijan", "Bahamas", "Bahrain", "Bangladesh", "Barbados", "Belarus", "Belgium", "Belize", "Benin", "Bermuda", "Bhutan", "Bolivia", "Bonaire", "Bosnia and Herzegovina", "Botswana", "Bouvet Island", "Brazil", "British Indian Ocean Territory", "Brunei Darussalam", "Bulgaria", "Burkina Faso", "Burundi", "Cambodia", "Cameroon", "Canada", "Cape Verde", "Cayman Islands", "Central African Republic", "Chad", "Chile", "China", "Christmas Island", "Cocos (Keeling) Islands", "Colombia", "Comoros", "Congo", "Congo, Republic of", "Cook Islands", "Costa Rica", "Croatia", "Cuba", "Curaçao", "Cyprus", "Czech Republic", "Côte D'ivoire", "Denmark", "Djibouti", "Dominica", "Dominican Republic", "Ecuador", "Egypt", "El Salvador", "Equatorial Guinea", "Eritrea", "Estonia", "Ethiopia", "Falkland Islands (Malvinas)", "Faroe Islands", "Fiji", "Finland", "France", "French Guiana", "French Polynesia", "French Southern Territories", "Gabon", "Gambia", "Georgia", "Germany", "Ghana", "Gibraltar (UK)", "Greece", "Greenland", "Grenada", "Guadeloupe", "Guam", "Guatemala", "Guernsey", "Guinea", "Guinea-Bissau", "Guyana", "Haiti", "Heard Island and McDonald Mcdonald Islands", "Holy See (Vatican City State)", "Honduras", "Hong Kong, China", "Hungary", "Iceland", "India", "Indonesia", "Iran, Islamic Republic of", "Iraq", "Ireland", "Isle of Man", "Israel", "Italy", "Jamaica", "Japan", "Jersey", "Jordan", "Kazakhstan", "Kenya", "Kiribati", "Korea, Democratic People's Republic of", "Korea, Republic of", "Kuwait", "Kyrgyzstan", "Lao People's Democratic Republic", "Latvia", "Lebanon", "Lesotho", "Liberia", "Libya", "Liechtenstein", "Lithuania", "Luxembourg", "Macau, China", "The Former Yugoslav Republic of Macedonia", "Madagascar", "Malawi", "Malaysia", "Maldives", "Mali", "Malta", "Marshall Islands", "Martinique", "Mauritania", "Mauritius", "Mayotte", "Mexico", "Micronesia, Federated States of", "Moldova, Republic of", "Monaco", "Mongolia", "Montenegro", "Montserrat", "Morocco", "Mozambique", "Myanmar", "Namibia", "Nauru", "Nepal", "Netherlands", "New Caledonia", "New Zealand", "Nicaragua", "Niger", "Nigeria", "Niue", "Norfolk Island", "Northern Mariana Islands", "Norway", "Oman", "Pakistan", "Palau", "Palestine", "Panama", "Papua New Guinea", "Paraguay", "Peru", "Philippines", "Pitcairn", "Poland", "Portugal", "Puerto Rico", "Qatar", "Romania", "Russian Federation", "Rwanda", "Reunion", "Saint Barthelemy", "Saint Helena", "Saint Kitts and Nevis", "Saint Lucia", "Saint Martin (French part)", "Saint Pierre and Miquelon", "Saint Vincent and the Grenadines", "Samoa", "San Marino, Republic of", "Sao Tome and Principe", "Saudi Arabia", "Senegal", "Serbia", "Seychelles", "Sierra Leone", "Singapore", "Sint Maarten (Dutch part)", "Slovakia", "Slovenia", "Solomon Islands", "Somalia", "South Africa", "South Georgia and the South Sandwich Islands", "South Sudan", "Spain", "Sri Lanka", "Sudan", "Suriname", "Svalbard and Jan Mayen", "Swaziland", "Sweden", "Switzerland", "Syrian Arab Republic", "Taiwan, Province of China", "Tajikistan", "Tanzania, United Republic of", "Thailand", "Timor-Leste", "Togo", "Tokelau", "Tonga", "Trinidad and Tobago", "Tunisia", "Turkey", "Turkmenistan", "Turks and Caicos Islands", "Tuvalu", "Uganda", "Ukraine", "United Arab Emirates", "United Kingdom", "United States of America", "United States Minor Outlying Islands", "Uruguay", "Uzbekistan", "Vanuatu", "Venezuela", "Viet Nam", "British Virgin Islands", "US Virgin Islands", "Wallis and Futuna", "Western Sahara", "Yemen", "Zambia", "Zimbabwe", "Aland Islands", "Taipei, Chinese")
  25 + country_short <- c("AF", "AL", "DZ", "AS", "AD", "AO", "AI", "AQ", "AG", "AR", "AM", "AW", "AU", "AT", "AZ", "BS", "BH", "BD", "BB", "BY", "BE", "BZ", "BJ", "BM", "BT", "BO", "BQ", "BA", "BW", "BV", "BR", "IO", "BN", "BG", "BF", "BI", "KH", "CM", "CA", "CV", "KY", "CF", "TD", "CL", "CN", "CX", "CC", "CO", "KM", "CG", "CD", "CK", "CR", "HR", "CU", "CW", "CY", "CZ", "CI", "DK", "DJ", "DM", "DO", "EC", "EG", "SV", "GQ", "ER", "EE", "ET", "FK", "FO", "FJ", "FI", "FR", "GF", "PF", "TF", "GA", "GM", "GE", "DE", "GH", "GI", "GR", "GL", "GD", "GP", "GU", "GT", "GG", "GN", "GW", "GY", "HT", "HM", "VA", "HN", "HK", "HU", "IS", "IN", "ID", "IR", "IQ", "IE", "IM", "IL", "IT", "JM", "JP", "JE", "JO", "KZ", "KE", "KI", "KP", "KR", "KW", "KG", "LA", "LV", "LB", "LS", "LR", "LY", "LI", "LT", "LU", "MO", "MK", "MG", "MW", "MY", "MV", "ML", "MT", "MH", "MQ", "MR", "MU", "YT", "MX", "FM", "MD", "MC", "MN", "ME", "MS", "MA", "MZ", "MM", "NA", "NR", "NP", "NL", "NC", "NZ", "NI", "NE", "NG", "NU", "NF", "MP", "NO", "OM", "PK", "PW", "PS", "PA", "PG", "PY", "PE", "PH", "PN", "PL", "PT", "PR", "QA", "RO", "RU", "RW", "RE", "BL", "SH", "KN", "LC", "MF", "PM", "VC", "WS", "SM", "ST", "SA", "SN", "RS", "SC", "SL", "SG", "SX", "SK", "SI", "SB", "SO", "ZA", "GS", "SS", "ES", "LK", "SD", "SR", "SJ", "SZ", "SE", "CH", "SY", "TW", "TJ", "TZ", "TH", "TL", "TG", "TK", "TO", "TT", "TN", "TR", "TM", "TC", "TV", "UG", "UA", "AE", "GB", "US", "UM", "UY", "UZ", "VU", "VE", "VN", "VG", "VI", "WF", "EH", "YE", "ZM", "ZW", "AX", "CN")
  26 +
  27 + dataset <- data.frame(Country, country_short)
  28 +
  29 + dataset
  30 +}
... ...