Added Main.R to test the implementations, changed [ProccesISOSurveyByCountryRaw]…

… to allow filter per year

Added Main.R to test the implementations, changed [ProccesISOSurveyByCountryRaw]…
… to allow filter per year
Miguel Tuñón
1 parent 2630a1ef
Showing 3 changed files with 45 additions and 17 deletions
ISO27001effectiveness/Main.R
ISO27001effectiveness/R/ISOSurvey_Parser.R
ISO27001effectiveness/R/Util.R
+source("./R/Util.R")
+LoadLibraries()
+source("./R/ISOSurvey_Parser.R")
+
+Cert_PerCountry <- ParseExcelFileRaw("./data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", 1)
+Sites_PerCountry <- ParseExcelFileRaw("./data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", 2)
+Cert_PerSector <- ParseExcelFileRaw("./data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", 3)
+
+Cert_PerCountry <- ProccesISOSurveyByCountryRaw(Cert_PerCountry, c("X2010", "X2011", "X2012", "X2013", "X2014", "X2015"))
+Sites_PerCountry <- ProccesISOSurveyByCountryRaw(Sites_PerCountry, c("X2010", "X2011", "X2012", "X2013", "X2014", "X2015"))
+#Cert_PerSector <- ProccesISOSurveyRaw(Cert_PerSector, c("X2010", "X2011", "X2012", "X2013", "X2014", "X2015"))
@@ -2,7 +2,6 @@
 #-----------------------------Parser Excel - ISO survey------------------------------------------------
 #------------------------------------------------------------------------------------------------------
-#-----------------------------Read from file-----------------------------------------------------------
 #' Get data frame from an excel file
 #'
@@ -11,6 +10,11 @@
 #' @param sheet index of sheet to parse
 #'
 #' @return data.frame
+#'
+#' @examples
+#' Cert_PerCountry <- ParseExcelFileRaw("./data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", 1)
+#' Sites_PerCountry <- ParseExcelFileRaw("./data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", 2)
+#' Cert_PerSector <- ParseExcelFileRaw("./data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", 3)
 ParseExcelFileRaw <- function(file, sheet){
   if (!file.exists(file)) {
@@ -22,21 +26,35 @@ ParseExcelFileRaw &lt;- function(file, sheet){
   dataset
 }
+
+
 #' Process raw data from ISO survey
 #'
-#' ...
+#' Proccess the raw data from ISO survey to replace NAs, normalizate country names and filter years
 #' @param dataset.raw raw data from ISO Survey excel file
+#' @param years List of years to return, c("X2006", "X2010", ...)
 #'
 #' @return data.frame
-ProccesISOSurveyRaw <- function(dataset.raw){
-  dataset <- dataset.raw[is.na(dataset.raw)]
+#'
+#' @examples
+#'
+#' Cert_PerCountry <- ProccesISOSurveyRaw(Cert_PerCountry, c("X2010", "X2011", "X2012", "X2013", "X2014", "X2015"))
+#' Sites_PerCountry <- ProccesISOSurveyRaw(Sites_PerCountry, c("X2010", "X2011", "X2012", "X2013", "X2014", "X2015"))
+#' Cert_PerSector <- ProccesISOSurveyRaw(Cert_PerSector, c("X2010", "X2011", "X2012", "X2013", "X2014", "X2015"))
+ProccesISOSurveyByCountryRaw <- function(dataset.raw, years){
+
+  #NAs to 0s
+  dataset <- dataset.raw
   dataset[is.na(dataset)] <- 0
   #Translate country names to 2 letter code
+  CountryNames <- GetCountryAbrev()
+
+  dataset <- merge(x = dataset, y = CountryNames, by = "Country", all.x = TRUE)
+
+  vars <- names(dataset)
+  years_checked <- intersect(vars, years)
+  dataset <- dataset[,c(c("Country", "country_short"), years_checked)]
   dataset
 }
-
-#ISO_survey_certificates_countries <- read.xlsx2(paste(getwd(), "/Data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", sep = ""), 1)
-#ISO_survey_sites_countries <- read.xlsx2(paste(getwd(), "/Data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", sep = ""), 2)
-#ISO_survey_certificates_sector <- read.xlsx2(paste(getwd(), "/Data/ISO/iso_27001_iso_survey2015_preprocessed.xlsx", sep = ""), 3)
@@ -14,18 +14,17 @@ LoadParserLibraries &lt;- function(){
   }
 }
-#' Return the 2 letter code of a country
+#' Return the 2 letter code of a country relation
 #'
-#' Translate from large country names included in the ISO Survey input file to 2 letter code
+#' Relation of country names included in the ISO Survey input file with 2 letter code
 #' included on the hackmaggedon input files
-#' @param largeName The normal large name of the country
 #'
-#' @return character with the 2 letter code of the country
-GetCountryAbrev <- function(largeName){
-  countries_large <- c("Afghanistan", "Albania", "Algeria", "Andorra", "Angola", "Argentina", "Armenia", "Australia", "Austria", "Azerbaijan", "Bahrain", "Bangladesh", "Belarus", "Belgium", "Belize", "Bolivia", "Bosnia and Herzegovina", "Botswana", "Brazil", "Bulgaria", "Cambodia", "Canada", "Cape Verde", "Chile", "China", "Hong Kong, China", "Taipei, Chinese", "Colombia", "Congo, Republic of", "Costa Rica", "CÔte D'Ivoire", "Croatia", "Cyprus", "Czech Republic", "Denmark", "Dominican Republic", "Ecuador", "Egypt", "El Salvador", "Estonia", "Ethiopia", "Finland", "France", "Georgia", "Germany", "Ghana", "Gibraltar (UK)", "Greece", "Guatemala", "Honduras", "Hungary", "Iceland", "India", "Indonesia", "Iran, Islamic Republic of", "Iraq", "Ireland", "Israel", "Italy", "Jamaica", "Japan", "Jordan", "Kazakhstan", "Kenya", "Korea, Democratic People's Republic of", "Korea, Republic of", "Kuwait", "Kyrgyzstan", "Lao People's Democratic Republic", "Latvia", "Lebanon", "Libyan Arab Jamahiriya", "Lithuania", "Luxembourg", "Macau, China", "Malawi", "Malaysia", "Mali", "Malta", "Mauritius", "Mexico", "Moldova, Republic of", "Montenegro", "Morocco", "Mozambique", "Namibia", "Nepal", "Netherlands", "New Zealand", "Nigeria", "Norway", "Oman", "Pakistan", "Panama", "Palestine", "Peru", "Philippines", "Poland", "Portugal", "Puerto Rico", "Qatar", "Romania", "Russian Federation", "Saint Lucia", "Saint Vincent and the Grenadines", "San Marino, Republic of", "Saudi Arabia", "Senegal", "Serbia", "Singapore", "Slovakia", "Slovenia", "Somalia", "South Africa", "Spain", "Sri Lanka", "Sudan", "Suriname", "Sweden", "Switzerland", "Syrian Arab Republic", "Tanzania, United Republic of", "Thailand", "The Former Yugoslav Republic of Macedonia", "Trinidad and Tobago", "Tunisia", "Turkey", "Turkmenistan", "Uganda", "Ukraine", "United Arab Emirates", "United Kingdom", "United States of America", "Uruguay", "Uzbekistan", "Venezuela", "Viet Nam", "Yemen")
-  countries_short <- c("AF", "AL", "DZ", "AD", "AO", "AR", "AM", "AU", "AT", "AZ", "BH", "BD", "BY", "BE", "BZ", "BO", "BA", "BW", "BR", "BG", "KH", "CA", "CV", "CL", "CN", "HK", "CN", "CO", "CD", "CR", "CI", "HR", "CY", "CZ", "DK", "DO", "EC", "EG", "SV", "EE", "ET", "FI", "FR", "GE", "DE", "GH", "GI", "GR", "GT", "HN", "HU", "IS", "IN", "ID", "IR", "IQ", "IE", "IL", "IT", "JM", "JP", "JO", "KZ", "KE", "KP", "KR", "KW", "KG", "LA", "LV", "LB", "LY", "LT", "LU", "MO", "MW", "MY", "ML", "MT", "MU", "MX", "MD", "ME", "MA", "MZ", "NA", "NP", "NL", "NZ", "NG", "NO", "OM", "PK", "PA", "PS", "PE", "PH", "PL", "PT", "PR", "QA", "RO", "RU", "LC", "VC", "SM", "SA", "SN", "RS", "SG", "SK", "SI", "SO", "ZA", "ES", "LK", "SD", "SR", "SE", "CH", "SY", "TZ", "TH", "MK", "TT", "TN", "TR", "TM", "UG", "UA", "AE", "GB", "US", "UY", "UZ", "VE", "VN", "YE")
+#' @return data.frame
+GetCountryAbrev <- function(){
+  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", "CuraÃ§ao", "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")
+  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")
-  dataset <- data.frame(countries_large, countries_short)
+  dataset <- data.frame(Country, country_short)
-  toString(dataset[dataset$countries_large == largeName, 2])
+  dataset
 }