Cambias parser hackmaggedon

Miguel Tuñón
1 parent 274ef06d
Showing 78 changed files with 125 additions and 11 deletions
ISO27001effectiveness/DESCRIPTION
ISO27001effectiveness/Main.R
ISO27001effectiveness/NAMESPACE
ISO27001effectiveness/R/Hackmageddon_Parser.R
ISO27001effectiveness/R/ISOSurvey_Parser.R
ISO27001effectiveness/data/hackmageddon/2016/1-15 April 2016 Cyber Attacks Timeline.xlsx → ISO27001effectiveness/data/hackmageddon/Format1/1-15 April 2016 Cyber Attacks Timeline.xlsx
ISO27001effectiveness/data/hackmageddon/2015/1-15 August 2015 Cyber Attacks Timeline.xlsx → ISO27001effectiveness/data/hackmageddon/Format1/1-15 August 2015 Cyber Attacks Timeline.xlsx
ISO27001effectiveness/data/hackmageddon/Format1/1-15 December 2015 Cyber Attacks Timeline.xlsx
ISO27001effectiveness/data/hackmageddon/2016/1-15 February 2016 Cyber Attacks Timeline.xlsx → ISO27001effectiveness/data/hackmageddon/Format1/1-15 February 2016 Cyber Attacks Timeline.xlsx
ISO27001effectiveness/data/hackmageddon/2016/1-15 January 2016 Cyber Attacks Timeline.xlsx → ISO27001effectiveness/data/hackmageddon/Format1/1-15 January 2016 Cyber Attacks Timeline.xlsx
ISO27001effectiveness/data/hackmageddon/Format1/1-15 Jul 2015 Cyber Attacks Timeline.xlsx
ISO27001effectiveness/data/hackmageddon/2016/1-15 July 2016 Cyber Attacks Timelines.xlsx → ISO27001effectiveness/data/hackmageddon/Format1/1-15 July 2016 Cyber Attacks Timelines.xlsx
ISO27001effectiveness/data/hackmageddon/2016/1-15 June 2016 Cyber Attacks Timeline.xlsx → ISO27001effectiveness/data/hackmageddon/Format1/1-15 June 2016 Cyber Attacks Timeline.xlsx
ISO27001effectiveness/data/hackmageddon/2016/1-15 March 2016 Cyber Attacks Timeline.xlsx → ISO27001effectiveness/data/hackmageddon/Format1/1-15 March 2016 Cyber Attacks Timeline.xlsx
ISO27001effectiveness/data/hackmageddon/2016/1-15 May 2016 Cyber Attacks Timeline.xlsx → ISO27001effectiveness/data/hackmageddon/Format1/1-15 May 2016 Cyber Attacks Timeline.xlsx
ISO27001effectiveness/data/hackmageddon/2015/1-15 November 2015 Cyber Attacks Timeline.xlsx → ISO27001effectiveness/data/hackmageddon/Format1/1-15 November 2015 Cyber Attacks Timeline.xlsx
ISO27001effectiveness/data/hackmageddon/2015/1-15 October 2015 Cyber Attacks Timeline.xlsx → ISO27001effectiveness/data/hackmageddon/Format1/1-15 October 2015 Cyber Attacks Timeline.xlsx
ISO27001effectiveness/data/hackmageddon/2016/1-15 October 2016 Cyber Attacks Timeline.xlsx → ISO27001effectiveness/data/hackmageddon/Format1/1-15 October 2016 Cyber Attacks Timeline.xlsx
ISO27001effectiveness/data/hackmageddon/2015/1-15 September 2015 Cyber Attacks Timeline.xlsx → ISO27001effectiveness/data/hackmageddon/Format1/1-15 September 2015 Cyber Attacks Timeline.xlsx
ISO27001effectiveness/data/hackmageddon/2016/1-15 September 2016 Cyber Attacks Timeline.xlsx → ISO27001effectiveness/data/hackmageddon/Format1/1-15 September 2016 Cyber Attacks Timeline.xlsx
@@ -8,4 +8,5 @@ Description: More about what it does (maybe more than one line)
     Use four spaces when indenting paragraphs within the Description.
 License: What license is it under?
 Encoding: UTF-8
-LazyData: true
 \ No newline at end of file
+LazyData: true
+RoxygenNote: 5.0.1
@@ -6,6 +6,8 @@ Cert_PerCountry &lt;- ParseExcelFileRaw(&quot;./data/ISO/iso_27001_iso_survey2015_prepro
 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"))
+Cert_PerCountry <- ProccesISOSurveyByCountryRaw(Cert_PerCountry, c("X2012", "X2013", "X2014", "X2015"))
+Sites_PerCountry <- ProccesISOSurveyByCountryRaw(Sites_PerCountry, c( "X2012", "X2013", "X2014", "X2015"))
+#Cert_PerSector <- ProccesISOSurveyRaw(Cert_PerSector, c("X2012", "X2013", "X2014", "X2015"))
+
+Attacks <- GetAttacksData()
-exportPattern("^[[:alpha:]]+")
+# Generated by roxygen2: do not edit by hand
+
@@ -4,33 +4,62 @@
  
  
  
-ParseHMExcel <- function(file){
+ParseHMExcel <- function(file, cols){
   print(file)
   if (!file.exists(file)) {
     stop(paste("Error, file [", file, "] not found"))
   }
-  dataset <- read.xlsx2(file, 1, header = TRUE,colIndex = 2:10, colClasses = c("Date", "character", "character", "character", "character", "character", "character", "character"))
+  dataset <- xlsx::read.xlsx2(file, 1, header = TRUE,colIndex = cols, colClasses = c("numeric", "character", "character", "character"))
+
+  if (is.null(dataset$Date)) {
+    dataset <- xlsx::read.xlsx2(file, 1, header = TRUE,colIndex = cols, colClasses = c("numeric", "character", "character", "character"), startRow = 2)
+  }
+
   dataset
 }
  
 ProccesHMRaw <- function(dataset.raw){
  
   #Remove rows with Date NA
+  print(class(dataset.raw$Date))
   dataset <- dataset.raw[!is.na(dataset.raw$Date),]
+  dataset$Date <- as.POSIXct(dataset$Date*86400, tz ="GMT", origin ="1904-01-01")
  
   dataset
 }
  
-ParseHMFolder <- function(folder){
+#' Title
+#'
+#' @param folder
+#' @param cols
+#'
+#' @return
+#' @export
+#'
+#' @examples
+ParseHMFolder <- function(folder, cols){
   filelist <- list.files(folder)
   #frames <- lapply(paste(folder,filelist,sep = ""),ParseHMExcel)
-  dataset <- ProccesHMRaw(ParseHMExcel(paste(folder,filelist[1],sep = "/")))
+
+  myFile <- paste(folder,filelist[1],sep = "")
+  dataset <- ProccesHMRaw(ParseHMExcel(myFile, cols))
  
   for (i in 2:length(filelist)) {
-    dataset <- rbind(dataset, ProccesHMRaw(ParseHMExcel(paste(folder,filelist[i],sep = "/"))))
+    dataset <- rbind(dataset, ProccesHMRaw(ParseHMExcel(paste(folder,filelist[i],sep = ""), cols)))
   }
  
   dataset
 }
  
+GetAttacksData <- function() {
+
+  format1 <- ParseHMFolder("./data/hackmageddon/Format1/", c(2, 9, 7, 6))
+  format2 <- ParseHMFolder("./data/hackmageddon/Format2/", c(2,7, 5, 6))
+  format3 <- ParseHMFolder("./data/hackmageddon/Format3/", c(2, 9, 7, 6))
+  format4 <- ParseHMFolder("./data/hackmageddon/Format4/", c(1, 9, 5, 3))
+
+  dataset <- rbind(format1, format2, format3, format4)
+
+  dataset
+}
  
@@ -21,7 +21,7 @@ ParseExcelFileRaw &lt;- function(file, sheet){
     stop(paste("Error, file [", file, "] not found"))
   }
  
-  dataset <- read.xlsx2(file, sheet,colClasses = c("character","numeric","numeric","numeric","numeric","numeric","numeric","numeric","numeric","numeric","numeric"), header = TRUE, as.data.frame = TRUE)
+  dataset <- xlsx::read.xlsx2(file, sheet,colClasses = c("character","numeric","numeric","numeric","numeric","numeric","numeric","numeric","numeric","numeric","numeric"), header = TRUE, as.data.frame = TRUE)
  
   dataset
 }
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/Util.R
+\name{GetCountryAbrev}
+\alias{GetCountryAbrev}
+\title{Return the 2 letter code of a country relation}
+\usage{
+GetCountryAbrev()
+}
+\value{
+data.frame
+}
+\description{
+Relation of country names included in the ISO Survey input file with 2 letter code
+included on the hackmaggedon input files
+}
+
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/Util.R
+\name{LoadParserLibraries}
+\alias{LoadParserLibraries}
+\title{Install and load required libraries}
+\usage{
+LoadParserLibraries()
+}
+\description{
+This function checks if every required library is installed to be loaded, if not they will be installed and then loaded.
+Libraries installed:
+ xlsx to parse excel files like ISO survey source format
+}
+
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/ISOSurvey_Parser.R
+\name{ParseExcelFileRaw}
+\alias{ParseExcelFileRaw}
+\title{Get data frame from an excel file}
+\usage{
+ParseExcelFileRaw(file, sheet)
+}
+\arguments{
+\item{file}{path to excel file}
+
+\item{sheet}{index of sheet to parse}
+}
+\value{
+data.frame
+}
+\description{
+Check if the file exists and then parse it into a 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)
+}
+
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/ISOSurvey_Parser.R
+\name{ProccesISOSurveyByCountryRaw}
+\alias{ProccesISOSurveyByCountryRaw}
+\title{Process raw data from ISO survey}
+\usage{
+ProccesISOSurveyByCountryRaw(dataset.raw, years)
+}
+\arguments{
+\item{dataset.raw}{raw data from ISO Survey excel file}
+
+\item{years}{List of years to return, c("X2006", "X2010", ...)}
+}
+\value{
+data.frame
+}
+\description{
+Proccess the raw data from ISO survey to replace NAs, normalizate country names and filter years
+}
+\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"))
+}
+