知识库 : JIRA数据处理

# 从人员 , 模块 , 时间三个维度考虑 BUG, 任务 , 特征数量 , 及其变化趋势 .

data <- read.csv("e:/jria.csv");

// 数据预处理

data$ASSIGNEE <- as.character(data$ASSIGNEE);

data$issuetype <- as.numeric(data$issuetype);

data$issuenum <- as.numeric(data$issuenum);

data$comname <- as.character(data$comname);

temp <-as.Date(as.character(data$RESOLUTIONDATE))

data$reso.year <- format(temp,format = "%Y")

data$reso.month <- format(temp,format = "%m")

data$reso.day <- format(temp,format = "%d")

temp <-as.Date(as.character(data$CREATED))

data$create.year <- format(temp,format = "%Y")

data$create.month <- format(temp,format = "%m")

data$create.day <- format(temp,format = "%d")

aggfun <- function(data,statcolname){

  result.new <- aggregate(data$issueid,by = list("year" = data$create.year,"month" = data$create.month,"day"=data$create.day,statcolname=data[,statcolname]),length);

  colnames(result.new)[5] <- paste(statcolname,"newnumber",sep = ".");

  colnames(result.new)[4] <- statcolname;

  result.new <-  result.new[order( result.new$year, result.new$month, result.new$day,decreasing = FALSE),];

  result.reso <- aggregate(data$issueid,by = list("year" = data$reso.year,"month" = data$reso.month,"day"=data$reso.day,statcolname=data[,statcolname]),length);

  colnames(result.reso)[5] <- paste(statcolname,"resonumber",sep = ".");;

  colnames(result.reso)[4] <- statcolname;

  result.reso <-  result.reso[order( result.reso$year, result.reso$month, result.reso$day,decreasing = FALSE),];

  result <- merge(result.new,result.reso,by=c("year","month","day",statcolname),all = TRUE);

  result[is.na(result[,5]),5] <- 0;

  result[is.na(result[,6]),6] <- 0;

  return(result);

}