In leppott/ContDataQC: Quality Control (QC) of Continous Monitoring Data

knitr::opts_chunk$set(results='asis', echo=FALSE, warning=FALSE)
# needed for trouble shooting
#myConfig <- file.path(system.file(package="ContDataQC"), "extdata", "config.ORIG.R")
#source(myConfig)

DATA FILE INFORMATION

  # Report Info
  myReportDate <- format(Sys.Date(),ContData.env$myFormat.Date)
  cat(paste("**Report Date:** ",myReportDate,"\n\n",sep=""))
  myUser <- Sys.getenv("USERNAME")
  cat(paste("**Generated By:** ",myUser,"\n\n",sep=""))

  #filename
  cat("**Filename:** ",strFile,"\n\n",sep="")

  cat(paste("**SiteID:** ",strFile.SiteID,"\n\n",sep=""))

  cat(paste("**Period of Record, Requested:** ",fun.myData.DateRange.Start," to ",fun.myData.DateRange.End,sep="",collapse="\n\n"))

  # myTimeDiff <- difftime(data.import[11,ContData.env$myName.DateTime],data.import[10,ContData.env$myName.DateTime],units="mins")
  #x <- data.import[,ContData.env$myName.DateTime]
  myT <- strptime(data.import[,ContData.env$myName.DateTime],format=ContData.env$myFormat.DateTime)
  myTimeDiff.all <- difftime(myT[-1],myT[-length(myT)],units="mins")
  myTimeDiff <- median(as.vector(myTimeDiff.all),na.rm=TRUE)

  cat(paste("\n\n**Period of Record, Actual:** ",min(data.import[,myName.Date])," to ",max(data.import[,myName.Date]),"\n\n",sep=""))

  cat(paste("**Recording Interval:** ",myTimeDiff[1]," minutes\n\n",sep=""))

  cat(paste("**Data Type:** ",strFile.DataType,"\n\n",sep=""))  # need to do better

   myParameters <- ContData.env$myNames.DataFields[ContData.env$myNames.DataFields %in% names(data.import)==TRUE] 
   myParameters.Lab <- ContData.env$myNames.DataFields.Lab[ContData.env$myNames.DataFields %in% names(data.import)==TRUE]
 #cat("**Parameters:** ",paste(myParameters.Lab,", ",sep=""),"\n\n",sep="")
  # above line not working, preventing pandoc conversion to WORD
  #cat("**Included Parameters:** \n\n")
  cat("**Parameters Included:** ",paste(myParameters,", ",sep=""),"\n\n",sep="")

STATISTICAL SUMMARY, BY PARAMETER

Summary statistics and plots by parameter and time frame (year, season, month, and daily)

#  # 3. Data Info, by Parameter
#     # Individual Data Type Report
#     # QC
#     #i <- myParameters[1]
#      for (i in myParameters) {##FOR.i.START
# #       #
#        i.num <- match(i,myParameters)
#        myTitle.Sub <- myParameters.Lab[i.num]
#        
#        
#       cat("## QC TESTS, ",i,"\n\n",sep="")
#        
#        #cat(paste("**QC TESTS,",myTitle.Sub,sep=""))
#        
#        # 3.1. Flags, overall
#        cat(myTitle.Sub <- "### Flags")
#              cat("\n\n")
#       cat("#### Flag summary, overall number of records.")
#       cat("\n\n")
#        myTable <- table(data.import[,paste("Flag",i,sep=".")])
#        print(knitr::kable(t(as.matrix(myTable)), format = "markdown"))
#       
#       cat("\n\n")
#        
#       #
#       # 3.1.A Records by Month/Day
#       cat("Month and Day versus number of records.")
#       cat("\n\n")
#       # split so easier to put on paper
#       # number of records by month/day (split 1:15 and 16:31)
#       # filter for records by parameter that are not NA
#       myTable <- table(data.import[,"month"][data.import[,"day"]<=15 & !is.na(data.import[,i]) & data.import[,i]!=""],data.import[,"day"][data.import[,"day"]<=15 & !is.na(data.import[,i]) & data.import[,i]!=""])
#       #print(myTable)
#       print(knitr::kable(as.matrix(myTable)), format = "markdown")
#       # don't (t)ransform this table
#       
#       myTable <- table(data.import[,"month"][data.import[,"day"]>15 & !is.na(data.import[,i]) & data.import[,i]!=""],data.import[,"day"][data.import[,"day"]>15 & !is.na(data.import[,i]) & data.import[,i]!=""])
#       #print(myTable)
#       print(knitr::kable(as.matrix(myTable)), format = "markdown")
#       # don't (t)ransform this table
#       
#       
#       
#       #
#       
#       cat("\n\n")
#       
#       # Convert time interval (minutes) to number per day
#       records.expected <- 24*60/as.numeric(myTimeDiff[1])
#       
#       cat(paste("Expected number of records per day is ",records.expected,".",sep=""))
#       
#       # identify days/months where not the expected number of records
#       # (expect first and last day)
#   #    print("days where not the expected number of records")
#       #
#       # 3.2. Flags by QC Test
#       
#       cat("\n\n")
#       
#       cat("#### Flags by QC Test")
#       
#       cat("\n\n")
#       
#       cat("##### Flags, Gross\n\n")
#       
#       myTable <- table(data.import[,paste("Flag.Gross",i,sep=".")])
#       print(knitr::kable(t(as.matrix(myTable)), format = "markdown"))
#         cat("\n\n")
#       cat("##### Flags, Spike\n\n")
#       
#       myTable <- table(data.import[,paste("Flag.Spike",i,sep=".")])
#       print(knitr::kable(t(as.matrix(myTable)), format = "markdown"))
#         cat("\n\n")
#       cat("##### Flags, RoC\n\n")
#       
#       myTable <- table(data.import[,paste("Flag.RoC",i,sep=".")])
#       print(knitr::kable(t(as.matrix(myTable)), format = "markdown"))
#         cat("\n\n")
#       cat("##### Flags, Flat\n\n")
#       
#       myTable <- table(data.import[,paste("Flag.Flat",i,sep=".")])
#       print(knitr::kable(t(as.matrix(myTable)), format = "markdown"))
#         cat("\n\n")
#       cat("QC Test Flag fields are saved in the data file so the user can identify data points that have been flagged as suspect or fail.")
#      
#       #
#       #myFlagTests <- c("Gross","Spike","RoC","Flat")
#       #(myTable.Flags.Flat <- ftable(data.import[,paste("Flag",myFlagTests,i,sep=".")]))
#       #
#       
#       
#       cat("\n\n Test results marked as 9 (Missing Data) if unable to calculate the end point needed for the test.  For example, the first record does not have a previous record for comparison for the Gross QC Test.  QC Test flags are saved in the data file.")
#       
#       #
#       # 3.3. Plot
#       data.plot <- data.import
#       #
#       # cheat on Date/Time axis
#       n.Total <- length(data.plot[,myName.Date])
#       pct <- c(20,40,60,80,100)*.01
#       myAT <- c(1,round(n.Total * pct,0))
#       myLab <- data.plot[,myName.Date][myAT]
#       #
#       myPlot.Y <- data.plot[,i]
#       myPlot.Ylab <- myParameters.Lab[i.num]
#       plot(myPlot.Y,type="l",main=fun.myData.SiteID,xlab=myLab.Date,ylab=myPlot.Ylab,col="gray", xaxt="n")
#       axis(1,at=myAT,labels=myLab,tick=TRUE)
#       
#       cat("\n\n")
#       
#       #
#     }##FOR.i.END