version 1.0.2

DESCRIPTION

@@ -1,18 +1,20 @@
 Package: tigerhitteR
 Type: Package
 Title: Pre-Process of Time Series Data Set in R
-Version: 1.0.1
-Date: 2016-07-05
+Version: 1.0.2
+Date: 2016-07-08
 Author: Will Kuan <aiien61will@gmail.com>
 Maintainer: Will Kuan <aiien61will@gmail.com>
 Description: Pre-process for discrete time series data set which is not continuous at the column
     of 'date'. Refilling records of missing 'date' and other columns to the hollow data set so that
     final data set is able to be dealt with time series analysis.
 License: GPL (>= 3)
+URL: https://github.com/Willdata/tigerhitteR
 LazyData: TRUE
 RoxygenNote: 5.0.1
-Depends: zoo (>= 1.7-12), openxlsx (>= 3.0.0)
+Imports: openxlsx (>= 3.0.0), zoo (>= 1.7-13), Hmisc (>= 3.17-4)
+Depends: R (>= 3.3.1)
 NeedsCompilation: no
-Packaged: 2016-07-05 07:24:35 UTC; will.kuan
+Packaged: 2016-07-07 18:11:13 UTC; will.kuan
 Repository: CRAN
-Date/Publication: 2016-07-05 11:01:45
+Date/Publication: 2016-07-07 23:52:13

MD5

@@ -1,6 +1,6 @@
-a821679ae390b677a049ee3f5137e185 *DESCRIPTION
-d4b5aaf4fc002307f0b4bc894b837682 *NAMESPACE
-234829e3243e4c3bc034f6f62af9aca8 *R/tigerhitteR.R
+c02a8a36f7530901852f772894317f16 *DESCRIPTION
+d84cc096f71b9e92752dc605d6b9f4d5 *NAMESPACE
+627fa4d7c996179bff929a586bfff62a *R/tigerhitteR.R
 9122cb0ccfb11fb24ff32f2b015572ee *data/data.example.rda
 32fa7739cad4285c6b4aad9a242ec2ea *man/data.example.Rd
 5f523a5b5685c3a5f13ad71268f6c62c *man/dateRefill.fromData.Rd

NAMESPACE

@@ -2,6 +2,8 @@
 
 export(dateRefill.fromData)
 export(dateRefill.fromsFile)
+import(Hmisc)
 import(openxlsx)
 import(zoo)
 importFrom(utils,head)
+importFrom(utils,install.packages)

R/tigerhitteR.R

@@ -8,8 +8,8 @@
 #' @param fixedVec  A row of column number which should be kept same values with the original
 #' @param pChanged The column number which should be changed to different value into new record.
 #' @param pChangedNum The value of a specific column which should be put into the new record.
-#' @import zoo openxlsx
-#' @importFrom utils head
+#' @import openxlsx zoo Hmisc
+#' @importFrom utils head install.packages
 #' @details Real time series sales dataset could be not continuous in 'date' field. e.g., monthly sales data is continuous,
 #'  but discrete in daily data.
 #'
@@ -22,17 +22,26 @@ dateRefill.fromsFile <-
   function(inPath, sheet, dateCol, outPath, fixedVec, pChanged, pChangedNum)
   {
     if(!requireNamespace("openxlsx",quietly = TRUE)){
-      stop("Please install package 'openxlsx'")
+      install.packages("openxlsx"); requireNamespace("openxlsx", quietly = TRUE)
+      #stop("Please install package 'openxlsx'. ")
     }else{
       requireNamespace("openxlsx", quietly = TRUE)
     }
 
     if(!requireNamespace("zoo", quietly = TRUE)){
-      stop("Please install package 'zoo'")
+      install.packages("zoo"); requireNamespace("zoo", quietly = TRUE)
+      #stop("Please install package 'zoo'. ")
     }else{
       requireNamespace("zoo", quietly = TRUE)
     }
 
+    if(!requireNamespace("Hmisc",quietly = TRUE)){
+      install.packages("Hmisc"); requireNamespace("Hmisc", quietly = TRUE)
+      #stop("Please install package 'Hmisc'. ")
+    }else{
+      requireNamespace("Hmisc", quietly = TRUE)
+    }
+
     data <- openxlsx::read.xlsx(inPath, sheet)
 
     data[,dateCol] <- zoo::as.Date(data[,dateCol], origin = "1899-12-30")
@@ -42,8 +51,7 @@ dateRefill.fromsFile <-
 
     data$Date <- as.POSIXlt(data$Date) # transform to POSIXlt type
 
-    y.min <- min(data$Date$year + 1900)
-    y.max <- max(data$Date$year + 1900)
+    year.list <- levels(factor(data$Date$year + 1900))
 
     ### sorting data
     inc.order <- order(data$Date, decreasing = FALSE)
@@ -60,18 +68,23 @@ dateRefill.fromsFile <-
     diff <- zoo::as.Date(data[1,2])-origin
     rm(year)
 
-    days <- as.numeric((y.max-y.min+1)*365-diff)
+    daySum <- 0
+    for(x in year.list)
+    {
+      daySum <- daySum + Hmisc::yearDays(zoo::as.Date(paste(x, "-01-01", sep = "")))
+    }
+    daySum <- as.numeric(daySum - diff)
 
-    final.data[1:days,] <- NA # remove first few null days because data is not start on 1/1
-    final.data[,2] <- seq(data[1,2], by = "1 days", length.out = days)
+    final.data[1:daySum,] <- NA # remove first few null days because data is not start on 1/1
+    final.data[,2] <- seq(data[1,2], by = "1 days", length.out = daySum)
 
     #### setting rownames
     rownames(data) <- c(1:nrow(data))
 
     my.index <- match(data$Date, as.POSIXlt(final.data$Date))
     final.data[my.index,] <- data[,]
 
-    for(i in days:1)
+    for(i in daySum:1)
     {
       if(!is.na(final.data[i,1])){
         tag <- i
@@ -91,7 +104,7 @@ dateRefill.fromsFile <-
       }
     }
 
-    final.data$Date <- as.Date(final.data$Date) # for correcting date time in excel
+    final.data$Date <- zoo::as.Date(final.data$Date) # for correcting date time in excel
 
     colnames(final.data) <- colNameVector
 
@@ -108,7 +121,8 @@ dateRefill.fromsFile <-
 #' @param fixedVec  A row of column number which should be kept same values with the original
 #' @param pChanged The column number which should be changed to different value into new record.
 #' @param pChangedNum The value of a specific column which should be put into the new record.
-#' @import zoo openxlsx
+#' @import zoo Hmisc
+#' @importFrom utils head install.packages
 #' @return The dataset which is completed.
 #' @details Real time series sales dataset could be not continuous in 'date' field. e.g., monthly sales data is continuous,
 #'  but discrete in daily data.
@@ -124,11 +138,19 @@ dateRefill.fromData <-
   function(data, dateCol, fixedVec, pChanged, pChangedNum)
   {
     if(!requireNamespace("zoo", quietly = TRUE)){
-      stop("Please install package 'zoo'")
+      install.packages("zoo"); requireNamespace("zoo", quietly = TRUE)
+      #stop("Please install package 'zoo'. ")
     }else{
       requireNamespace("zoo", quietly = TRUE)
     }
 
+    if(!requireNamespace("Hmisc",quietly = TRUE)){
+      install.packages("Hmisc"); requireNamespace("Hmisc", quietly = TRUE)
+      #stop("Please install package 'Hmisc'. ")
+    }else{
+      requireNamespace("Hmisc", quietly = TRUE)
+    }
+
     data <- data.frame(data)
 
     data[,dateCol] <- zoo::as.Date(data[,dateCol], origin = "1899-12-30")
@@ -138,8 +160,7 @@ dateRefill.fromData <-
 
     data$Date <- as.POSIXlt(data$Date) # transform to POSIXlt type
 
-    y.min <- min(data$Date$year + 1900)
-    y.max <- max(data$Date$year + 1900)
+    year.list <- levels(factor(data$Date$year + 1900))
 
     ### sorting data
     inc.order <- order(data$Date, decreasing = FALSE)
@@ -156,18 +177,23 @@ dateRefill.fromData <-
     diff <- zoo::as.Date(data[1,2])-origin
     rm(year)
 
-    days <- as.numeric((y.max-y.min+1)*365-diff)
+    daySum <- 0
+    for(x in year.list)
+    {
+      daySum <- daySum + Hmisc::yearDays(zoo::as.Date(paste(x, "-01-01", sep = "")))
+    }
+    daySum <- as.numeric(daySum - diff)
 
-    final.data[1:days,] <- NA # remove first few null days because data is not start on 1/1
-    final.data[,2] <- seq(data[1,2], by = "1 days", length.out = days)
+    final.data[1:daySum,] <- NA # remove first few null days because data is not start on 1/1
+    final.data[,2] <- seq(data[1,2], by = "1 days", length.out = daySum)
 
     #### setting rownames
     rownames(data) <- c(1:nrow(data))
 
     my.index <- match(data$Date, as.POSIXlt(final.data$Date))
     final.data[my.index,] <- data[,]
 
-    for(i in days:1)
+    for(i in daySum:1)
     {
       if(!is.na(final.data[i,1])){
         tag <- i
@@ -187,7 +213,7 @@ dateRefill.fromData <-
       }
     }
 
-    final.data$Date <- as.Date(final.data$Date) # for correcting date time in excel
+    final.data$Date <- zoo::as.Date(final.data$Date) # for correcting date time in excel
 
     colnames(final.data) <- colNameVector