start

.Rbuildignore

@@ -0,0 +1,2 @@
+^.*\.Rproj$
+^\.Rproj\.user$

.Rproj.user/366773DE/pcs/files-pane.pper

@@ -0,0 +1,9 @@
+{
+    "sortOrder": [
+        {
+            "columnIndex": 2,
+            "ascending": true
+        }
+    ],
+    "path": "~/bioinformatics/ggdendroplot"
+}

.Rproj.user/366773DE/pcs/source-pane.pper

@@ -0,0 +1,3 @@
+{
+    "activeTab": 1
+}

.Rproj.user/366773DE/pcs/windowlayoutstate.pper

@@ -0,0 +1,14 @@
+{
+    "left": {
+        "splitterpos": 428,
+        "topwindowstate": "NORMAL",
+        "panelheight": 1032,
+        "windowheight": 1070
+    },
+    "right": {
+        "splitterpos": 642,
+        "topwindowstate": "NORMAL",
+        "panelheight": 1032,
+        "windowheight": 1070
+    }
+}

.Rproj.user/366773DE/pcs/workbench-pane.pper

@@ -0,0 +1,5 @@
+{
+    "TabSet1": 0,
+    "TabSet2": 1,
+    "TabZoom": {}
+}

.Rproj.user/366773DE/persistent-state

@@ -0,0 +1,8 @@
+build-last-errors="[]"
+build-last-errors-base-dir="~/bioinformatics/ggdendroplot/"
+build-last-outputs="[{\"type\":0,\"output\":\"==> R CMD INSTALL --no-multiarch --with-keep.source ggdendroplot\\n\\n\"},{\"type\":1,\"output\":\"* installing to library ‘/home/nhuber/R/x86_64-redhat-linux-gnu-library/3.6’\\n\"},{\"type\":1,\"output\":\"* installing *source* package ‘ggdendroplot’ ...\\n\"},{\"type\":1,\"output\":\"** using staged installation\\n\"},{\"type\":1,\"output\":\"** R\\n\"},{\"type\":1,\"output\":\"** byte-compile and prepare package for lazy loading\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"  converting help for package ‘ggdendroplot’\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** help\\n\"},{\"type\":1,\"output\":\"*** installing help indices\\n\"},{\"type\":1,\"output\":\"    finding HTML links ...\"},{\"type\":1,\"output\":\"    geom_dendro                             html  \\n\"},{\"type\":1,\"output\":\"    hello                                   html  \\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\" done\\n\"},{\"type\":1,\"output\":\"** building package indices\\n\"},{\"type\":1,\"output\":\"** testing if installed package can be loaded from temporary location\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** testing if installed package can be loaded from final location\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** testing if installed package keeps a record of temporary installation path\\n\"},{\"type\":1,\"output\":\"* DONE (ggdendroplot)\\n\"},{\"type\":1,\"output\":\"\"}]"
+compile_pdf_state="{\"tab_visible\":false,\"running\":false,\"target_file\":\"\",\"output\":\"\",\"errors\":[]}"
+files.monitored-path=""
+find-in-files-state="{\"handle\":\"\",\"input\":\"\",\"path\":\"\",\"regex\":false,\"ignoreCase\":false,\"results\":{\"file\":[],\"line\":[],\"lineValue\":[],\"matchOn\":[],\"matchOff\":[],\"replaceMatchOn\":[],\"replaceMatchOff\":[]},\"running\":false,\"replace\":false,\"preview\":false,\"gitFlag\":false,\"replacePattern\":\"\"}"
+imageDirtyState="1"
+saveActionState="-1"

.Rproj.user/366773DE/rmd-outputs

@@ -0,0 +1,5 @@
+
+
+
+
+

.Rproj.user/366773DE/saved_source_markers

@@ -0,0 +1 @@
+{"active_set":"","sets":[]}

.Rproj.user/366773DE/sources/prop/35DB2880

@@ -0,0 +1,5 @@
+{
+    "tempName": "Untitled1",
+    "cursorPosition": "0,2",
+    "scrollLine": "0"
+}

.Rproj.user/366773DE/sources/prop/B307ED6A

@@ -0,0 +1,4 @@
+{
+    "cursorPosition": "2,0",
+    "scrollLine": "0"
+}

.Rproj.user/366773DE/sources/prop/CFE6B31E

@@ -0,0 +1 @@
+{}

.Rproj.user/366773DE/sources/prop/INDEX

@@ -0,0 +1,3 @@
+~%2FDesktop%2Fgghierarchy.R="B307ED6A"
+~%2Fbioinformatics%2Fggdendroplot%2FR%2Fgeom_dendro.R="35DB2880"
+~%2Fbioinformatics%2Fggdendroplot%2FR%2Fhello.R="CFE6B31E"

.Rproj.user/366773DE/sources/s-9810FC5B/52DBD5A1-contents

@@ -0,0 +1,18 @@
+# Hello, world!
+#
+# This is an example function named 'hello' 
+# which prints 'Hello, world!'.
+#
+# You can learn more about package authoring with RStudio at:
+#
+#   http://r-pkgs.had.co.nz/
+#
+# Some useful keyboard shortcuts for package authoring:
+#
+#   Install Package:           'Ctrl + Shift + B'
+#   Check Package:             'Ctrl + Shift + E'
+#   Test Package:              'Ctrl + Shift + T'
+
+hello <- function() {
+  print("Hello, world!")
+}

.Rproj.user/366773DE/sources/s-9810FC5B/98169FE9-contents

@@ -0,0 +1,104 @@
+seeqR::main()
+x <- matrix(rnorm(100), nrow = 8)
+rownames(x) <- paste0("a",seq(nrow(x)))
+a <- dist(x)
+clust <- hclust(a, method="complete")
+ggdendro::ggdendrogram(clust)
+ggplot() + geom_dendro(clust)
+ggplot() + geom_dendro(x, axis.labels = T, pointing = "side", ylim = c(3,12))
+
+
+geom_dendro <- function(clust, xlim=NULL, ylim=NULL, pointing="updown", show.labels=TRUE, axis.labels=TRUE, ...){
+  ranks <- clust$order
+  samples <- clust$labels[ranks]
+  dflabel <- data.frame(label=samples, x=seq(length(samples)), y=0)
+
+  confusingRanks <- sapply(seq(length(ranks)), function(x) which(ranks==x))
+
+  #========================
+  #df is a data.frame with one row for each arch
+  df <- as.data.frame(clust$merge) %>% mutate(y=clust$height)
+  dfy <- data.frame(y1=apply(df, 1, function(x) ifelse(x[1]<0, 0, df[x[1],"y"])),
+                    y2=apply(df, 1, function(x) ifelse(x[2]<0, 0, df[x[2],"y"])) )
+
+  #needs to be a loop because the rows are calculated successively and depend on those that were calculated before
+  dfx <- data.frame()
+  for(i in 1:nrow(df)){
+    dfx[i,1] <- ifelse(df[i,1]<0, confusingRanks[abs(df[i,1])], mean(c(dfx[df[i,1],1], dfx[df[i,1],2])))
+    dfx[i,2] <- ifelse(df[i,2]<0, confusingRanks[abs(df[i,2])], mean(c(dfx[df[i,2],1], dfx[df[i,2],2])))
+  }
+  colnames(dfx) <- c("x1","x2")
+  df <- cbind(df, dfy, dfx)
+
+  #========================
+  #df2 is a list of data.frames (one for each arch), listing their x and y coordinates for a geom_path
+  df2 <- lapply(seq(nrow(df)), function(xyz){
+    rx <- unlist(df[xyz,])
+    return( data.frame(x=c(rx[6], rx[6], rx[7], rx[7]), y=c(rx[4], rx[3], rx[3], rx[5]), z=xyz ))
+  })
+
+  #========================
+  #df3 rbinds all data.frames from df2, with one column for x, y and z (z just stats which arch it is)
+  df3 <- do.call(rbind, df2)
+  if(pointing %in% "side"){
+    colnames(df3) <- c("y","x","z")
+    colnames(dflabel) <- c("label","y","x")
+  }
+
+  extremes <- c(range(df3$x), range(df3$y))
+  delta <- c(abs(extremes[2]-extremes[1]), abs(extremes[4]-extremes[3]))
+  if(is.null(xlim)) xlim <- extremes[1:2]
+  if(is.null(ylim)) ylim <- extremes[3:4]
+
+
+  #relevel the coordinates from 0 to 1 for both x and y
+  df4 <- df3
+  df4$x <- (df3$x-extremes[1])/delta[1]
+  df4$y <- (df3$y-extremes[3])/delta[2]
+  dflabel$x <- (dflabel$x-extremes[1])/delta[1]
+  dflabel$y <- (dflabel$y-extremes[3])/delta[2]
+
+  #relevel the coordinates to fit xlim and ylim (if not user-defined, the original values are taken)
+  df5 <- df4
+  df5$x <- (xlim[2]-xlim[1])*df4$x + xlim[1]
+  df5$y <- (ylim[2]-ylim[1])*df4$y + ylim[1]
+  dflabel$x <- (xlim[2]-xlim[1])*dflabel$x + xlim[1]
+  dflabel$y <- (ylim[2]-ylim[1])*dflabel$y + ylim[1]
+
+  df6 <- split(df5, df5$z)
+
+  output1 <- lapply(df6, function(x, ...){
+    return(ggplot2::layer(
+      data=x,
+      mapping=ggplot2::aes(x=x, y=y),
+      geom="path",
+      stat="identity",
+      position="identity",
+      show.legend=FALSE,
+      params=list(...)
+    ))
+  })
+  if(show.labels){
+    output2 <- ggplot2::layer(
+      data=dflabel,
+      mapping=ggplot2::aes(x=x, y=y, label=label),
+      geom="text",
+      stat="identity",
+      position="identity",
+      show.legend=FALSE,
+      params=list(...)
+    )
+    if(pointing %in% "updown" & ylim[1]<ylim[2]){
+      output2$aes_params[["vjust"]] <- 1
+    }else if(pointing %in% "updown" & ylim[1]>ylim[2]){
+      output2$aes_params[["vjust"]] <- 0
+    }else if(pointing %in% "side" & xlim[1]<xlim[2]){
+      output2$aes_params[["hjust"]] <- 1
+    }else if(pointing %in% "side" & xlim[1]>xlim[2]){
+      output2$aes_params[["hjust"]] <- 0
+    }else{NULL}
+
+  }
+  return(c(output1, output2))
+}
+

.Rproj.user/366773DE/sources/s-9810FC5B/9C084B7F

@@ -0,0 +1,25 @@
+{
+    "id": "9C084B7F",
+    "path": "~/bioinformatics/ggdendroplot/R/geom_dendro.R",
+    "project_path": "R/geom_dendro.R",
+    "type": "r_source",
+    "hash": "0",
+    "contents": "",
+    "dirty": false,
+    "created": 1614929393099.0,
+    "source_on_save": false,
+    "relative_order": 2,
+    "properties": {
+        "tempName": "Untitled1",
+        "cursorPosition": "0,2",
+        "scrollLine": "0"
+    },
+    "folds": "",
+    "lastKnownWriteTime": 1614935809,
+    "encoding": "UTF-8",
+    "collab_server": "",
+    "source_window": "",
+    "last_content_update": 1614935809263,
+    "read_only": false,
+    "read_only_alternatives": []
+}

.Rproj.user/366773DE/sources/s-9810FC5B/9C084B7F-contents

@@ -0,0 +1,131 @@
+# devtools::document()
+
+#' create a dendrogram as several geom_path layers ready to be added to a ggplot object
+#'
+#' Imports:
+#' ggplot2
+#'
+#' @inheritParams ggplot2::geom_path
+#' @import ggplot2
+#'
+#' @param data data.frame, columns will be clustered based on their rows.
+#' @param xlim, vector with 2 numbers, on the x axis the dendrogram will beginn at the first number and end at the second.
+#' @param ylim, vector with 2 numbers, on the y axis the dendrogram will beginn at the first number and end at the second.
+#' @param pointing, string, either "side" or "updown" (default) to indicate where the dendrogram should point.
+#' @param clustmethod string, method to be used by the hclust function (check ?hclust for available methods).
+#' @param axis.labels, boolean, whether or not the axis should show the column names of data. This adds another layer to define the axis labels.
+#' @return a list of several ggplot2 layer objects (geom_path for the dendrogram) that can directly be added to a ggplot2 object
+#' @details the function uses geom_path for the dendrogram, so ... takes all arguements that geom_path would also take, such as color, size, etc.
+#' @export
+#' @examples
+#' library(ggdendroplot)
+#' library(ggplot2)
+#'
+#' df <- matrix(rnorm(128), ncol = 8)
+#' colnames(df) <- paste0("a",seq(ncol(df)))
+#'
+#' ggplot() + geom_dendro(data=df)
+#' ggplot() + geom_dendro(data=df, pointing="side")
+#' ggplot() + geom_dendro(data=df, xlim=c(3,0))
+#' ggplot() + geom_dendro(data=df, ylim=c(3,0))
+#' ggplot() + geom_dendro(data=df, size=2, color="blue", linetype="dashed")
+#' ggplot() + geom_dendro(data=df, size=4, lineend="round")
+#'
+geom_dendro <- function(data, xlim=NULL, ylim=NULL, pointing="updown", clustmethod="complete", axis.labels=TRUE, ...){
+
+  calc <- .plotcalculation(data=data, xlim=xlim, ylim=ylim, pointing=pointing, clustmethod=clustmethod)
+
+  dendro <- calc[["dendro"]] #for the dendrogram
+  plotlabels <- calc[["plotlabels"]] #for labels as axis text
+
+  #plot many geom_paths to create one dendrogram; each path is an item in a list
+  output <- lapply(dendro, function(x){
+    return(ggplot2::layer(
+      data=x,
+      mapping=ggplot2::aes(x=x, y=y),
+      geom="path",
+      stat="identity",
+      position="identity",
+      show.legend=FALSE,
+      params=list(...)
+    ))
+  })
+
+  if(axis.labels){
+    ggplotlabel <- switch(pointing,
+                          "updown"=scale_x_continuous(breaks=plotlabels$x, labels=plotlabels$label),
+                          "side"=scale_y_continuous(breaks=plotlabels$y, labels=plotlabels$label))
+
+    output <- c(output, ggplotlabel)
+  }
+
+  return(output)
+}
+
+.plotcalculation <- function(data, xlim, ylim, pointing, clustmethod){
+  distmatrix <- dist(t(data))
+  clust <- hclust(distmatrix, method=clustmethod)
+
+  ranks <- clust$order
+  samples <- clust$labels[ranks]
+  dflabel <- data.frame(label=samples, x=seq(length(samples)), y=0)
+
+  confusingRanks <- sapply(seq(length(ranks)), function(x) which(ranks==x))
+
+  #========================
+  #df is a data.frame with one row for each arch
+  df <- cbind(as.data.frame(clust$merge), y=clust$height)
+  dfy <- data.frame(y1=apply(df, 1, function(x) ifelse(x[1]<0, 0, df[x[1],"y"])),
+                    y2=apply(df, 1, function(x) ifelse(x[2]<0, 0, df[x[2],"y"])) )
+
+  #needs to be a loop because the rows are calculated successively and depend on those that were calculated before
+  dfx <- data.frame()
+  for(i in 1:nrow(df)){
+    dfx[i,1] <- ifelse(df[i,1]<0, confusingRanks[abs(df[i,1])], mean(c(dfx[df[i,1],1], dfx[df[i,1],2])))
+    dfx[i,2] <- ifelse(df[i,2]<0, confusingRanks[abs(df[i,2])], mean(c(dfx[df[i,2],1], dfx[df[i,2],2])))
+  }
+  colnames(dfx) <- c("x1","x2")
+  df <- cbind(df, dfy, dfx)
+
+  #========================
+  #df2 is a list of data.frames (one for each arch), listing their x and y coordinates for a geom_path
+  df2 <- lapply(seq(nrow(df)), function(xyz){
+    rx <- unlist(df[xyz,])
+    return( data.frame(x=c(rx[6], rx[6], rx[7], rx[7]), y=c(rx[4], rx[3], rx[3], rx[5]), z=xyz ))
+  })
+
+  #========================
+  #df3 rbinds all data.frames from df2, with one column for x, y and z (z just stats which arch it is)
+  df3 <- do.call(rbind, df2)
+  if(pointing %in% "side"){
+    colnames(df3) <- c("y","x","z")
+    colnames(dflabel) <- c("label","y","x")
+  }
+
+  extremes <- c(range(df3$x), range(df3$y))
+  delta <- c(abs(extremes[2]-extremes[1]), abs(extremes[4]-extremes[3]))
+  if(is.null(xlim)) xlim <- extremes[1:2]
+  if(is.null(ylim)) ylim <- extremes[3:4]
+
+
+  #relevel the coordinates from 0 to 1 for both x and y
+  df4 <- df3
+  df4$x <- (df3$x-extremes[1])/delta[1]
+  df4$y <- (df3$y-extremes[3])/delta[2]
+  dflabel$x <- (dflabel$x-extremes[1])/delta[1]
+  dflabel$y <- (dflabel$y-extremes[3])/delta[2]
+
+  #relevel the coordinates to fit xlim and ylim (if not user-defined, the original values are taken)
+  df5 <- df4
+  df5$x <- (xlim[2]-xlim[1])*df4$x + xlim[1]
+  df5$y <- (ylim[2]-ylim[1])*df4$y + ylim[1]
+  dflabel$x <- (xlim[2]-xlim[1])*dflabel$x + xlim[1]
+  dflabel$y <- (ylim[2]-ylim[1])*dflabel$y + ylim[1]
+
+  labelsInOrder=dflabel$label[order(dflabel$x, dflabel$y)]
+
+  df6 <- split(df5, df5$z)
+
+  output <- list(dendro=df6, plotlabels=dflabel, labelsInOrder=labelsInOrder)
+  return(output)
+}

.Rproj.user/shared/notebooks/paths

@@ -0,0 +1,3 @@
+/home/nhuber/Desktop/gghierarchy.R="1ACF579E"
+/home/nhuber/bioinformatics/ggdendroplot/R/geom_dendro.R="E1598E29"
+/home/nhuber/bioinformatics/ggdendroplot/R/hello.R="7AD6E14A"

DESCRIPTION

@@ -0,0 +1,13 @@
+Package: ggdendroplot
+Type: Package
+Title: Create dendrograms for ggplot
+Depends: R, stats
+Imports: ggplot2
+Version: 0.1.0
+Author: Nicolas Huber
+Maintainer: Nicolas Huber <info.huber@aol.de>
+Description: Create a dendrogram as a layer, ready to be added to ggplot.
+License: What license is it under?
+Encoding: UTF-8
+LazyData: true
+RoxygenNote: 7.1.0

NAMESPACE

@@ -0,0 +1,4 @@
+# Generated by roxygen2: do not edit by hand
+
+export(geom_dendro)
+import(ggplot2)