Galaxy |

Changeset 0:dc678d2c1976 (2018-01-18)

Commit message:
planemo upload commit a2411926bebc2ca3bb31215899a9f18a67e59556

added:
LICENSE
h_clust.R
h_clust.xml
h_clust_galaxy.R
test-data/decathlon.tsv
test-data/log_file
test-data/output_file

diff -r 000000000000 -r dc678d2c1976 LICENSE
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/LICENSE Thu Jan 18 07:56:33 2018 -0500

b'@@ -0,0 +1,674 @@\n+ GNU GENERAL PUBLIC LICENSE\n+ Version 3, 29 June 2007\n+\n+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>\n+ Everyone is permitted to copy and distribute verbatim copies\n+ of this license document, but changing it is not allowed.\n+\n+ Preamble\n+\n+ The GNU General Public License is a free, copyleft license for\n+software and other kinds of works.\n+\n+ The licenses for most software and other practical works are designed\n+to take away your freedom to share and change the works. By contrast,\n+the GNU General Public License is intended to guarantee your freedom to\n+share and change all versions of a program--to make sure it remains free\n+software for all its users. We, the Free Software Foundation, use the\n+GNU General Public License for most of our software; it applies also to\n+any other work released this way by its authors. You can apply it to\n+your programs, too.\n+\n+ When we speak of free software, we are referring to freedom, not\n+price. Our General Public Licenses are designed to make sure that you\n+have the freedom to distribute copies of free software (and charge for\n+them if you wish), that you receive source code or can get it if you\n+want it, that you can change the software or use pieces of it in new\n+free programs, and that you know you can do these things.\n+\n+ To protect your rights, we need to prevent others from denying you\n+these rights or asking you to surrender the rights. Therefore, you have\n+certain responsibilities if you distribute copies of the software, or if\n+you modify it: responsibilities to respect the freedom of others.\n+\n+ For example, if you distribute copies of such a program, whether\n+gratis or for a fee, you must pass on to the recipients the same\n+freedoms that you received. You must make sure that they, too, receive\n+or can get the source code. And you must show them these terms so they\n+know their rights.\n+\n+ Developers that use the GNU GPL protect your rights with two steps:\n+(1) assert copyright on the software, and (2) offer you this License\n+giving you legal permission to copy, distribute and/or modify it.\n+\n+ For the developers\' and authors\' protection, the GPL clearly explains\n+that there is no warranty for this free software. For both users\' and\n+authors\' sake, the GPL requires that modified versions be marked as\n+changed, so that their problems will not be attributed erroneously to\n+authors of previous versions.\n+\n+ Some devices are designed to deny users access to install or run\n+modified versions of the software inside them, although the manufacturer\n+can do so. This is fundamentally incompatible with the aim of\n+protecting users\' freedom to change the software. The systematic\n+pattern of such abuse occurs in the area of products for individuals to\n+use, which is precisely where it is most unacceptable. Therefore, we\n+have designed this version of the GPL to prohibit the practice for those\n+products. If such problems arise substantially in other domains, we\n+stand ready to extend this provision to those domains in future versions\n+of the GPL, as needed to protect the freedom of users.\n+\n+ Finally, every program is threatened constantly by software patents.\n+States should not allow patents to restrict development and use of\n+software on general-purpose computers, but in those that do, we wish to\n+avoid the special danger that patents applied to a free program could\n+make it effectively proprietary. To prevent this, the GPL assures that\n+patents cannot be used to render the program non-free.\n+\n+ The precise terms and conditions for copying, distribution and\n+modification follow.\n+\n+ TERMS AND CONDITIONS\n+\n+ 0. Definitions.\n+\n+ "This License" refers to version 3 of the GNU General Public License.\n+\n+ "Copyright" also means copyright-like laws that apply to other kinds of\n+works, such as semiconductor masks.\n+\n+ "The Program" refers to a'..b'CE OF THE PROGRAM\n+IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF\n+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.\n+\n+ 16. Limitation of Liability.\n+\n+ IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING\n+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS\n+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY\n+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE\n+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF\n+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD\n+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),\n+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF\n+SUCH DAMAGES.\n+\n+ 17. Interpretation of Sections 15 and 16.\n+\n+ If the disclaimer of warranty and limitation of liability provided\n+above cannot be given local legal effect according to their terms,\n+reviewing courts shall apply local law that most closely approximates\n+an absolute waiver of all civil liability in connection with the\n+Program, unless a warranty or assumption of liability accompanies a\n+copy of the Program in return for a fee.\n+\n+ END OF TERMS AND CONDITIONS\n+\n+ How to Apply These Terms to Your New Programs\n+\n+ If you develop a new program, and you want it to be of the greatest\n+possible use to the public, the best way to achieve this is to make it\n+free software which everyone can redistribute and change under these terms.\n+\n+ To do so, attach the following notices to the program. It is safest\n+to attach them to the start of each source file to most effectively\n+state the exclusion of warranty; and each file should have at least\n+the "copyright" line and a pointer to where the full notice is found.\n+\n+ {one line to give the program\'s name and a brief idea of what it does.}\n+ Copyright (C) {year} {name of author}\n+\n+ This program is free software: you can redistribute it and/or modify\n+ it under the terms of the GNU General Public License as published by\n+ the Free Software Foundation, either version 3 of the License, or\n+ (at your option) any later version.\n+\n+ This program is distributed in the hope that it will be useful,\n+ but WITHOUT ANY WARRANTY; without even the implied warranty of\n+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\n+ GNU General Public License for more details.\n+\n+ You should have received a copy of the GNU General Public License\n+ along with this program. If not, see <http://www.gnu.org/licenses/>.\n+\n+Also add information on how to contact you by electronic and paper mail.\n+\n+ If the program does terminal interaction, make it output a short\n+notice like this when it starts in an interactive mode:\n+\n+ {project} Copyright (C) {year} {fullname}\n+ This program comes with ABSOLUTELY NO WARRANTY; for details type `show w\'.\n+ This is free software, and you are welcome to redistribute it\n+ under certain conditions; type `show c\' for details.\n+\n+The hypothetical commands `show w\' and `show c\' should show the appropriate\n+parts of the General Public License. Of course, your program\'s commands\n+might be different; for a GUI interface, you would use an "about box".\n+\n+ You should also get your employer (if you work as a programmer) or school,\n+if any, to sign a "copyright disclaimer" for the program, if necessary.\n+For more information on this, and how to apply and follow the GNU GPL, see\n+<http://www.gnu.org/licenses/>.\n+\n+ The GNU General Public License does not permit incorporating your program\n+into proprietary programs. If your program is a subroutine library, you\n+may consider it more useful to permit linking proprietary applications with\n+the library. If this is what you want to do, use the GNU Lesser General\n+Public License instead of this License. But first, please read\n+<http://www.gnu.org/philosophy/why-not-lgpl.html>.\n'

diff -r 000000000000 -r dc678d2c1976 h_clust.R
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/h_clust.R Thu Jan 18 07:56:33 2018 -0500

[

b'@@ -0,0 +1,391 @@\n+# R Script producing a hierarchical clustering\n+# Input : a file containing a table with numeric values\n+#\t except for the first column containing sample names\n+#\t and the first line containing variable names\n+#\t separator expected is <TAB>\n+#\n+# Clustering method :\n+#\t euclidean, correlation, ...\n+#\n+# Ouptut : a file containing the image of the clustering\n+#-----------------------------------------------------------------\n+# Authors : sophie.lamarre(at)insa-toulouse.fr\n+#\t ignacio.gonzalez(at)toulouse.inra.fr\n+#\t luc.jouneau(at)inra.fr\n+#\t valentin.marcon(at)inra.fr\n+# Version : 0.9\n+# Date : 13/3/2017\n+\n+# The function -------------------------------------\n+#---------------------------------------------------\n+h_clust <- function(input_file,\n+ group_member_file = NULL,\n+ output_file = "out/myplot",\n+ log_file = "log/H_Clust.html",\n+ format_image_out = "png",\n+ distance_method = "euclidean",\n+ agglomeration_method = "ward",\n+ column_clustering = TRUE,\n+ select = NULL,\n+ plot_title = "",\n+ xlab = "",\n+ ylab = "Height",\n+ width = 7,\n+ height = 7,\n+ ppi = 300,\n+\t\t na_encoding="NA"\n+) {\n+\n+ # This function allows to generate hierarchical cluster analysis on a table according to differents parameters.\n+ # It needs a dataset : the table of data and optionally a group_member data to set colored labels.\n+ # It generates a clustering tree graphic from hierarchical clustering.\n+ #\n+ # Parameters :\n+ # - input_file : input_file name\n+ # - group_member_file : input sample/tag group_member_file name\n+ # - output_file : output_file name\n+ # - log_file : log file name\n+ # - format_image_out : graphic format of the output_file. This must be one of "png", "jpeg", "tiff", "pdf"\n+ # - distance_method : the distance measure to be used. This must be one of "euclidean", "correlation", "maximum", "manhattan", "canberra", "binary" or "minkowski"\n+ # - agglomeration_method : the agglomeration_method to be used. This should be one of "ward", "single", "complete", "average", "mcquitty", "median" or "centroid"\n+ # - column_clustering : if TRUE clustering is performed on the columns\n+ # - select : number of top variables to use for clustering, selected by highest row variance. If NULL all the variables are selected\n+ # - plot_title : an overall title for the plot\n+ # - xlab : a title for the x axis\n+ # - ylab : a title for the y axis\n+ # - width : the width of the graphics region in inches\n+ # - height : the height of the graphics region in inches\n+ # - ppi : the nominal resolution in ppi\n+ # - na_encoding : label used to indicate missing values\n+ \n+ library(RColorBrewer)\n+ \n+ #---------------------------------------------------\n+ # Auxiliary function\n+ #---------------------------------------------------\n+ insert.blank = function(x) {paste(strsplit(x, "@$\xc2\xa7", fixed = TRUE)[[1]], collapse = " ")}\n+ \n+ #---------------------------------------------------\n+ # Titles \n+ #---------------------------------------------------\n+ plot_title = insert.blank(plot_title)\n+ xlab = insert.blank(xlab)\n+ ylab = insert.blank(ylab)\n+ \n+ #---------------------------------------------------\n+ # Read and verify data\n+ #---------------------------------------------------\n+ #1\xb0) Checks valid for all modules\n+ if (column_clustering) {\n+\tvariable_in_line=1\n+ \tcolumn_use="individual"\n+ \tline_use="variable"\n+ } else {\n+\tvariable_in_line=0\n+ \tline_use="individual"\n+ \tcolumn_use="variable"\n+ }\n+\t\n+ log_error=function(message="") {\n+ \t\tcat("<HTML><HEAD><TITLE>Hierarchical clustering report</TITLE></HEAD><BODY>\\n",file=log_file,append=F,sep="")\n+ \t\tcat("&#9888 An error occurred while trying to read your ta'..b'#########################################################\n+ # Treatment successfull\n+ ##########################################################\n+ cat("<HTML><HEAD><TITLE>Hierarchical clustering report</TITLE></HEAD><BODY>\\n",file=log_file,append=F,sep="")\n+ cat("✓ Your clustering process is successfull !<BR>",file=log_file,append=T,sep="")\n+ cat("</BODY></HTML>\\n",file=log_file,append=T,sep="")\n+ \n+ q(save="no",status=0)\n+\n+} # end of function\n+\n+#### Test clustering ####\n+#LJO : 13/3/2017\n+#setwd("H:/INRA/cati/groupe stats/Galaxy/hclust")\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon1")\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon2",column_clustering=FALSE,\n+# xlab="Competitors",ylab="Distance")\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon3",column_clustering=FALSE,\n+# select=5)\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon4",column_clustering=FALSE,\n+# distance_method="correlation",agglomeration_method="average",\n+# format_image_out="tiff",ppi=100,width=3,height=3\n+#)\n+##Group : competitors\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon5",column_clustering=FALSE,\n+# xlab="Competitors",ylab="Distance",group_member_file="in/competitors_groups - 1 column.txt")\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon6",column_clustering=FALSE,\n+# xlab="Competitors",ylab="Distance",group_member_file="in/competitors_groups - 2 columns.txt")\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon7",column_clustering=FALSE,\n+# xlab="Competitors",ylab="Distance",group_member_file="in/competitors_groups - 1 column with header.txt")\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon8",column_clustering=FALSE,\n+# xlab="Competitors",ylab="Distance",group_member_file="in/competitors_groups - 2 columns with header.txt")\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon8",column_clustering=FALSE,\n+# xlab="Competitors",ylab="Distance",group_member_file="in/competitors_groups - 2 columns - with error.txt")\n+#\n+##Group : competitions\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon9",column_clustering=TRUE,\n+# xlab="Competitions",ylab="Distance",group_member_file="in/competitions_groups - 1 column.txt")\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon10",column_clustering=TRUE,\n+# xlab="Competitions",ylab="Distance",group_member_file="in/competitions_groups - 2 columns.txt")\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon11",column_clustering=TRUE,\n+# xlab="Competitions",ylab="Distance",group_member_file="in/competitions_groups - 1 column with header.txt")\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon12",column_clustering=TRUE,\n+# xlab="Competitions",ylab="Distance",group_member_file="in/competitions_groups - 2 columns with header.txt")\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon13",column_clustering=TRUE,\n+# xlab="Competitions",ylab="Distance",group_member_file="in/competitions_groups - 2 columns - with error.txt")\n+#\n+##Missing values\n+#h_clust(input_file="in/decathlon - with NA.txt",plot_title="declathlon",output_file="out/decathlon14",column_clustering=TRUE,\n+# xlab="Competitions",ylab="Distance",na_encoding="missing_value")\n+#\n+##Top 5 competitions\n+#h_clust(input_file="in/decathlon.txt",plot_title="declathlon",output_file="out/decathlon15",column_clustering=TRUE,\n+# xlab="Competitions",ylab="Distance",select=5)\n'

diff -r 000000000000 -r dc678d2c1976 h_clust.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/h_clust.xml Thu Jan 18 07:56:33 2018 -0500

[

b'@@ -0,0 +1,280 @@\n+\n+\n+<tool id="h_clust" name="Hierarchical clustering" version="1.0.0">\n+ <description>Generate hierarchical cluster analysis on a numeric data table</description>\n+ <requirements>\n+ <requirement type="package">R</requirement>\n+ <requirement type="package">r-rcolorbrewer</requirement>\n+ <requirement type="package">r-batch</requirement>\n+ </requirements>\n+ <stdio>\n+ \n+ <exit_code range="1:" level="fatal"/>\n+ <exit_code range=":-1" level="fatal"/>\n+ </stdio>\n+ <command interpreter="Rscript"><![CDATA[\n+ h_clust_galaxy.R\n+ input_file \'${input_file}\'\n+ #if $conditional.selector == "YES":\n+ group_member_file \'${conditional.group_member_file}\'\n+ #else\n+ group_member_file \'${conditional.selector}\'\n+ #end if\n+ output_file \'${output_file}\'\n+ log_file \'${log_file}\'\n+ distance_method \'${distance_method}\'\n+ agglomeration_method \'${agglomeration_method}\'\n+ column_clustering \'${sample_clustering}\'\n+ select \'${select}\'\n+ plot_title \'${plot_title}\'\n+ xlab \'${xlab}\'\n+ ylab \'${ylab}\'\n+ #if $moreoption.more == "YES":\n+ width \'${moreoption.width}\'\n+ height \'${moreoption.height}\'\n+ ppi \'${moreoption.ppi}\'\n+ format_image_out \'${moreoption.format_image_out}\'\n+ #end if\n+ #if $moreoption.more == "NO":\n+ width "7"\n+ height "7"\n+ ppi "300"\n+ format_image_out "png"\n+ #end if\n+ na_encoding \'${NA_code}\'\n+ ]]></command>\n+ <inputs>\n+ <param format="csv,tabular" name="input_file" type="data" label="Input file" help="Data file on which clustering will be performed" />\n+ <conditional name="conditional">\n+ <param name="selector" type="select" label="Do you have an input variable/individual group member file ?">\n+ <option value="NO">No</option>\n+ <option value="YES">Yes</option>\n+ </param>\n+ <when value="YES">\n+ <param format="csv, txt" name="group_member_file" type="data" label="Input variable/individual group member file" />\n+ </when>\n+ <when value="NO" />\n+ </conditional>\n+ <param name="distance_method" type="select" label="The distance measure to be used (one choice mandatory)">\n+ <option value="euclidean">euclidean</option>\n+ <option value="correlation">correlation</option>\n+ <option value="maximum">maximum</option>\n+ <validator type="empty_field" message="Please choose, at least, one distance measure to be used." />\n+ </param>\n+ <param name="agglomeration_method" type="select" label="The agglomeration method to be used (one choice mandatory)">\n+ <option value="ward">ward</option> <option value="single">single</option><option value="complete">complete</option><option value="average">average</option><validator type="empty_field" message="Please choose, at least, one agglomeration method to be used." /></param>\n+ <param name="sample_clustering" type="select" label="Clustering is performed on:" help="(default columns)">\n+ <opti'..b'ice mandatory)\n+ | This must be one of "euclidean", "correlation" or "maximum". The distance measure mostly used is "euclidean" and "correlation". \n+ |\n+\n+The agglomeration method to be used (one choice mandatory)\n+ | This should be one of "ward", "single", "complete" or "average". The distance measure mostly used is "ward".\n+ |\n+\n+Clustering is performed on the columns\n+ | if YES clustering is performed on the columns. if NO clustering is performed on the lines.\n+ |\n+\n+Number of top elements to use for clustering\n+ | Number of columns (or lines) to take into account for the clustering. The top elements will be selected by variance (top 10 elements with the biggest variance). If NULL all the elements will be used to perform clustering. For NGS or microarray data, this allows to perform a clustering on the top n most variables genes.\n+ |\n+\n+Label used for Missing values\n+ | Missing value coding characters\n+ |\n+\n+An overall title for the plot\n+ | enter a title for the plot\n+ |\n+\n+A title for the x axis\n+ | enter a title for the x axis\n+ |\n+\n+A title for the y axis\n+ | enter a title for the y axis\n+ |\n+\n+The width of the graphics region in inches\n+ | enter a number\n+ |\n+\n+The height of the graphics region in inches\n+ | enter a number\n+ |\n+\n+The nominal resolution in ppi\n+ | enter a number (a higher number means a high resolution which can take times to open)\n+ |\n+\n+Graphic format of the output file\n+ | choose a format between "png", "jpeg", "tiff" and "pdf"\n+ |\n+\n+------------\n+Output files\n+------------\n+\n+Hierarchical_clustering_report\n+ |\n+\n+Hierarchical_clustering_log\n+ |\n+\n+------\n+\n+**Authors** Luc Jouneau (luc.jouneau@inra.fr), Sarah Maman (sarah.maman@inra.fr) and Valentin Marcon (valentin.marcon@inra.fr)\n+\n+Contact : support.sigenae@inra.fr \n+\n+E-learning available : Not yet.\n+\n+.. class:: infomark\n+\n+-------------\n+Please cite :\n+-------------\n+\n+- (Depending on the help provided you can cite us in acknowledgements, references or both.)\n+ \n+Acknowledgements\n+ | We wish to thank SIGENAE group and the statistical CATI BIOS4Biol group : Ignacio Gonzalez, Sophie Lamarre, Sarah Maman, Luc Jouneau, Christophe Klopp\n+ | Re-packaging was provided by Valentin Marcon (INRA, Migale platform http://migale.jouy.inra.fr), as part of the IFB project \'Galaxy For Life Science\' (http://www.france-bioinformatique.fr/fr)\n+ | \n+\n+References\n+ | SIGENAE [http://www.sigenae.org/]\n+ |\n+ \n+ ]]></help>\n+ <citations>\n+ <citation type="bibtex">\n+ @article {Love002832,\n+\tauthor = {Love, Michael I and Huber, Wolfgang and Anders, Simon},\n+\ttitle = {Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2},\n+\tyear = {2014},\n+\tdoi = {10.1101/002832},\n+\tpublisher = {Cold Spring Harbor Laboratory},\n+\tabstract = {In comparative high-throughput sequencing assays, a fundamental task is the analysis of count data, such as read counts per gene in RNA-seq data, for evidence of systematic changes across experimental conditions. Small replicate numbers, discreteness, large dynamic range and the presence of outliers require a suitable statistical approach. We present DESeq2, a method for differential analysis of count data. DESeq2 uses shrinkage estimation for dispersions and fold changes to improve stability and interpretability of the estimates. This enables a more quantitative analysis focused on the strength rather than the mere presence of differential expression and facilitates downstream tasks such as gene ranking and visualization. DESeq2 is available as an R/Bioconductor package.},\n+\tURL = {https://www.biorxiv.org/content/early/2014/11/17/002832},\n+\teprint = {https://www.biorxiv.org/content/early/2014/11/17/002832.full.pdf},\n+\tjournal = {bioRxiv}}\n+ </citation>\n+ </citations>\n+</tool>\n'

diff -r 000000000000 -r dc678d2c1976 h_clust_galaxy.R
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/h_clust_galaxy.R Thu Jan 18 07:56:33 2018 -0500

[

@@ -0,0 +1,79 @@
+#!/usr/local/bioinfo/bin/Rscript --vanilla --slave --no-site-file
+
+# R Script producing a hierarchical clustering
+# Input : a file containing a table with numeric values
+#         except for the first column containing sample names
+#         and the first line containing variable names
+#         separator expected is <TAB>
+#
+# Clustering method :
+#         euclidean, correlation, ...
+#
+# Ouptut : a file containing the image of the clustering
+#-----------------------------------------------------------------
+# Authors : sophie.lamarre(at)insa-toulouse.fr
+#           ignacio.gonzalez(at)toulouse.inra.fr
+#           luc.jouneau(at)inra.fr
+#           valentin.marcon(at)inra.fr
+# Version : 0.9
+# Date    : 06/09/2017
+
+##------------------------------
+## Options
+##------------------------------
+strAsFacL <- options()$stringsAsFactors
+options(stringsAsFactors = FALSE)
+
+##------------------------------
+## Libraries laoding
+##------------------------------
+# For parseCommandArgs function
+library(batch)
+
+# R script call
+source_local <- function(fname)
+{
+ argv <- commandArgs(trailingOnly = FALSE)
+ base_dir <- dirname(substring(argv[grep("--file=", argv)], 8))
+ source(paste(base_dir, fname, sep="/"))
+}
+
+#Import the different functions used for the hierarchical clustering
+source_local("h_clust.R")
+
+##------------------------------
+## Lecture parametres
+##------------------------------
+argLs <- parseCommandArgs(evaluate=FALSE)
+
+group_member_file=argLs[["group_member_file"]]
+if (group_member_file=="NO"){
+    group_member_file<-NULL
+}
+select=argLs[["select"]]
+if (select=="NULL"){
+    select<-NULL
+}
+column_clustering=argLs[["column_clustering"]]
+if (column_clustering=="TRUE"){
+    column_clustering<-TRUE
+} else {
+    column_clustering<-FALSE
+}
+
+h_clust(input_file=argLs[["input_file"]],
+     group_member_file=group_member_file,
+     output_file=argLs[["output_file"]],
+     log_file=argLs[["log_file"]],
+     format_image_out=argLs[["format_image_out"]],
+     distance_method=argLs[["distance_method"]],
+     agglomeration_method=argLs[["agglomeration_method"]],
+     column_clustering=column_clustering,
+     select=select,
+     plot_title=argLs[["plot_title"]],
+     xlab=argLs[["xlab"]],
+     ylab=argLs[["ylab"]],
+     width=argLs[["width"]],
+     height=argLs[["height"]],
+     ppi=argLs[["ppi"]],
+     na_encoding=argLs[["NA_code"]])

diff -r 000000000000 -r dc678d2c1976 test-data/decathlon.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/decathlon.tsv Thu Jan 18 07:56:33 2018 -0500

@@ -0,0 +1,42 @@
+"name" "100m" "Long.jump" "Shot.put" "High.jump" "400m" "110m.hurdle" "Discus" "Pole.vault" "Javeline" "1500m"
+"SEBRLE" 11.04 7.58 14.83 2.07 49.81 14.69 43.75 5.02 63.19 291.7
+"CLAY" 10.76 7.4 14.26 1.86 49.37 14.05 50.72 4.92 60.15 301.5
+"KARPOV" 11.02 7.3 14.77 2.04 48.37 14.09 48.95 4.92 50.31 300.2
+"BERNARD" 11.02 7.23 14.25 1.92 48.93 14.99 40.87 5.32 62.77 280.1
+"YURKOV" 11.34 7.09 15.19 2.1 50.42 15.31 46.26 4.72 63.44 276.4
+"WARNERS" 11.11 7.6 14.31 1.98 48.68 14.23 41.1 4.92 51.77 278.1
+"ZSIVOCZKY" 11.13 7.3 13.48 2.01 48.62 14.17 45.67 4.42 55.37 268
+"McMULLEN" 10.83 7.31 13.76 2.13 49.91 14.38 44.41 4.42 56.37 285.1
+"MARTINEAU" 11.64 6.81 14.57 1.95 50.14 14.93 47.6 4.92 52.33 262.1
+"HERNU" 11.37 7.56 14.41 1.86 51.1 15.06 44.99 4.82 57.19 285.1
+"BARRAS" 11.33 6.97 14.09 1.95 49.48 14.48 42.1 4.72 55.4 282
+"NOOL" 11.33 7.27 12.68 1.98 49.2 15.29 37.92 4.62 57.44 266.6
+"BOURGUIGNON" 11.36 6.8 13.46 1.86 51.16 15.67 40.49 5.02 54.68 291.7
+"Sebrle" 10.85 7.84 16.36 2.12 48.36 14.05 48.72 5 70.52 280.01
+"Clay" 10.44 7.96 15.23 2.06 49.19 14.13 50.11 4.9 69.71 282
+"Karpov" 10.5 7.81 15.93 2.09 46.81 13.97 51.65 4.6 55.54 278.11
+"Macey" 10.89 7.47 15.73 2.15 48.97 14.56 48.34 4.4 58.46 265.42
+"Warners" 10.62 7.74 14.48 1.97 47.97 14.01 43.73 4.9 55.39 278.05
+"Zsivoczky" 10.91 7.14 15.31 2.12 49.4 14.95 45.62 4.7 63.45 269.54
+"Hernu" 10.97 7.19 14.65 2.03 48.73 14.25 44.72 4.8 57.76 264.35
+"Nool" 10.8 7.53 14.26 1.88 48.81 14.8 42.05 5.4 61.33 276.33
+"Bernard" 10.69 7.48 14.8 2.12 49.13 14.17 44.75 4.4 55.27 276.31
+"Schwarzl" 10.98 7.49 14.01 1.94 49.76 14.25 42.43 5.1 56.32 273.56
+"Pogorelov" 10.95 7.31 15.1 2.06 50.79 14.21 44.6 5 53.45 287.63
+"Schoenbeck" 10.9 7.3 14.77 1.88 50.3 14.34 44.41 5 60.89 278.82
+"Barras" 11.14 6.99 14.91 1.94 49.41 14.37 44.83 4.6 64.55 267.09
+"Smith" 10.85 6.81 15.24 1.91 49.27 14.01 49.02 4.2 61.52 272.74
+"Averyanov" 10.55 7.34 14.44 1.94 49.72 14.39 39.88 4.8 54.51 271.02
+"Ojaniemi" 10.68 7.5 14.97 1.94 49.12 15.01 40.35 4.6 59.26 275.71
+"Smirnov" 10.89 7.07 13.88 1.94 49.11 14.77 42.47 4.7 60.88 263.31
+"Qi" 11.06 7.34 13.55 1.97 49.65 14.78 45.13 4.5 60.79 272.63
+"Drews" 10.87 7.38 13.07 1.88 48.51 14.01 40.11 5 51.53 274.21
+"Parkhomenko" 11.14 6.61 15.69 2.03 51.04 14.88 41.9 4.8 65.82 277.94
+"Terek" 10.92 6.94 15.15 1.94 49.56 15.12 45.62 5.3 50.62 290.36
+"Gomez" 11.08 7.26 14.57 1.85 48.61 14.41 40.95 4.4 60.71 269.7
+"Turi" 11.08 6.91 13.62 2.03 51.67 14.26 39.83 4.8 59.34 290.01
+"Lorenzo" 11.1 7.03 13.22 1.85 49.34 15.38 40.22 4.5 58.36 263.08
+"Karlivans" 11.33 7.26 13.3 1.97 50.54 14.98 43.34 4.5 52.92 278.67
+"Korkizoglou" 10.86 7.07 14.81 1.94 51.16 14.96 46.07 4.7 53.05 317
+"Uldal" 11.23 6.99 13.53 1.85 50.95 15.09 43.01 4.5 60 281.7
+"Casarsa" 11.36 6.68 14.92 1.94 53.2 15.39 48.66 4.4 58.62 296.12

diff -r 000000000000 -r dc678d2c1976 test-data/log_file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/log_file Thu Jan 18 07:56:33 2018 -0500

@@ -0,0 +1,2 @@
+<HTML><HEAD><TITLE>Hierarchical clustering report</TITLE></HEAD><BODY>
+✓ Your clustering process is successfull !<BR></BODY></HTML>

diff -r 000000000000 -r dc678d2c1976 test-data/output_file

Binary file test-data/output_file has changed