annotate test-data/annotemp/pivot_wider_jupytool_notebook.ipynb @ 0:33e8a66c99dd draft

planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
author ecology
date Tue, 10 Sep 2024 12:48:44 +0000
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
1 {
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
2 "cells": [
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
3 {
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
4 "cell_type": "markdown",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
5 "metadata": {},
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
6 "source": [
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
7 "# Pivot wider Jupytool "
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
8 ]
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
9 },
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
10 {
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
11 "cell_type": "markdown",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
12 "metadata": {},
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
13 "source": [
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
14 "This Jupyter notebook is dedicated to the pivot_wider function from the tidyr R package. \n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
15 "This script is the final part of the data preparation for the ecoregionalization Galaxy workflow. "
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
16 ]
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
17 },
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
18 {
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
19 "cell_type": "code",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
20 "execution_count": 62,
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
21 "metadata": {
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
22 "tags": []
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
23 },
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
24 "outputs": [],
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
25 "source": [
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
26 "#Date : 22/05/2024\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
27 "#Author : Seguineau Pauline & Yvan Le Bras \n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
28 "\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
29 "#Load libraries\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
30 "library(tidyr)\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
31 "\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
32 "#load file \n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
33 "\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
34 "input_path = \"galaxy_inputs\"\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
35 "\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
36 "for (dir in list.dirs(input_path)){\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
37 " for (file in list.files(dir)) {\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
38 " file_path = file.path(dir, file)}\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
39 "}\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
40 "\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
41 "file = read.table(file_path,header=T, sep = \"\\t\")\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
42 "\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
43 "#Run pivot_wider function\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
44 "pivot_file = pivot_wider(data = file,\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
45 " names_from = phylum_class_order_family_genus_specificEpithet,\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
46 " values_from = individualCount,\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
47 " values_fill = 0,\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
48 " values_fn = sum)\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
49 "\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
50 "#Replace all occurences >= 1 by 1 to have only presence (1) or absence (0) data\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
51 "for(c in 3:length(pivot_file)){\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
52 " pivot_file[c][pivot_file[c]>=1] <- 1}\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
53 "\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
54 "\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
55 "write.table(pivot_file, \"outputs/pivot_file.tabular\", sep = \"\\t\", quote = F, row.names = F)"
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
56 ]
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
57 },
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
58 {
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
59 "cell_type": "markdown",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
60 "metadata": {},
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
61 "source": [
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
62 "In this Jupyter notebook, we used the pivot_wider function of the tidyr package to transform our data into a wider format and adapted to subsequent analyses as part of the Galaxy workflow for ecoregionalization. This transformation allowed us to convert our data to a format where each taxon becomes a separate column. We also took care to fill in the missing values with zeros and to sum the individual counts in case of duplications. Then all data >= 1 are replace by 1 to have only presence (1) or abscence (0) data.\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
63 "\n",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
64 "Thus, this notebook is an essential building block of our analysis pipeline, ensuring that the data is properly formatted and ready to be explored and interpreted for ecoregionalization studies."
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
65 ]
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
66 }
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
67 ],
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
68 "metadata": {
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
69 "kernelspec": {
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
70 "display_name": "R",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
71 "language": "R",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
72 "name": "ir"
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
73 },
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
74 "language_info": {
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
75 "codemirror_mode": "r",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
76 "file_extension": ".r",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
77 "mimetype": "text/x-r-source",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
78 "name": "R",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
79 "pygments_lexer": "r",
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
80 "version": "4.0.3"
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
81 }
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
82 },
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
83 "nbformat": 4,
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
84 "nbformat_minor": 4
33e8a66c99dd planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/EMLassemblyline commit 2d36dc964f548b5acbc43ffd78e51e6fc7dc80bb
ecology
parents:
diff changeset
85 }