Mercurial > repos > tduigou > icfree_learner

comparison learner.xml @ 0:da588cac4813 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/brsynth/icfree-ml commit 48497f3422d15940998cf709ea74e4b1460fb76c
author tduigou
date Wed, 05 Feb 2025 14:04:54 +0000
parents
children 8e8569c19fa7
comparison
equal deleted inserted replaced
-1:000000000000 0:da588cac4813
1 <tool id="icfree_learner" name="iCFree learner" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" license="MIT">
2 <description>Active learning and model training</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements"/>
7 <command detect_errors="exit_code"><![CDATA[
8 #import os
9 cp '$input_param_tsv' param.tsv &&
10 unzip '$input_folder_zip' -d indir &&
11 (find indir -type f | while read file; do mv "\$file" indir; done) &&
12 python -m icfree.learner
13 --data_folder indir
14 --parameter_file param.tsv
15 --output_folder 'outdir'
16 #if str($adv.name_list) != ''
17 --name_list '$adv.name_list'
18 #end if
19 #if str($adv.test) == 'true'
20 --test
21 #end if
22 --nb_rep '$adv.nb_rep'
23 #if str($adv.flatten) != ''
24 --flatten
25 #end if
26 #if str($adv.seed_cond.seed_param) == 'not_random'
27 --seed '$adv.seed_cond.seed'
28 #end if
29 --nb_new_data_predict '$adv.nb_new_data_predict'
30 --nb_new_data '$adv.nb_new_data'
31 --parameter_step '$adv.parameter_step'
32 --n_group '$adv.n_group'
33 --km '$adv.km'
34 --ks '$adv.ks'
35 --save_plot
36 --verbose && ls 'outdir'
37 ]]></command>
38 <inputs>
39 <param name="input_folder_zip" type="data" format="zip" label="Zip folder containing the data files" help="Zip folder containing the data file"/>
40 <param name="input_param_tsv" type="data" format="tabular" label="Parameter values for the experiments" help="Parameter values for the experiment"/>
41 <section name="adv" title="Advanced Options" expanded="false">
42 <param name="name_list" type="text" value="" label="Labels of the feature list" help="A comma-separated string of column names or identifiers, converted to a list of strings representing columns that contain labels (y). This separates y columns from the rest (X features). (Default: Yield1,Yield2,Yield3,Yield4,Yield5)" />
43 <param name="test" type="boolean" label="Validate the model" help="A flag for validating the model; not required to run inside the active learning loop. If not set, skip the validating step" checked="false" />
44 <param name="nb_rep" type="integer" value="100" label="Number of test repetitions for validation the model behavior" help="The number of test repetitions for validating the model behavior. 80% of data is randomly separated for training, and 20% is used for testing." />
45 <param name="flatten" type="boolean" label="Flattent feature data" help="A flag to indicate whether to flatten Y data. If set, treats each repetition in the same experiment independently; multiple same X values with different y outputs are modeled. Else, calculates the average of y across repetitions and only model with y average." />
46 <param name="nb_new_data_predict" type="integer" value="1000" label="Number of new data points generated" help="The number of new data points sampled from all possible cases." />
47 <param name="nb_new_data" type="integer" value="50" label="Number of new data points used" help="The number of new data points selected from the generated ones. These are the data points labeled after active learning loops. `nb_new_data_predict` must be greater than `nb_new_data` to be meaningful." />
48 <param name="parameter_step" type="integer" value="10" label="Step size used to decrement the maximum predefined concentration sequentially" help="The step size used to decrement the maximum predefined concentration sequentially. For example, if the maximum concentration is `max`, the sequence of concentrations is calculated as: `max - 1 * parameter_step`, `max - 2 * parameter_step`, `max - 3 * parameter_step`, and so on. Each concentration is a candidate for experimental testing. Smaller steps result in more possible combinations to sample." />
49 <param name="n_group" type="integer" value="15" label="Number of clusters" help="Parameter for the cluster margin algorithm, specifying the number of groups into which generated data will be clustered." />
50 <param name="km" type="integer" value="50" label="Number of data points for the first selection" help="Parameter for the cluster margin algorithm, specifying the number of data points for the first selection. Ensure `nb_new_data_predict > ks > km`." />
51 <param name="ks" type="integer" value="20" label="Number of data points for the second selection" help="Parameter for the cluster margin algorithm, specifying the number of data points for the second selection. This is also similar to `nb_new_data`." />
52 <!-- Seed -->
53 <conditional name="seed_cond">
54 <param name="seed_param" type="select" label="Seed" help="Choose a seed or let it as random">
55 <option value="not_random" selected="true">fixed</option>
56 <option value="random">random</option>
57 </param>
58 <when value="random"/>
59 <when value="not_random">
60 <param name="seed" type="text" value="85" label="Seed value" help="Only integer allowed">
61 <validator type="empty_field" message="Not empty, select random"/>
62 <validator type="regex" message="Only integer allowed">^(?:\d+)$</validator>
63 </param>
64 </when>
65 </conditional>
66 </section>
67 </inputs>
68 <outputs>
69 <collection name="output_csv" type="list" label="${tool.name} - Data">
70 <discover_datasets pattern="(?P&lt;name&gt;.*).csv" format="csv" directory="outdir" />
71 </collection>
72 <collection name="output_png" type="list" label="${tool.name} - Plot">
73 <discover_datasets pattern="(?P&lt;name&gt;.*).png" format="png" directory="outdir" />
74 </collection>
75 </outputs>
76 <tests>
77 <test>
78 <!-- python -m icfree.learner -data_folder learner -parameter_file learner.input.param.tsv -output_folder tmp -save_plot -verbose -seed 85 -->
79 <param name="input_folder_zip" value="learner.input.folder.zip" />
80 <param name="input_param_tsv" value="learner.input.param.tsv" />
81 <output_collection name="output_csv" type="list" count="1">
82 <element name="next_sampling_ei50" ftype="csv" >
83 <assert_contents>
84 <has_n_lines n="51" />
85 </assert_contents>
86 </element>
87 </output_collection>
88 <output_collection name="output_png" type="list" count="4">
89 <element name="EI selected">
90 <assert_contents>
91 <has_size value="77k" delta="1k"/>
92 </assert_contents>
93 </element>
94 <element name="EI">
95 <assert_contents>
96 <has_size value="36k" delta="1k"/>
97 </assert_contents>
98 </element>
99 <element name="Train_Test">
100 <assert_contents>
101 <has_size value="64k" delta="1k"/>
102 </assert_contents>
103 </element>
104 <element name="Yield evolution through each active learning query">
105 <assert_contents>
106 <has_size value="19k" delta="1k"/>
107 </assert_contents>
108 </element>
109 </output_collection>
110 </test>
111 <test>
112 <!-- python -m icfree.learner -data_folder learner -parameter_file learner.input.param.tsv -output_folder tmp2 -name_list "Yield1,Yield2" -nb_rep 5 -flatten -seed 85 -nb_new_data_predict 20 -nb_new_data 2 -parameter_step 2 -n_group 3 -km 5 -ks 2 -save_plot -verbose -->
113 <param name="input_folder_zip" value="learner.input.folder.zip" />
114 <param name="input_param_tsv" value="learner.input.param.tsv" />
115 <param name="name_list" value="Yield1,Yield2" />
116 <param name="nb_rep" value="5" />
117 <param name="flatten" value="true" />
118 <param name="nb_new_data_predict" value="20" />
119 <param name="nb_new_data" value="2" />
120 <param name="parameter_step" value="2" />
121 <param name="n_group" value="3" />
122 <param name="km" value="5" />
123 <param name="ks" value="2" />
124 <output_collection name="output_csv" type="list" count="1">
125 <element name="next_sampling_ei5" file="learner.output.data.2.csv" ftype="csv" >
126 <assert_contents>
127 <has_n_lines n="6" />
128 </assert_contents>
129 </element>
130 </output_collection>
131 <output_collection name="output_png" type="list" count="4">
132 <element name="EI selected">
133 <assert_contents>
134 <has_size value="24k" delta="1k"/>
135 </assert_contents>
136 </element>
137 <element name="EI">
138 <assert_contents>
139 <has_size value="36k" delta="1k"/>
140 </assert_contents>
141 </element>
142 <element name="Train_Test">
143 <assert_contents>
144 <has_size value="60k" delta="1k"/>
145 </assert_contents>
146 </element>
147 <element name="Yield evolution through each active learning query">
148 <assert_contents>
149 <has_size value="19k" delta="1k"/>
150 </assert_contents>
151 </element>
152 </output_collection>
153 </test>
154 </tests>
155 <help><![CDATA[
156 Learner
157 =======
158 Active learning and model training
159
160 ]]></help>
161 <expand macro="creator"/>
162 <expand macro="citation"/>
163 </tool>