Mercurial > repos > goeckslab > tabular_learner

comparison tabular_learner.xml @ 15:01e7c5481f13 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/goeckslab/gleam commit f632803cda732005bdcf3ac3e8fe7a807a82c1d9
author goeckslab
date Mon, 19 Jan 2026 05:54:52 +0000
parents edd515746388
children
comparison
equal deleted inserted replaced
14:edd515746388 15:01e7c5481f13
5 </macros> 5 </macros>
6 <expand macro="python_requirements" /> 6 <expand macro="python_requirements" />
7 <command> 7 <command>
8 <![CDATA[ 8 <![CDATA[
9 python $__tool_directory__/pycaret_train.py --input_file '$input_file' --target_col '$target_feature' --output_dir '.' --random_seed '$random_seed' --n-jobs \${GALAXY_SLOTS:-1} 9 python $__tool_directory__/pycaret_train.py --input_file '$input_file' --target_col '$target_feature' --output_dir '.' --random_seed '$random_seed' --n-jobs \${GALAXY_SLOTS:-1}
10 #if $sample_id_selector.use_sample_id == "yes"
11 --sample-id-column '$sample_id_selector.sample_id_column'
12 #end if
10 #if $model_selection.model_type == "classification" 13 #if $model_selection.model_type == "classification"
11 #if $model_selection.classification_models 14 #if $model_selection.classification_models
12 --models '$model_selection.classification_models' 15 --models '$model_selection.classification_models'
13 #end if 16 #end if
14 #end if 17 #end if
79 <when value="no"> 82 <when value="no">
80 <!-- Nothing extra shown --> 83 <!-- Nothing extra shown -->
81 </when> 84 </when>
82 </conditional> 85 </conditional>
83 <param name="target_feature" multiple="false" type="data_column" use_header_names="true" data_ref="input_file" label="Select the target column:" /> 86 <param name="target_feature" multiple="false" type="data_column" use_header_names="true" data_ref="input_file" label="Select the target column:" />
87 <conditional name="sample_id_selector">
88 <param name="use_sample_id" type="select" label="Use a sample ID column for leakage-aware splitting?" help="Select yes to choose a column that groups related records (e.g., patient_id or slide_id).">
89 <option value="no" selected="true">No column selected</option>
90 <option value="yes">Yes</option>
91 </param>
92 <when value="yes">
93 <param name="sample_id_column" type="data_column" data_ref="input_file" use_header_names="true" label="Sample ID column" help="All rows with the same ID stay in the same split to reduce leakage. Used for group-aware splitting when no separate test file is provided, and for group-aware cross-validation when enabled." />
94 </when>
95 <when value="no">
96 <!-- No sample ID column -->
97 </when>
98 </conditional>
84 <conditional name="model_selection"> 99 <conditional name="model_selection">
85 <param name="model_type" type="select" label="Task"> 100 <param name="model_type" type="select" label="Task">
86 <option value="classification">classification</option> 101 <option value="classification">classification</option>
87 <option value="regression">regression</option> 102 <option value="regression">regression</option>
88 </param> 103 </param>
309 </test> 324 </test>
310 </tests> 325 </tests>
311 <help> 326 <help>
312 This tool uses PyCaret to train and evaluate machine learning models. 327 This tool uses PyCaret to train and evaluate machine learning models.
313 It compares different models on a dataset and provides the best model based on the performance metrics. 328 It compares different models on a dataset and provides the best model based on the performance metrics.
329 You can optionally select a sample ID column to keep related records in the same split and reduce data leakage when the tool creates splits internally.
314 330
315 **Outputs** 331 **Outputs**
316 332
317 - **Model**: The best model trained on the dataset in h5 format. 333 - **Model**: The best model trained on the dataset in h5 format.
318 334