Mercurial > repos > goeckslab > pycaret_compare
diff pycaret_train.xml @ 4:4aa511539199 draft default tip
planemo upload for repository https://github.com/goeckslab/Galaxy-Pycaret commit cf47efb521b91a9cb44ae5c5ade860627f9b9030
| author | goeckslab |
|---|---|
| date | Tue, 03 Jun 2025 19:31:16 +0000 |
| parents | 009b18a75dc3 |
| children |
line wrap: on
line diff
--- a/pycaret_train.xml Wed Jan 01 03:19:40 2025 +0000 +++ b/pycaret_train.xml Tue Jun 03 19:31:16 2025 +0000 @@ -1,5 +1,5 @@ -<tool id="pycaret_compare" name="PyCaret Model Comparison" version="@VERSION@" profile="@PROFILE@"> - <description>compares different machine learning models on a dataset using PyCaret. Do feature analyses using Random Forest and LightGBM. </description> +<tool id="pycaret_compare" name="Tabular Learner" version="@VERSION@" profile="@PROFILE@"> + <description>applies and evaluates multiple machine learning models on a tabular dataset</description> <macros> <import>pycaret_macros.xml</import> </macros> @@ -53,12 +53,12 @@ ]]> </command> <inputs> - <param name="input_file" type="data" format="csv,tabular" label="Train Dataset (CSV or TSV)" /> - <param name="test_file" type="data" format="csv,tabular" optional="true" label="Test Dataset (CSV or TSV)" - help="If a test set is not provided, - the selected training set will be split into training, validation, and test sets. - If a test set is provided, the training set will only be split into training and validation sets. - BTW, cross-validation is always applied by default." /> + <param name="input_file" type="data" format="csv,tabular" label="Tabular Input Dataset" /> + <param name="test_file" type="data" format="csv,tabular" optional="true" label="Tabular Test Dataset" + help="If a test dataset is not provided, + the input dataset will be split into training, validation, and test sets. + If a test set is provided, the input dataset will be split into training and validation sets. + Cross-validation is applied by default during training." /> <param name="target_feature" multiple="false" type="data_column" use_header_names="true" data_ref="input_file" label="Select the target column:" /> <conditional name="model_selection"> <param name="model_type" type="select" label="Task"> @@ -124,25 +124,25 @@ <option value="true">Yes</option> </param> <when value="true"> - <param name="train_size" type="float" value="0.7" min="0.1" max="0.9" label="Train Size" help="Proportion of the dataset to include in the train split." /> + <param name="train_size" type="float" value="0.7" min="0.1" max="0.9" label="Train Size" help="Proportion of the input dataset to include in the train split." /> <param name="normalize" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Normalize Data" help="Whether to normalize data before training." /> <param name="feature_selection" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Feature Selection" help="Whether to perform feature selection." /> <conditional name="cross_validation"> - <param name="enable_cross_validation" type="select" label="Enable Cross Validation?" help="Select whether to enable cross-validation. Default: Yes" > + <param name="enable_cross_validation" type="select" label="Enable Cross Validation?" help="Select whether to enable cross-validation." > <option value="false" >No</option> <option value="true" selected="true">Yes</option> </param> <when value="true"> - <param name="cross_validation_folds" type="integer" value="10" min="2" max="20" label="Cross Validation Folds" help="Number of folds to use for cross-validation. Default: 10" /> + <param name="cross_validation_folds" type="integer" value="10" min="2" max="20" label="Cross Validation Folds" help="Number of folds to use for cross-validation." /> </when> <when value="false"> <!-- No additional parameters to show if the user selects 'No' --> </when> </conditional> - <param name="remove_outliers" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Remove Outliers" help="Whether to remove outliers from the dataset before training. Default: False" /> - <param name="remove_multicollinearity" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Remove Multicollinearity" help="Whether to remove multicollinear features before training. Default: False" /> - <param name="polynomial_features" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Polynomial Features" help="Whether to create polynomial features before training. Default: False" /> - <param name="fix_imbalance" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Fix Imbalance" help="ONLY for classfication! Whether to use SMOTE or similar methods to fix imbalance in the dataset. Default: False" /> + <param name="remove_outliers" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Remove Outliers" help="Whether to remove outliers from the input dataset before training." /> + <param name="remove_multicollinearity" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Remove Multicollinearity" help="Whether to remove multicollinear features before training." /> + <param name="polynomial_features" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Polynomial Features" help="Whether to create polynomial features before training." /> + <param name="fix_imbalance" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Fix Imbalance" help="ONLY for classfication! Whether to use SMOTE or similar methods to fix imbalance in the input dataset." /> </when> <when value="false"> <!-- No additional parameters to show if the user selects 'No' --> @@ -150,9 +150,9 @@ </conditional> </inputs> <outputs> + <data name="comparison_result" format="html" from_work_dir="comparison_result.html" label="${tool.name} analysis report on ${on_string}"/> <data name="model" format="h5" from_work_dir="pycaret_model.h5" label="${tool.name} best model on ${on_string}" /> - <data name="comparison_result" format="html" from_work_dir="comparison_result.html" label="${tool.name} Comparison result on ${on_string}"/> - <data name="best_model_csv" format="csv" from_work_dir="best_model.csv" label="${tool.name} The prams of the best model on ${on_string}" hidden="true" /> + <data name="best_model_csv" format="csv" from_work_dir="best_model.csv" label="${tool.name} The parameters of the best model on ${on_string}" hidden="true" /> </outputs> <tests> <test>
