Mercurial > repos > goeckslab > tabular_learner
comparison tabular_learner.xml @ 4:11fdac5affb3 draft
planemo upload for repository https://github.com/goeckslab/gleam commit 8112548ac44b7a4769093d76c722c8fcdeaaef54
| author | goeckslab |
|---|---|
| date | Fri, 25 Jul 2025 19:02:12 +0000 |
| parents | f6a65e05d6ec |
| children | 3d42f82b3c7f |
comparison
equal
deleted
inserted
replaced
| 3:f6a65e05d6ec | 4:11fdac5affb3 |
|---|---|
| 15 #if $model_type == "regression" | 15 #if $model_type == "regression" |
| 16 #if $regression_models | 16 #if $regression_models |
| 17 --models '$regression_models' | 17 --models '$regression_models' |
| 18 #end if | 18 #end if |
| 19 #end if | 19 #end if |
| 20 #if $tune_model | |
| 21 --tune_model | |
| 22 #end if | |
| 20 #if $customize_defaults == "true" | 23 #if $customize_defaults == "true" |
| 21 #if $train_size | 24 #if $train_size |
| 22 --train_size '$train_size' | 25 --train_size '$train_size' |
| 23 #end if | 26 #end if |
| 24 #if $normalize | 27 #if $normalize |
| 25 --normalize | 28 --normalize |
| 26 #end if | 29 #end if |
| 27 #if $feature_selection | 30 #if $feature_selection |
| 28 --feature_selection | 31 --feature_selection |
| 29 #end if | 32 #end if |
| 30 #if $enable_cross_validation == "true" | 33 #if $enable_cross_validation == "true" |
| 31 --cross_validation | 34 --cross_validation |
| 32 #if $cross_validation_folds | 35 #if $cross_validation_folds |
| 33 --cross_validation_folds '$cross_validation_folds' | 36 --cross_validation_folds '$cross_validation_folds' |
| 34 #end if | 37 #end if |
| 35 #end if | 38 #end if |
| 56 ]]> | 59 ]]> |
| 57 </command> | 60 </command> |
| 58 <inputs> | 61 <inputs> |
| 59 <param name="input_file" type="data" format="csv,tabular" label="Tabular Input Dataset" /> | 62 <param name="input_file" type="data" format="csv,tabular" label="Tabular Input Dataset" /> |
| 60 <param name="test_file" type="data" format="csv,tabular" optional="true" label="Tabular Test Dataset" | 63 <param name="test_file" type="data" format="csv,tabular" optional="true" label="Tabular Test Dataset" |
| 61 help="If a test dataset is not provided, | 64 help="If a test dataset is not provided, |
| 62 the input dataset will be split into training, validation, and test sets. | 65 the input dataset will be split into training, validation, and test sets. |
| 63 If a test set is provided, the input dataset will be split into training and validation sets. | 66 If a test set is provided, the input dataset will be split into training and validation sets. |
| 64 Cross-validation is applied by default during training." /> | 67 Cross-validation is applied by default during training." /> |
| 65 <param name="target_feature" multiple="false" type="data_column" use_header_names="true" data_ref="input_file" label="Select the target column:" /> | 68 <param name="target_feature" multiple="false" type="data_column" use_header_names="true" data_ref="input_file" label="Select the target column:" /> |
| 66 <conditional name="model_selection"> | 69 <conditional name="model_selection"> |
| 67 <param name="model_type" type="select" label="Task"> | 70 <param name="model_type" type="select" label="Task"> |
| 68 <option value="classification">classification</option> | 71 <option value="classification">classification</option> |
| 118 <option value="lightgbm">Light Gradient Boosting Machine</option> | 121 <option value="lightgbm">Light Gradient Boosting Machine</option> |
| 119 <option value="catboost">CatBoost Regressor</option> | 122 <option value="catboost">CatBoost Regressor</option> |
| 120 </param> | 123 </param> |
| 121 </when> | 124 </when> |
| 122 </conditional> | 125 </conditional> |
| 126 <param name="tune_model" type="boolean" truevalue="True" falsevalue="False" label="Tune hyperparameters" help="Hyperparameter tuning on the best model" /> | |
| 123 <param name="random_seed" type="integer" value="42" label="Random Seed" help="Random seed for reproducibility." /> | 127 <param name="random_seed" type="integer" value="42" label="Random Seed" help="Random seed for reproducibility." /> |
| 124 <conditional name="advanced_settings"> | 128 <conditional name="advanced_settings"> |
| 125 <param name="customize_defaults" type="select" label="Customize Default Settings?" help="Select yes if you want to customize the default settings of the experiment."> | 129 <param name="customize_defaults" type="select" label="Customize Default Settings?" help="Select yes if you want to customize the default settings of the experiment."> |
| 126 <option value="false" selected="true">No</option> | 130 <option value="false" selected="true">No</option> |
| 127 <option value="true">Yes</option> | 131 <option value="true">Yes</option> |
| 172 <param name="remove_outliers" value="true"/> | 176 <param name="remove_outliers" value="true"/> |
| 173 <param name="remove_multicollinearity" value="true"/> | 177 <param name="remove_multicollinearity" value="true"/> |
| 174 <output name="model" file="expected_model_classification_customized.h5" compare="sim_size"/> | 178 <output name="model" file="expected_model_classification_customized.h5" compare="sim_size"/> |
| 175 <output name="comparison_result"> | 179 <output name="comparison_result"> |
| 176 <assert_contents> | 180 <assert_contents> |
| 177 <has_text text="Validation Result Summary" /> | 181 <has_text text="Validation Summary" /> |
| 178 <has_text text="Test Results" /> | 182 <has_text text="Test Summary" /> |
| 179 <has_text text="Feature Importance" /> | 183 <has_text text="Feature Importance" /> |
| 180 </assert_contents> | 184 </assert_contents> |
| 181 </output> | 185 </output> |
| 182 <output name="best_model_csv" value="expected_best_model_classification_customized.csv" /> | 186 <output name="best_model_csv" value="expected_best_model_classification_customized.csv" /> |
| 183 </test> | 187 </test> |
| 194 <param name="remove_outliers" value="true"/> | 198 <param name="remove_outliers" value="true"/> |
| 195 <param name="remove_multicollinearity" value="true"/> | 199 <param name="remove_multicollinearity" value="true"/> |
| 196 <output name="model" file="expected_model_classification_customized_cross_off.h5" compare="sim_size"/> | 200 <output name="model" file="expected_model_classification_customized_cross_off.h5" compare="sim_size"/> |
| 197 <output name="comparison_result"> | 201 <output name="comparison_result"> |
| 198 <assert_contents> | 202 <assert_contents> |
| 199 <has_text text="Validation Result Summary" /> | 203 <has_text text="Validation Summary" /> |
| 200 <has_text text="Test Results" /> | 204 <has_text text="Test Summary" /> |
| 201 <has_text text="Feature Importance" /> | 205 <has_text text="Feature Importance" /> |
| 202 </assert_contents> | 206 </assert_contents> |
| 203 </output> | 207 </output> |
| 204 <output name="best_model_csv" value="expected_best_model_classification_customized_cross_off.csv" /> | 208 <output name="best_model_csv" value="expected_best_model_classification_customized_cross_off.csv" /> |
| 205 </test> | 209 </test> |
| 206 <test> | 210 <test> |
| 207 <param name="input_file" value="pcr.tsv"/> | 211 <param name="input_file" value="pcr.tsv"/> |
| 208 <param name="target_feature" value="11"/> | 212 <param name="target_feature" value="11"/> |
| 209 <param name="model_type" value="classification"/> | 213 <param name="model_type" value="classification"/> |
| 210 <param name="random_seed" value="42"/> | 214 <param name="random_seed" value="42"/> |
| 215 <param name="tune_model" value="true"/> | |
| 211 <output name="model" file="expected_model_classification.h5" compare="sim_size"/> | 216 <output name="model" file="expected_model_classification.h5" compare="sim_size"/> |
| 212 <output name="comparison_result"> | 217 <output name="comparison_result"> |
| 213 <assert_contents> | 218 <assert_contents> |
| 214 <has_text text="Validation Result Summary" /> | 219 <has_text text="Validation Summary" /> |
| 215 <has_text text="Test Results" /> | 220 <has_text text="Test Summary" /> |
| 221 <has_text text="Feature Importance" /> | |
| 222 </assert_contents> | |
| 223 </output> | |
| 224 <output name="best_model_csv" value="expected_best_model_classification.csv" /> | |
| 225 </test> | |
| 226 <test> | |
| 227 <param name="input_file" value="pcr.tsv"/> | |
| 228 <param name="target_feature" value="11"/> | |
| 229 <param name="model_type" value="classification"/> | |
| 230 <param name="random_seed" value="42"/> | |
| 231 <output name="model" file="expected_model_classification.h5" compare="sim_size"/> | |
| 232 <output name="comparison_result"> | |
| 233 <assert_contents> | |
| 234 <has_text text="Validation Summary" /> | |
| 235 <has_text text="Test Summary" /> | |
| 216 <has_text text="Feature Importance" /> | 236 <has_text text="Feature Importance" /> |
| 217 </assert_contents> | 237 </assert_contents> |
| 218 </output> | 238 </output> |
| 219 <output name="best_model_csv" value="expected_best_model_classification.csv" /> | 239 <output name="best_model_csv" value="expected_best_model_classification.csv" /> |
| 220 </test> | 240 </test> |
| 224 <param name="model_type" value="regression"/> | 244 <param name="model_type" value="regression"/> |
| 225 <param name="random_seed" value="42"/> | 245 <param name="random_seed" value="42"/> |
| 226 <output name="model" file="expected_model_regression.h5" compare="sim_size" /> | 246 <output name="model" file="expected_model_regression.h5" compare="sim_size" /> |
| 227 <output name="comparison_result"> | 247 <output name="comparison_result"> |
| 228 <assert_contents> | 248 <assert_contents> |
| 229 <has_text text="Validation Result Summary" /> | 249 <has_text text="Validation Summary" /> |
| 230 <has_text text="Test Results" /> | 250 <has_text text="Test Summary" /> |
| 231 <has_text text="Feature Importance" /> | 251 <has_text text="Feature Importance" /> |
| 232 </assert_contents> | 252 </assert_contents> |
| 233 </output> | 253 </output> |
| 234 <output name="best_model_csv" value="expected_best_model_regression.csv" /> | 254 <output name="best_model_csv" value="expected_best_model_regression.csv" /> |
| 235 </test> | 255 </test> |