comparison tabular_learner.xml @ 9:e7dd78077b72 draft default tip

planemo upload for repository https://github.com/goeckslab/gleam commit 84d5cd0b1fa5c1ff0ad892bc39c95dad1ceb4920

8:ba45bc057d70

        #end if
        #if $has_test_file == "yes"
            --test_file '$test_file'
        #end if
        --model_type '$model_type'
        ]]>
    </command>
    <inputs>
        <param name="input_file" type="data" format="csv,tabular" label="Tabular Input Dataset" />
        <conditional name="test_data_choice">

                    <option value="et">Extra Trees Classifier</option>
                    <option value="xgboost">Extreme Gradient Boosting</option>
                    <option value="lightgbm">Light Gradient Boosting Machine</option>
                    <option value="catboost">CatBoost Classifier</option>
                </param>
            </when>
            <when value="regression">
                <param name="regression_models" type="select" multiple="true" label="Only Select Regression Models if you don't want to compare all models">
                    <option value="lr">Linear Regression</option>
                    <option value="lasso">Lasso Regression</option>

                    <option value="gbr">Gradient Boosting Regressor</option>
                    <option value="mlp">MLP Regressor</option>
                    <option value="xgboost">Extreme Gradient Boosting</option>
                    <option value="lightgbm">Light Gradient Boosting Machine</option>
                    <option value="catboost">CatBoost Regressor</option>
                </param>
            </when>
        </conditional>
        <param name="tune_model" type="boolean" truevalue="True" falsevalue="False" label="Tune hyperparameters" help="Hyperparameter tuning on the best model" />
        <param name="random_seed" type="integer" value="42" label="Random Seed" help="Random seed for reproducibility." />

    <tests>
        <test>
            <param name="input_file" value="pcr.tsv"/>
            <param name="target_feature" value="11"/> 
            <param name="model_type" value="classification"/>
            <param name="random_seed" value="42"/>
            <param name="customize_defaults" value="true"/>
            <param name="train_size" value="0.8"/>
            <param name="normalize" value="true"/>
            <param name="feature_selection" value="true"/>

            <output name="comparison_result">
                <assert_contents>
                    <has_text text="Validation Summary" />
                    <has_text text="Test Summary" />
                    <has_text text="Feature Importance" />
                </assert_contents>
            </output>
            <output name="best_model_csv" value="expected_best_model_classification_customized.csv" />
        </test>
        <test>

        </test>
        <test>
            <param name="input_file" value="auto-mpg.tsv"/>
            <param name="target_feature" value="1"/> 
            <param name="model_type" value="regression"/>
            <param name="random_seed" value="42"/>
            <output name="model" file="expected_model_regression.h5" compare="sim_size" />
            <output name="comparison_result">
                <assert_contents>
                    <has_text text="Validation Summary" />
                    <has_text text="Test Summary" />
                    <has_text text="Feature Importance" />
                </assert_contents>
            </output>
            <output name="best_model_csv" value="expected_best_model_regression.csv" />
        </test>
    </tests>

9:e7dd78077b72

        #end if
        #if $has_test_file == "yes"
            --test_file '$test_file'
        #end if
        --model_type '$model_type'
        #if $best_model_metric
            --best_model_metric '$best_model_metric'
        #end if
        ]]>
    </command>
    <inputs>
        <param name="input_file" type="data" format="csv,tabular" label="Tabular Input Dataset" />
        <conditional name="test_data_choice">

                    <option value="et">Extra Trees Classifier</option>
                    <option value="xgboost">Extreme Gradient Boosting</option>
                    <option value="lightgbm">Light Gradient Boosting Machine</option>
                    <option value="catboost">CatBoost Classifier</option>
                </param>
                <param name="best_model_metric" type="select" label="Select metric to pick the best model" help="PyCaret will rank models by this metric. Default is Accuracy.">
                    <option value="Accuracy" selected="true">Accuracy</option>
                    <option value="AUC">ROC-AUC</option>
                    <option value="Precision">Precision</option>
                    <option value="Recall">Recall</option>
                    <option value="F1">F1</option>
                    <option value="Kappa">Cohen’s Kappa</option>
                    <option value="Log Loss">Log Loss (lower is better)</option>
                    <option value="PR-AUC-Weighted">PR-AUC (weighted)</option>
                </param>
            </when>
            <when value="regression">
                <param name="regression_models" type="select" multiple="true" label="Only Select Regression Models if you don't want to compare all models">
                    <option value="lr">Linear Regression</option>
                    <option value="lasso">Lasso Regression</option>

                    <option value="gbr">Gradient Boosting Regressor</option>
                    <option value="mlp">MLP Regressor</option>
                    <option value="xgboost">Extreme Gradient Boosting</option>
                    <option value="lightgbm">Light Gradient Boosting Machine</option>
                    <option value="catboost">CatBoost Regressor</option>
                </param>
                <param name="best_model_metric" type="select" label="Select metric to pick the best model" help="PyCaret will rank models by this metric. Default is R².">
                    <option value="R2" selected="true">R²</option>
                    <option value="MAE">MAE</option>
                    <option value="MSE">MSE</option>
                    <option value="RMSE">RMSE</option>
                    <option value="RMSLE">RMSLE</option>
                    <option value="MAPE">MAPE</option>
                </param>
            </when>
        </conditional>
        <param name="tune_model" type="boolean" truevalue="True" falsevalue="False" label="Tune hyperparameters" help="Hyperparameter tuning on the best model" />
        <param name="random_seed" type="integer" value="42" label="Random Seed" help="Random seed for reproducibility." />

    <tests>
        <test>
            <param name="input_file" value="pcr.tsv"/>
            <param name="target_feature" value="11"/> 
            <param name="model_type" value="classification"/>
            <param name="best_model_metric" value="F1"/>
            <param name="random_seed" value="42"/>
            <param name="customize_defaults" value="true"/>
            <param name="train_size" value="0.8"/>
            <param name="normalize" value="true"/>
            <param name="feature_selection" value="true"/>

            <output name="comparison_result">
                <assert_contents>
                    <has_text text="Validation Summary" />
                    <has_text text="Test Summary" />
                    <has_text text="Feature Importance" />
                    <has_text text="Best Model Metric" />
                    <has_text text="F1" />
                </assert_contents>
            </output>
            <output name="best_model_csv" value="expected_best_model_classification_customized.csv" />
        </test>
        <test>

        </test>
        <test>
            <param name="input_file" value="auto-mpg.tsv"/>
            <param name="target_feature" value="1"/> 
            <param name="model_type" value="regression"/>
            <param name="best_model_metric" value="RMSE"/>
            <param name="random_seed" value="42"/>
            <output name="model" file="expected_model_regression.h5" compare="sim_size" />
            <output name="comparison_result">
                <assert_contents>
                    <has_text text="Validation Summary" />
                    <has_text text="Test Summary" />
                    <has_text text="Feature Importance" />
                    <has_text text="Best Model Metric" />
                    <has_text text="RMSE" />
                </assert_contents>
            </output>
            <output name="best_model_csv" value="expected_best_model_regression.csv" />
        </test>
    </tests>