comparison tabular_learner.xml @ 10:49f73a3c12f3 draft default tip

planemo upload for repository https://github.com/goeckslab/gleam commit 1ffd143e57fa952ee9dd84fc141771520aea0791

9:e7dd78077b72

        <import>pycaret_macros.xml</import>
    </macros>
    <expand macro="python_requirements" />
    <command>
        <![CDATA[
        python $__tool_directory__/pycaret_train.py --input_file '$input_file' --target_col '$target_feature' --output_dir '.' --random_seed '$random_seed'
        #if $model_type == "classification"
            #if $classification_models
                --models '$classification_models'
            #end if
        #end if

    </outputs>
    <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"/>
            <param name="enable_cross_validation" value="true"/>
            <param name="cross_validation_folds" value="5"/>
            <param name="remove_outliers" value="true"/>
            <param name="remove_multicollinearity" value="true"/>
            <param name="probability_threshold" value="0.4" />
            <output name="model" file="expected_model_classification_customized.h5" compare="sim_size"/>
            <output name="comparison_result">
                <assert_contents>
                    <has_text text="Validation Summary" />
                    <has_text text="Test Summary" />

            <output name="best_model_csv" value="expected_best_model_classification_customized.csv" />
        </test>
        <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"/>
            <param name="enable_cross_validation" value="false"/>
            <param name="remove_outliers" value="true"/>
            <param name="remove_multicollinearity" value="true"/>
            <param name="probability_threshold" value="0.6" />
            <output name="model" file="expected_model_classification_customized_cross_off.h5" compare="sim_size"/>
            <output name="comparison_result">
                <assert_contents>
                    <has_text text="Validation Summary" />
                    <has_text text="Test Summary" />

            <output name="best_model_csv" value="expected_best_model_classification_customized_cross_off.csv" />
        </test>
        <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="tune_model" value="true"/>
            <output name="model" file="expected_model_classification.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_classification.csv" />
        </test>
        <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"/>
            <output name="model" file="expected_model_classification.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_classification.csv" />
        </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" />

10:49f73a3c12f3

        <import>pycaret_macros.xml</import>
    </macros>
    <expand macro="python_requirements" />
    <command>
        <![CDATA[
        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}
        #if $model_type == "classification"
            #if $classification_models
                --models '$classification_models'
            #end if
        #end if

    </outputs>
    <tests>
        <test>
            <param name="input_file" value="pcr.tsv"/>
            <param name="target_feature" value="11"/> 
            <param name="model_selection|model_type" value="classification"/>
            <param name="model_selection|best_model_metric" value="F1"/>
            <param name="random_seed" value="42"/>
            <param name="advanced_settings|customize_defaults" value="true"/>
            <param name="advanced_settings|train_size" value="0.8"/>
            <param name="advanced_settings|normalize" value="true"/>
            <param name="advanced_settings|feature_selection" value="true"/>
            <param name="advanced_settings|cross_validation|enable_cross_validation" value="true"/>
            <param name="advanced_settings|cross_validation|cross_validation_folds" value="5"/>
            <param name="advanced_settings|remove_outliers" value="true"/>
            <param name="advanced_settings|remove_multicollinearity" value="true"/>
            <param name="advanced_settings|probability_threshold" value="0.4" />
            <output name="model" file="expected_model_classification_customized.h5" compare="sim_size"/>
            <output name="comparison_result">
                <assert_contents>
                    <has_text text="Validation Summary" />
                    <has_text text="Test Summary" />

            <output name="best_model_csv" value="expected_best_model_classification_customized.csv" />
        </test>
        <test>
            <param name="input_file" value="pcr.tsv"/>
            <param name="target_feature" value="11"/> 
            <param name="model_selection|model_type" value="classification"/>
            <param name="random_seed" value="42"/>
            <param name="advanced_settings|customize_defaults" value="true"/>
            <param name="advanced_settings|train_size" value="0.8"/>
            <param name="advanced_settings|normalize" value="true"/>
            <param name="advanced_settings|feature_selection" value="true"/>
            <param name="advanced_settings|cross_validation|enable_cross_validation" value="false"/>
            <param name="advanced_settings|remove_outliers" value="true"/>
            <param name="advanced_settings|remove_multicollinearity" value="true"/>
            <param name="advanced_settings|probability_threshold" value="0.6" />
            <output name="model" file="expected_model_classification_customized_cross_off.h5" compare="sim_size"/>
            <output name="comparison_result">
                <assert_contents>
                    <has_text text="Validation Summary" />
                    <has_text text="Test Summary" />

            <output name="best_model_csv" value="expected_best_model_classification_customized_cross_off.csv" />
        </test>
        <test>
            <param name="input_file" value="pcr.tsv"/>
            <param name="target_feature" value="11"/> 
            <param name="model_selection|model_type" value="classification"/>
            <param name="random_seed" value="42"/>
            <param name="tune_model" value="true"/>
            <output name="model" file="expected_model_classification.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">
                <assert_contents>
                    <has_text text="n_estimators,100" />
                    <has_text text="num_leaves,31" />
                    <has_text text="learning_rate,0.1" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input_file" value="pcr.tsv"/>
            <param name="target_feature" value="11"/> 
            <param name="model_selection|model_type" value="classification"/>
            <param name="random_seed" value="42"/>
            <output name="model" file="expected_model_classification.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">
                <assert_contents>
                    <has_text text="n_estimators,100" />
                    <has_text text="num_leaves,31" />
                    <has_text text="learning_rate,0.1" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input_file" value="auto-mpg.tsv"/>
            <param name="target_feature" value="1"/> 
            <param name="model_selection|model_type" value="regression"/>
            <param name="model_selection|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" />