Mercurial > repos > bgruening > keras_train_and_eval
diff keras_train_and_eval.xml @ 4:3866911c93ae draft
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit e2a5eade6d0e5ddf3a47630381a0ad90d80e8a04"
author | bgruening |
---|---|
date | Tue, 13 Apr 2021 18:37:35 +0000 |
parents | ccd6269fad60 |
children | b3093f953091 |
line wrap: on
line diff
--- a/keras_train_and_eval.xml Thu Oct 01 21:12:39 2020 +0000 +++ b/keras_train_and_eval.xml Tue Apr 13 18:37:35 2021 +0000 @@ -1,11 +1,11 @@ -<tool id="keras_train_and_eval" name="Deep learning training and evaluation" version="@VERSION@"> +<tool id="keras_train_and_eval" name="Deep learning training and evaluation" version="@VERSION@" profile="20.05"> <description>conduct deep training and evaluation either implicitly or explicitly</description> <macros> <import>main_macros.xml</import> <import>keras_macros.xml</import> </macros> - <expand macro="python_requirements"/> - <expand macro="macro_stdio"/> + <expand macro="python_requirements" /> + <expand macro="macro_stdio" /> <version_command>echo "@VERSION@"</version_command> <command> <![CDATA[ @@ -19,30 +19,27 @@ --inputs '$inputs' --estimator '$experiment_schemes.infile_estimator' #if $input_options.selected_input == 'seq_fasta' - --fasta_path '$input_options.fasta_path' + --fasta_path '$input_options.fasta_path' #elif $input_options.selected_input == 'refseq_and_interval' - --ref_seq "`pwd`/${ref_genome_file.element_identifier}" - --interval '$input_options.interval_file' - --targets "`pwd`/${target_file.element_identifier}.gz" + --ref_seq "`pwd`/${ref_genome_file.element_identifier}" + --interval '$input_options.interval_file' + --targets "`pwd`/${target_file.element_identifier}.gz" #else - --infile1 '$input_options.infile1' + --infile1 '$input_options.infile1' #end if - --infile2 '$input_options.infile2' - --outfile_result "`pwd`/tmp_outfile_result" + --infile2 '$input_options.infile2' + --outfile_result '$outfile_result' #if $save and 'save_estimator' in str($save) - --outfile_object '$outfile_object' - --outfile_weights '$outfile_weights' + --outfile_object '$outfile_object' + --outfile_weights '$outfile_weights' #end if #if $save and 'save_prediction' in str($save) - --outfile_y_true '$outfile_y_true' - --outfile_y_preds '$outfile_y_preds' + --outfile_y_true '$outfile_y_true' + --outfile_y_preds '$outfile_y_preds' #end if #if $experiment_schemes.test_split.split_algos.shuffle == 'group' - --groups '$experiment_schemes.test_split.split_algos.groups_selector.infile_g' + --groups '$experiment_schemes.test_split.split_algos.groups_selector.infile_g' #end if - >'$outfile_result' && cp '$outfile_result' "`pwd`/../tool_stdout" - && cp tmp_outfile_result '$outfile_result'; - ]]> </command> <configfiles> @@ -55,39 +52,39 @@ <option value="train_val_test">Train, Validate and and Evaluate</option> </param> <when value="train_val"> - <expand macro="estimator_and_hyperparameter"/> + <expand macro="estimator_and_hyperparameter" /> <section name="test_split" title="Validation holdout" expanded="false"> <expand macro="train_test_split_params"> - <expand macro="cv_groups"/> + <expand macro="cv_groups" /> </expand> </section> <section name="metrics" title="Metrics for evaluation" expanded="false"> - <expand macro="scoring_selection"/> + <expand macro="scoring_selection" /> </section> </when> <when value="train_val_test"> - <expand macro="estimator_and_hyperparameter"/> + <expand macro="estimator_and_hyperparameter" /> <section name="test_split" title="Test holdout" expanded="false"> <expand macro="train_test_split_params"> - <expand macro="cv_groups"/> + <expand macro="cv_groups" /> </expand> </section> <section name="val_split" title="Validation holdout (recommend using the same splitting method as for test holdout)" expanded="false"> - <expand macro="train_test_split_params"/> + <expand macro="train_test_split_params" /> </section> <section name="metrics" title="Metrics for evaluation" expanded="false"> - <expand macro="scoring_selection"/> + <expand macro="scoring_selection" /> </section> </when> </conditional> - <expand macro="sl_mixed_input_plus_sequence"/> + <expand macro="sl_mixed_input_plus_sequence" /> <param name="save" type="select" multiple='true' display="checkboxes" label="Save the fitted model" optional="true" help="Evaluation scores will be output by default."> <option value="save_estimator" selected="true">Fitted estimator in skeleton and weights, separately</option> <option value="save_prediction">True labels and prediction results from evaluation for downstream analysis</option> </param> </inputs> <outputs> - <data format="tabular" name="outfile_result"/> + <data format="tabular" name="outfile_result" /> <data format="zip" name="outfile_object" label="Fitted estimator or estimator skeleton on ${on_string}"> <filter>str(save) and 'save_estimator' in str(save)</filter> </data> @@ -104,176 +101,176 @@ <tests> <test> <conditional name="experiment_schemes"> - <param name="selected_exp_scheme" value="train_val_test"/> - <param name="infile_estimator" value="keras_model04" ftype="zip"/> + <param name="selected_exp_scheme" value="train_val_test" /> + <param name="infile_estimator" value="keras_model04" ftype="zip" /> <section name="hyperparams_swapping"> - <param name="infile_params" value="keras_params04.tabular" ftype="tabular"/> + <param name="infile_params" value="keras_params04.tabular" ftype="tabular" /> <repeat name="param_set"> - <param name="sp_value" value="999"/> - <param name="sp_name" value="layers_0_Dense__config__kernel_initializer__config__seed"/> + <param name="sp_value" value="999" /> + <param name="sp_name" value="layers_0_Dense__config__kernel_initializer__config__seed" /> </repeat> <repeat name="param_set"> - <param name="sp_value" value="999"/> - <param name="sp_name" value="layers_2_Dense__config__kernel_initializer__config__seed"/> + <param name="sp_value" value="999" /> + <param name="sp_name" value="layers_2_Dense__config__kernel_initializer__config__seed" /> </repeat> <repeat name="param_set"> - <param name="sp_value" value="0.1"/> - <param name="sp_name" value="lr"/> + <param name="sp_value" value="0.1" /> + <param name="sp_name" value="lr" /> </repeat> <repeat name="param_set"> - <param name="sp_value" value="'adamax'"/> - <param name="sp_name" value="optimizer"/> + <param name="sp_value" value="'adamax'" /> + <param name="sp_name" value="optimizer" /> </repeat> </section> <section name="test_split"> <conditional name="split_algos"> - <param name="shuffle" value="simple"/> - <param name="test_size" value="0.2"/> - <param name="random_state" value="123"/> + <param name="shuffle" value="simple" /> + <param name="test_size" value="0.2" /> + <param name="random_state" value="123" /> </conditional> </section> <section name="val_split"> <conditional name="split_algos"> - <param name="shuffle" value="simple"/> - <param name="test_size" value="0.2"/> - <param name="random_state" value="456"/> + <param name="shuffle" value="simple" /> + <param name="test_size" value="0.2" /> + <param name="random_state" value="456" /> </conditional> </section> <section name="metrics"> <conditional name="scoring"> - <param name="primary_scoring" value="r2"/> - <param name="secondary_scoring" value="neg_mean_absolute_error"/> + <param name="primary_scoring" value="r2" /> + <param name="secondary_scoring" value="neg_mean_absolute_error" /> </conditional> </section> </conditional> - <param name="infile1" value="regression_X.tabular" ftype="tabular"/> + <param name="infile1" value="regression_X.tabular" ftype="tabular" /> <param name="header1" value="true" /> - <param name="selected_column_selector_option" value="all_columns"/> - <param name="infile2" value="regression_y.tabular" ftype="tabular"/> + <param name="selected_column_selector_option" value="all_columns" /> + <param name="infile2" value="regression_y.tabular" ftype="tabular" /> <param name="header2" value="true" /> - <param name="selected_column_selector_option2" value="all_columns"/> - <param name="save" value="save_estimator"/> + <param name="selected_column_selector_option2" value="all_columns" /> + <param name="save" value="save_estimator" /> <output name="outfile_result"> <assert_contents> - <has_n_columns n="2"/> - <has_text text="0.6626"/> - <has_text text="5.598"/> + <has_n_columns n="2" /> + <has_text text="0.638" /> + <has_text text="-6.072" /> </assert_contents> </output> - <output name="outfile_object" file="train_test_eval_model01" compare="sim_size" delta="5"/> - <output name="outfile_weights" file="train_test_eval_weights01.h5" compare="sim_size" delta="5"/> + <output name="outfile_object" file="train_test_eval_model01" compare="sim_size" delta="50" /> + <output name="outfile_weights" file="train_test_eval_weights01.h5" compare="sim_size" delta="50" /> </test> <test> <conditional name="experiment_schemes"> - <param name="selected_exp_scheme" value="train_val_test"/> - <param name="infile_estimator" value="keras_model04" ftype="zip"/> + <param name="selected_exp_scheme" value="train_val_test" /> + <param name="infile_estimator" value="keras_model04" ftype="zip" /> <section name="hyperparams_swapping"> - <param name="infile_params" value="keras_params04.tabular" ftype="tabular"/> + <param name="infile_params" value="keras_params04.tabular" ftype="tabular" /> <repeat name="param_set"> - <param name="sp_value" value="999"/> - <param name="sp_name" value="layers_0_Dense__config__kernel_initializer__config__seed"/> + <param name="sp_value" value="999" /> + <param name="sp_name" value="layers_0_Dense__config__kernel_initializer__config__seed" /> </repeat> <repeat name="param_set"> - <param name="sp_value" value="999"/> - <param name="sp_name" value="layers_2_Dense__config__kernel_initializer__config__seed"/> + <param name="sp_value" value="999" /> + <param name="sp_name" value="layers_2_Dense__config__kernel_initializer__config__seed" /> </repeat> <repeat name="param_set"> - <param name="sp_value" value="0.1"/> - <param name="sp_name" value="lr"/> + <param name="sp_value" value="0.1" /> + <param name="sp_name" value="lr" /> </repeat> <repeat name="param_set"> - <param name="sp_value" value="'adamax'"/> - <param name="sp_name" value="optimizer"/> + <param name="sp_value" value="'adamax'" /> + <param name="sp_name" value="optimizer" /> </repeat> </section> <section name="test_split"> <conditional name="split_algos"> - <param name="shuffle" value="group"/> - <param name="group_names" value="test"/> + <param name="shuffle" value="group" /> + <param name="group_names" value="test" /> <section name="groups_selector"> - <param name="infile_g" value="regression_groups.tabular" ftype="tabular"/> - <param name="header_g" value="true"/> + <param name="infile_g" value="regression_groups.tabular" ftype="tabular" /> + <param name="header_g" value="true" /> <conditional name="column_selector_options_g"> - <param name="selected_column_selector_option_g" value="by_index_number"/> - <param name="col_g" value="1"/> + <param name="selected_column_selector_option_g" value="by_index_number" /> + <param name="col_g" value="1" /> </conditional> </section> </conditional> </section> <section name="val_split"> <conditional name="split_algos"> - <param name="shuffle" value="group"/> - <param name="group_names" value="validation"/> + <param name="shuffle" value="group" /> + <param name="group_names" value="validation" /> </conditional> </section> <section name="metrics"> <conditional name="scoring"> - <param name="primary_scoring" value="r2"/> - <param name="secondary_scoring" value="neg_mean_absolute_error"/> + <param name="primary_scoring" value="r2" /> + <param name="secondary_scoring" value="neg_mean_absolute_error" /> </conditional> </section> </conditional> - <param name="infile1" value="regression_X.tabular" ftype="tabular"/> + <param name="infile1" value="regression_X.tabular" ftype="tabular" /> <param name="header1" value="true" /> - <param name="selected_column_selector_option" value="all_columns"/> - <param name="infile2" value="regression_y.tabular" ftype="tabular"/> + <param name="selected_column_selector_option" value="all_columns" /> + <param name="infile2" value="regression_y.tabular" ftype="tabular" /> <param name="header2" value="true" /> - <param name="selected_column_selector_option2" value="all_columns"/> - <param name="save" value="save_estimator,save_prediction"/> - <output name="outfile_result" > + <param name="selected_column_selector_option2" value="all_columns" /> + <param name="save" value="save_estimator,save_prediction" /> + <output name="outfile_result"> <assert_contents> - <has_n_columns n="2"/> - <has_text text="0.667"/> - <has_text text="5.586"/> + <has_n_columns n="2" /> + <has_text text="0.627" /> + <has_text text="-6.012" /> </assert_contents> </output> - <output name="outfile_weights" file="train_test_eval_weights02.h5" compare="sim_size" delta="5"/> - <output name="outfile_y_true" file="keras_train_eval_y_true02.tabular" ftype="tabular"/> + <output name="outfile_weights" file="train_test_eval_weights02.h5" compare="sim_size" delta="50" /> + <output name="outfile_y_true" file="keras_train_eval_y_true02.tabular" ftype="tabular" /> </test> <test> <conditional name="experiment_schemes"> - <param name="selected_exp_scheme" value="train_val"/> - <param name="infile_estimator" value="pipeline10" ftype="zip"/> + <param name="selected_exp_scheme" value="train_val" /> + <param name="infile_estimator" value="pipeline10" ftype="zip" /> <section name="hyperparams_swapping"> - <param name="infile_params" value="get_params10.tabular" ftype="tabular"/> + <param name="infile_params" value="get_params10.tabular" ftype="tabular" /> <repeat name="param_set"> - <param name="sp_value" value="10"/> - <param name="sp_name" value="adaboostregressor__random_state"/> + <param name="sp_value" value="10" /> + <param name="sp_name" value="adaboostregressor__random_state" /> </repeat> <repeat name="param_set"> - <param name="sp_value" value=": sklearn_tree.ExtraTreeRegressor(random_state=0)"/> - <param name="sp_name" value="adaboostregressor__base_estimator"/> + <param name="sp_value" value=": sklearn_tree.ExtraTreeRegressor(random_state=0)" /> + <param name="sp_name" value="adaboostregressor__base_estimator" /> </repeat> </section> <section name="test_split"> <conditional name="split_algos"> - <param name="shuffle" value="simple"/> - <param name="test_size" value="0.2"/> - <param name="random_state" value="123"/> + <param name="shuffle" value="simple" /> + <param name="test_size" value="0.2" /> + <param name="random_state" value="123" /> </conditional> </section> <section name="val_split"> <conditional name="split_algos"> - <param name="shuffle" value="simple"/> - <param name="test_size" value="0.2"/> - <param name="random_state" value="456"/> + <param name="shuffle" value="simple" /> + <param name="test_size" value="0.2" /> + <param name="random_state" value="456" /> </conditional> </section> <section name="metrics"> <conditional name="scoring"> - <param name="primary_scoring" value="r2"/> - <param name="secondary_scoring" value="neg_mean_absolute_error"/> + <param name="primary_scoring" value="r2" /> + <param name="secondary_scoring" value="neg_mean_absolute_error" /> </conditional> </section> </conditional> - <param name="infile1" value="regression_X.tabular" ftype="tabular"/> + <param name="infile1" value="regression_X.tabular" ftype="tabular" /> <param name="header1" value="true" /> - <param name="selected_column_selector_option" value="all_columns"/> - <param name="infile2" value="regression_y.tabular" ftype="tabular"/> + <param name="selected_column_selector_option" value="all_columns" /> + <param name="infile2" value="regression_y.tabular" ftype="tabular" /> <param name="header2" value="true" /> - <param name="selected_column_selector_option2" value="all_columns"/> - <param name="save" value=""/> - <output name="outfile_result" file="train_test_eval03.tabular"/> + <param name="selected_column_selector_option2" value="all_columns" /> + <param name="save" value="" /> + <output name="outfile_result" file="train_test_eval03.tabular" /> </test> </tests> <help> @@ -307,6 +304,6 @@ ]]> </help> <expand macro="sklearn_citation"> - <expand macro="keras_citation"/> + <expand macro="keras_citation" /> </expand> </tool>