Mercurial > repos > bgruening > ml_visualization_ex
diff ml_visualization_ex.xml @ 0:f96efab83b65 draft
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit ba6a47bdf76bbf4cb276206ac1a8cbf61332fd16"
author | bgruening |
---|---|
date | Fri, 13 Sep 2019 12:23:39 -0400 |
parents | |
children | 09efff9a5765 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ml_visualization_ex.xml Fri Sep 13 12:23:39 2019 -0400 @@ -0,0 +1,184 @@ +<tool id="ml_visualization_ex" name="Machine Learning Visualization Extension" version="@VERSION@"> + <description>includes several types of plotting for machine learning</description> + <macros> + <import>main_macros.xml</import> + <import>keras_macros.xml</import> + </macros> + <expand macro="python_requirements"> + <requirement type="package" version="3.1.1">plotly</requirement> + <requirement type="package" version="2.40.1">graphviz</requirement> + <requirement type="package" version="1.4.1">pydot</requirement> + </expand> + <expand macro="macro_stdio"/> + <version_command>echo "@VERSION@"</version_command> + <command> + <![CDATA[ + python '$__tool_directory__/ml_visualization_ex.py' + --inputs '$inputs' + #if $plotting_selection.plot_type in ['learning_curve', 'rfecv_gridscores'] + --infile1 '$plotting_selection.infile1' + #elif $plotting_selection.plot_type in ['pr_curve', 'roc_curve'] + --infile1 '$plotting_selection.infile1' + --infile2 '$plotting_selection.infile2' + #elif $plotting_selection.plot_type == 'feature_importances' + --estimator '$plotting_selection.infile_estimator' + --infile1 '$plotting_selection.infile1' + #elif $plotting_selection.plot_type == 'keras_plot_model' + --model_config '$plotting_selection.infile_model_config' + #end if + ]]> + </command> + <configfiles> + <inputs name="inputs" /> + </configfiles> + <inputs> + <conditional name="plotting_selection"> + <param name="plot_type" type="select" label="Select a plotting type"> + <option value="learning_curve" selected="true">Learning curve</option> + <option value="pr_curve">2-class Precison Recall curve</option> + <option value="roc_curve">2-class Receiver Operating Characteristic (ROC) curve</option> + <option value="rfecv_gridscores">Number of features vs. Recursive Feature Elimination gridscores with corss-validation</option> + <option value="feature_importances">Feature Importances plot</option> + <option value="keras_plot_model">keras plot model - plot configuration of a neural network model</option> + </param> + <when value="learning_curve"> + <param name="infile1" type="data" format="tabular" label="Select the dataset containing values for plotting learning curve." help="This dataset should be the output of tool model_validation->learning_curve."/> + <param name="plot_std_err" type="boolean" truevalue="booltrue" falsevalue="boolfalse" optional="true" checked="false" label="Whether to plot standard error bar?"/> + <param name="title" type="text" value="" optional="true" label="Plot title" help="Optional. If change is desired."/> + </when> + <when value="pr_curve"> + <param name="infile1" type="data" format="tabular" label="Select the dataset containing true labels." help="No headers. Each column corresponds to one class."/> + <param name="infile2" type="data" format="tabular" label="Select the dataset containing predicted probabilities." help="No headers. Each column corresponds to one class."/> + <param name="pos_label" type="text" value="" optional="true" label="pos_label" help="The label of positive class. If not specified, it will be 1 by default."/> + <param name="title" type="text" value="" optional="true" label="Plot title" help="Optional. If change is desired."/> + </when> + <when value="roc_curve"> + <param name="infile1" type="data" format="tabular" label="Select the dataset containing true labels." help="No headers. Each column corresponds to one class."/> + <param name="infile2" type="data" format="tabular" label="Select the dataset containing predicted probabilities." help="No headers. Each column corresponds to one class."/> + <param name="pos_label" type="text" value="" optional="true" label="pos_label" help="The label of positive class. If not specified, it will be 1 by default."/> + <param name="drop_intermediate" type="boolean" truevalue="booltrue" falsevalue="boolfalse" optional="true" checked="true" label="drop_intermediate" help="Whether to drop some suboptimal thresholds which would not appear on a plotted ROC curve."/> + <param name="title" type="text" value="" optional="true" label="Plot title" help="Optional. If change is desired."/> + </when> + <when value="rfecv_gridscores"> + <param name="infile1" type="data" format="tabular" label="Select the dataset containing grid_scores from a fitted RFECV object." help="Headered. Single column. Could be Output from `estimator_attributes->grid_scores_`."/> + <param name="steps" type="text" value="" optional="true" label="Step IDs" help="List, containing hover labels for each grid_score. For example: `list(range(10)) + [15, 20]`."/> + <param name="title" type="text" value="" optional="true" label="Plot title" help="Optional. If change is desired."/> + </when> + <when value="feature_importances"> + <param name="infile_estimator" type="data" format="zip" label="Select the dataset containing fitted estimator/pipeline" /> + <param name="infile1" type="data" format="tabular" label="Select the dataset containing feature names" help="Make sure the headers (first row) are feature names."/> + <conditional name="column_selector_options"> + <expand macro="samples_column_selector_options" multiple="true"/> + </conditional> + <param name="threshold" type="float" value="" optional="true" min="0." label="Threshold value" help="Features with importance below the threshold value will be ignored."/> + <param name="title" type="text" value="" optional="true" label="Custom plot title" help="Optional."/> + </when> + <when value="keras_plot_model"> + <param name="infile_model_config" type="data" format="json" label="Select the JSON dataset containing configuration for a neural network model"/> + <param name="title" type="hidden" value="" optional="true" label="Plot title" help="Optional. If change is desired."/> + </when> + </conditional> + </inputs> + <outputs> + <data name="output" format="html" from_work_dir="output" label="${plotting_selection.plot_type} plot on ${on_string}"> + <change_format> + <when input="plotting_selection.plot_type" value="keras_plot_model" format="png"/> + </change_format> + </data> + </outputs> + <tests> + <test> + <param name="plot_type" value="roc_curve"/> + <param name="infile1" value="y_true.tabular" ftype="tabular"/> + <param name="infile2" value="y_score.tabular" ftype="tabular"/> + <output name="output" file="ml_vis04.html" compare="sim_size"/> + </test> + <test> + <param name="plot_type" value="feature_importances"/> + <param name="infile_estimator" value="best_estimator_.zip" ftype="zip"/> + <param name="infile1" value="regression_X.tabular" ftype="tabular"/> + <param name="selected_column_selector_option" value="all_columns"/> + <output name="output" file="ml_vis01.html" compare="sim_size"/> + </test> + <test> + <param name="plot_type" value="learning_curve"/> + <param name="infile1" value="mv_result03.tabular" ftype="tabular"/> + <output name="output" file="ml_vis02.html" compare="sim_size"/> + </test> + <test> + <param name="plot_type" value="pr_curve"/> + <param name="infile1" value="y_true.tabular" ftype="tabular"/> + <param name="infile2" value="y_score.tabular" ftype="tabular"/> + <output name="output" file="ml_vis03.html" compare="sim_size"/> + </test> + <test> + <param name="plot_type" value="rfecv_gridscores"/> + <param name="infile1" value="grid_scores_.tabular" ftype="tabular"/> + <output name="output" file="ml_vis05.html" compare="sim_size"/> + </test> + <test> + <param name="plot_type" value="keras_plot_model"/> + <param name="infile_model_config" value="deepsear_1feature.json" ftype="json"/> + <output name="output" file="ml_vis05.png" compare="sim_size" delta="20000"/> + </test> + </tests> + <help> + <![CDATA[ +**What it does** +This tool ouputs serveral machine learning visualization plots using Plotly, including 'feature_importances', 'learning curve', 'precison recall curve', 'roc_curve', and 'number of featues vs. rfecv gridscores'. This tool also ouputs configuration diagram for a deep learning model using the Keras model JSON file as input. + + +**Feature importances** + +.. image:: https://raw.githubusercontent.com/goeckslab/Galaxy-ML/master/galaxy_ml/tools/images/feature_importances.png + :width: 400 + :alt: feature importances + + +**Learning curve** + +.. image:: https://raw.githubusercontent.com/goeckslab/Galaxy-ML/master/galaxy_ml/tools/images/learning_curve.png + :width: 400 + :alt: learning curve + + +**Precison recall curve** + +.. image:: https://raw.githubusercontent.com/goeckslab/Galaxy-ML/master/galaxy_ml/tools/images/pr_curve.png + :width: 400 + :alt: precison recall curve + + +**Receiver operating characteristic curve** + +.. image:: https://raw.githubusercontent.com/goeckslab/Galaxy-ML/master/galaxy_ml/tools/images/roc_curve.png + :width: 400 + :alt: Receiver operating characteristic curve + + +**Number of featues vs. rfecv gridscores** + +.. image:: https://raw.githubusercontent.com/goeckslab/Galaxy-ML/master/galaxy_ml/tools/images/rfecv_gridscore.png + :width: 400 + :alt: Number of featues vs. rfecv gridscores + + +**Deep learning model configuration** + +.. image:: https://raw.githubusercontent.com/goeckslab/Galaxy-ML/master/galaxy_ml/tools/images/deepsea.png + :width: 400 + :alt: deapsea model configuration + ]]> + </help> + <expand macro="sklearn_citation"> + <citation type="bibtex"> + @online{plotly, + author = {Plotly Technologies Inc.}, + title = {Collaborative data science}, + publisher = {Plotly Technologies Inc.}, + address = {Montreal, QC}, + year = {2015}, + url = {https://plot.ly}} + </citation> + </expand> +</tool>