annotate pipeline.xml @ 7:99038af8deda draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 57f4407e278a615f47a377a3328782b1d8e0b54d

<tool id="sklearn_build_pipeline" name="Pipeline Builder" version="@VERSION@">
    <description>constructs a list of transforms and a final estimator</description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements">
        <requirement type="package" version="0.6">skrebate</requirement>
        <requirement type="package" version="0.4.2">imbalanced-learn</requirement>
    </expand>
    <expand macro="macro_stdio"/>
    <version_command>echo "@VERSION@"</version_command>
    <command>
        <![CDATA[
        python "$sklearn_pipeline_script" '$inputs'
        ]]>
    </command>
    <configfiles>
        <inputs name="inputs" />
        <configfile name="sklearn_pipeline_script">
            <![CDATA[
import json
import pprint
import skrebate
import imblearn
from imblearn import under_sampling, over_sampling, combine
from imblearn.pipeline import Pipeline as imbPipeline
from sklearn import (preprocessing, svm, linear_model, ensemble, naive_bayes,
                    tree, neighbors, decomposition, kernel_approximation, cluster)
from sklearn.pipeline import Pipeline

with open('$__tool_directory__/sk_whitelist.json', 'r') as f:
    sk_whitelist = json.load(f)
exec(open('$__tool_directory__/utils.py').read(), globals())

warnings.filterwarnings('ignore')

safe_eval = SafeEval()

input_json_path = sys.argv[1]
with open(input_json_path, 'r') as param_handler:
    params = json.load(param_handler)

#if $final_estimator.estimator_selector.selected_module == 'customer_estimator':
params['final_estimator']['estimator_selector']['c_estimator'] =\
        '$final_estimator.estimator_selector.c_estimator'
#end if

pipeline_steps = []

def get_component(input_json, check_none=False):
    is_imblearn = False
    if input_json['component_type'] == 'None':
        if not check_none:
            return None, False
        else:
            sys.exit("The pre-processing component type can't be None when the number of components is greater than 1.")
    if input_json['component_type'] == 'pre_processor':
        preprocessor = input_json['pre_processors']['selected_pre_processor']
        pre_processor_options = input_json['pre_processors']['options']
        my_class = getattr(preprocessing, preprocessor)
        obj = my_class(**pre_processor_options)
    elif input_json['component_type'] == 'feature_selection':
        obj = feature_selector(input_json['fs_algorithm_selector'])
    elif input_json['component_type'] == 'decomposition':
        algorithm = input_json['matrix_decomposition_selector']['select_algorithm']
        obj = getattr(decomposition, algorithm)()
        options = input_json['matrix_decomposition_selector']['text_params'].strip()
        if options != '':
            options = safe_eval( 'dict(' + options + ')' )
            obj.set_params(**options)
    elif input_json['component_type'] == 'kernel_approximation':
        algorithm = input_json['kernel_approximation_selector']['select_algorithm']
        obj = getattr(kernel_approximation, algorithm)()
        options = input_json['kernel_approximation_selector']['text_params'].strip()
        if options != '':
            options = safe_eval( 'dict(' + options + ')' )
            obj.set_params(**options)
    elif input_json['component_type'] == 'FeatureAgglomeration':
        algorithm = input_json['FeatureAgglomeration_selector']['select_algorithm']
        obj = getattr(cluster, algorithm)()
        options = input_json['FeatureAgglomeration_selector']['text_params'].strip()
        if options != '':
            options = safe_eval( 'dict(' + options + ')' )
            obj.set_params(**options)
    elif input_json['component_type'] == 'skrebate':
        algorithm = input_json['skrebate_selector']['select_algorithm']
        if algorithm == 'TuRF':
            obj = getattr(skrebate, algorithm)(core_algorithm='ReliefF')
        else:
            obj = getattr(skrebate, algorithm)()
        options = input_json['skrebate_selector']['text_params'].strip()
        if options != '':
            options = safe_eval( 'dict(' + options + ')' )
            obj.set_params(**options)
    elif input_json['component_type'] == 'imblearn':
        is_imblearn = True
        algorithm = input_json['imblearn_selector']['select_algorithm']
        if algorithm == 'over_sampling.SMOTENC':
            obj = over_sampling.SMOTENC(categorical_features=[])
        else:
            globals = algorithm.split('.')
            mod, klass = globals[0], globals[1]
            obj = getattr(getattr(imblearn, mod), klass)()
        options = input_json['imblearn_selector']['text_params'].strip()
        if options != '':
            options = safe_eval( 'dict(' + options + ')' )
            obj.set_params(**options)
    if 'n_jobs' in obj.get_params():
        obj.set_params( n_jobs=N_JOBS )
    return obj, is_imblearn

has_imblearn = False
if len(params['pipeline_component']) == 1:
    step_obj, is_imblearn = get_component( params['pipeline_component'][0]['component_selector'])
    if step_obj:
        pipeline_steps.append( ('preprocessing_1', step_obj) )
        if is_imblearn:
            has_imblearn = True
else:
    for i, c in enumerate(params['pipeline_component']):
        step_obj, is_imblearn = get_component( c['component_selector'], check_none=True )
        pipeline_steps.append( ('preprocessing_' + str(i+1), step_obj) )
        if is_imblearn:
            has_imblearn = True

# Set up final estimator and add to pipeline.
estimator_json = params['final_estimator']['estimator_selector']
if estimator_json['selected_module'] == 'none':
    if len(pipeline_steps) == 0:
        sys.exit("No pipeline steps specified!")
    else:   # turn the last pre-process component to final estimator
        pipeline_steps[-1] = ('estimator', pipeline_steps[-1][-1])
else:
    estimator = get_estimator(estimator_json)
    pipeline_steps.append( ('estimator', estimator) )

if has_imblearn:
    pipeline = imbPipeline(pipeline_steps)
else:
    pipeline = Pipeline(pipeline_steps)
pprint.pprint(pipeline.named_steps)

with open('$outfile', 'wb') as out_handler:
    pickle.dump(pipeline, out_handler, pickle.HIGHEST_PROTOCOL)

            ]]>
        </configfile>
    </configfiles>
    <inputs>
        <repeat name="pipeline_component" min="1" max="5" title="Pre-processing step">
            <conditional name="component_selector">
                <param name="component_type" type="select" label="Choose the type of transformation:">
                    <option value="None" selected="true">None</option>
                    <option value="pre_processor">Sklearn Preprocessor</option>
                    <option value="feature_selection">Feature Selection</option>
                    <option value="decomposition">Matrix Decomposition</option>
                    <option value="kernel_approximation">Kernel Approximation</option>
                    <option value="FeatureAgglomeration">Agglomerate Features</option>
                    <option value="skrebate">SK-rebate feature selection</option>
                    <option value="imblearn">imbalanced-learn sampling</option>
                </param>
                <when value="None"/>
                <when value="pre_processor">
                    <conditional name="pre_processors">
                        <expand macro="sparse_preprocessors_ext" />
                        <expand macro="sparse_preprocessor_options_ext" />
                    </conditional>
                </when>
                <when value="feature_selection">
                    <expand macro="feature_selection_pipeline"/>
                </when>
                <when value="decomposition">
                    <expand macro="matrix_decomposition_all"/>
                </when>
                <when value="kernel_approximation">
                    <expand macro="kernel_approximation_all"/>
                </when>
                <when value="FeatureAgglomeration">
                    <expand macro="FeatureAgglomeration"/>
                </when>
                <when value="skrebate">
                    <expand macro="skrebate"/>
                </when>
                <when value="imblearn">
                    <expand macro="imbalanced_learn_sampling"/>
                </when>
            </conditional>
        </repeat>
        <section name="final_estimator" title="Final Estimator" expanded="true">
            <conditional name="estimator_selector">
                <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
                    <expand macro="estimator_module_options">
                        <option value="customer_estimator">Load a customer estimator</option>
                        <option value="none">none -- The last component of pre-processing step will turn to a final estimator</option>
                    </expand>
                </param>
                <expand macro="estimator_suboptions">
                    <when value="customer_estimator">
                        <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the customer estimator or pipeline:"/>
                    </when>
                    <when value="none"/>
                </expand>
            </conditional>
        </section>
    </inputs>
    <outputs>
        <data format="zip" name="outfile"/>
    </outputs>
    <tests>
        <test>
            <repeat name="pipeline_component">
                <conditional name="component_selector">
                    <param name="component_type" value="pre_processor"/>
                    <conditional name="pre_processors">
                        <param name="selected_pre_processor" value="RobustScaler"/>
                    </conditional>
                </conditional>
            </repeat>
            <repeat name="pipeline_component">
                <conditional name="component_selector">
                    <param name="component_type" value="feature_selection"/>
                    <conditional name="fs_algorithm_selector">
                        <param name="selected_algorithm" value="SelectKBest"/>
                        <param name="score_func" value="f_classif"/>
                    </conditional>
                </conditional>
            </repeat>
            <param name="selected_module" value="svm"/>
            <param name="selected_estimator" value="SVR"/>
            <param name="text_params" value="kernel='linear'"/>
            <output name="outfile" file="pipeline01" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="component_selector">
                <param name="component_type" value="pre_processor"/>
                <conditional name="pre_processors">
                    <param name="selected_pre_processor" value="RobustScaler"/>
                </conditional>
            </conditional>
            <param name="selected_module" value="linear_model"/>
            <param name="selected_estimator" value="LassoCV"/>
            <output name="outfile" file="pipeline02" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="component_selector">
                <param name="component_type" value="pre_processor"/>
                <conditional name="pre_processors">
                    <param name="selected_pre_processor" value="RobustScaler"/>
                </conditional>
            </conditional>
            <param name="selected_module" value="xgboost"/>
            <param name="selected_estimator" value="XGBClassifier"/>
            <output name="outfile" file="pipeline03" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="component_selector">
                <param name="component_type" value="feature_selection"/>
                <conditional name="fs_algorithm_selector">
                    <param name="selected_algorithm" value="SelectFromModel"/>
                    <conditional name="model_inputter">
                        <conditional name="estimator_selector">
                            <param name="selected_module" value="ensemble"/>
                            <param name="selected_estimator" value="AdaBoostClassifier"/>
                        </conditional>
                    </conditional>
                </conditional>
            </conditional>
            <section name="final_estimator">
                <param name="selected_module" value="svm"/>
                <param name="selected_estimator" value="LinearSVC"/>
            </section>
            <output name="outfile" file="pipeline04" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="component_selector">
                <param name="component_type" value="None"/>
            </conditional>
            <param name="selected_module" value="ensemble"/>
            <param name="selected_estimator" value="RandomForestRegressor"/>
            <param name="text_params" value="n_estimators=100, random_state=42"/>
            <output name="outfile" file="pipeline05" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="component_selector">
                <param name="component_type" value="decomposition"/>
                    <conditional name="matrix_decomposition_selector">
                        <param name="select_algorithm" value="PCA"/>
                    </conditional>
            </conditional>
            <param name="selected_module" value="ensemble"/>
            <param name="selected_estimator" value="AdaBoostRegressor"/>
            <output name="outfile" file="pipeline06" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="component_selector">
                <param name="component_type" value="kernel_approximation"/>
                    <conditional name="kernel_approximation_selector">
                        <param name="select_algorithm" value="RBFSampler"/>
                        <param name="text_params" value="n_components=10, gamma=2.0"/>
                    </conditional>
            </conditional>
            <param name="selected_module" value="ensemble"/>
            <param name="selected_estimator" value="AdaBoostClassifier"/>
            <output name="outfile" file="pipeline07" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="component_selector">
                <param name="component_type" value="FeatureAgglomeration"/>
                    <conditional name="FeatureAgglomeration_selector">
                        <param name="select_algorithm" value="FeatureAgglomeration"/>
                        <param name="text_params" value="n_clusters=3, affinity='euclidean'"/>
                    </conditional>
            </conditional>
            <param name="selected_module" value="ensemble"/>
            <param name="selected_estimator" value="AdaBoostClassifier"/>
            <output name="outfile" file="pipeline08" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="component_selector">
                <param name="component_type" value="skrebate"/>
                    <conditional name="skrebate_selector">
                        <param name="select_algorithm" value="ReliefF"/>
                        <param name="text_params" value="n_features_to_select=3, n_neighbors=100"/>
                    </conditional>
            </conditional>
            <param name="selected_module" value="ensemble"/>
            <param name="selected_estimator" value="RandomForestRegressor"/>
            <output name="outfile" file="pipeline09" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="component_selector">
                <param name="component_type" value="None"/>
            </conditional>
            <param name="selected_module" value="ensemble"/>
            <param name="selected_estimator" value="AdaBoostRegressor"/>
            <output name="outfile" file="pipeline10" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="component_selector">
                <param name="component_type" value="imblearn"/>
                <conditional name="imblearn_selector">
                    <param name="select_algorithm" value="under_sampling.EditedNearestNeighbours"/>
                </conditional>
            </conditional>
            <param name="selected_module" value="ensemble"/>
            <param name="selected_estimator" value="RandomForestClassifier"/>
            <output name="outfile" file="pipeline11" compare="sim_size" delta="5"/>
        </test>
        <test expect_failure="true">
            <conditional name="component_selector">
                <param name="component_type" value="None"/>
            </conditional>
            <param name="selected_module" value="ensemble"/>
            <param name="selected_estimator" value="RandomForestRegressor"/>
            <param name="text_params" value="n_estimators=__import__('os').system('ls ~')"/>
        </test>
        <test>
            <conditional name="component_selector">
                <param name="component_type" value="feature_selection"/>
                <conditional name="fs_algorithm_selector">
                    <param name="selected_algorithm" value="RFE"/>
                    <conditional name="estimator_selector">
                        <param name="selected_module" value="xgboost"/>
                        <param name="selected_estimator" value="XGBRegressor"/>
                        <param name="text_params" value="random_state=0"/>
                    </conditional>
                </conditional>
            </conditional>
            <section name="final_estimator">
                <conditional name="estimator_selector">
                    <param name="selected_module" value="none"/>
                </conditional>
            </section>
            <output name="outfile" file="pipeline12" compare="sim_size" delta="5"/>
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**
Constructs a pipeline that contains a list of transfroms and a final estimator. Pipeline assembles several steps
that can be cross-validated together while setting different parameters.
please refer to `Scikit-learn pipeline Pipeline`_.

**Pre-processing components** allow None, one or a combination of up to 5 transformations from `sklearn.preprocessing`_, `feature_selection`_, `decomposition`_, `kernel_approximation`_, `cluster.FeatureAgglomeration`_ and/or `skrebate`_.

**Estimator** selector supports estimators from `xgboost`_ and many scikit-learn modules, including `svm`_, `linear_model`_, `ensemble`_, `naive_bayes`_, `tree`_ and `neighbors`_.


.. _`Scikit-learn pipeline Pipeline`: http://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html
.. _`svm`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.svm
.. _`linear_model`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.linear_model
.. _`ensemble`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.ensemble
.. _`naive_bayes`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.naive_bayes
.. _`tree`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.tree
.. _`neighbors`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.neighbors
.. _`xgboost`: https://xgboost.readthedocs.io/en/latest/python/python_api.html

.. _`sklearn.preprocessing`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.preprocessing
.. _`feature_selection`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.feature_selection
.. _`decomposition`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.decomposition
.. _`kernel_approximation`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.kernel_approximation
.. _`cluster.FeatureAgglomeration`: http://scikit-learn.org/stable/modules/generated/sklearn.cluster.FeatureAgglomeration.html
.. _`skrebate`: https://epistasislab.github.io/scikit-rebate/using/

        ]]>
    </help>
    <expand macro="sklearn_citation">
        <expand macro="skrebate_citation"/>
        <expand macro="xgboost_citation"/>
        <expand macro="imblearn_citation"/>
    </expand>
</tool>