comparison ensemble.xml @ 5:f1761288587e draft

planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 35fa73d6e9ba8f0789ddfb743d893d950a68af02

4:0431274c367d

#if $selected_tasks.selected_task == "train":

algorithm = params["selected_tasks"]["selected_algorithms"]["selected_algorithm"]
options = params["selected_tasks"]["selected_algorithms"]["options"]
input_type = params["selected_tasks"]["selected_algorithms"]["input_options"]["selected_input"]
if input_type=="tabular":
    header = 'infer' if params["selected_tasks"]["selected_algorithms"]["input_options"]["header1"] else None
    X = read_columns(
            "$selected_tasks.selected_algorithms.input_options.infile1",

        "$selected_tasks.selected_algorithms.input_options.col2",
        sep='\t',
        header=header,
        parse_dates=True
)

my_class = getattr(sklearn.ensemble, algorithm)
estimator = my_class(**options)
estimator.fit(X,y)
pickle.dump(estimator,open("$outfile_fit", 'w+'), pickle.HIGHEST_PROTOCOL)

#else:
classifier_object = pickle.load(open("$selected_tasks.infile_model", 'r'))
data = pandas.read_csv("$selected_tasks.infile_data", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False)
prediction = classifier_object.predict(data)
prediction_df = pandas.DataFrame(prediction)
res = pandas.concat([data, prediction_df], axis=1)
res.to_csv(path_or_buf = "$outfile_predict", sep="\t", index=False)
#end if

    <inputs>
        <expand macro="sl_Conditional" model="zip">
            <param name="selected_algorithm" type="select" label="Select an ensemble method:">
                <option value="RandomForestClassifier" selected="true">Random forest classifier</option>
                <option value="AdaBoostClassifier">Ada boost classifier</option>
                <option value="RandomForestRegressor">Random forest regressor</option>
                <option value="AdaBoostRegressor">Ada boost regressor</option>
            </param>
            <when value="RandomForestClassifier">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <expand macro="n_estimators"/>

                    <expand macro="min_samples_leaf"/>
                    <expand macro="min_weight_fraction_leaf"/>
                    <expand macro="max_leaf_nodes"/>
                    <expand macro="bootstrap"/>
                    <expand macro="warm_start" checked="false"/>
                    <expand macro="random_state"/>
                    <expand macro="oob_score"/>
                    <!--class_weight=None-->
                </section>
            </when>

                        <option value="SAMME">SAMME</option>
                    </param>
                    <expand macro="random_state"/>
                </section>
            </when>
            <when value="RandomForestRegressor">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <expand macro="n_estimators"/>
                    <expand macro="max_features"/>
                    <expand macro="max_depth"/>
                    <expand macro="min_samples_split"/>
                    <expand macro="min_samples_leaf"/>
                    <expand macro="min_weight_fraction_leaf"/>
                    <expand macro="max_leaf_nodes"/>
                    <expand macro="bootstrap"/>
                    <expand macro="warm_start" checked="false"/>
                    <expand macro="random_state"/>
                    <expand macro="oob_score"/>
                </section>
            </when>
            <when value="AdaBoostRegressor">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">

                        <option value="exponential">exponential</option>
                    </param>
                    <expand macro="random_state"/>
                </section>
            </when>
        </expand>
    </inputs>

    <expand macro="output"/>

            <param name="infile_model" value="rfc_model01" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="rfc_result01" compare="sim_size" delta="500"/>
        </test>

        <test>
            <param name="infile1" value="regression_train.tabular" ftype="tabular"/>
            <param name="infile2" value="regression_train.tabular" ftype="tabular"/>
            <param name="col1" value="1,2,3,4,5"/>
            <param name="col2" value="6"/>

        <test>
            <param name="infile_model" value="rfr_model01" ftype="zip"/>
            <param name="infile_data" value="regression_test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="rfr_result01" compare="sim_size" delta="500"/>
        </test>
    </tests>
    <help><![CDATA[
***What it does***
The goal of ensemble methods is to combine the predictions of several base estimators built with a given learning algorithm in order to improve generalizability / robustness over a single estimator. This tool offers two sets of ensemble algorithms for classification and regression: random forests and ADA boosting which are based on sklearn.ensemble library from Scikit-learn. Here you can find out about the input, output and methods presented in the tools. For information about ensemble methods and parameters settings please refer to `Scikit-learn ensemble`_.

5:f1761288587e

#if $selected_tasks.selected_task == "train":

algorithm = params["selected_tasks"]["selected_algorithms"]["selected_algorithm"]
options = params["selected_tasks"]["selected_algorithms"]["options"]
if "select_max_features" in options:
    if options["select_max_features"]["max_features"] == "number_input":
        options["select_max_features"]["max_features"] = options["select_max_features"]["num_max_features"]
        options["select_max_features"].pop("num_max_features")
    options["max_features"] = options["select_max_features"]["max_features"]
    options.pop("select_max_features")
if "presort" in options:
    if options["presort"] == "true":
        options["presort"] = True
    if options["presort"] == "false":
        options["presort"] = False
if "min_samples_leaf" in options and options["min_samples_leaf"] == 1.0:
    options["min_samples_leaf"] = 1
if "min_samples_split" in options and options["min_samples_split"] > 1.0:
    options["min_samples_split"] = int(options["min_samples_split"])
input_type = params["selected_tasks"]["selected_algorithms"]["input_options"]["selected_input"]
if input_type=="tabular":
    header = 'infer' if params["selected_tasks"]["selected_algorithms"]["input_options"]["header1"] else None
    X = read_columns(
            "$selected_tasks.selected_algorithms.input_options.infile1",

        "$selected_tasks.selected_algorithms.input_options.col2",
        sep='\t',
        header=header,
        parse_dates=True
)
y=y.ravel()

my_class = getattr(sklearn.ensemble, algorithm)
estimator = my_class(**options)
estimator.fit(X,y)
pickle.dump(estimator,open("$outfile_fit", 'w+'), pickle.HIGHEST_PROTOCOL)

#else:
classifier_object = pickle.load(open("$selected_tasks.infile_model", 'r'))
header = 'infer' if params["selected_tasks"]["header"] else None
data = pandas.read_csv("$selected_tasks.infile_data", sep='\t', header=header, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False)
prediction = classifier_object.predict(data)
prediction_df = pandas.DataFrame(prediction)
res = pandas.concat([data, prediction_df], axis=1)
res.to_csv(path_or_buf = "$outfile_predict", sep="\t", index=False)
#end if

    <inputs>
        <expand macro="sl_Conditional" model="zip">
            <param name="selected_algorithm" type="select" label="Select an ensemble method:">
                <option value="RandomForestClassifier" selected="true">Random forest classifier</option>
                <option value="AdaBoostClassifier">Ada boost classifier</option>
                <option value="GradientBoostingClassifier">Gradient Boosting Classifier</option>
                <option value="RandomForestRegressor">Random forest regressor</option>
                <option value="AdaBoostRegressor">Ada boost regressor</option>
                <option value="GradientBoostingRegressor">Gradient Boosting Regressor</option>
            </param>
            <when value="RandomForestClassifier">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <expand macro="n_estimators"/>

                    <expand macro="min_samples_leaf"/>
                    <expand macro="min_weight_fraction_leaf"/>
                    <expand macro="max_leaf_nodes"/>
                    <expand macro="bootstrap"/>
                    <expand macro="warm_start" checked="false"/>
                    <expand macro="n_jobs"/>
                    <expand macro="random_state"/>
                    <expand macro="oob_score"/>
                    <!--class_weight=None-->
                </section>
            </when>

                        <option value="SAMME">SAMME</option>
                    </param>
                    <expand macro="random_state"/>
                </section>
            </when>
            <when value="GradientBoostingClassifier">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <!--base_estimator=None-->
                    <param argument="loss" type="select" label="Loss function">
                        <option value="deviance" selected="true">deviance - logistic regression with probabilistic outputs</option>
                        <option value="exponential">exponential - gradient boosting recovers the AdaBoost algorithm</option>
                    </param>
                    <expand macro="learning_rate" default_value='0.1'/>
                    <expand macro="n_estimators" default_value="100" help="The number of boosting stages to perform"/>
                    <expand macro="max_depth" default_value="3" help="maximum depth of the individual regression estimators"/>
                    <expand macro="criterion2">
                        <option value="friedman_mse" selected="true">friedman_mse - mean squared error with improvement score by Friedman</option>
                    </expand>
                    <expand macro="min_samples_split" type="float"/>
                    <expand macro="min_samples_leaf" type="float" label="The minimum number of samples required to be at a leaf node"/>
                    <expand macro="min_weight_fraction_leaf"/>
                    <expand macro="subsample"/>
                    <expand macro="max_features"/>
                    <expand macro="max_leaf_nodes"/>
                    <expand macro="min_impurity_decrease"/>
                    <expand macro="verbose"/>
                    <expand macro="warm_start" checked="false"/>
                    <expand macro="random_state"/>
                    <expand macro="presort"/>
                </section>
            </when>
            <when value="RandomForestRegressor">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <expand macro="n_estimators"/>
                    <expand macro="criterion2"/>
                    <expand macro="max_features"/>
                    <expand macro="max_depth"/>
                    <expand macro="min_samples_split"/>
                    <expand macro="min_samples_leaf"/>
                    <expand macro="min_weight_fraction_leaf"/>
                    <expand macro="max_leaf_nodes"/>
                    <expand macro="min_impurity_decrease"/>
                    <expand macro="bootstrap"/>
                    <expand macro="oob_score"/>
                    <expand macro="n_jobs"/>
                    <expand macro="random_state"/>
                    <expand macro="verbose"/>
                    <expand macro="warm_start" checked="false"/>
                </section>
            </when>
            <when value="AdaBoostRegressor">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">

                        <option value="exponential">exponential</option>
                    </param>
                    <expand macro="random_state"/>
                </section>
            </when>
            <when value="GradientBoostingRegressor">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <param argument="loss" type="select" label="Loss function">
                        <option value="ls" selected="true">ls - least squares regression</option>
                        <option value="lad">lad - least absolute deviation</option>
                        <option value="huber">huber - combination of least squares regression and least absolute deviation</option>
                        <option value="quantile">quantile - use alpha to specify the quantile</option>
                    </param>
                    <expand macro="learning_rate" default_value="0.1"/>
                    <expand macro="n_estimators" default_value="100" help="The number of boosting stages to perform"/>
                    <expand macro="max_depth" default_value="3" help="maximum depth of the individual regression estimators"/>
                    <expand macro="criterion2">
                        <option value="friedman_mse" selected="true">friedman_mse - mean squared error with improvement score by Friedman</option>
                    </expand>
                    <expand macro="min_samples_split" type="float"/>
                    <expand macro="min_samples_leaf" type="float" label="The minimum number of samples required to be at a leaf node"/>
                    <expand macro="min_weight_fraction_leaf"/>
                    <expand macro="subsample"/>
                    <expand macro="max_features"/>
                    <expand macro="max_leaf_nodes"/>
                    <expand macro="min_impurity_decrease"/>
                    <param argument="alpha" type="float" value="0.9" label="alpha" help="The alpha-quantile of the huber loss function and the quantile loss function" />
                    <!--base_estimator=None-->
                    <expand macro="verbose"/>
                    <expand macro="warm_start" checked="false"/>
                    <expand macro="random_state"/>
                    <expand macro="presort"/>
                </section>
            </when>
        </expand>
    </inputs>

    <expand macro="output"/>

            <param name="infile_model" value="rfc_model01" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="rfc_result01" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile1" value="regression_train.tabular" ftype="tabular"/>
            <param name="infile2" value="regression_train.tabular" ftype="tabular"/>
            <param name="col1" value="1,2,3,4,5"/>
            <param name="col2" value="6"/>

        <test>
            <param name="infile_model" value="rfr_model01" ftype="zip"/>
            <param name="infile_data" value="regression_test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="rfr_result01" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
            <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="col1" value="1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17"/>
            <param name="header2" value="True"/>
            <param name="col2" value="1"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="GradientBoostingRegressor"/>
            <param name="max_features" value="number_input"/>
            <param name="num_max_features" value=""/>
            <param name="random_state" value="42"/>
            <output name="outfile_fit" file="gbr_model01" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile_model" value="gbr_model01" ftype="zip"/>
            <param name="infile_data" value="regression_test_X.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <param name="header" value="True"/>
            <output name="outfile_predict" file="gbr_prediction_result01.tabular" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular"/>
            <param name="infile2" value="train.tabular" ftype="tabular"/>
            <param name="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="GradientBoostingClassifier"/>
            <output name="outfile_fit" file="gbc_model01" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile_model" value="gbc_model01" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="gbc_result01" compare="sim_size" delta="500"/>
        </test>
    </tests>
    <help><![CDATA[
***What it does***
The goal of ensemble methods is to combine the predictions of several base estimators built with a given learning algorithm in order to improve generalizability / robustness over a single estimator. This tool offers two sets of ensemble algorithms for classification and regression: random forests and ADA boosting which are based on sklearn.ensemble library from Scikit-learn. Here you can find out about the input, output and methods presented in the tools. For information about ensemble methods and parameters settings please refer to `Scikit-learn ensemble`_.