comparison model_prediction.xml @ 15:3bb1b688b0e4 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 9981e25b00de29ed881b2229a173a8c812ded9bb

14:29e4122c90de

<tool id="model_prediction" name="Model Prediction" version="@VERSION@" profile="20.05">
    <description>predicts on new data using a preffited model</description>
    <macros>
        <import>main_macros.xml</import>
        <import>keras_macros.xml</import>
    </macros>

        export HDF5_USE_FILE_LOCKING='FALSE';
        python '$__tool_directory__/model_prediction.py'
            --inputs '$inputs'
            --infile_estimator '$infile_estimator'
            --outfile_predict '$outfile_predict'
            --infile_weights '$infile_weights'
            #if $input_options.selected_input == 'seq_fasta'
            --fasta_path '$input_options.fasta_path'
            #elif $input_options.selected_input == 'variant_effect'
            --ref_seq '$input_options.ref_genome_file'
            --vcf_path '$input_options.vcf_file'

    </command>
    <configfiles>
        <inputs name="inputs" />
    </configfiles>
    <inputs>
        <param name="infile_estimator" type="data" format="zip" label="Choose the dataset containing pipeline/estimator object" />
        <param name="infile_weights" type="data" format="h5" optional="true" label="Choose the dataset containing weights for the estimator above" help="Optional. For deep learning only." />
        <param argument="method" type="select" label="Select invocation method">
            <option value="predict" selected="true">predict</option>
            <option value="predict_proba">predict_proba</option>
        </param>
        <conditional name="input_options">

    <outputs>
        <data format="tabular" name="outfile_predict" />
    </outputs>
    <tests>
        <test>
            <param name="infile_estimator" value="best_estimator_.zip" ftype="zip" />
            <param name="method" value="predict" />
            <param name="infile1" value="regression_X.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" />
            <output name="outfile_predict" file="model_pred01.tabular" />
        </test>
        <test>
            <param name="infile_estimator" value="keras_model04" ftype="zip" />
            <param name="infile_weights" value="train_test_eval_weights02.h5" ftype="h5" />
            <param name="method" value="predict" />
            <param name="infile1" value="regression_X.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" />
            <output name="outfile_predict">
                <assert_contents>
                    <has_n_columns n="1" />
                    <has_text text="70.2" />
                    <has_text text="61.2" />
                    <has_text text="74.2" />
                    <has_text text="65.9" />
                    <has_text text="52.9" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**

Given a fitted estimator and new data sets, this tool outpus the prediction results on the data sets via invoking the estimator's `predict` or `predict_proba` method.

For estimator, this tool supports fitted sklearn estimators (pickled) and trained deep learning models (model skeleton + weights). It predicts on three different dataset inputs,

- tabular

- sparse

15:3bb1b688b0e4

<tool id="model_prediction" name="Model Prediction" version="@VERSION@" profile="@PROFILE@">
    <description>predicts on new data using a preffited model</description>
    <macros>
        <import>main_macros.xml</import>
        <import>keras_macros.xml</import>
    </macros>

        export HDF5_USE_FILE_LOCKING='FALSE';
        python '$__tool_directory__/model_prediction.py'
            --inputs '$inputs'
            --infile_estimator '$infile_estimator'
            --outfile_predict '$outfile_predict'
            #if $input_options.selected_input == 'seq_fasta'
            --fasta_path '$input_options.fasta_path'
            #elif $input_options.selected_input == 'variant_effect'
            --ref_seq '$input_options.ref_genome_file'
            --vcf_path '$input_options.vcf_file'

    </command>
    <configfiles>
        <inputs name="inputs" />
    </configfiles>
    <inputs>
        <param name="infile_estimator" type="data" format="h5mlm" label="Choose the dataset containing pipeline/estimator object" />
        <param argument="method" type="select" label="Select invocation method">
            <option value="predict" selected="true">predict</option>
            <option value="predict_proba">predict_proba</option>
        </param>
        <conditional name="input_options">

    <outputs>
        <data format="tabular" name="outfile_predict" />
    </outputs>
    <tests>
        <test>
            <param name="infile_estimator" value="best_estimator_.h5mlm" ftype="h5mlm" />
            <param name="method" value="predict" />
            <param name="infile1" value="regression_X.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" />
            <output name="outfile_predict" file="model_pred01.tabular" />
        </test>
        <test>
            <param name="infile_estimator" value="train_test_eval_model01" ftype="h5mlm" />
            <param name="method" value="predict" />
            <param name="infile1" value="regression_X.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" />
            <output name="outfile_predict" >
                <assert_contents>
                    <has_n_columns n="1" />
                    <has_text text="71.0" />
                    <has_text text="61.3" />
                    <has_text text="83.7" />
                    <has_text text="69.2" />
                    <has_text text="51.8" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**

Given a fitted estimator and new data sets, this tool outpus the prediction results on the data sets via invoking the estimator's `predict` or `predict_proba` method.

For estimator, this tool supports fitted sklearn estimators and trained deep learning models. It predicts on three different dataset inputs,

- tabular

- sparse