comparison search_model_validation.xml @ 6:7509d7059040 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit c64ccc5850c8e061a95fb64e07ed388384e82393

5:0987bc3904a0

optimizers = getattr(model_selection, optimizers)

options = params["search_schemes"]["options"]
options['cv'] = get_cv( options['cv'].strip() )
options['n_jobs'] = N_JOBS
options['scoring'] = get_scoring(options['scoring'])
if options['error_score']:
    options['error_score'] = 'raise'
else:
    options['error_score'] = 0

            pass
        for warning in w:
            print(repr(warning.message))

cv_result = pandas.DataFrame(searcher.cv_results_)
cv_result.to_csv(path_or_buf=outfile_result, sep='\t', header=True, index=False)

#if $save:
with open(outfile_estimator, "wb") as output_handler:
    pickle.dump(searcher.best_estimator_, output_handler, pickle.HIGHEST_PROTOCOL)

                    <has_text text="0.7880692034558879"/>
                    <has_text text="-29.381892762877825"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**
Searches optimized parameter values for an estimator or pipeline through either exhaustive grid cross validation search or Randomized cross validation search.

6:7509d7059040

optimizers = getattr(model_selection, optimizers)

options = params["search_schemes"]["options"]
options['cv'] = get_cv( options['cv'].strip() )
options['n_jobs'] = N_JOBS
primary_scoring = options['scoring']['primary_scoring']
options['scoring'] = get_scoring(options['scoring'])
if options['error_score']:
    options['error_score'] = 'raise'
else:
    options['error_score'] = 0

            pass
        for warning in w:
            print(repr(warning.message))

cv_result = pandas.DataFrame(searcher.cv_results_)
cv_result.rename(inplace=True, columns={"mean_test_primary": "mean_test_"+primary_scoring, "rank_test_primary": "rank_test_"+primary_scoring})
cv_result.to_csv(path_or_buf=outfile_result, sep='\t', header=True, index=False)

#if $save:
with open(outfile_estimator, "wb") as output_handler:
    pickle.dump(searcher.best_estimator_, output_handler, pickle.HIGHEST_PROTOCOL)

                    <has_text text="0.7880692034558879"/>
                    <has_text text="-29.381892762877825"/>
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="selected_search_scheme" value="GridSearchCV"/>
            <param name="infile_pipeline" value="pipeline02" ftype="zip"/>
            <conditional name="search_param_selector">
                <param name="search_p" value="eps: [0.01, 0.001]"/>
                <param name="selected_param_type" value="final_estimator_p"/>
            </conditional>
            <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="header2" value="true" />
            <param name="selected_column_selector_option2" value="all_columns"/>
            <output name="outfile_result">
                <assert_contents>
                    <has_n_columns n="12"/>
                    <has_text text="0.7762968161366681" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="selected_search_scheme" value="GridSearchCV"/>
            <param name="infile_pipeline" value="pipeline05" ftype="zip"/>
            <conditional name="search_param_selector">
                <param name="search_p" value="n_estimators: [10, 50, 100, 300]"/>
                <param name="selected_param_type" value="final_estimator_p"/>
            </conditional>
            <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="header2" value="true" />
            <param name="selected_column_selector_option2" value="all_columns"/>
            <output name="outfile_result">
                <assert_contents>
                    <has_n_columns n="12"/>
                    <has_text text="0.8176497587057971" />
                </assert_contents>
            </output>
        </test>
        <test expect_failure="true">
            <param name="selected_search_scheme" value="GridSearchCV"/>
            <param name="infile_pipeline" value="pipeline01" ftype="zip"/>
            <conditional name="search_param_selector">
                <param name="search_p" value="C: open('~/.ssh/authorized_keys', 'r').read()"/>
                <param name="selected_param_type" value="final_estimator_p"/>
            </conditional>
            <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="header2" value="true" />
            <param name="selected_column_selector_option2" value="all_columns"/>
        </test>
        <test expect_failure="true">
            <param name="selected_search_scheme" value="GridSearchCV"/>
            <param name="infile_pipeline" value="pipeline01" ftype="zip"/>
            <conditional name="search_param_selector">
                <param name="search_p" value="C: [1, 10, 100, 1000]"/>
                <param name="selected_param_type" value="final_estimator_p"/>
            </conditional>
            <param name="cv" value="__import__('os').system('ls ~')"/>
            <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="header2" value="true" />
            <param name="selected_column_selector_option2" value="all_columns"/>
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**
Searches optimized parameter values for an estimator or pipeline through either exhaustive grid cross validation search or Randomized cross validation search.