comparison search_model_validation.xml @ 5:0987bc3904a0 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 2a058459e6daf0486871f93845f00fdb4a4eaca1

4:2e6540c11251

import pandas
import skrebate
from sklearn import model_selection
from sklearn.exceptions import FitFailedWarning

execfile("$__tool_directory__/sk_whitelist.py")
execfile("$__tool_directory__/utils.py", globals())

warnings.simplefilter('ignore')

input_json_path = sys.argv[1]
with open(input_json_path, "r") as param_handler:

    options['refit'] = 'primary'
if 'pre_dispatch' in options and options['pre_dispatch'] == '':
    options['pre_dispatch'] = None

with open(infile_pipeline, 'rb') as pipeline_handler:
    pipeline = SafePickler.load(pipeline_handler)

search_params = get_search_params(params_builder)
searcher = optimizers(pipeline, search_params, **options)

warnings.simplefilter('always', FitFailedWarning)
with warnings.catch_warnings(record=True) as w:
    try:
        searcher.fit(X, y)
    except ValueError:
        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:

            <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_text_matching expression="[^/d]+0.7938837807353147[^/d]+{u'estimator__C': 1, u'preprocessing_2__k': 9}[^/d]+1" />
                    <has_text text="0.0"/>
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="selected_search_scheme" value="RandomizedSearchCV"/>
            <param name="infile_pipeline" value="pipeline01" ftype="zip"/>
            <conditional name="search_param_selector">

            <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_estimator" file="searchCV01" compare="sim_size" delta="1"/>
        </test>
        <test>
            <param name="selected_search_scheme" value="GridSearchCV"/>
            <param name="infile_pipeline" value="pipeline03" ftype="zip"/>
            <conditional name="search_param_selector">

            <param name="header2" value="true" />
            <param name="selected_column_selector_option2" value="all_columns"/>
            <output name="outfile_result" >
                <assert_contents>
                    <has_n_columns n="13" />
                    <has_text text="0.05366527890058046"/>
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="selected_search_scheme" value="GridSearchCV"/>

5:0987bc3904a0

import pandas
import skrebate
from sklearn import model_selection
from sklearn.exceptions import FitFailedWarning

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

warnings.simplefilter('ignore')

input_json_path = sys.argv[1]
with open(input_json_path, "r") as param_handler:

    options['refit'] = 'primary'
if 'pre_dispatch' in options and options['pre_dispatch'] == '':
    options['pre_dispatch'] = None

with open(infile_pipeline, 'rb') as pipeline_handler:
    pipeline = load_model(pipeline_handler)

search_params = get_search_params(params_builder)
searcher = optimizers(pipeline, search_params, **options)

if options['error_score'] == 'raise':
    searcher.fit(X, y)
else:
    warnings.simplefilter('always', FitFailedWarning)
    with warnings.catch_warnings(record=True) as w:
        try:
            searcher.fit(X, y)
        except ValueError:
            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:

            <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="13"/>
                    <has_text text="0.7938837807353147"/>
                    <has_text text="{'estimator__C': 1, 'preprocessing_2__k': 9}"/>
                </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: [1, 10, 100, 1000]"/>
                <param name="selected_param_type" value="final_estimator_p"/>
            </conditional>
            <conditional name="search_param_selector">
                <param name="search_p" value="k: [-1, 3, 5, 7, 9]"/>
                <param name="selected_param_type" value="prep_2_p"/>
            </conditional>
            <param name="error_score" value="true"/>
            <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>
            <param name="selected_search_scheme" value="RandomizedSearchCV"/>
            <param name="infile_pipeline" value="pipeline01" ftype="zip"/>
            <conditional name="search_param_selector">

            <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_estimator" file="searchCV02" compare="sim_size" delta="1"/>
        </test>
        <test>
            <param name="selected_search_scheme" value="GridSearchCV"/>
            <param name="infile_pipeline" value="pipeline03" ftype="zip"/>
            <conditional name="search_param_selector">

            <param name="header2" value="true" />
            <param name="selected_column_selector_option2" value="all_columns"/>
            <output name="outfile_result" >
                <assert_contents>
                    <has_n_columns n="13" />
                    <has_text text="0.09003449195911103"/>
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="selected_search_scheme" value="GridSearchCV"/>