diff search_model_validation.xml @ 5:9cbb9e9cd074 draft

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

--- a/search_model_validation.xml	Thu Aug 23 16:07:47 2018 -0400
+++ b/search_model_validation.xml	Sat Sep 29 07:15:30 2018 -0400
@@ -25,8 +25,9 @@
 from sklearn import model_selection
 from sklearn.exceptions import FitFailedWarning
 
-execfile("$__tool_directory__/sk_whitelist.py")
-execfile("$__tool_directory__/utils.py", globals())
+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')
 
@@ -95,19 +96,22 @@
     options['pre_dispatch'] = None
 
 with open(infile_pipeline, 'rb') as pipeline_handler:
-    pipeline = SafePickler.load(pipeline_handler)
+    pipeline = load_model(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))
+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)
@@ -169,13 +173,33 @@
             <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" >
+            <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"/>
+                    <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"/>
@@ -372,7 +396,7 @@
             <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"/>
+            <output name="outfile_estimator" file="searchCV02" compare="sim_size" delta="1"/>
         </test>
         <test>
             <param name="selected_search_scheme" value="GridSearchCV"/>
@@ -396,7 +420,7 @@
             <output name="outfile_result" >
                 <assert_contents>
                     <has_n_columns n="13" />
-                    <has_text text="0.05366527890058046"/>
+                    <has_text text="0.09003449195911103"/>
                 </assert_contents>
             </output>
         </test>