--- a/feature_selection.xml	Sat Apr 28 18:08:48 2018 -0400
+++ b/feature_selection.xml	Tue May 22 19:31:59 2018 -0400
@@ -1,4 +1,4 @@
-<tool id="sklearn_feature_selection" name="Feature Selection" version="@VERSION@">
+<tool id="sklearn_feature_selection" name="Feature Selection" version="@VERSION@.1">
     <description>module, including univariate filter selection methods and recursive feature elimination algorithm</description>
     <macros>
         <import>main_macros.xml</import>
@@ -28,12 +28,16 @@
 input_json_path = sys.argv[1]
 params = json.load(open(input_json_path, "r"))
 
+## Read features
+features_has_header = params["input_options"]["header1"]
 input_type = params["input_options"]["selected_input"]
 if input_type=="tabular":
+    header = 'infer' if features_has_header else None
     header = 'infer' if params["input_options"]["header1"] else None
-    X = read_columns(
+    X, input_df = read_columns(
             "$input_options.infile1",
             "$input_options.col1",
+            return_df = True,
             sep='\t',
             header=header,
             parse_dates=True
@@ -41,6 +45,7 @@
 else:
     X = mmread(open("$input_options.infile1", 'r'))
 
+## Read labels
 header = 'infer' if params["input_options"]["header2"] else None
 y = read_columns(
         "$input_options.infile2",
@@ -51,54 +56,55 @@
 )
 y=y.ravel()
 
+## Create feature selector
 selector = params["feature_selection_algorithms"]["selected_algorithm"]
 selector = getattr(sklearn.feature_selection, selector)
 options = params["feature_selection_algorithms"]["options"]
 
-#if $feature_selection_algorithms.selected_algorithm == 'SelectFromModel':
-if not options['threshold'] or options['threshold'] == 'None':
-    options['threshold'] = None
-#if $feature_selection_algorithms.extra_estimator.has_estimator == 'no_load':
-fitted_estimator = pickle.load(open("$feature_selection_algorithms.extra_estimator.fitted_estimator", 'r'))
-new_selector = selector(fitted_estimator, prefit=True, **options)
-#else:    
-estimator=params["feature_selection_algorithms"]["estimator"]
-if params["feature_selection_algorithms"]["extra_estimator"]["has_estimator"]=='no':
-    estimator=params["feature_selection_algorithms"]["extra_estimator"]["new_estimator"]
-estimator=eval(estimator.replace('__dq__', '"').replace("__sq__","'"))
-new_selector = selector(estimator, **options)
-new_selector.fit(X, y)
-#end if
+if params['feature_selection_algorithms']['selected_algorithm'] == 'SelectFromModel':
+    if not options['threshold'] or options['threshold'] == 'None':
+        options['threshold'] = None
+        if 'extra_estimator' in params['feature_selection_algorithms'] and params['feature_selection_algorithms']['extra_estimator']['has_estimator'] == 'no_load':
+            fitted_estimator = pickle.load(open("params['feature_selection_algorithms']['extra_estimator']['fitted_estimator']", 'r'))
+            new_selector = selector(fitted_estimator, prefit=True, **options)
+        else:
+            estimator=params["feature_selection_algorithms"]["estimator"]
+            if params["feature_selection_algorithms"]["extra_estimator"]["has_estimator"]=='no':
+                estimator=params["feature_selection_algorithms"]["extra_estimator"]["new_estimator"]
+            estimator=eval(estimator.replace('__dq__', '"').replace("__sq__","'"))
+            new_selector = selector(estimator, **options)
+            new_selector.fit(X, y)
 
-#elif $feature_selection_algorithms.selected_algorithm in ['RFE', 'RFECV']:
-if 'scoring' in options and (not options['scoring'] or options['scoring'] == 'None'):
-    options['scoring'] = None
-estimator=params["feature_selection_algorithms"]["estimator"]
-if params["feature_selection_algorithms"]["extra_estimator"]["has_estimator"]=='no':
-    estimator=params["feature_selection_algorithms"]["extra_estimator"]["new_estimator"]
-estimator=eval(estimator.replace('__dq__', '"').replace("__sq__","'"))
-new_selector = selector(estimator, **options)
-new_selector.fit(X, y)
+elif params['feature_selection_algorithms']['selected_algorithm'] in ['RFE', 'RFECV']:
+    if 'scoring' in options and (not options['scoring'] or options['scoring'] == 'None'):
+        options['scoring'] = None
+    estimator=params["feature_selection_algorithms"]["estimator"]
+    if params["feature_selection_algorithms"]["extra_estimator"]["has_estimator"]=='no':
+        estimator=params["feature_selection_algorithms"]["extra_estimator"]["new_estimator"]
+    estimator=eval(estimator.replace('__dq__', '"').replace("__sq__","'"))
+    new_selector = selector(estimator, **options)
+    new_selector.fit(X, y)
 
-#elif $feature_selection_algorithms.selected_algorithm == "VarianceThreshold":
-new_selector = selector(**options)
-new_selector.fit(X, y)
+elif params['feature_selection_algorithms']['selected_algorithm'] == "VarianceThreshold":
+    new_selector = selector(**options)
+    new_selector.fit(X, y)
 
-#else:
-score_func = params["feature_selection_algorithms"]["score_func"]
-score_func = getattr(sklearn.feature_selection, score_func)
-new_selector = selector(score_func, **options)
-new_selector.fit(X, y)
-#end if
+else:
+    score_func = params["feature_selection_algorithms"]["score_func"]
+    score_func = getattr(sklearn.feature_selection, score_func)
+    new_selector = selector(score_func, **options)
+    new_selector.fit(X, y)
 
-#if $select_methods.selected_method == "fit_transform":
-res = new_selector.transform(X)
+## Transform to select features
+selected_names = None
+if "$select_methods.selected_method" == "fit_transform":
+    res = new_selector.transform(X)
+    if features_has_header:
+        selected_names = input_df.columns[new_selector.get_support(indices=True)]
+else:
+    res = new_selector.get_support(params["select_methods"]["indices"])
 
-#else:
-res = new_selector.get_support(params["select_methods"]["indices"])
-#end if
-
-res = pandas.DataFrame(res)
+res = pandas.DataFrame(res, columns = selected_names)
 res.to_csv(path_or_buf="$outfile", sep='\t', index=False)
 
 
@@ -106,131 +112,12 @@
         </configfile>
     </configfiles>
     <inputs>
-        <conditional name="feature_selection_algorithms">
-            <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
-                <option value="SelectFromModel" selected="true">SelectFromModel - Meta-transformer for selecting features based on importance weights</option>
-                <option value="GenericUnivariateSelect" selected="true">GenericUnivariateSelect - Univariate feature selector with configurable strategy</option>
-                <option value="SelectPercentile">SelectPercentile - Select features according to a percentile of the highest scores</option>
-                <option value="SelectKBest">SelectKBest - Select features according to the k highest scores</option>
-                <option value="SelectFpr">SelectFpr - Filter: Select the p-values below alpha based on a FPR test</option>
-                <option value="SelectFdr">SelectFdr - Filter: Select the p-values for an estimated false discovery rate</option>
-                <option value="SelectFwe">SelectFwe - Filter: Select the p-values corresponding to Family-wise error rate</option>
-                <option value="RFE">RFE - Feature ranking with recursive feature elimination</option>
-                <option value="RFECV">RFECV - Feature ranking with recursive feature elimination and cross-validated selection of the best number of features</option>
-                <option value="VarianceThreshold">VarianceThreshold - Feature selector that removes all low-variance features</option>
-                <!--option value="chi2">Compute chi-squared stats between each non-negative feature and class</option-->
-                <!--option value="f_classif">Compute the ANOVA F-value for the provided sample</option-->
-                <!--option value="f_regression">Univariate linear regression tests</option-->
-                <!--option value="mutual_info_classif">Estimate mutual information for a discrete target variable</option-->
-                <!--option value="mutual_info_regression">Estimate mutual information for a continuous target variable</option-->
-            </param>
-            <when value="SelectFromModel">
-                <expand macro="feature_selection_estimator" />
-                <conditional name="extra_estimator">
-                    <expand macro="feature_selection_extra_estimator" >
-                        <option value="no_load">No, I will load a prefitted estimator</option>
-                    </expand>
-                    <expand macro="feature_selection_estimator_choices" >
-                        <when value="no_load">
-                            <param name="fitted_estimator" type="data" format='zip' label="Load a prefitted estimator" />
-                        </when>
-                    </expand>
-                </conditional>
-                <section name="options" title="Other Options" expanded="True">
-                    <param argument="threshold" type="text" value="" optional="true" label="threshold" help="The threshold value to use for feature selection. e.g. 'mean', 'median', '1.25*mean'." />
-                    <param argument="norm_order" type="integer" value="1" label="norm_order" help="Order of the norm used to filter the vectors of coefficients below threshold in the case where the coef_ attribute of the estimator is of dimension 2. " />
-                </section>
-            </when>
-            <when value="GenericUnivariateSelect">
-                <expand macro="feature_selection_score_function" />
-                <section name="options" title="Other Options" expanded="True">
-                    <param argument="mode" type="select" label="Feature selection mode">
-                        <option value="percentile">percentile</option>
-                        <option value="k_best">k_best</option>
-                        <option value="fpr">fpr</option>
-                        <option value="fdr">fdr</option>
-                        <option value="fwe">fwe</option>
-                    </param>
-                    <param argument="param" type="float" value="" optional="true" label="Parameter of the corresponding mode" help="float or int depending on the feature selection mode" />
-                </section>
-            </when>
-            <when value="SelectPercentile">
-                <expand macro="feature_selection_score_function" />
-                <section name="options" title="Other Options" expanded="True">
-                    <param argument="percentile" type="integer" value="10" optional="True" label="Percent of features to keep" />
-                </section>
-            </when>
-            <when value="SelectKBest">
-                <expand macro="feature_selection_score_function" />
-                <section name="options" title="Other Options" expanded="True">
-                    <param argument="k" type="integer" value="10" optional="True" label="Number of top features to select" help="No 'all' option is supported." />
-                </section>
-            </when>
-            <when value="SelectFpr">
-                <expand macro="feature_selection_score_function" />
-                <section name="options" title="Other Options" expanded="True">
-                    <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest p-value for features to be kept."/>
-                </section>
-            </when>
-            <when value="SelectFdr">
-                <expand macro="feature_selection_score_function" />
-                <section name="options" title="Other Options" expanded="True">
-                    <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep."/>
-                </section>
-            </when>
-            <when value="SelectFwe">
-                <expand macro="feature_selection_score_function" />
-                <section name="options" title="Other Options" expanded="True">
-                    <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep."/>
-                </section>
-            </when>
-            <when value="RFE">
-                <expand macro="feature_selection_estimator" />
-                <conditional name="extra_estimator">
-                    <expand macro="feature_selection_extra_estimator" />
-                    <expand macro="feature_selection_estimator_choices" />
-                </conditional>
-                <section name="options" title="Other Options" expanded="True">
-                    <param argument="n_features_to_select" type="integer" value="" optional="true" label="n_features_to_select" help="The number of features to select. If None, half of the features are selected." />
-                    <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
-                    <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
-                </section>
-            </when>
-            <when value="RFECV">
-                <expand macro="feature_selection_estimator" />
-                <conditional name="extra_estimator">
-                    <expand macro="feature_selection_extra_estimator" />
-                    <expand macro="feature_selection_estimator_choices" />
-                </conditional>
-                <section name="options" title="Other Options" expanded="True">
-                    <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
-                    <param argument="cv" type="integer" value="" optional="true" label="cv" help="Determines the cross-validation splitting strategy" />
-                    <param argument="scoring" type="text" value="" optional="true" label="scoring" help="A string (see model evaluation documentation) or a scorer callable object / function with signature scorer(estimator, X, y)."/>
-                    <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
-                    <param argument="n_jobs" type="integer" value="1" label="n_jobs" help="Number of cores to run in parallel while fitting across folds. Defaults to 1 core."/>
-                </section>
-            </when>
-            <when value="VarianceThreshold">
-                <section name="options" title="Options" expanded="True">
-                    <param argument="threshold" type="float" value="" optional="True" label="Threshold" help="Features with a training-set variance lower than this threshold will be removed."/>
-                </section>
-            </when>
-            <!--when value="chi2">
-            </when>
-            <when value="f_classif">
-            </when>
-            <when value="f_regression">
-            </when>
-            <when value="mutual_info_classif">
-            </when>
-            <when value="mutual_info_regression">
-            </when-->
-        </conditional>
+        <expand macro="feature_selection_all" />
         <expand macro="feature_selection_methods" />
         <expand macro="sl_mixed_input"/>
     </inputs>
     <outputs>
-        <data format="txt" name="outfile"/>
+        <data format="tabular" name="outfile"/>
     </outputs>
     <tests>
         <test>