Mercurial > repos > bgruening > sklearn_data_preprocess

diff pre_process.xml @ 35:0e5fcf7ddc75 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit e2a5eade6d0e5ddf3a47630381a0ad90d80e8a04"
author bgruening
date Tue, 13 Apr 2021 18:53:33 +0000
parents eb79bde99328
children a16f33c6ca64
line wrap: on
line diff
--- a/pre_process.xml	Fri Oct 02 08:47:25 2020 +0000
+++ b/pre_process.xml	Tue Apr 13 18:53:33 2021 +0000
@@ -1,10 +1,10 @@
-<tool id="sklearn_data_preprocess" name="Preprocess" version="@VERSION@">
+<tool id="sklearn_data_preprocess" name="Preprocess" version="@VERSION@" profile="20.05">
     <description>raw feature vectors into standardized datasets</description>
     <macros>
         <import>main_macros.xml</import>
     </macros>
-    <expand macro="python_requirements"/>
-    <expand macro="macro_stdio"/>
+    <expand macro="python_requirements" />
+    <expand macro="macro_stdio" />
     <version_command>echo "@VERSION@"</version_command>
     <command>
         <![CDATA[
@@ -97,7 +97,7 @@
                 <param name="infile" type="data" format="tabular" label="Select a tabular file you want to train your preprocessor on its data:" />
                 <param name="header1" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" />
                 <conditional name="column_selector_options_1">
-                    <expand macro="samples_column_selector_options" multiple="true" column_option="selected_column_selector_option" col_name="col1" infile="infile"/>
+                    <expand macro="samples_column_selector_options" multiple="true" column_option="selected_column_selector_option" col_name="col1" infile="infile" />
                 </conditional>
                 <conditional name="pre_processors">
                     <expand macro="sparse_preprocessors_ext" />
@@ -105,102 +105,100 @@
                 </conditional>
             </when>
             <when value="sparse">
-                <param name="infile" type="data" format="txt" label="Select a sparse representation you want to train your preprocessor on its data:"/>
+                <param name="infile" type="data" format="txt" label="Select a sparse representation you want to train your preprocessor on its data:" />
                 <conditional name="pre_processors">
-                    <expand macro="sparse_preprocessors"/>
-                    <expand macro="sparse_preprocessor_options"/>
+                    <expand macro="sparse_preprocessors" />
+                    <expand macro="sparse_preprocessor_options" />
                 </conditional>
             </when>
         </conditional>
-        <param name="save" type="boolean" truevalue="booltrue" falsevalue="boolflase" checked="false"
-            label="Save the preprocessor"
-            help="Saves the preprocessor after fitting to the data. The preprocessor can then be passed to other tools and used in later operations."/>
+        <param name="save" type="boolean" truevalue="booltrue" falsevalue="boolflase" checked="false" label="Save the preprocessor" help="Saves the preprocessor after fitting to the data. The preprocessor can then be passed to other tools and used in later operations." />
     </inputs>
     <outputs>
-        <data format="tabular" name="outfile_transform" from_work_dir="./output"/>
+        <data format="tabular" name="outfile_transform" from_work_dir="./output" />
         <data format="zip" name="outfile_fit">
             <filter>save</filter>
         </data>
     </outputs>
     <tests>
         <test>
-            <param name="infile" value="train.tabular" ftype="tabular"/>
-            <param name="selected_column_selector_option" value="all_columns"/>
-            <param name="selected_input_type" value="tabular"/>
-            <param name="selected_pre_processor" value="KernelCenterer"/>
-            <param name="save" value="true"/>
-            <output name="outfile_transform" file="prp_result01" ftype="tabular"/>
-            <output name="outfile_fit" file="prp_model01" ftype="zip" compare="sim_size" delta="5"/>
+            <param name="infile" value="train.tabular" ftype="tabular" />
+            <param name="selected_column_selector_option" value="all_columns" />
+            <param name="selected_input_type" value="tabular" />
+            <param name="selected_pre_processor" value="KernelCenterer" />
+            <param name="save" value="true" />
+            <output name="outfile_transform" file="prp_result01" ftype="tabular" />
+            <output name="outfile_fit" file="prp_model01" ftype="zip" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile" value="train.tabular" ftype="tabular"/>
-            <param name="selected_column_selector_option" value="all_columns"/>
-            <param name="selected_input_type" value="tabular"/>
-            <param name="selected_pre_processor" value="MinMaxScaler"/>
-            <param name="save" value="true"/>
-            <output name="outfile_transform" file="prp_result02" ftype="tabular"/>
-            <output name="outfile_fit" file="prp_model02" ftype="zip" compare="sim_size" delta="5"/>
+            <param name="infile" value="train.tabular" ftype="tabular" />
+            <param name="selected_column_selector_option" value="all_columns" />
+            <param name="selected_input_type" value="tabular" />
+            <param name="selected_pre_processor" value="MinMaxScaler" />
+            <param name="save" value="true" />
+            <output name="outfile_transform" file="prp_result02" ftype="tabular" />
+            <output name="outfile_fit" file="prp_model02" ftype="zip" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile" value="train.tabular" ftype="tabular"/>
-            <param name="selected_column_selector_option" value="all_columns"/>
-            <param name="selected_input_type" value="tabular"/>
-            <param name="selected_pre_processor" value="PolynomialFeatures"/>
-            <param name="save" value="true"/>
-            <output name="outfile_transform" file="prp_result03" ftype="tabular"/>
-            <output name="outfile_fit" file="prp_model03" ftype="zip" compare="sim_size" delta="5"/>
+            <param name="infile" value="train.tabular" ftype="tabular" />
+            <param name="selected_column_selector_option" value="all_columns" />
+            <param name="selected_input_type" value="tabular" />
+            <param name="selected_pre_processor" value="PolynomialFeatures" />
+            <param name="save" value="true" />
+            <output name="outfile_transform" file="prp_result03" ftype="tabular" />
+            <output name="outfile_fit" file="prp_model03" ftype="zip" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile" value="train.tabular" ftype="tabular"/>
-            <param name="selected_column_selector_option" value="all_columns"/>
-            <param name="selected_input_type" value="tabular"/>
-            <param name="selected_pre_processor" value="RobustScaler"/>
-            <param name="save" value="true"/>
-            <output name="outfile_transform" file="prp_result04" ftype="tabular"/>
-            <output name="outfile_fit" file="prp_model04" ftype="zip" compare="sim_size" delta="5"/>
+            <param name="infile" value="train.tabular" ftype="tabular" />
+            <param name="selected_column_selector_option" value="all_columns" />
+            <param name="selected_input_type" value="tabular" />
+            <param name="selected_pre_processor" value="RobustScaler" />
+            <param name="save" value="true" />
+            <output name="outfile_transform" file="prp_result04" ftype="tabular" />
+            <output name="outfile_fit" file="prp_model04" ftype="zip" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile" value="csr_sparse2.mtx" ftype="txt"/>
-            <param name="selected_input_type" value="sparse"/>
-            <param name="selected_pre_processor" value="Binarizer"/>
-            <param name="save" value="true"/>
-            <output name="outfile_transform" file="prp_result05" ftype="tabular"/>
-            <output name="outfile_fit" file="prp_model05" ftype="zip" compare="sim_size" delta="5"/>
+            <param name="infile" value="csr_sparse2.mtx" ftype="txt" />
+            <param name="selected_input_type" value="sparse" />
+            <param name="selected_pre_processor" value="Binarizer" />
+            <param name="save" value="true" />
+            <output name="outfile_transform" file="prp_result05" ftype="tabular" />
+            <output name="outfile_fit" file="prp_model05" ftype="zip" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile" value="train.tabular" ftype="tabular"/>
-            <param name="selected_input_type" value="tabular"/>
-            <param name="selected_column_selector_option" value="all_columns"/>
-            <param name="selected_pre_processor" value="StandardScaler"/>
-            <param name="save" value="true"/>
-            <output name="outfile_transform" file="prp_result07" ftype="tabular"/>
-            <output name="outfile_fit" file="prp_model07" ftype="zip" compare="sim_size" delta="5"/>
+            <param name="infile" value="train.tabular" ftype="tabular" />
+            <param name="selected_input_type" value="tabular" />
+            <param name="selected_column_selector_option" value="all_columns" />
+            <param name="selected_pre_processor" value="StandardScaler" />
+            <param name="save" value="true" />
+            <output name="outfile_transform" file="prp_result07" ftype="tabular" />
+            <output name="outfile_fit" file="prp_model07" ftype="zip" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile" value="csr_sparse2.mtx" ftype="txt"/>
-            <param name="selected_input_type" value="sparse"/>
-            <param name="selected_pre_processor" value="MaxAbsScaler"/>
-            <param name="save" value="true"/>
-            <output name="outfile_transform" file="prp_result08" ftype="tabular"/>
-            <output name="outfile_fit" file="prp_model08" ftype="zip" compare="sim_size" delta="5"/>
+            <param name="infile" value="csr_sparse2.mtx" ftype="txt" />
+            <param name="selected_input_type" value="sparse" />
+            <param name="selected_pre_processor" value="MaxAbsScaler" />
+            <param name="save" value="true" />
+            <output name="outfile_transform" file="prp_result08" ftype="tabular" />
+            <output name="outfile_fit" file="prp_model08" ftype="zip" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile" value="csr_sparse2.mtx" ftype="txt"/>
-            <param name="selected_input_type" value="sparse"/>
-            <param name="selected_pre_processor" value="Normalizer"/>
-            <param name="save" value="true"/>
-            <output name="outfile_transform" file="prp_result09" ftype="tabular"/>
-            <output name="outfile_fit" file="prp_model09" ftype="zip" compare="sim_size" delta="5"/>
+            <param name="infile" value="csr_sparse2.mtx" ftype="txt" />
+            <param name="selected_input_type" value="sparse" />
+            <param name="selected_pre_processor" value="Normalizer" />
+            <param name="save" value="true" />
+            <output name="outfile_transform" file="prp_result09" ftype="tabular" />
+            <output name="outfile_fit" file="prp_model09" ftype="zip" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile" value="regression_X.tabular" ftype="tabular"/>
-            <param name="header1" value="true"/>
-            <param name="selected_column_selector_option" value="all_columns"/>
-            <param name="selected_input_type" value="tabular"/>
-            <param name="selected_pre_processor" value="MinMaxScaler"/>
-            <param name="feature_range" value="(-1, 1)"/>
-            <param name="save" value="false"/>
-            <output name="outfile_transform" file="prp_result10" ftype="tabular"/>
+            <param name="infile" value="regression_X.tabular" ftype="tabular" />
+            <param name="header1" value="true" />
+            <param name="selected_column_selector_option" value="all_columns" />
+            <param name="selected_input_type" value="tabular" />
+            <param name="selected_pre_processor" value="MinMaxScaler" />
+            <param name="feature_range" value="(-1, 1)" />
+            <param name="save" value="false" />
+            <output name="outfile_transform" file="prp_result10" ftype="tabular" />
         </test>
     </tests>
     <help>
@@ -214,5 +212,5 @@
 .. _`Scikit-learn preprocessing`: http://scikit-learn.org/stable/modules/preprocessing.html
         ]]>
     </help>
-    <expand macro="sklearn_citation"/>
+    <expand macro="sklearn_citation" />
 </tool>