diff main_macros.xml @ 5:06b71e58a943 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 35fa73d6e9ba8f0789ddfb743d893d950a68af02
author bgruening
date Tue, 10 Apr 2018 15:18:18 -0400
parents d2f23b211af8
children 9eecaf90aeb6
line wrap: on
line diff
--- a/main_macros.xml	Thu Mar 22 13:46:16 2018 -0400
+++ b/main_macros.xml	Tue Apr 10 15:18:18 2018 -0400
@@ -66,6 +66,7 @@
         <when value="load">
             <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file."/>
             <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
+            <param name="header" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
             <conditional name="prediction_options">
                 <param name="prediction_option" type="select" label="Select the type of prediction">
                     <option value="predict">Predict class labels</option>
@@ -174,12 +175,12 @@
     <param argument="max_depth" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@"/>
   </xml>
 
-  <xml name="min_samples_split" token_default_value="2" token_help=" ">
-    <param argument="min_samples_split" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Minimum number of samples required to split an internal node" help="@HELP@"/>
+  <xml name="min_samples_split" token_type="integer" token_default_value="2" token_help=" ">
+    <param argument="min_samples_split" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="Minimum number of samples required to split an internal node" help="@HELP@"/>
   </xml>
 
-  <xml name="min_samples_leaf" token_default_value="1" token_help=" ">
-    <param argument="min_samples_leaf" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Minimum number of samples in newly created leaves" help="@HELP@"/>
+  <xml name="min_samples_leaf" token_type="integer" token_default_value="1" token_label="Minimum number of samples in newly created leaves" token_help=" ">
+    <param argument="min_samples_leaf" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP@"/>
   </xml>
 
   <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" ">
@@ -190,6 +191,10 @@
     <param argument="max_leaf_nodes" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum number of leaf nodes in best-first method" help="@HELP@"/>
   </xml>
 
+  <xml name="min_impurity_decrease" token_default_value="0" token_help=" ">
+    <param argument="min_impurity_decrease" type="float" value="@DEFAULT_VALUE@" optional="true" label="The threshold value of impurity for stopping node splitting" help="@HELP@"/>
+  </xml>
+
   <xml name="bootstrap" token_checked="true" token_help=" ">
     <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@"/>
   </xml>
@@ -202,18 +207,57 @@
     </param>
   </xml>
 
+  <xml name="criterion2" token_help="">
+    <param argument="criterion" type="select" label="Function to measure the quality of a split" >
+      <option value="mse">mse - mean squared error</option>
+      <option value="mae">mae - mean absolute error</option>
+      <yield/>
+    </param>
+  </xml>
+
   <xml name="oob_score" token_checked="false" token_help=" ">
     <param argument="oob_score" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Use out-of-bag samples to estimate the generalization error" help="@HELP@"/>
   </xml>
 
-  <xml name="max_features" token_default_value="auto" token_help="This could be an integer, float, string, or None. For more information please refer to help. ">
-    <param argument="max_features" type="text" optional="true" value="@DEFAULT_VALUE@" label="Number of features for finding the best split" help="@HELP@"/>
+  <xml name="max_features">
+    <conditional name="select_max_features">
+      <param argument="max_features" type="select" label="max_features">
+        <option value="auto" selected="true">auto - max_features=n_features</option>
+        <option value="sqrt">sqrt - max_features=sqrt(n_features)</option>
+        <option value="log2">log2 - max_features=log2(n_features)</option>
+        <option value="number_input">I want to type the number in or input None type</option>
+      </param>
+      <when value="auto">
+      </when>
+      <when value="sqrt">
+      </when>
+      <when value="log2">
+      </when>
+      <when value="number_input">
+        <param name="num_max_features" type="float" value="" optional="true" label="Input max_features number:" help="If int, consider the number of features at each split; If float, then max_features is a percentage and int(max_features * n_features) features are considered at each split."/>
+      </when>
+    </conditional>
+  </xml>
+
+  <xml name="verbose" token_default_value="0" token_help="If 1 then it prints progress and performance once in a while. If greater than 1 then it prints progress and performance for every tree.">
+    <param argument="verbose" type="integer" value="@DEFAULT_VALUE@" optional="true" label="Enable verbose output" help="@HELP@"/>
   </xml>
 
   <xml name="learning_rate" token_default_value="1.0" token_help=" ">
     <param argument="learning_rate" type="float" optional="true" value="@DEFAULT_VALUE@" label="Learning rate" help="@HELP@"/>
   </xml>
 
+  <xml name="subsample" token_help=" ">
+    <param argument="subsample" type="float" value="1.0" optional="true" label="The fraction of samples to be used for fitting the individual base learners" help="@HELP@"/>
+  </xml>
+
+  <xml name="presort">
+    <param argument="presort" type="select" label="Whether to presort the data to speed up the finding of best splits in fitting" >
+      <option value="auto" selected="true">auto</option>
+      <option value="true">true</option>
+      <option value="false">false</option>
+    </param>
+  </xml>
 
   <!--Parameters-->
   <xml name="tol" token_default_value="0.0" token_help_text="Early stopping heuristics based on the relative center changes. Set to default (0.0) to disable this convergence detection.">
@@ -228,6 +272,10 @@
     <param argument="fit_intercept" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Estimate the intercept" help="If false, the data is assumed to be already centered."/>
   </xml>
 
+  <xml name="n_jobs" token_default_value="1" token_label="The number of jobs to run in parallel for both fit and predict">
+    <param argument="n_jobs" type="integer" value="@DEFAULT_VALUE@" optional="true" label="@LABEL@" help="If -1, then the number of jobs is set to the number of cores"/>
+  </xml>
+
   <xml name="n_iter" token_default_value="5" token_help_text="The number of passes over the training data (aka epochs). ">
     <param argument="n_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of iterations" help="@HELP_TEXT@"/>
   </xml>