Mercurial > repos > bgruening > sklearn_model_validation

changeset 21:887e0aaa482e 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 02087ce2966cf8b4aac9197a41171e7f986c11d1-dirty"
author bgruening
date Wed, 02 Oct 2019 04:06:01 -0400
parents 5895fe0b8bde
children 95b04e086576
files main_macros.xml ml_visualization_ex.py model_validation.xml stacking_ensembles.py
diffstat 4 files changed, 43 insertions(+), 23 deletions(-) [+]
line wrap: on
line diff
--- a/main_macros.xml	Fri Sep 13 12:16:02 2019 -0400
+++ b/main_macros.xml	Wed Oct 02 04:06:01 2019 -0400
@@ -421,27 +421,46 @@
 
   <xml name="sl_mixed_input">
     <conditional name="input_options">
-      <param name="selected_input" type="select" label="Select input type:">
-          <option value="tabular" selected="true">tabular data</option>
-          <option value="sparse">sparse matrix</option>
-          <option value="seq_fasta">sequnences in a fasta file</option>
-          <option value="refseq_and_interval">reference genome and intervals</option>
-      </param>
-      <when value="tabular">
-          <expand macro="samples_tabular" multiple1="true" multiple2="false"/>
-      </when>
-      <when value="sparse">
-          <expand macro="sparse_target"/>
-      </when>
-      <when value="seq_fasta">
-          <expand macro="inputs_seq_fasta"/>
-      </when>
-      <when value="refseq_and_interval">
-          <expand macro="inputs_refseq_and_interval"/>
-      </when>
+        <expand macro="data_input_options"/>
+        <expand macro="data_input_whens"/>
     </conditional>
   </xml>
 
+  <xml name="sl_mixed_input_plus_sequence">
+    <conditional name="input_options">
+        <expand macro="data_input_options">
+            <option value="seq_fasta">sequnences in a fasta file</option>
+            <option value="refseq_and_interval">reference genome and intervals</option>
+        </expand>
+        <expand macro="data_input_whens">
+            <when value="seq_fasta">
+                <expand macro="inputs_seq_fasta"/>
+            </when>
+            <when value="refseq_and_interval">
+                <expand macro="inputs_refseq_and_interval"/>
+            </when>
+        </expand>
+    </conditional>
+  </xml>
+
+  <xml name="data_input_options">
+    <param name="selected_input" type="select" label="Select input type:">
+        <option value="tabular" selected="true">tabular data</option>
+        <option value="sparse">sparse matrix</option>
+        <yield/>
+    </param>
+  </xml>
+
+  <xml name="data_input_whens">
+    <when value="tabular">
+        <expand macro="samples_tabular" multiple1="true" multiple2="false"/>
+    </when>
+    <when value="sparse">
+        <expand macro="sparse_target"/>
+    </when>
+    <yield/>
+  </xml>
+
   <xml name="input_tabular_target">
     <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:"/>
     <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" />
--- a/ml_visualization_ex.py	Fri Sep 13 12:16:02 2019 -0400
+++ b/ml_visualization_ex.py	Wed Oct 02 04:06:01 2019 -0400
@@ -146,7 +146,8 @@
             precision["micro"], recall["micro"], _ = precision_recall_curve(
                 df1.values.ravel(), df2.values.ravel(), pos_label=pos_label)
             ap['micro'] = average_precision_score(
-                df1.values, df2.values, average='micro', pos_label=pos_label or 1)
+                df1.values, df2.values, average='micro',
+                pos_label=pos_label or 1)
 
         data = []
         for key in precision.keys():
@@ -201,7 +202,7 @@
             )
             data.append(trace)
 
-        trace = go.Scatter(x=[0, 1], y=[0, 1], 
+        trace = go.Scatter(x=[0, 1], y=[0, 1],
                            mode='lines', 
                            line=dict(color='black', dash='dash'),
                            showlegend=False)
--- a/model_validation.xml	Fri Sep 13 12:16:02 2019 -0400
+++ b/model_validation.xml	Wed Oct 02 04:06:01 2019 -0400
@@ -325,7 +325,7 @@
             </when>
             <when value="validation_curve"/>
         </conditional>
-        <expand macro="sl_mixed_input"/>
+        <expand macro="sl_mixed_input_plus_sequence"/>
     </inputs>
     <outputs>
         <data format="tabular" name="outfile"/>
@@ -354,7 +354,7 @@
             <param name="col1" value="1,2,3,4,5"/>
             <param name="infile2" value="regression_train.tabular" ftype="tabular"/>
             <param name="col2" value="6"/>
-            <output name="outfile" file="mv_result02.tabular" lines_diff="4"/>
+            <output name="outfile" file="mv_result02.tabular" lines_diff="14"/>
         </test>
         <test>
             <param name="infile_estimator" value="pipeline05"/>
--- a/stacking_ensembles.py	Fri Sep 13 12:16:02 2019 -0400
+++ b/stacking_ensembles.py	Wed Oct 02 04:06:01 2019 -0400
@@ -11,7 +11,7 @@
 from sklearn import ensemble
 
 from galaxy_ml.utils import (load_model, get_cv, get_estimator,
-                          get_search_params)
+                             get_search_params)
 
 
 warnings.filterwarnings('ignore')