diff regression_metrics.xml @ 0:ca05b5889dfc draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 2e1e78576b38110cf5b1f2ed83b08b9c3a6cbfee
author bgruening
date Sat, 28 Apr 2018 18:05:04 -0400
parents
children c5feb1a67e9b
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/regression_metrics.xml	Sat Apr 28 18:05:04 2018 -0400
@@ -0,0 +1,186 @@
+<tool id="sklearn_regression_metrics" name="Calculate metrics" version="@VERSION@">
+    <description>for regression performance</description>
+    <macros>
+        <import>main_macros.xml</import>
+    </macros>
+    <expand macro="python_requirements"/>
+    <expand macro="macro_stdio"/>
+    <version_command>echo "@VERSION@"</version_command>
+    <command>
+        <![CDATA[
+        python "$regression_metrics_script" '$inputs'
+        ]]>
+    </command>
+    <configfiles>
+        <inputs name="inputs" />
+        <configfile name="regression_metrics_script">
+            <![CDATA[
+import sys
+import json
+import pandas
+import numpy as np
+from sklearn import metrics
+
+@COLUMNS_FUNCTION@
+
+input_json_path = sys.argv[1]
+params = json.load(open(input_json_path, "r"))
+
+header='infer' if params["regression_metrics"]["header1"] else None
+y_t = read_columns(
+        "$regression_metrics.infile1",
+        "$regression_metrics.col1",
+        sep='\t',
+        header=header,
+        parse_dates=True
+)
+
+header='infer' if params["regression_metrics"]["header2"] else None
+y_p = read_columns(
+        "$regression_metrics.infile2",
+        "$regression_metrics.col2",
+        sep='\t',
+        header=header,
+        parse_dates=True
+)
+
+options = params["regression_metrics"].get("options", {})
+if options and options.get('average', '') == 'None':
+    options['average'] = None
+metric = params["regression_metrics"]["selected_metric"]
+metric_function = getattr(metrics, metric)
+res = metric_function(y_t,y_p,**options)
+res= format(res, '.4f')
+with open("$outfile", 'w+') as out_file:
+    out_file.write( metric + ' : ' + '\n' + str(res) + '\n' )
+
+            ]]>
+        </configfile>
+    </configfiles>
+    <inputs>
+        <conditional name="regression_metrics">
+            <param name="selected_metric" type="select" label="Metrics">
+                <option value="explained_variance_score" selected="true">explained_variance_score - Explained variance regression score function</option>
+                <option value="mean_absolute_error">mean_absolute_error - Mean absolute error regression loss</option>
+                <option value="mean_squared_error">mean_squared_error - Mean squared error regression loss</option>
+                <option value="mean_squared_log_error">mean_squared_log_error - Mean squared logarithmic error regression loss</option>
+                <option value="median_absolute_error">median_absolute_error - Median absolute error regression loss</option>
+                <option value="r2_score">r2_score - R^2 (coefficient of determination) regression score function</option>
+            </param>
+            <when value="explained_variance_score">
+                <expand macro="clf_inputs"/>
+                <!--section name="options" title="Advanced Options" expanded="False">
+                    <!- -sample_weight- ->
+                    <!- -multioutput- ->
+                </section-->
+            </when>
+            <when value="mean_absolute_error">
+                <expand macro="clf_inputs"/>
+                <!--section name="options" title="Advanced Options" expanded="False">
+                    <!- -sample_weight- ->
+                    <!- -multioutput- ->
+                </section-->
+            </when>
+            <when value="mean_squared_error">
+                <expand macro="clf_inputs"/>
+                <!--section name="options" title="Advanced Options" expanded="False">
+                    <!- -sample_weight- ->
+                    <!- -multioutput- ->
+                </section-->
+            </when>
+            <when value="mean_squared_log_error">
+                <expand macro="clf_inputs"/>
+                <!--section name="options" title="Advanced Options" expanded="False">
+                    <!- -sample_weight- ->
+                    <!- -multioutput- ->
+                </section-->
+            </when>
+            <when value="median_absolute_error">
+                <expand macro="clf_inputs"/>
+            </when>
+            <when value="r2_score">
+                <expand macro="clf_inputs"/>
+                <!--section name="options" title="Advanced Options" expanded="False">
+                    <!- -sample_weight- ->
+                    <!- -multioutput- ->
+                </section-->
+            </when>
+        </conditional>
+    </inputs>
+    <outputs>
+        <data format="txt" name="outfile"/>
+    </outputs>
+    <tests>
+        <test>
+            <param name="selected_metric" value="explained_variance_score"/>
+            <param name="infile1" value="regression_test_y.tabular" ftype="tabular"/>
+            <param name="header1" value="True"/>
+            <param name="col1" value="1"/>
+            <param name="infile2" value="regression_test_y.tabular" ftype="tabular"/>
+            <param name="header2" value="True"/>
+            <param name="col2" value="2"/>
+            <output name="outfile" file="regression_metrics_result01"/>
+        </test>
+        <test>
+            <param name="selected_metric" value="mean_absolute_error"/>
+            <param name="infile1" value="regression_test_y.tabular" ftype="tabular"/>
+            <param name="header1" value="True"/>
+            <param name="col1" value="1"/>
+            <param name="infile2" value="regression_test_y.tabular" ftype="tabular"/>
+            <param name="header2" value="True"/>
+            <param name="col2" value="2"/>
+            <output name="outfile" file="regression_metrics_result02"/>
+        </test>
+        <test>
+            <param name="selected_metric" value="mean_squared_error"/>
+            <param name="infile1" value="regression_test_y.tabular" ftype="tabular"/>
+            <param name="header1" value="True"/>
+            <param name="col1" value="1"/>
+            <param name="infile2" value="regression_test_y.tabular" ftype="tabular"/>
+            <param name="header2" value="True"/>
+            <param name="col2" value="2"/>
+            <output name="outfile" file="regression_metrics_result03"/>
+        </test>
+        <test>
+            <param name="selected_metric" value="mean_squared_log_error"/>
+            <param name="infile1" value="regression_test_y.tabular" ftype="tabular"/>
+            <param name="header1" value="True"/>
+            <param name="col1" value="1"/>
+            <param name="infile2" value="regression_test_y.tabular" ftype="tabular"/>
+            <param name="header2" value="True"/>
+            <param name="col2" value="2"/>
+            <output name="outfile" file="regression_metrics_result04"/>
+        </test>
+        <test>
+            <param name="selected_metric" value="median_absolute_error"/>
+            <param name="infile1" value="regression_test_y.tabular" ftype="tabular"/>
+            <param name="header1" value="True"/>
+            <param name="col1" value="1"/>
+            <param name="infile2" value="regression_test_y.tabular" ftype="tabular"/>
+            <param name="header2" value="True"/>
+            <param name="col2" value="2"/>
+            <output name="outfile" file="regression_metrics_result05"/>
+        </test>
+        <test>
+            <param name="selected_metric" value="r2_score"/>
+            <param name="infile1" value="regression_test_y.tabular" ftype="tabular"/>
+            <param name="header1" value="True"/>
+            <param name="col1" value="1"/>
+            <param name="infile2" value="regression_test_y.tabular" ftype="tabular"/>
+            <param name="header2" value="True"/>
+            <param name="col2" value="2"/>
+            <output name="outfile" file="regression_metrics_result06"/>
+        </test>
+    </tests>
+    <help>
+        <![CDATA[
+**What it does**
+This tool provides several loss, score, and utility functions to measure classification performance. Some metrics might require probability estimates of the positive class, confidence values, or binary decisions values. This tool is based on
+sklearn.metrics package.
+For information about classification metric functions and their parameter settings please refer to `Scikit-learn classification metrics`_.
+
+.. _`Scikit-learn classification metrics`: http://scikit-learn.org/stable/modules/model_evaluation.html#classification-metrics
+        ]]>
+    </help>
+    <expand macro="sklearn_citation"/>
+</tool>