annotate regression_metrics.xml @ 30:70c5a9127f99 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit ea12f973df4b97a2691d9e4ce6bf6fae59d57717"

<tool id="sklearn_regression_metrics" name="Calculate metrics" version="@VERSION@" profile="20.05">
    <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
from galaxy_ml.utils import read_columns


input_json_path = sys.argv[1]
with open(input_json_path, "r") as param_handler:
    params = json.load(param_handler)

header='infer' if params["regression_metrics"]["header1"] else None
column_option = params["regression_metrics"]["column_selector_options_1"]["selected_column_selector_option"]
if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:
    c = params["regression_metrics"]["column_selector_options_1"]["col1"]
else:
    c = None
y_t = read_columns(
        "$regression_metrics.infile1",
        c = c,
        c_option = column_option,
        sep='\t',
        header=header,
        parse_dates=True)

header='infer' if params["regression_metrics"]["header2"] else None
column_option = params["regression_metrics"]["column_selector_options_2"]["selected_column_selector_option2"]
if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:
    c = params["regression_metrics"]["column_selector_options_2"]["col2"]
else:
    c = None
y_p = read_columns(
        "$regression_metrics.infile2",
        c = c,
        c_option = column_option,
        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="selected_column_selector_option" value="all_but_by_index_number" />
            <param name="col1" value="2" />
            <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="selected_column_selector_option2" value="all_but_by_index_number" />
            <param name="col2" value="1" />
            <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>