view feature_selection.xml @ 8:38faa5ade609 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 7c2fd140e89605fe689c39e21d70a400545e38cf
author bgruening
date Tue, 10 Jul 2018 03:11:48 -0400
parents b0d554b38770
children 537c6763c018
line wrap: on
line source

<tool id="sklearn_feature_selection" name="Feature Selection" version="@VERSION@.1">
    <description>module, including univariate filter selection methods and recursive feature elimination algorithm</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 "$feature_selection_script" '$inputs'
        ]]>
    </command>
    <configfiles>
        <inputs name="inputs" />
        <configfile name="feature_selection_script">
            <![CDATA[
import sys
import json
import pandas
import pickle
import numpy as np
import sklearn.feature_selection
from sklearn import svm, linear_model, ensemble

@COLUMNS_FUNCTION@

@FEATURE_SELECTOR_FUNCTION@

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

## Read features
features_has_header = params["input_options"]["header1"]
input_type = params["input_options"]["selected_input"]
if input_type=="tabular":
    header = 'infer' if features_has_header else None
    column_option = params["input_options"]["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["input_options"]["column_selector_options_1"]["col1"]
    else:
        c = None
    X, input_df = read_columns(
            "$input_options.infile1",
            c = c,
            c_option = column_option,
            return_df = True,
            sep='\t',
            header=header,
            parse_dates=True
    )
else:
    X = mmread(open("$input_options.infile1", 'r'))

## Read labels
header = 'infer' if params["input_options"]["header2"] else None
column_option = params["input_options"]["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["input_options"]["column_selector_options_2"]["col2"]
else:
    c = None
y = read_columns(
        "$input_options.infile2",
        c = c,
        c_option = column_option,
        sep='\t',
        header=header,
        parse_dates=True
)
y=y.ravel()

## Create feature selector
new_selector = feature_selector(params['feature_selection_algorithms'])
if params['feature_selection_algorithms']['selected_algorithm'] != 'SelectFromModel' or \
        'extra_estimator' not in params['feature_selection_algorithms'] or \
        params['feature_selection_algorithms']['extra_estimator']['has_estimator'] != 'no_load' :
    new_selector.fit(X, y)

## Transform to select features
selected_names = None
if "$select_methods.selected_method" == "fit_transform":
    res = new_selector.transform(X)
    if features_has_header:
        selected_names = input_df.columns[new_selector.get_support(indices=True)]
else:
    res = new_selector.get_support(params["select_methods"]["indices"])

res = pandas.DataFrame(res, columns = selected_names)
res.to_csv(path_or_buf="$outfile", sep='\t', index=False)


            ]]>
        </configfile>
    </configfiles>
    <inputs>
        <expand macro="feature_selection_all" />
        <expand macro="feature_selection_methods" />
        <expand macro="sl_mixed_input"/>
    </inputs>
    <outputs>
        <data format="tabular" name="outfile"/>
    </outputs>
    <tests>
        <test>
            <param name="selected_algorithm" value="SelectFromModel"/>
            <param name="has_estimator" value="no"/>
            <param name="new_estimator" value="ensemble.RandomForestRegressor(n_estimators = 1000, random_state = 42)"/>
            <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="col1" value="1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17"/>
            <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
            <param name="col2" value="1"/>
            <param name="header2" value="True"/>
            <output name="outfile" file="feature_selection_result01"/>
        </test>
        <test>
            <param name="selected_algorithm" value="GenericUnivariateSelect"/>
            <param name="param" value="20"/>
            <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="col1" value="1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17"/>
            <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
            <param name="col2" value="1"/>
            <param name="header2" value="True"/>
            <output name="outfile" file="feature_selection_result02"/>
        </test>
        <test>
            <param name="selected_algorithm" value="SelectPercentile"/>
            <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="col1" value="1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17"/>
            <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
            <param name="col2" value="1"/>
            <param name="header2" value="True"/>
            <output name="outfile" file="feature_selection_result03"/>
        </test>
        <test>
            <param name="selected_algorithm" value="SelectKBest"/>
            <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="col1" value="1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17"/>
            <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
            <param name="col2" value="1"/>
            <param name="header2" value="True"/>
            <output name="outfile" file="feature_selection_result04"/>
        </test>
        <test>
            <param name="selected_algorithm" value="SelectFpr"/>
            <param name="alpha" value="0.05"/>
            <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="col1" value="1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17"/>
            <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
            <param name="col2" value="1"/>
            <param name="header2" value="True"/>
            <output name="outfile" file="feature_selection_result05"/>
        </test>
        <test>
            <param name="selected_algorithm" value="SelectFdr"/>
            <param name="alpha" value="0.05"/>
            <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="col1" value="1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17"/>
            <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
            <param name="col2" value="1"/>
            <param name="header2" value="True"/>
            <output name="outfile" file="feature_selection_result06"/>
        </test>
        <test>
            <param name="selected_algorithm" value="SelectFwe"/>
            <param name="alpha" value="0.05"/>
            <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="col1" value="1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17"/>
            <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
            <param name="col2" value="1"/>
            <param name="header2" value="True"/>
            <output name="outfile" file="feature_selection_result07"/>
        </test>
        <test>
            <param name="selected_algorithm" value="RFE"/>
            <param name="has_estimator" value="no"/>
            <param name="new_estimator" value="ensemble.RandomForestRegressor(n_estimators = 1000, random_state = 42)"/>
            <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="col1" value="1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17"/>
            <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
            <param name="col2" value="1"/>
            <param name="header2" value="True"/>
            <output name="outfile" file="feature_selection_result08"/>
        </test>
        <test>
            <param name="selected_algorithm" value="RFECV"/>
            <param name="has_estimator" value="no"/>
            <param name="new_estimator" value="ensemble.RandomForestRegressor(n_estimators = 1000, random_state = 42)"/>
            <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="col1" value="1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17"/>
            <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
            <param name="col2" value="1"/>
            <param name="header2" value="True"/>
            <output name="outfile" file="feature_selection_result09"/>
        </test>
        <test>
            <param name="selected_algorithm" value="VarianceThreshold"/>
            <param name="threshold" value="0.1"/>
            <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="col1" value="1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17"/>
            <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
            <param name="col2" value="1"/>
            <param name="header2" value="True"/>
            <output name="outfile" file="feature_selection_result10"/>
        </test>
        <test>
            <param name="selected_algorithm" value="SelectKBest"/>
            <param name="k" value="3"/>
            <param name="infile1" value="test3.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="selected_column_selector_option" value="all_but_by_header_name"/>
            <param name="col1" value="target"/>
            <param name="infile2" value="test3.tabular" ftype="tabular"/>
            <param name="header2" value="True"/>
            <param name="selected_column_selector_option2" value="by_header_name"/>
            <param name="col2" value="target"/>
            <output name="outfile" file="feature_selection_result11"/>
        </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>