view nn_classifier.xml @ 9:56e001c53a47 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 4ed8c4f6ef9ece81797a398b17a99bbaf49a6978

<tool id="nn_classifier" name="Nearest Neighbors Classification" version="@VERSION@">
    <description></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 "$nnc_script" '$inputs'
]]>
    </command>
    <configfiles>
        <inputs name="inputs"/>
        <configfile name="nnc_script">
<![CDATA[
import sys
import json
import numpy as np
import sklearn.neighbors
import pandas
import pickle

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


#if $selected_tasks.selected_task == "load":

classifier_object = pickle.load(open("$infile_model", 'r'))

data = pandas.read_csv("$selected_tasks.infile_data", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False )
prediction = classifier_object.predict(data)
prediction_df = pandas.DataFrame(prediction)
res = pandas.concat([data, prediction_df], axis=1)
res.to_csv(path_or_buf = "$outfile_predict", sep="\t", index=False)

#else:

data_train = pandas.read_csv("$selected_tasks.infile_train", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False )

data = data_train.ix[:,0:len(data_train.columns)-1]
labels = np.array(data_train[data_train.columns[len(data_train.columns)-1]])

selected_algorithm = params["selected_tasks"]["selected_algorithms"]["selected_algorithm"]

if selected_algorithm == "nneighbors":
    classifier = params["selected_tasks"]["selected_algorithms"]["sampling_methods"]["sampling_method"]
    sys.stdout.write(classifier)
    options = params["selected_tasks"]["selected_algorithms"]["sampling_methods"]["options"]
    sys.stdout.write(str(options))
elif selected_algorithm == "ncentroid":
    options = params["selected_tasks"]["selected_algorithms"]["options"]
    classifier = "NearestCentroid"

my_class = getattr(sklearn.neighbors, classifier)
classifier_object = my_class(**options)
classifier_object.fit(data,labels)

pickle.dump(classifier_object,open("$outfile_fit", 'w+'))

#end if

]]>
        </configfile>
    </configfiles>
    <inputs>
        <expand macro="train_loadConditional" model="zip"><!--Todo: add sparse to targets-->
            <param name="selected_algorithm" type="select" label="Classifier type">
                <option value="nneighbors">Nearest Neighbors</option>
                <option value="ncentroid">Nearest Centroid</option>
            </param>
            <when value="nneighbors">
                <conditional name="sampling_methods">
                    <param name="sampling_method" type="select" label="Neighbor selection method">
                        <option value="KNeighborsClassifier" selected="true">K-nearest neighbors</option>
                        <option value="RadiusNeighborsClassifier">Radius-based</option>
                    </param>
                    <when value="KNeighborsClassifier">
                        <expand macro="nn_advanced_options">
                            <param argument="n_neighbors" type="integer" optional="true" value="5" label="Number of neighbors" help=" "/>
                        </expand>
                    </when>
                    <when value="RadiusNeighborsClassifier">
                        <expand macro="nn_advanced_options">
                            <param argument="radius" type="float" optional="true" value="1.0" label="Radius"
                                help="Range of parameter space to use by default for :meth ''radius_neighbors'' queries."/>
                        </expand>
                    </when>
                </conditional>
            </when>
            <when value="ncentroid">
                <section name="options" title="Advanced Options" expanded="False">
                    <param argument="metric" type="text" optional="true" value="euclidean" label="Metric"
                        help="The metric to use when calculating distance between instances in a feature array."/>
                    <param argument="shrink_threshold" type="float" optional="true" value="" label="Shrink threshold"
                        help="Floating point number for shrinking centroids to remove features."/>
                </section>
            </when>
        </expand>
    </inputs>

    <expand macro="output"/>

    <tests>
        <test>
            <param name="infile_train" value="train_set.tabular" ftype="tabular"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="nneighbors"/>
            <param name="sampling_method" value="KNeighborsClassifier" />
            <param name="algorithm" value="brute" />
            <output name="outfile_fit" file="nn_model01.txt"/>
        </test>
        <test>
            <param name="infile_train" value="train_set.tabular" ftype="tabular"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value=""/>
            <param name="selected_algorithm" value="nneighbors"/>
            <param name="sampling_method" value="RadiusNeighborsClassifier" />
            <output name="outfile_fit" file="nn_model02.txt"/>
        </test>
        <test>
            <param name="infile_train" value="train_set.tabular" ftype="tabular"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="ncentroid"/>
            <output name="outfile_fit" file="nn_model03.txt"/>
        </test>
        <test>
            <param name="infile_model" value="nn_model01.txt" ftype="txt"/>
            <param name="infile_data" value="test_set.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="nn_prediction_result01.tabular"/>
        </test>
        <test>
            <param name="infile_model" value="nn_model02.txt" ftype="txt"/>
            <param name="infile_data" value="test_set.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="nn_prediction_result02.tabular"/>
        </test>
        <test>
            <param name="infile_model" value="nn_model03.txt" ftype="txt"/>
            <param name="infile_data" value="test_set.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="nn_prediction_result03.tabular"/>
        </test>
    </tests>
    <help><![CDATA[
**What it does**
This module implements the k-nearest neighbors classification algorithms.
For more information check http://scikit-learn.org/stable/modules/neighbors.html
    ]]></help>
    <expand macro="sklearn_citation"/>
</tool>