view nn_classifier.xml @ 23:823ecc0bce45 draft

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

<tool id="sklearn_nn_classifier" name="Nearest Neighbors Classification" version="@VERSION@" profile="20.05">
    <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

from galaxy_ml.utils import load_model, get_X_y


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

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

with open("$infile_model", 'rb') as model_handler:
    classifier_object = load_model(model_handler)

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

#else:

X, y = get_X_y(params, "$selected_tasks.selected_algorithms.input_options.infile1" ,"$selected_tasks.selected_algorithms.input_options.infile2")

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(X, y)

with open("$outfile_fit", 'wb') as out_handler:
    pickle.dump(classifier_object, out_handler)

#end if

]]>
        </configfile>
    </configfiles>
    <inputs>
        <expand macro="sl_Conditional" 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">
                <expand macro="sl_mixed_input" />
                <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">
                <expand macro="sl_mixed_input" />
                <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="infile1" value="train_set.tabular" ftype="tabular" />
            <param name="infile2" value="train_set.tabular" ftype="tabular" />
            <param name="header1" value="True" />
            <param name="header2" value="True" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <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" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile1" value="train_set.tabular" ftype="tabular" />
            <param name="infile2" value="train_set.tabular" ftype="tabular" />
            <param name="header1" value="True" />
            <param name="header2" value="True" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="nneighbors" />
            <param name="sampling_method" value="RadiusNeighborsClassifier" />
            <output name="outfile_fit" file="nn_model02" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile1" value="train_set.tabular" ftype="tabular" />
            <param name="infile2" value="train_set.tabular" ftype="tabular" />
            <param name="header1" value="True" />
            <param name="header2" value="True" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="ncentroid" />
            <output name="outfile_fit" file="nn_model03" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile_model" value="nn_model01" ftype="zip" />
            <param name="infile_data" value="test_set.tabular" ftype="tabular" />
            <param name="header" value="True" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="nn_prediction_result01.tabular" />
        </test>
        <test>
            <param name="infile_model" value="nn_model02" ftype="zip" />
            <param name="infile_data" value="test_set.tabular" ftype="tabular" />
            <param name="header" value="True" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="nn_prediction_result02.tabular" />
        </test>
        <test>
            <param name="infile_model" value="nn_model03" ftype="zip" />
            <param name="infile_data" value="test_set.tabular" ftype="tabular" />
            <param name="header" value="True" />
            <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>