comparison svm.xml @ 5:1c5989b930e3 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 2a058459e6daf0486871f93845f00fdb4a4eaca1

4:41d0edb7d1fc

import sys
import json
import sklearn.svm
import pandas

execfile("$__tool_directory__/sk_whitelist.py")
execfile("$__tool_directory__/utils.py", globals())

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 = SafePickler.load(model_handler)

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

my_class = getattr(sklearn.svm, selected_algorithm)
classifier_object = my_class(**options)
classifier_object.fit(X, y)

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

#end if

]]>
        </configfile>

                    <param argument="intercept_scaling" type="float" optional="true" value="1" label="Add synthetic feature to the instance vector" help=" "/>
                </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="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="SVC"/>
            <param name="random_state" value="5"/>
            <output name="outfile_fit" file="svc_model01.txt" compare="sim_size" delta="1"/>
        </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="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="NuSVC"/>
            <param name="random_state" value="5"/>
            <output name="outfile_fit" file="svc_model02.txt" compare="sim_size" delta="1"/>
        </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="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="LinearSVC"/>
            <param name="random_state" value="5"/>
            <output name="outfile_fit" file="svc_model03.txt" compare="sim_size" delta="1"/>
        </test>
        <test>
            <param name="infile_model" value="svc_model01.txt" 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="svc_prediction_result01.tabular"/>
        </test>
        <test>
            <param name="infile_model" value="svc_model02.txt" 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="svc_prediction_result02.tabular"/>
        </test>
        <test>
            <param name="infile_model" value="svc_model03.txt" 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="svc_prediction_result03.tabular"/>
        </test>
    </tests>
    <help><![CDATA[
**What it does**
This module implements the Support Vector Machine (SVM) classification algorithms.

5:1c5989b930e3

import sys
import json
import sklearn.svm
import pandas

with open("$__tool_directory__/sk_whitelist.json", "r") as f:
    sk_whitelist = json.load(f)
exec(open("$__tool_directory__/utils.py").read(), globals())

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":

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, tupleize_cols=False)

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

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)

my_class = getattr(sklearn.svm, selected_algorithm)
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>

                    <param argument="intercept_scaling" type="float" optional="true" value="1" label="Add synthetic feature to the instance vector" help=" "/>
                </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="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="SVC"/>
            <param name="random_state" value="5"/>
            <output name="outfile_fit" file="svc_model01" compare="sim_size"/>
        </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="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="NuSVC"/>
            <param name="random_state" value="5"/>
            <output name="outfile_fit" file="svc_model02" compare="sim_size"/>
        </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="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="LinearSVC"/>
            <param name="random_state" value="5"/>
            <output name="outfile_fit" file="svc_model03" compare="sim_size"/>
        </test>
        <test>
            <param name="infile_model" value="svc_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="svc_prediction_result01.tabular"/>
        </test>
        <test>
            <param name="infile_model" value="svc_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="svc_prediction_result02.tabular"/>
        </test>
        <test>
            <param name="infile_model" value="svc_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="svc_prediction_result03.tabular"/>
        </test>
        <!-- The following test is expected to fail, it is testing the whitelist/blacklist filtering.
        It loads a pickle with malicious content that we do not accept. -->
        <test expect_failure="true">
            <param name="infile_model" value="pickle_blacklist" ftype="zip"/>
            <param name="infile_data" value="test_set.tabular" ftype="tabular"/>
            <param name="header" value="True"/>
            <param name="selected_task" value="load"/>
        </test>
    </tests>
    <help><![CDATA[
**What it does**
This module implements the Support Vector Machine (SVM) classification algorithms.