comparison svm.xml @ 25:b878e4cdd63a draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 9981e25b00de29ed881b2229a173a8c812ded9bb

24:b7c3e9a3b954

<tool id="sklearn_svm_classifier" name="Support vector machines (SVMs)" version="@VERSION@" profile="20.05">
    <description>for classification</description>
    <macros>
        <import>main_macros.xml</import>
        <!-- macro name="class_weight" argument="class_weight"-->
    </macros>

            <![CDATA[
import sys
import json
import sklearn.svm
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":

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)

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>
    </configfiles>
    <inputs>
        <expand macro="sl_Conditional" model="zip">
            <param name="selected_algorithm" type="select" label="Classifier type">
                <option value="SVC">C-Support Vector Classification</option>
                <option value="NuSVC">Nu-Support Vector Classification</option>
                <option value="LinearSVC">Linear Support Vector Classification</option>
            </param>

            <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>

25:b878e4cdd63a

<tool id="sklearn_svm_classifier" name="Support vector machines (SVMs)" version="@VERSION@" profile="@PROFILE@">
    <description>for classification</description>
    <macros>
        <import>main_macros.xml</import>
        <!-- macro name="class_weight" argument="class_weight"-->
    </macros>

            <![CDATA[
import sys
import json
import sklearn.svm
import pandas

from galaxy_ml.model_persist import dump_model_to_h5, load_model_from_h5
from galaxy_ml.utils import clean_params, 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":

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)

classifier_object = load_model_from_h5('$infile_model')
classifier_object = clean_params(classifier_object)

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)

dump_model_to_h5(classifier_object, '$outfile_fit')

#end if

]]>
        </configfile>
    </configfiles>
    <inputs>
        <expand macro="sl_Conditional" model="h5mlm">
            <param name="selected_algorithm" type="select" label="Classifier type">
                <option value="SVC">C-Support Vector Classification</option>
                <option value="NuSVC">Nu-Support Vector Classification</option>
                <option value="LinearSVC">Linear Support Vector Classification</option>
            </param>

            <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="h5mlm" />
            <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="h5mlm" />
            <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="h5mlm" />
            <param name="infile_data" value="test_set.tabular" ftype="tabular" />
            <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="unsafe_model.h5mlm" />
            <param name="infile_data" value="test_set.tabular" ftype="tabular" />
            <param name="header" value="True" />
            <param name="selected_task" value="load" />
        </test>
    </tests>