comparison svm.xml @ 13:78c664cc1841 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 5d71c93a3dd804b1469852240a86021ab9130364

12:ada7bb28fe13

import numpy as np
import sklearn.svm
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", 'rb'))

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]])

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

if not(selected_algorithm=="LinearSVC"):
    if options["kernel"]:
        options["kernel"] = str(options["kernel"])

my_class = getattr(sklearn.svm, selected_algorithm)
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">
            <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>
            <when value="SVC">
                <expand macro="svc_advanced_options">
                    <expand macro="C"/>
                </expand>
            </when>
            <when value="NuSVC">
                <expand macro="svc_advanced_options">
                    <param argument="nu" type="float" optional="true" value="0.5" label="Nu control parameter" help="Controls the number of support vectors. Should be in the interval (0, 1]. "/>
                </expand>
            </when>
            <when value="LinearSVC">
                <section name="options" title="Advanced Options" expanded="False">
                    <expand macro="C"/>
                    <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. "/>
                    <expand macro="random_state" help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data for probability estimation. A fixed seed allows reproducible results."/>
                    <!--expand macro="class_weight"/-->

    <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="SVC"/>
            <param name="random_state" value="5"/>
            <output name="outfile_fit" file="svc_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="NuSVC"/>
            <param name="random_state" value="5"/>
            <output name="outfile_fit" file="svc_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="LinearSVC"/>
            <param name="random_state" value="5"/>
            <output name="outfile_fit" file="svc_model03.txt"/>
        </test>
        <test>
            <param name="infile_model" value="svc_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="svc_prediction_result01.tabular"/>
        </test>
        <test>
            <param name="infile_model" value="svc_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="svc_prediction_result02.tabular"/>
        </test>
        <test>
            <param name="infile_model" value="svc_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="svc_prediction_result03.tabular"/>
        </test>
    </tests>
    <help><![CDATA[

13:78c664cc1841

import numpy as np
import sklearn.svm
import pandas
import pickle

@COLUMNS_FUNCTION@
@GET_X_y_FUNCTION@

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", 'rb'))

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)

#else:

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

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

if not(selected_algorithm=="LinearSVC"):
    if options["kernel"]:
        options["kernel"] = str(options["kernel"])

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

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

#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>
            <when value="SVC">
                <expand macro="sl_mixed_input"/>
                <expand macro="svc_advanced_options">
                    <expand macro="C"/>
                </expand>
            </when>
            <when value="NuSVC">
                <expand macro="sl_mixed_input"/>
                <expand macro="svc_advanced_options">
                    <param argument="nu" type="float" optional="true" value="0.5" label="Nu control parameter" help="Controls the number of support vectors. Should be in the interval (0, 1]. "/>
                </expand>
            </when>
            <when value="LinearSVC">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <expand macro="C"/>
                    <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. "/>
                    <expand macro="random_state" help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data for probability estimation. A fixed seed allows reproducible results."/>
                    <!--expand macro="class_weight"/-->

    <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="SVC"/>
            <param name="random_state" value="5"/>
            <output name="outfile_fit" file="svc_model01.txt"/>
        </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="NuSVC"/>
            <param name="random_state" value="5"/>
            <output name="outfile_fit" file="svc_model02.txt"/>
        </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="LinearSVC"/>
            <param name="random_state" value="5"/>
            <output name="outfile_fit" file="svc_model03.txt"/>
        </test>
        <test>
            <param name="infile_model" value="svc_model01.txt" ftype="txt"/>
            <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="txt"/>
            <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="txt"/>
            <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[